CN119255697A - System and method for simulating crop yield based on detection of plant stressors in crops - Google Patents

Abstract

One variation of the method includes obtaining an image of a sensitive plant in a crop of one crop type sown within a geographic area and configured to signal the presence of an stressor, interpreting a first pressure of the stressor within a first sub-area based on a first subset of features extracted from the image, interpreting a second pressure of the stressor within a second sub-area based on a second subset of features extracted from the image, deriving a pressure map representing the pressure of the stressor within the geographic area based on the first pressure and the second pressure, obtaining a yield model that correlates the pressure of the stressor with crop yield of the crop of the one crop type in the geographic area, and predicting crop yield of the crop of the one crop type in the geographic area based on the pressure map and the yield model.

Description

System and method for simulating crop yield based on detection of plant stressors in crops

Cross Reference to Related Applications

The present application claims the benefit of U.S. provisional application No. 63/417,247 filed on month 10, 2022 and U.S. provisional application No. 63/338,618 filed on month 05, 2022, each of which is incorporated by reference in its entirety.

The present application relates to U.S. patent application Ser. No. 17/592,275, filed on even 03 at 2022, which is a continuation of U.S. patent application Ser. No. 17/217,840, filed on even 30 at 2021, which is a continuation of U.S. patent application Ser. No. 16/908,526, filed on even 22 at 2020, which is claimed to be the benefit of U.S. provisional application Ser. No. 62/864,401, filed on even 20 at 2019, each of which is incorporated herein by reference in its entirety.

Technical Field

The present invention relates generally to the field of agriculture, and more particularly to a new and useful method for detecting stressors in crops and simulating crop yields in the field of agriculture.

Brief Description of Drawings

FIG. 1 is a flow chart representation of a method;

FIGS. 2A and 2B are flow chart representations of a variation of a method;

FIG. 3 is a flow chart representation of a variation of the method;

FIGS. 4A and 4B are flow chart representations of a variation of a method, and

Fig. 5 is a flow chart representation of a variation of the method.

Description of the embodiments

The following description of the embodiments of the invention is not intended to limit the invention to those embodiments, but to enable any person skilled in the art to make and use the invention. Variations, configurations, embodiments, example embodiments, and examples described herein are optional and are not limited to the variations, configurations, embodiments, example embodiments, and examples described herein. The invention described herein may include any and all combinations of these variations, configurations, embodiments, example embodiments, and examples.

1. Method of

As shown in fig. 1, 2A, 2B, 3, 4A, 4B, and 5, the method S100 includes obtaining an image feed of sensitive plants of a sensitive plant type sown in a set of farmlands within a geographic area, the image feed being recorded during a first time period, the sensitive plants of the sensitive plant type being configured to signal the presence of a set of stressors at the sensitive plants, interpreting a first pressure map of a first stressor in the first subregion in the set of stressors based on features extracted from a first subset of images of the sensitive plants in a first subregion of the image feed in block S112, interpreting a second pressure map of the first stressor in the second subregion in the image feed based on features extracted from a second subset of images of the sensitive plants in the second subregion in the geographic region, deriving a first pressure map of the geographic area based on the first pressure map and the second pressure, the first pressure map of the first region in block S120, the first pressure map of the first region being based on the first pressure map of the first time period, and the first pressure map of the crop type being correlated with a yield map of the crop type in the first region in the geographic region in the first time region in the block S112, and the crop type being predicted based on the first pressure map of the first yield map of the set of the first stress map in the first region in the geographic region.

One variation of the method S100 includes obtaining an image feed of a population of sensitive plants of one crop type sown in a farmland, the image feed being recorded by an air sensor during a first time period, the population of sensitive plants being configured to signal presence of a set of conditions and including a first set of sensitive plants arranged in a first area of the farmland, in block S110, interpreting the first set of conditions at plants in the first area based on features extracted from a first subset of images of sensitive plants depicted in the first area in the image feed, in block S112, in block S116, obtaining a set of target conditions defined for plants in the first area of the farmland, in block S140, predicting a first health score of plants in the first area based on a first difference between the first set of conditions and the set of target conditions, in block S150, selecting a first processing pathway for plants in the first area based on the first health score, the first processing pathway being configured to drive the set of conditions toward the first area in block S, and generating a prompt for the plants in the first area in the first time period, in block S140, and generating a prompt for the plants in the first time period, in block S160, and the prompt to be applied to the user.

One variation of the method S100 includes acquiring, in block S110, an image feed of a population of sensitive plants in a crop of one crop type sown within a target area, and the population of sensitive plants is configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first time period, interpreting, in block S112, a first time sequence of pressure data of plants in a first subset of the image feed captured during the first time period, the first time sequence of pressure data representing a change in pressure of a set of stressors at plants in the first subset of the target area during the first time period, based on features extracted from a second subset of images captured in the image feed during the first time period, the second time sequence of pressure data representing a second time sequence of pressure data of plants in the second subset of the target area captured during the first time period, interpreting, the first time sequence of pressure data representing a first time sequence of pressure data of plants in the first subset of the target area, the first time sequence of stress data representing a change in the first time period, a model of the crop type of stress in the first time period, and a frame of yield of the crop in the first time period, and a frame of the crop type in the first time frame, the crop type in the first time frame being correlated with the crop type in the first time sequence of stress model, the crop type in the first time frame, and the yield of the crop type in the first time sequence of the crop type in the first time frame, and the crop type in the crop in the first time frame of the crop type.

One variation of method S100 includes obtaining an image feed of a population of sensitive plants in a crop of one crop type sown within a target area and configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first time period in block S110, interpreting a first pressure of a first stressor in a first sub-region within the target area in the set of stressors based on features extracted from a first subset of images depicting the first set of sensitive plants in the image feed in block S112, in block S122, interpreting a second pressure of the first stressor in the second sub-region within the target area based on features extracted from a second subset of images depicting the second set of sensitive plants in the image feed, in block S120, based on the first pressure and the second pressure, deriving a first pressure map of the target area during the first time period, in block S122, correlating the yield in the first time period with a yield of the crop in the first time period based on features extracted from a second subset of images depicting the second set of sensitive plants in the target area, and harvesting the crop type in the first time period in the frame S114.

One variation of the method S100 includes acquiring an image feed of a sensitive plant population of one crop type (e.g., cotton, soybean, corn) sown in a farmland recorded by an aerial sensor during a first period of time, the sensitive plant population configured to signal the presence of a set of conditions, the sensitive plant population including a first set of sensitive plants disposed in a first sub-area of the farmland and a second set of sensitive plants disposed in a second sub-area of the farmland, in block S110, interpreting a first set of conditions at the plants in the first sub-area based on a first set of plant signals (e.g., fluorescent signals) detected in a first subset of images of the sensitive plants depicted in the first sub-area in the image feed, and interpreting a second set of conditions at the plants in the second sub-area based on a second set of signals (e.g., fluorescent signals) detected in a second subset of images of the sensitive plants depicted in the second sub-area in the image feed, in block S114. The method S100 further includes obtaining a first set of target conditions defined for the plants in the first sub-area in block S116, predicting a first health score for the plants in the first sub-area of the farmland based on a first difference between the first set of conditions and the first set of target conditions in block S140, and selecting a first treatment pathway for the plants in the first sub-area based on the first health score in block S150.

In the former variant, the method S100 further comprises, in block S116, obtaining a second set of target conditions defined for the plants in the second subregion, in block S140, predicting a second health score for the plants in the second subregion of the farmland based on a second difference between the second set of conditions and the second set of target conditions, and in block S150, selecting a second treatment pathway for the plants in the second subregion based on the second health score. In one variation, the method S100 further includes integrating (assembling) the treatment map based on the first treatment path selected for the first sub-region and the second treatment path selected for the second sub-region, specifying a location and magnitude (e.g., frequency and/or number) of application for each treatment path selected for the crop, in block S170.

One variation of method S100 includes acquiring, in block S110, an image feed of a population of sensitive plants sown in a crop of one crop type (e.g., cotton, soybean, corn) within a target area (e.g., a target geographic area), the image feed being recorded by an air sensor during a first time period, the population of sensitive plants being configured to signal the presence of a set of stressors (e.g., non-biological stressors and/or biological stressors) at the sensitive plants, in block S112, interpreting, based on first signals (e.g., fluorescent signals) detected in a first subset of images of the sensitive plants in a first region in the image feed in the set of stressors in the first region, a first pressure of the first stressor in the first region being based on a second signal (e.g., fluorescent signals) detected in a second subset of images of the sensitive plants in a second region in the image feed, interpreting, in block S112, a second pressure of the first stressor in the second region being based on a first pressure map in the first region, and a yield model of the crop in the first time period, and based on the first time period, and a yield model of the crop in the first time period, and a yield model, in block S114, and a yield of the crop in the first time period being derived based on the pressure map of the first pressure in the first region, in the first pressure map, the first yield model, in the first time period, and the yield model, and the yield of the crop in the first yield model, in the first region, and the yield.

In one variation, the method S100 further includes obtaining a pressure model configured to predict a future pressure of the first stressor in the target region based on the pressure of the first stressor detected in the target region, and in block S180, predicting a second pressure map of the target region during a second time period subsequent to the first time period based on the first pressure map and the pressure model. In response to the second pressure map predicting that the third pressure of the first stressor in the third sub-region within the target region exceeds the threshold pressure, the method S100 further includes sending, in blocks S160 and S162, a first prompt to a first group of users associated with maintenance of crops located within the third sub-region implementing a first mitigation technique of a set of mitigation techniques configured to mitigate the pressure of the first stressor, sending, in blocks S160 and S162, a second prompt to a second group of users associated with manufacture of the crop treatments to generate a supply of the first crop treatment corresponding to the first mitigation technique and configured to handle the pressure of the first stressor, and notifying, in blocks S160 and S162, a third group of users associated with maintenance of crops in the vicinity of the third sub-region of the prediction of the third pressure of the first stressor in the third sub-region during the second period of time.

2. Application of

Generally, the blocks of method S100 may be performed by a computer system (e.g., a remote server, a local computing device, a computer network) in conjunction with a sensitive plant platform (e.g., a local application or web-based application) to detect signals generated by sensitive plants, interpret (e.g., estimate) stress of stressors at sensitive plants sown in crops, on various crops, and/or on a particular geographic area based on these sensitive plant signals, derive a set of crop models for a particular crop and/or for a particular crop area configured to predict various indicators of crop health and/or crop operation, such as the presence of stressors in crops, crop yield (e.g., with respect to a particular growing season) and/or crop stress resistance (e.g., speed and/or magnitude of stress relief), and selectively distribute insight, instructions and/or advice related to the detection of stress in crops to various users associated with a crop supply chain via the sensitive plant platform.

For example, a computer system that cooperates with the sensitive plant platform may selectively distribute cues to users in various departments or industries associated with local users (e.g., farmers, agronomists, researchers) near or in conjunction with crops containing such sensitive plants and/or supply chains associated with such crops, such as users associated with food, clothing, or textile, distribution (e.g., truck transportation, shipping, storage), health, government, insurance, and/or chemical industries.

In one embodiment, a system may acquire images of a farm (e.g., satellite or aviation color or infrared images), scan the images to obtain signals indicative of sensitive plants (e.g., fluorescence in specific spectral characteristics of the sensitive plants or characteristics of specific stressors present at the sensitive plants), identify a population of sensitive plants sown in specific geographic areas depicted in the images based on the characteristic signals (or "baseline signals") detected in the images, and interpret the pressure of stressors within the population of sensitive plants based on the presence and/or amplitude of optical signals present at the sensitive plants, and integrate a pressure map for the specific geographic areas depicting the pressure of a set of stressors in the population of sensitive plants during a specific period of time.

The system may continuously acquire images of sensitive plants in the population of sensitive plants over time to integrate a time series of pressure data for that particular geographic region. The system may then utilize the time series of pressure data, combined into a time series of pressure data collected across many crops and/or many sensitive plant populations of many areas, to predict future pressure of stressors in that particular geographic area based on the current pressure map. The system may also fuse the time series of pressure data with other data collected for the particular geographic area, such as time series weather data and/or time series crop treatment data, to predict future pressure of stressors in the particular area based on (currently) detected pressure, applied crop treatment, average air temperature, average humidity, average rainfall, etc., corresponding to the particular geographic area.

Further, the system may estimate the change in expected crop yield based on detection and/or prediction of stress source pressure in the particular geographic area, such as based on historical crop data collected for the particular geographic area (including time series of pressure data and/or corresponding time series crop yield data). Thus, based on these predicted changes in stress-source pressure and/or expected crop yield, the system may selectively generate cues related to the detection and/or mitigation of crops in the particular geographic area and distribute these cues to the user.

2.1 Area simulation

In one embodiment, the system may utilize fluorescent signals expressed by sensitive plants distributed throughout a geographic area (such as sensitive plants sown in several crops and/or on farms within a geographic area) to derive insight into crop health, spread and/or distribution of stress (e.g., insects, fungi, dehydration, flooding, heat stress, cold stress, soil stressors) stress and/or crop yield of crops of different crop types within the geographic area.

For example, the system may acquire images (e.g., spectral images) of sensitive plants in crops sown throughout a geographic area, extract features indicative of the pressure of one or more stressors in the sensitive plants in the geographic area, such as the intensity of fluorescence of specific wavelengths, interpolate or extrapolate these pressures of stressors in the sensitive plants to other plants (e.g., sensitive plants and non-sensitive plants) in the same geographic area, and detect and/or predict the changes over time of these pressures of the set of stressors to predict crop yield of crops of each crop type within the geographic area. Thus, the system can derive a yield profile for a geographic area defining predicted crop yields for each crop type (e.g., soybean, tomato, corn, cotton) present in the geographic area, and share the predicted yield profile with users associated with crops in the geographic area (such as farmers, food suppliers, food processing facility managers, pesticide and/or fertilizer manufacturers, etc.), thereby enabling the users to better predict results associated with the crops in the particular geographic area.

2.2 Local crop simulation

Additionally or alternatively, in another embodiment, the system may utilize fluorescent signals expressed by sensitive plants sown in a particular crop or field to derive insight into crop health, the spread and/or distribution of stress-source stress within the crop, and/or crop yield of the particular crop. In particular, the system may utilize a time series of crop data collected over one or more growth cycles of the crop (including a time series of pressure data, a time series of environmental data (e.g., weather data, process data), a time series of yield data, etc.), derive a high resolution pressure map for the crop (which represents the pressure and/or pressure gradient of stressors at plants in various areas of the crop), predict future pressures of stressors in different areas of the crop, characterize the health of individual plants or groups of plants within the crop, predict yield of the crop over a particular growth cycle based on the health of plants in the crop over time, and/or suggest custom crop treatments for different areas of the crop that are predicted to relieve the pressure of stressors in the crop to more accurately adjust the health of plants in the entire crop.

Further, in this embodiment, the system can utilize the time series of crop data collected for the crop to derive a set of target plant conditions (e.g., soil pH, nitrogen levels in the soil, irrigation levels, fertilizer levels, pest population size, fungal growth) for the plants in the crop and/or for a particular set of plants located in different areas of the crop that are predicted to maximize crop yield for the particular crop. The system may then detect deviations from the set of target conditions in different areas of the crop (e.g., throughout the growth cycle), and thus selectively suggest treatments configured to drive plant conditions in those areas toward the set of target plant conditions for embodiments in particular areas of the crop. Thus, by prompting the alignment of plant conditions in the entire crop with a set of target conditions derived for that particular crop, the system can drive crop yield toward a predicted maximum crop yield for that crop.

3. Sensitive plants

Typically, the sensitive plant comprises a promoter-reporter pair configured to detect the presence of stressors in the sensitive plant and to generate a detectable signal (e.g., in the electromagnetic spectrum) to indicate the presence of these stressors in the sensitive plant or in the area of the crop where the sensitive plant is generally located. In particular, sensitive plants can be transgenic to include a promoter gene sequence (hereinafter referred to as a "promoter") configured to activate in the presence of a particular stressor (e.g., to "correlate" with a particular stressor), and a reporter gene sequence (hereinafter referred to as a "reporter") configured to activate in response to activation of the promoter, encoding a particular molecule (e.g., a fluorescent molecule) configured to express a detectable signal (e.g., a fluorescent signal). The promoter-reporter pair may be incorporated into susceptible plants by genetic engineering techniques that correlate expression of a promoter responsive to a particular biological stress with a reporter that produces a measurable signal when the promoter is expressed.

In one embodiment, the susceptible plant may be configured to include a promoter-reporter pair configured to signal the presence of a particular biotic and/or abiotic stress experienced by the susceptible plant, such as pest, disease, water, heat, soil health, and/or nutritional stress or lack thereof. For example, a susceptible plant can be transgenic to include a promoter having activity associated with the presence of a stressor at the plant, such as fungi, bacteria, pests, heat, water (e.g., dehydration and/or overhydration), disease or nutritional stress (e.g., nutrient deficiency), phytoplasma disease, poor soil health (e.g., soil pH), and the like. The susceptible plant may also be transgenic to include a reporter paired with a promoter, and the reporter is configured to produce a detectable signal, such as an electromagnetic signal (e.g., a fluorescent signal) in the visible or infrared spectrum when the corresponding promoter is activated. For example, a susceptible plant may be transgenic to fluoresce (i.e., absorb photons at one frequency and emit photons at a different frequency) in the presence of (and in proportion to) the pressure of a particular stressor. Thus, by expression of the reporter, the promoter-reporter pair can produce a measurable signal of a particular biological stress or trait in a susceptible plant.

In another embodiment, the susceptible plant can be transgenic to include a plurality of promoter-reporter pairs, each promoter-reporter pair being indicative of a particular biological process occurring in the susceptible plant cell in response to a particular stressor. For example, a susceptible plant can include a first promoter-reporter pair that includes a first promoter that is indicative of a first biological process associated with the presence of a water stressor, the first promoter labeled with a red fluorescent protein reporter, and a second promoter-reporter pair that includes a second promoter that is indicative of a second biological process associated with the presence of a fungal stressor, the second promoter labeled with a yellow fluorescent protein reporter. Thus, a susceptible plant can be signaled for the presence of multiple stressors via transgenesis on the susceptible plant cell to include a set of promoter-reporter pairs.

In one variation, the susceptible plant may be transgenic to include a composite gene-sensing network representing a set of combined promoter-reporter pairs. In this variant, sensitive plants can utilize small amounts of reporter (e.g., fluorescent compounds) to monitor and detect a larger number of promoters and/or biological processes, and thus simplify the detection process by reducing the number of reporter needed, as fluorescent compounds exhibit broad spectral characteristics, and it can be difficult to simultaneously measure and distinguish large amounts of these fluorescent compounds.

3.1 Variants plant identifier

In one variation, a population of susceptible plants can be transgenic to express a detectable baseline signal (e.g., a fluorescent signal) associated with susceptible plants in the population of susceptible plants. In particular, the genome of each sensitive plant in the population of sensitive plants may be transgenic to include an identifier gene (hereinafter "identifier") configured to express a baseline signal (e.g., a fluorescent signal) comprising identification information (e.g., crop position, type of sensitivity, crop type) of the sensitive plant, e.g., independent of the presence of stressors at the sensitive plants in the population of sensitive plants.

In one embodiment, the population of susceptible plants may be configured to express baseline signal characteristics of susceptible plants grown in a particular region. For example, the first population of susceptible plants can be configured to express a first baseline signal associated with a first geographic region, the first baseline signal corresponding to fluorescence over a first range of wavelengths. The second population of susceptible plants can be configured to express a second baseline signal associated with a second geographic region, the second baseline signal corresponding to fluorescence in a second wavelength range different from the first wavelength range. Thus, the system may acquire an image and/or images of a larger geographic area including a first geographic area and a second geographic area, distinguish between sensitive plants in the first geographic area and sensitive plants in the second geographic area based on detection of the first baseline signal and the second baseline signal in the images, interpret stress sources' pressures, generate a pressure map, derive yield predictions for both the first geographic area and the second geographic area, and so forth.

In particular, in one example, a population of susceptible plants can be transgenic to include a fluorescent tag configured to express a first fluorescent signal (e.g., red, yellow, and/or green fluorescence) in a first wavelength range (e.g., presence of light). The system can correlate the fluorescent tag and corresponding first fluorescent signal to a first region and/or crop comprising a population of sensitive plants. In particular, in this example, the system may store a first fluorescence spectrum depicting a fluorescence signal in a first wavelength range in a first region crop profile associated with the first region in a set of region crop profiles. The system may then correlate the sensitive plant and/or the population of sensitive plants including the sensitive plant to a first fluorescent signal in a first wavelength range. The system may then acquire an image feed of a geographic region including the sensitive plant and/or the population of sensitive plants recorded by an aerial sensor (e.g., satellite), and identify the sensitive plant and/or the population of sensitive plants in the image from the image feed based on detection of a first fluorescent signal (i.e., baseline signal) expressed by the sensitive plant.

The system may further append in the first regional crop profile a sensitive plant type of a sensitive plant in the sensitive plant population, such as a specific promoter-reporter pair comprising a signal configured to detect a specific stressor in a set of stressors, and/or a crop type of a sensitive plant in the sensitive plant population (e.g., cotton, corn, soybean, grape). The population of susceptible plants (e.g., susceptible plant seeds and/or susceptible plant seedlings) can then be distributed (e.g., planted) among one crop and/or among multiple crops within the first area (e.g., by a farmer or other user associated with the crop). Subsequently (e.g., during the growth of a sensitive plant population in the crop and/or crop), the system may acquire an image feed of the first region recorded by the satellite at about the target frequency (e.g., weekly, biweekly, monthly). The system may then acquire the set of regional crop profiles in response to detecting the fluorescent signal in the first image in the image feed, and identify the detected fluorescent signal as corresponding to the sensitive plant type and/or the sensitive plant population of the crop type located in the first region in response to the detected fluorescent signal corresponding to the first fluorescent signal in the first wavelength range.

Further, in the foregoing examples, the population of susceptible plants can be transgenic to include a promoter-reporter pair configured to signal detection of a first stressor at the susceptible plants, the promoter-reporter pair including a promoter configured to be expressed in response to detection of the first stressor, and a reporter configured to express a second fluorescent signal in a second wavelength range different from the first wavelength range in response to expression of the promoter. Thus, in this example, the sensitive plant may be configured to include a first fluorescent tag configured to express a first fluorescent signal in a first wavelength range such that the expression of the first fluorescent signal does not interfere with the detection of a second fluorescent signal indicative of the presence of the first stressor, thereby reducing errors due to the detection of the added or overlapping fluorescent signals.

Additionally or alternatively, in another embodiment, each sensitive plant population may be configured to express a baseline signal associated with a particular crop type of a set of crop types. For example, the first population of susceptible plants can be configured to express a first baseline signal associated with a first crop type (e.g., soybean) that corresponds to fluorescence over a first wavelength range. The second population of sensitive plants can be configured to express a second baseline signal associated with a second crop type (e.g., tomato) that corresponds to fluorescence in a second wavelength range different from the first wavelength range. Thus, the system may acquire an image and/or images of an area including a crop of a first crop type and a second crop type, distinguish between sensitive plants of the first crop type and sensitive plants of the second crop type based on detection of the first baseline signal and the second baseline signal in the images, interpret stress of stressors, generate a pressure map, derive a yield prediction of the crop of the first crop type and the crop of the second crop type, and so on.

Additionally or alternatively, in one variation, the susceptible plant can be transgenic to include an identifier configured to express a detectable signal (e.g., a fluorescent signal) associated with the growth stage of the susceptible plant. Additionally, in this variation, the susceptible plant may be transgenic to include a set of identifiers, each identifier of the set of identifiers configured to express one of a set of detectable signals associated with a particular stage of growth of the susceptible plant. For example, the susceptible plant and/or population of susceptible plants can be configured to include a first identifier configured to express a first baseline signal during an initial growth phase (e.g., seed, seedling (seedling), and/or early stage of nutrition), a second identifier configured to express a second baseline signal during the initial growth phase (e.g., budding and/or flowering phase), and a third identifier configured to express a third baseline signal during a final growth phase (e.g., maturation). Thus, the system can track the growth of sensitive plants throughout their life cycle and derive insight and information related to crop health and/or yield of a particular crop based upon detection of these baseline signals at various stages of the sensitive plant's life cycle.

4. Stressor detection

The system may detect and interpret signals generated by the sensitive plant by extracting features from the image of the sensitive plant, the features being related to the presence of a specific stressor at the sensitive plant. More specifically, the system may acquire digital images (e.g., spectral images) of sensitive plants and/or plant canopy (e.g., sensitive plants and surrounding plants) captured by optical sensors (e.g., multispectral or hyperspectral imaging devices) to detect reporter signals and interpret stressors present in the sensitive plants based on the reporter signals.

In particular, the optical device may record (e.g., in the form of color or multispectral images) the optical signals generated by the sensitive plants, and the computer system may extract features (e.g., intensities at specific wavelengths) from these images, interpret the presence and/or magnitude of specific stressors exposed to the sensitive plants based on these features, and interpolate or extrapolate the health and environmental conditions of other plants in the vicinity (e.g., non-sensitive plants; other non-imaged sensitive plants) based on the presence and/or magnitude of stressors indicated by the sensitive plants.

For example, the computer system may extract intensities corresponding to particular wavelengths of particular compounds (e.g., proteins) in the sensitive plant and interpret the stress of the particular stressor exposed to the sensitive plant based on the intensities of those wavelengths (such as based on a stored model that correlates plant stressors with wavelengths of interest, the stored model being based on known characteristics of promoter genes and reporter genes in the sensitive plant) and before such stressors are visually (i.e., with the human eye) discernable in the visible spectrum. The computer system may also interpolate or extrapolate the presence or magnitude of these stressors in other plants in the vicinity of the sensitive plant to predict the overall health of the crop or farmland.

In particular, in one example, a system may obtain a first subset of images (e.g., an image, a series of images) of sensitive plants sown in a farmland within a geographic area, the sensitive plants configured to signal a pressure of a set of stressors in the plants, extract a first set of fluorescence measurements (such as a first set of fluorescence intensities) corresponding to a first wavelength range from the first subset of images, extract a second set of fluorescence measurements (such as a second set of fluorescence intensities) corresponding to a second wavelength range from the first subset of images, interpret a first pressure of a first stressor in the set of stressors in the plants within the geographic area based on the first set of fluorescence measurements, and interpret a second pressure of a second stressor in the set of stressors in the plants within the geographic area based on the second set of fluorescence measurements.

The system may acquire images of the sensitive plant captured by an optical sensor, such as from a hand-held camera, a hand-held spectrometer, a mobile phone, a UAV, a satellite, or from any other device, including a high resolution spectrometer, a device that includes a band-specific filter or is otherwise configured to detect electromagnetic radiation fluorescence, luminescence (luminescence), or the wavelength of any other optical signal emitted by the sensitive plant in the presence of a particular stressor. More specifically, the system may acquire hyperspectral images of sensitive plants, leaf area of an entire sensitive plant, a group of similar sensitive plants, an entire sensitive plant crop or a plurality of fields of sensitive plants recorded by a remote sensing system (e.g., satellite, in an aircraft, in a manned or unmanned field device such as a tractor, in a handheld device, in a boom or stick mounted in a field), extract spectral characteristics from these hyperspectral images, and interpret the presence and/or magnitude of a particular stressor present at the sensitive plant, group of plants, crop or field based on correlation between the spectral characteristics extracted from these hyperspectral images and known characteristics (e.g., fluorescence) expressed by a particular promoter-reporter pair in the sensitive plant.

5. Sensitive plant platform

The system can compile a large amount of crop data (such as historical pressure data and/or (near) real-time pressure data, process data, environmental data, and/or crop yield data) collected for sensitive plant populations planted, grown, and/or harvested across multiple crops and/or multiple areas (e.g., geographic areas) to derive insight and additional information related to crop health, supply, and/or management practices for a particular crop, a particular area, and/or a global crop supply.

The system may provide such data, instructions, insights, suggestions, information, and/or recommendations to users associated with particular crops, crop areas, and/or crop types, such as farmers, food suppliers, insurance agents (e.g., insurance agents associated with farm evaluation), retailers, etc., to enable such users to monitor stress of stressors in such crops and/or mitigate risks associated with such stress.

5.1 Crop Profile

In one embodiment, the system may compile sensitive plant data collected over time for a particular crop and/or a particular area (e.g., including a number of crops) into a crop profile for the particular crop and/or area in a set of crop profiles. Thus, the crop profile may include information representing historical sensitive plant data of the crop, such as the type of stress source detected, the pressure of the stress source detected over time, and the like.

The system may also gather additional information from the user regarding the crop, such as a schedule in which the crop is planted, a schedule in which the crop is harvested, irrigation frequency, amount of irrigation, type of treatment typically applied to the crop, information regarding soil health, information regarding crop nutrients, and so forth. Thus, with this additional information, the system can estimate the stress of the crop with increased sensitivity and increased confidence, thereby enabling the user to be more confident in the information provided by the system and obtain additional and more accurate insight and information about the health of the crop.

5.1.1 Baseline pressure curve

In one variation, the system may identify patterns and/or trends of sensitive plant data collected over time (e.g., during growth periods) for a particular crop or area. In particular, in this embodiment, the system may utilize sensitive plant data collected for a particular crop or area over one or more growing periods to derive a baseline pressure curve (e.g., an annual pressure curve) that represents detected or expected changes in pressure of stressors in the particular crop or area during a particular time period, such as corresponding to the growing period and/or a particular time of year.

For example, during a first growing season of a crop, the system may monitor reporter signals expressed by sensitive plants sown in the crop, derive a time series of stress of a set of stressors at set intervals (e.g., once a week, once every two weeks, once a month) with detection of these reporter signals over time, and extract insight and information regarding moisture movement on the crop, sun exposure on the crop (e.g., daily, weekly, monthly, each season), and timing and/or movement of stress of other stressors (such as insects, fungi, and/or nutritional deficiencies) based on the time series of stress of the set of stressors. Thus, the computer system may integrate a time series of stress and/or stressor data (corresponding to the moisture movement, sunlight irradiation, and/or other stressor pressures) into a set of baseline pressure curves for a set of stressors in that particular crop. The system may then obtain these baseline pressure profiles to predict conditions of the crop and/or area at the beginning of and/or throughout a subsequent growing season and/or suggest embodiments for farming practices and/or stressors at the crop based on the predicted plant conditions.

In one embodiment, during a first growth cycle of plants sown within a first area (e.g., crop, farmland, geographic area), the system may interpret a first set of pressures of a set of stressors at the sensitive plants in the first area based on a first image or a first set of images captured at a first time and depicting the sensitive plants in the first area, each pressure in the first set of pressures corresponding to a particular stressor in the set of stressors, interpret a second set of pressures of the set of stressors at the sensitive plants in the first area based on a second image or a second set of images captured at a second time after the first time and depicting the sensitive plants in the first area, and interpret a third set of pressures of the set of stressors at the sensitive plants in the first area based on a third image or a third set of images captured at a third time after the second time and depicting the sensitive plants in the first area.

The system may then integrate a time series of pressure data representing a change in pressure of the set of stressors in the first region during the growth cycle, the time series of pressure data including a first time value corresponding to a first time associated with the first set of pressures of the set of stressors, a second time value corresponding to a second time associated with the second set of pressures of the set of stressors, and a third time value corresponding to a third time associated with the third set of pressures of the set of stressors. Based on the time series of pressure data, the system may then derive a set of baseline pressure curves representing the observed pressure changes of the set of stressors over time. Subsequently, the system may use the set of baseline pressure profiles to predict the pressure change of the set of stressors over time. For example, the system may derive a first baseline pressure curve in the set of baseline pressure curves that represents a change in pressure of the insect stressor in the first region over time, derive a second baseline pressure curve in the set of baseline pressure curves that represents a change in pressure of the fungal stressor in the first region over time, and/or derive a third baseline pressure curve in the set of baseline pressure curves that represents a change in pressure of the soil stressor (e.g., soil pH, nitrogen level) in the first region over time.

The system may also refine such baseline pressure profile over time for a particular stressor within a particular region (e.g., a particular crop, a particular geographic region), such as based on additional time-series pressure data collected for the particular stressor within the particular region.

5.2 Area pressure diagram

In one embodiment, the system may utilize detection of stress of stressors at sensitive plants (e.g., individuals, clusters, and/or crops of sensitive plants) sown within a particular region to generate a pressure map representing non-biological stressors and/or biological stressors detected in the particular region during a corresponding detection period.

For example, the system may acquire a first image of a first crop of sensitive plants located in a first geographic area recorded during a first detection period in a satellite image feed (e.g., recorded by an optical sensor mounted on a satellite), acquire a second image of a second crop of sensitive plants located in the first geographic area recorded during the first detection period in the satellite image feed, and acquire a third image of a third crop of sensitive plants located in the first geographic area recorded during the first detection period in the satellite image feed.

The system may then interpret a first pressure of a first stressor in a first crop of sensitive plants in a set of stressors based on an optical signal (e.g., a fluorescent signal) expressed by a sensitive plant in a first crop of sensitive plants and detected in a first image, interpret a second pressure of the first stressor in the first crop of sensitive plants based on an optical signal expressed by a sensitive plant in a second crop of sensitive plants and detected in a second image, and interpret a third pressure of a second stressor in a third crop of sensitive plants in the set of stressors based on an optical signal expressed by a sensitive plant in a third crop of sensitive plants and detected in a third image. Then, at a first time after the first detection period, the system may interpret a first pressure map representing the presence of the set of stressors in the first geographical area during the first detection period based on the first pressure of the first stressor, the second pressure of the first stressor, and the third pressure of the third stressor.

Additionally and/or alternatively, in another embodiment, the system may generate a pressure map of a particular stressor. For example, the system may generate a first pressure map representing the presence of a first stressor in a set of stressors within a specific region, and generate a second pressure map representing the presence of a second stressor in the set of stressors within the specific region. Additionally and/or alternatively, in yet another embodiment, the system may generate a pressure map for a particular crop type. For example, the system may generate a first pressure map representing the presence of a set of stressors in a crop of a first crop type (e.g., cotton) within a specific area, and generate a second pressure map representing the presence of the set of stressors in a crop of a second crop type (e.g., soybean) within the specific area.

In each of these embodiments, the system may repeat the process over time to generate additional pressure maps that indicate the presence of a set of stressors in a particular region and/or in a crop of a particular crop type. By repeating this process over time, the system can provide data and/or recommendations to users associated with the crops in these areas, enabling active relief of stressors in these crops. In addition, the system may utilize the time series of pressure data represented in these pressure maps to derive insight and information related to the changes over time in the pressure and/or stressors present in these areas (and/or particular crops).

5.2.1 Area pressure map interpolation

In one embodiment, the system may utilize the detected and/or predicted pressure of stressors in plants at different locations (e.g., crop, farmland, geographic locations) to interpolate the pressure in plants and/or crops sown between those locations. In particular, in this variant, the system may interpolate between the pressures of the stressors derived for the plants in the first and second subregions to predict one or more pressures of the stressors present in the plants sown in the crop between the first and second subregions. The system may then generate a pressure map for a geographic region (including the first sub-region, the second sub-region, and a series of regions between the first sub-region and the second sub-region) that represents the predicted pressure of the stressor across the sub-regions, regardless of the presence or absence of the sensitive plant in each of these sub-regions.

For example, the system may interpret a first pressure of a first stressor in a first sub-region within a geographic region of a set of stressors based on features extracted from a first subset of images of sensitive plants in the first sub-region depicted during a first time period in an image feed of the sensitive plants within the geographic region, and interpret a second pressure of the first stressor in a second sub-region within the geographic region based on features extracted from a second subset of images of sensitive plants in the second sub-region depicted during the first time period in the image feed. The system may then predict a third pressure of the first stressor at a third sub-region within the geographic region based on the first pressure of the first stressor in the first sub-region and the second pressure of the first stressor in the second sub-region, and derive a first pressure map for a time period of the geographic region based on the first pressure, the second pressure, and the third pressure. Additionally and/or alternatively, in this embodiment, the system may similarly predict a fourth pressure of the first stressor at the fourth subregion, predict a fifth pressure of the first stressor at the fifth subregion, predict a sixth pressure of the first stressor at the sixth subregion, and the like, and update the first pressure map accordingly.

In one variation, the system may utilize environmental data collected for crops within a geographic area to more accurately predict stress-source pressures in various sub-areas throughout the geographic area.

5.2.2 Real-time pressure prediction

In one embodiment, the system may utilize detection of a first pressure of a particular stressor within a first region (e.g., crop, farmland, geographic region) to predict a second pressure of the particular stressor in a second region proximate to (e.g., adjacent to, bordering, near) the first region. For example, the system may implement the above-described methods and techniques to predict a first pressure of a stressor in a first crop field where a crop of a first crop type is grown, and predict a second pressure of the first stressor in a second crop field adjacent the first crop field where the crop of the first crop type is grown based on a known and/or predicted pattern of movement, diffusion, growth, decay, etc. of the first stressor.

In one example, a system may interpret a first pressure of a first stressor in a first crop comprising a set of sensitive plants configured to signal the pressure of the first stressor based on features extracted from an image of the first crop captured at a first time, and predict a second pressure of the first stressor in a second crop at about the first time with the first pressure of the first stressor based on a known and/or derived correlation between the pressure of the first stressor in the first crop and the pressure of the first stressor in the second crop.

In one variation, the system may derive a pressure model that correlates the pressure of a set of stressors in a first region (e.g., crop, farmland, geographic region) with the pressure of the set of stressors in a second region.

For example, during a first growth period of a series of growth periods, the system may acquire an image feed of a set of sensitive plants captured during the first growth period, the set of sensitive plants sown in a first crop and configured to signal a pressure of a set of stressors at the set of sensitive plants, and interpret a first time sequence of pressure data based on features extracted from time-stamped images in the image feed, the first time sequence of pressure data representing a change in pressure of the set of stressors at the set of sensitive plants throughout the first growth period. For example, a first time series of pressure data may define a first pressure of a first stressor in the set of stressors at a first time during an initial time period, a second pressure of the first stressor at a second time during the initial time period after the first time, a third pressure of the first stressor at a third time during the initial time period after the second time, and so forth. The first time series of pressure data may similarly include a time series of pressures of a second stressor in the set of stressors throughout the initial period of time, a time series of pressures of a third stressor in the set of stressors throughout the initial period of time, and so forth.

Further, in the foregoing example, the system can prompt one or more users (e.g., farmers, crop owners, crop operators) associated with a second crop (proximate to the first crop and excluding sensitive plants) to manually input a second time series of pressure data captured for the second crop during the initial period of time. For example, the farmer and/or agrologist may record the time series of moisture levels in the soil and/or plants of the second crop, record the time series of nitrogen uptake in the plants within the second crop, record the time series of pH levels of the soil within the second crop, record the time series of densities and/or presence of insects and/or fungi within the second crop, and so forth. Upon receiving the assembled time-series stress data from the user regarding the second crop, the system may implement regression, machine learning, deep learning, and/or other techniques to derive correlations between the stress of the set of stressors in the first crop and the stress of the set of stressors in the second crop, and store the correlations in a stress model configured to predict the stress of the set of stressors in the second crop based on the detected stress of the set of stressors in the first crop.

5.3 Pressure prediction over time

In one variation, the system may predict future pressure of the stressor in the plant within the specific region based on the current pressure of the stressor in the plant within the specific region. In particular, in this variation, the system may interpret a first pressure of a first stressor in a first crop comprising a set of sensitive plants configured to signal the pressure of the first stressor based on features extracted from an image of the first crop captured at a first time, and predict a second pressure of the first stressor in the first crop at a second time after the first time based on observed and/or predicted diffusion (e.g., dispersion or movement, growth, decay) over time of the first stressor within the first crop.

In one embodiment, the system may derive a pressure model configured to predict future pressures of stressors in a specific crop and/or region based on the (current) detected pressures of the stressors in the specific crop and/or region. In particular, the system may utilize a time series of stressor data representing the presence and/or magnitude of a set of stressors detectable in sensitive plants in a specific geographic region over a specific period of time to predict the current or future pressure of the stressor in the specific geographic region.

For example, during a first time period, the system may interpret a first pressure of a first stressor within a first sub-region of the geographic area, interpret a second pressure of the first stressor within a second sub-region of the geographic area, and interpret a third pressure of the first stressor within a third sub-region of the geographic area. The system may then derive a first pressure map based on the first pressure, the second pressure, and the third pressure, the first pressure map indicating the presence of the first stressor within the geographic region during the first time period. Then, during the second time period, the system may interpret the fourth pressure of the first stressor in the first subregion, interpret the fifth pressure of the first stressor in the second subregion, and interpret the sixth pressure of the first stressor in the third subregion. The system may then derive a second pressure map based on the fourth pressure, the fifth pressure, and the sixth pressure, the second pressure map indicating the presence of the first stressor within the geographic region during the second time period. The system may then use the first pressure map and the second pressure map to derive a pressure model configured to predict a change in pressure of the first stressor in the geographic region as a function of time.

Thus, in the foregoing example, during a third time period subsequent to the second time period, the system may derive a third pressure map indicating the presence of the first stressor within the geographic region during the third time period based on the detected pressures of the first stressor in the first, second and/or third subregions, obtain a pressure model, and predict a fourth pressure map indicating the presence of the first stressor within the geographic region during a fourth time period subsequent to the third time period based on the third pressure map and the pressure model.

Further, in another embodiment, additionally, the system may obtain a time series of environmental data, such as a time series of weather data and/or a time series of process data (e.g., crop process data), for a particular crop and/or region corresponding to the time series of stressor data. In this embodiment, the system may fuse the environmental data time series with the stressor data time series to derive a pressure model configured to predict future pressures of stressors and/or changes in pressures of stressors in a particular crop and/or region based on the detected pressures of stressors and/or environmental data (e.g., current crop treatment, weather, crop management information) of the particular crop and/or region.

Thus, the system can derive a correlation between stressor data (e.g., recorded stress source pressure over time) for a particular crop and/or region and recorded environmental data to identify a stressor process that best matches the particular crop and/or region and predict a change in stress source pressure in the particular crop and/or region based on the detected stress source pressure and/or recorded environmental data. Thus, by tracking historical stressor data for the particular region or crop over time (e.g., over a month, over a crop season, over multiple crop seasons), the system can derive a correlation configured to predict future pressures of stressors in the particular region or crop, thereby enabling a user associated with the crop (e.g., farmer, agrologist, field worker) to quickly implement techniques configured to alleviate and/or prevent the pressures of these stressors and thus increase crop yield and/or reduce costs and/or crop losses associated with handling the stressors in the crop.

5.3.1 Environmental data diffusion conditions

In one variation, the system may utilize a time series of environmental data recorded for a particular area (e.g., crop, farmland, geographic area) to predict the current and/or future pressure of stressors within the particular area.

In one embodiment, the system may predict the pressure change of a particular stressor over time based on the environmental data time series. In particular, the system may predict a first pressure of a first stressor present in plants sown in an area of a crop based on a first image of sensitive plants in the area captured at a first time, acquire a first time sequence of environmental data (such as including weather data, process data, observed stressor data, etc.) corresponding to environmental conditions in the area of the crop during the first time period including the first time, and predict a second pressure of the first stressor at a future time based on the first pressure and the first time sequence of environmental data. In particular, the system may utilize a known and/or derived correlation between the environmental data and the pressure of the first stressor over time to predict a second pressure of the first stressor at a future time.

Furthermore, in the foregoing embodiments, the system may utilize the detected pressure of a particular stressor in a first region to predict the pressure of the particular stressor in a second region (e.g., proximate to the first region) based on the environmental data recorded for each of the regions.

Additionally or alternatively, in another embodiment, the system may utilize known characteristics of a particular stressor or stressors to predict the pressure change of the particular stressor over time. For example, at a first time during the growth period of a crop within a particular area, the system may predict a first pressure of fungal stressor at a first sub-area within the particular area and predict a second pressure of fungal stressor at a second sub-area within the particular area. The system may then obtain a set of diffusion conditions defined for the fungal stressor and defining the conditions required for the fungal stressor to spread between plants in the specific region, such as minimum and/or maximum temperature (e.g., air temperature), minimum and/or maximum rainfall, minimum and/or maximum solar exposure, a set of soil conditions (e.g., nitrogen level, pH level), maturity of plants in the specific region, and the like. The system may then acquire a time series of environmental data captured for a particular region during a time period including a first time, including a time series of conditions (e.g., weather, treatments) at plants in the particular region, characterize a correlation between the set of diffusion conditions and the time series of environmental data, and predict diffusion of fungal stressors within the particular region, such as at a first rate and/or according to a first pattern or profile, in response to the correlation exceeding a threshold correlation. Based on this predicted spread, the system may thus predict a third pressure of the fungal stressor at the first sub-region at a second time subsequent to the first time, and a fourth pressure of the fungal stressor at the second sub-region at the second time.

5.4 Yield prediction

In one embodiment, the system can predict the yield of a particular crop type (e.g., soybean, tomato, cotton, lettuce) and/or a particular crop in a particular geographic area.

In general, the system can predict the yield of certain crop types based on the stress of stressors present in those crops. In particular, the system may detect optical signals expressed by sensitive plants present in crops within a geographic area using images of the crops, predict pressures of a set of stressors throughout the geographic area based on the detected optical signals, derive a pressure map representing magnitudes and/or distributions of the pressures of the set of stressors throughout the geographic area based on the predicted pressures of the set of stressors, and predict crop yield for a particular crop type within the geographic area based on the derived pressure map.

For example, the system may predict a first pressure of a first stressor in a first crop of a first crop type (including a first set of sensitive plants configured to signal the presence of the first stressor) within a geographic area, predict a second pressure of the first stressor in a second crop of the first crop type (including a second set of sensitive plants configured to signal the presence of the first stressor) within the geographic area, predict a third pressure of the first stressor in a third crop of the first crop type (including a third set of sensitive plants configured to signal the presence of the first stressor) within the geographic area, and derive a pressure map representing the pressure of the first stressor throughout the geographic area based on the first pressure, the second pressure, and the third pressure. The system may then predict crop yield for crops of the first crop type in the geographic area based on the pressure map. The system may then repeat the process to similarly predict crop yield for each crop type in the set of crop types present in the geographic area.

In one variation, the system may utilize environmental data (including weather data, process data, and/or observed stressor data) recorded in conjunction with the pressure map for the geographic region to predict crop yield. For example, the system may derive a pressure map representing conditions (such as soil conditions (e.g., soil pH, nitrogen content), insect or fungus presence, disease, drought or flood, etc.) across a geographic area including a set of crops of a first crop type, acquire a time series of environmental data recorded for the geographic area during a growth period, acquire a time series of process data recorded for the geographic area during the growth period, such as a type and/or dose (e.g., quantity, duration) of a process (e.g., pesticide, fungicide, water, soil pH regulator, fertilizer) applied to one or more crops, and predict a crop yield of the first crop type within the geographic area based on the pressure map and the time series of environmental data.

5.4.1 Yield model

In one embodiment, the system may utilize a yield model to predict yield in a particular crop, in a particular area, and/or in a particular crop type (e.g., cotton, soybean, corn) worldwide. The system may then selectively distribute insights, instructions, and/or advice to various users associated with various departments of the agricultural supply chain based on the predicted yield for that particular crop type.

In this embodiment, the system may derive a yield model configured to predict crop yield for a particular crop, a particular area, and/or a particular crop type within a particular area. In particular, the system may record a time series of pressure data representing the pressure of a set of stressors within an area (e.g., a crop, a geographic area) throughout an initial growing period, record a final crop yield of a crop type of crop (e.g., soybean, cotton, lettuce, tomato) within the area, such as a final crop yield recorded during and/or after harvesting the crop type at the end of the initial growing period, store the time series of pressure data and the final crop yield in a first growth period packet (e.g., a data packet), and derive a yield model relating the pressure of the set of stressors within the geographic area to the crop yield of the crop type of crop within the geographic area based on the time series of pressure data and the final crop yield.

The system may further repeat the process during a subsequent growing period of the crop type within the geographic area to further refine the yield model. Specifically, the system may generate a series of growth periods, such as including a first growth period grouping, a second growth period grouping generated for a second growth period, a third growth period grouping generated for a third growth period, and the like, and modify the yield model based on each growth period grouping in the series of growth period groupings generated for crops of the crop type in the particular area. Further, the system may perform the process to derive a yield model for each crop type of crop present in the area. For example, the system may derive a first crop yield model configured to predict a crop yield of a tomato crop in the area, derive a second crop yield model configured to predict a crop yield of a soybean crop in the area, derive a third crop yield model configured to predict a crop yield of a cotton crop in the area, and so forth.

For example, the system may obtain a first time series of pressure data representing a change in pressure of a set of stressors in a first region during a first growth period, obtain a first crop yield of a crop of a first crop type (e.g., cotton) in the first region during a first harvest period corresponding to the first growth period, obtain a second time series of pressure data representing a change in pressure of the set of stressors in the first region during a second growth period subsequent to the first harvest period, obtain a second crop yield of a crop of the first crop type (e.g., cotton) in the first region during a second harvest period corresponding to the second growth period. The system may then implement regression, machine learning, deep learning, and/or other techniques to derive a correlation between stress-source pressure and crop yield in the particular region and/or in a particular crop in the region.

5.5 Yield Profile

In one variation, the system may derive a yield profile that represents predicted yields for crops of a set of crop types (e.g., soybean, tomato, cabbage, corn, cotton) within a particular area.

In particular, in this variation, the system may implement the above-described methods and techniques to interpret the pressure of a set of stressors in various sub-regions within a specific region and derive a pressure map for the specific region accordingly, predict crop yields in a set of crop yields for each crop type in a set of crop types based on the pressure map, and compile the set of crop yields into a yield profile for the specific region defining predicted crop yields for each crop type in the set of crop types. Over time, the system may update the yield profile based on detected and/or predicted changes in the pressure of a set of stressors throughout the geographic region.

For example, during a growth period, the system may acquire a first set of images depicting sensitive plants sown in crops within a first geographic area captured during a first period of time within the growth period, interpret pressures of a set of stressors within the geographic area based on features extracted from the first set of images, and integrate a first pressure map accordingly depicting pressures of the set of stressors within the first geographic area during the first period of time. The system may then predict a first crop yield of the crop of the first crop type in the first set of crop yields based on a first subset of features extracted from an area of the first pressure map corresponding to the crop of the first crop type (e.g., soybean), generate a first yield profile for the first geographic area in a set of yield profiles representing the predicted yields of the crop of the set of crop types during the first time period, and store the first crop yield associated with the first crop type in the first yield profile.

The system may also predict a second crop yield of the crop of the first set of crop yields with respect to a second crop type (e.g., tomato) based on a second subset of features extracted from an area of the crop corresponding to the second crop type of the first pressure map, store the second crop yield associated with the second crop type in the first yield profile, and repeat the process for each crop type of the set of crop types to integrate the integrated yield profile with respect to the first geographic area during the first time period.

Subsequently, during the growth period, the system may acquire a second set of images captured during a second period of time subsequent to the first period of time during the growth period, the second set of images depicting sensitive plants sown in crops within the first geographic area, interpret pressures of a set of stressors within the geographic area based on features extracted from the second set of images, integrate a second pressure map depicting pressures of a set of stressors within the first geographic area during the first period of time accordingly, predict crop yields in the second set of crop yields for crops of each crop type in the set of crop types based on features extracted from an area of the second pressure map corresponding to the crops of each crop type, and generate a second yield profile in the set of yield profiles for the first geographic area, the second yield profile representing predicted yields for crops of the set of crop types during the second period of time.

The system may then store a second set of crop yields (each crop yield associated with a particular crop type) in a second yield profile, associate the first yield profile with a first time value (e.g., a timestamp) corresponding to the first time period, associate the second yield profile with a second time value corresponding to the second time period, and derive a time series of crop yield profiles for the first geographic area including the first yield profile associated with the first time value (e.g., a timestamp) corresponding to the first time period and the second yield profile associated with the second time value corresponding to the second time period. The system may repeat the process for the remainder of the entire growing season and for each subsequent growing season to derive a comprehensive time series of crop yield profiles for the first geographic region.

5.6 Crop health status

In one embodiment, the system may utilize a time series of crop data (e.g., pressure, stressor, and/or environmental data) collected for a particular crop and/or a particular area to characterize the health of the particular crop and/or the particular area (hereinafter "crop health").

For example, the system may acquire a first set of crop data corresponding to operation of a first crop located in a first area during a first time period, including a number of stressors detected during the first time period, an average pressure of each stressor detected, stress resistance of the crop to each stressor detected (e.g., an average duration of recovery), total yield of the crop during a harvest season corresponding to the first time period, and/or quality of harvested crop (such as assessed by a user associated with the crop during the harvest season), and so forth. The system may then characterize a health score (e.g., a percentage between 0% and 99%, a scale value from 1 to 10, classified as "poor", "general", "good", or "excellent") for the crop based on the first set of crop data collected during the first period of time.

In the foregoing examples, the system may repeat the process for multiple crops and/or crop areas to integrate health maps that represent crop health in various areas and/or across those areas during a particular period of time. Furthermore, the system may update the health map over time (such as over multiple growth periods).

In one variation, the system may predict crop yield for a crop of one crop type within a particular area based on a predicted crop health of the crop of that crop type within the particular area. In particular, in this variation, the system may characterize a plant health of a crop of one crop type within an area based on a set of crop data collected for the crop of the crop type in the area, such as a time series including pressure data and/or environmental data (e.g., process data, weather data), obtain a yield model that relates the plant health of the crop type to crop yield, and predict a crop yield of the crop type (e.g., at the end of a current growing season) based on the plant health and yield model of the crop type in the area.

For example, at a first time during a growth period, the system may obtain a first time sequence of crop data recorded for a crop of a first crop type of a group of crop types sown in a first subregion of the region during a first time period preceding the first time, including a first time sequence of pressure data and a first time sequence of environmental data, obtain a second time sequence of crop data recorded for a plant of the first crop type sown in a second subregion of the region during the first time period, including a second time sequence of pressure data and a second time sequence of environmental data, and obtain a third time sequence of crop data recorded for a plant of the first crop type sown in a third subregion of the region during the first time period, including a third time sequence of pressure data and a third time sequence of environmental data. The system may then predict a first health score for the crop of the first crop type in the first sub-region based on the first time sequence of crop data, predict a second health score for the crop of the first crop type in the second sub-region based on the second time sequence of crop data, predict a third health score for the crop of the first crop type in the third sub-region based on the third time sequence of crop data, and predict a first crop yield for the crop of the first crop type based on the yield model and the set of health scores, such as at a future time after the first time (e.g., at the end of the growing period).

5.7 Prompting

In one embodiment, the system may selectively generate and distribute cues related to the detection and alleviation of stress of stressors within a crop or within a specific area. In particular, the system may identify and suggest stress relief techniques configured to reduce the pressure of a detected stressor in a crop or an area, minimize the spread of the detected pressure within a crop or over a specific area, and maximize crop yield within and/or over a specific crop.

For example, as described above, the system may derive a first pressure map for a particular region that represents the locations of various pressures of the stressor detected during the first time period. The system may then predict a second pressure map representing a predicted location of the predicted pressure of the stressor detected during a second time period subsequent to the first time period based on the first pressure map and the pressure model generated for the specific region, and/or estimate a predicted crop yield of the first crop type crop in the specific region based on the first pressure map, the second pressure map, and a yield model that correlates the pressure map with crop yields of the first crop type crop in the specific region.

The system may then send a set of prompts to a set of crop operators associated with the crop in the particular area based on the first pressure map to perform a set of mitigation techniques configured to increase the efficiency of crop treatment and maintenance over time and/or to maintain or increase the yield of the crop. Further, the system may update a crop profile associated with the crop in the particular area based on the first pressure map, the second predicted pressure map, and the predicted crop yield. The system may then send the data to additional end users (e.g., crop treatment developers, clothing retailers, food retailers) associated with and/or interested in the yield and/or health of the crop in the particular area.

5.7.1 Treatment Effect

In one embodiment, the system may characterize the effect of a crop treatment based on a detected change in pressure of a particular stressor or stressors.

For example, the system may interpret a first pressure of a first stressor in a crop of a particular crop type based on features extracted from a first image of the crop recorded during a first time period, and in response to interpreting the first pressure of the first stressor, generate a prompt to apply a first treatment, such as a particular dose and/or type of treatment (e.g., pesticide, fungicide, irrigation, fertilizer, soil pH treatment), to the crop during a second time period after the first time period, and send the prompt to a user (e.g., farmer) associated with the crop. The system may then interpret a second pressure of the first stressor in the crop based on features extracted from a second image of the crop recorded during a third time period subsequent to the second time period, characterize a difference between the first pressure and the second pressure of the first stressor, and characterize an effect of the first treatment in relieving the pressure of the first stressor based on the difference.

For example, in response to the difference exceeding a threshold difference such that the detected pressure of the first stressor decreases (e.g., by more than a threshold amount) in response to the administration of the first treatment, the system may characterize the first treatment as highly effective in relieving the pressure of the first stressor. However, in response to the difference falling below the threshold difference such that the detected pressure of the first stressor increases and/or exhibits a minimal decrease (e.g., decreases by less than a threshold amount) in response to administration of the first treatment, the system may characterize the first treatment as ineffective in relieving the pressure of the first stressor. The system may store this information in the crop profile of the crop to inform future treatment recommendations for the first stressor in the particular crop, the crop of the crop type, and/or the crops of all crop types.

5.8 Supply chain tracking

In one embodiment, the system may track the distribution of populations of sensitive plants modified to include specific identifiers throughout the life cycle of these sensitive plants (e.g., along the crop supply chain) during transfer of the sensitive plants through the crop supply chain, such as from a growing period within the crop, to loading onto a specific transport vehicle, to storage within a specific storage facility, to processing within a specific facility, and so forth.

For example, for a first sensitive plant including a fluorescent tag configured to express a baseline fluorescent signal, the system may acquire a first image (e.g., a hyperspectral image) in a set of images captured by a farmer or an agronomst (e.g., via a mobile device) associated with a crop containing the sensitive plant, the first image including a first timestamp and depicting the baseline fluorescent signal, acquire a second image in the set of images captured by an optical sensor disposed within a crop storage facility, the second image including a second timestamp and a lot identifier for a lot containing the sensitive plant and depicting the baseline fluorescent signal, acquire a third image in the set of images captured by an optical sensor installed within a processing and/or manufacturing facility (e.g., food manufacturing and/or processing facility, clothing manufacturing facility), the third image including a third timestamp and depicting the baseline fluorescent signal, and acquire a fourth image in the set of images captured by an optical sensor installed within a retail facility (e.g., grocery store, clothing) the fourth image including a fourth timestamp and depicting the baseline fluorescent signal. Thus, the system can correlate sensitive plants (e.g., products of sensitive plants) sold in the retail facility to crops and/or origin areas based on detection of the baseline fluorescence signal in the set of images.

Over time, based on these associations, the system may obtain additional information about crop yield and crop distribution, and thus update the crop profile for a particular crop and/or a particular crop area based on that information. The system may then use this information to derive more accurate insights or information about crop yield, crop supply, crop health, crop quality, and/or crop management for a particular crop and/or crop area. For example, soybean plant crops (e.g., susceptible soybean plants) can be modified to express a baseline fluorescence signal configured to fluoresce only in the soybean pods, thereby enabling direct reporting of soybean yield through the soybean plant crops throughout the life cycle of these soybean plants (such as during growth, harvesting, and/or distribution throughout the supply chain). In particular, the system can acquire images of soybean plants sown in and/or harvested from the crop, characterize the magnitude (e.g., intensity) of baseline fluorescence signals detected in the images, and estimate yield of the soybean crop based on the magnitude of the baseline fluorescence signals. The system may then repeat the process to update the yield estimate of the soybean crop over time.

Further, in this embodiment, the system may utilize this information to identify a subset of users associated with the supply chain of a particular crop and/or crop area, and over time, selectively send information, insights, instructions, recommendations, and/or suggestions to these different subsets of users, such as information, insights, instructions, recommendations, and/or suggestions related to actual and/or predicted crop yield, crop supply, crop health, crop quality, crop management, and the like.

For example, the system may identify a subset of users associated with cotton manufacturing clothing grown from a particular area based on receiving an identification of a baseline fluorescence signal associated with cotton grown in the particular area from among cotton stored in a manufacturing plant associated with the subset of users. Then, during the next growing period of cotton in the particular area, the system may selectively provide notifications and/or cues to the subset of users, such as in response to detecting a high pressure of a particular stressor in the area, in response to predicting that crop supply of cotton in the particular area is very low, in response to predicting that crop supply of cotton in the particular area is very high, and so forth. Thus, the system may then (near) supply the subset of users with valuable insights or information in real time, which relate to derived data and/or predictions relating to cotton supply for the particular subset of users and cotton supply from the particular area during the growing period.

In one variation, the system can utilize the detection of the baseline signal to distinguish between plants in the crop (e.g., susceptible plants) and weeds growing in the crop. For example, the system may acquire images of crops recorded by optical sensors (e.g., optical sensors mounted on a manned or unmanned field device such as a tractor, optical sensors on a handheld device operated by a farmer or an agronomic, and/or optical sensors mounted on a boom or stick in the field) including a set of sensitive plants configured to express a baseline fluorescence signal, isolate areas in the image corresponding to the absence of the baseline fluorescence signal, and mark these areas for application of a particular weed treatment (such as by alerting the farmer to apply the particular weed treatment and/or by triggering application of the weed treatment by an automated field device (e.g., an automated sprayer mounted on a tractor)) and/or for further review. The system may repeat the process periodically (e.g., daily, weekly) to review weeds and/or other threats (e.g., invasive plants) present in the crop, thereby reducing the risk of the crop and achieving an increase in yield.

6. Simulating plant health

In one embodiment, the system may utilize sensitive plant data collected over time from a particular sensitive plant or group of sensitive plants grown within a particular crop to characterize plant health of individual plants, groups of plants, and/or all plants in the particular crop.

In particular, in this embodiment, the system may focus on a particular set of conditions (e.g., environmental conditions) indicative of plant health of plants in the particular crop (e.g., a single sensitive plant or a group of sensitive plants and/or an entire sensitive plant crop within the particular crop), such as the presence of a set of stressors (e.g., abiotic stressors and/or biological stressors), soil conditions (e.g., pH levels, nitrogen levels), weather conditions, and the like. Thus, the system can detect signals (e.g., fluorescent signals) expressed by a set of sensitive plants in the particular crop, predict a set of current conditions at the set of sensitive plants based on the signals, and interpret plant health, such as individual plant health of each sensitive plant in the set of sensitive plants and/or composite plant health of the set of sensitive plants, based on the set of current conditions detected at the set of sensitive plants.

Based on the predicted plant health, the system may select a particular crop treatment configured to improve or maintain the plant health tailored to a particular plant or group of plants within the crop.

Thus, in this embodiment, the system can utilize sensitive plant data collected over time for one or more sensitive plants sown in a particular crop to predict conditions at the plants throughout the particular crop, such as magnitudes and/or distributions corresponding to plant stressors (e.g., soil pH level, nitrogen absorption, moisture retention, insect presence, fungus presence), and thus characterize the health of individual plants or groups of plants with high resolution, enabling custom treatment of a particular group of plants in the crop in response to changes in plant health.

6.1 Target conditions

In one embodiment, the system may define a set of target plant conditions (e.g., soil pH, nitrogen levels in the soil, irrigation levels, fertilizer levels, fungicide levels) for a particular crop. Generally, in this embodiment, the system may derive a set of target plant conditions that yield at least a target crop health condition, such as a set of target plant conditions corresponding to a threshold crop yield (e.g., minimum crop yield), and store the sets of target plant conditions as constituting a "healthy crop" or "healthy plant" (e.g., in a crop profile generated for that particular crop).

In particular, in this embodiment, during an initial period, the system may track plant conditions in sensitive plants located within the crop, such as the magnitude of insect stress, the magnitude of fungal stress, the magnitude of drought stress (e.g., dehydration), plant nitrogen content (e.g., the amount of nitrogen the plant consumes from the soil), and analyze these data to derive a correlation between plant conditions and plant health. Thus, the system can derive a set of target plant conditions for plants in the crop that produce at least a minimum or target plant health condition, assign sensitive plants to signal plant conditions that are close to (e.g., within a threshold deviation of) the set of target plant conditions that qualify as "healthy" plants, such as by outputting a set of fluorescent signals within a particular wavelength range associated with the plant conditions, and implement the set of target plant conditions to selectively distinguish "healthy" plants in the crop from "unhealthy" or "unhealthy" plants in the crop during a growing season that, if not treated, may result in crop loss (e.g., reduced crop yield).

In one example of the foregoing embodiment, the system may track a time series of plant conditions of sensitive plants grown within a crop over an initial period of time, such as including stress data, soil data, weather data, and the like, acquire a time series of crop data recorded for plants in the crop during the initial period of time, such as including plant health data (e.g., observed growth, wilting, plant death, color change, fruit growth) and/or yield data, calculate a correlation between plant conditions and plant health of the sensitive plants in a particular crop based on the time series of plant conditions and the time series of crop data, and define a set of target plant conditions associated with a threshold plant health, such as a set of target plant conditions associated with a threshold probability of achieving a threshold crop yield, based on the correlation. More specifically, in this example, the system may implement machine learning, artificial intelligence, neural networks, or other analysis techniques to characterize plant health as a function of plant conditions based on detected plant conditions and observed health data for sensitive plants in the particular crop. Based on a target or threshold health score (e.g., a minimum health score) defined for plants in a particular crop, such as a target or threshold health score predicted to achieve a threshold crop yield such as specified by an advertisement publisher for an advertisement campaign, the system may derive a set of target conditions predicted to produce the threshold health score for plants in the crop.

6.1.1 Example Nitrogen content in soil

In one example, the system may define a target nitrogen content for plants in a particular crop. In particular, in this example, the crop (e.g., soybean crop, corn crop, cotton crop) may include a set of sensitive plants, such as a set of sensitive plants that are planted in clusters in various areas of the crop and/or throughout the field, such that the set of sensitive plants includes each plant in the crop configured to signal a soil condition at the set of sensitive plants. In particular, in this example, each sensitive plant of the set of sensitive plants can include a promoter associated with the presence of nitrogen at the plant, and a reporter (e.g., a fluorescent protein) associated with the promoter, the reporter configured to express a fluorescent signal indicative of the uptake of nitrogen by the sensitive plant. Thus, in this example, the system may detect the fluorescent signal (such as in an image of the sensitive plant recorded by the satellite) and interpret the amount of nitrogen consumed by the sensitive plant based on the intensity of the fluorescent signal.

During a first growing season of the particular crop, the system may utilize a global target nitrogen content, such as a universal nitrogen content defined for substantially all plants or all plants of the particular crop type (e.g., soybean, corn, cotton), to predict plant health throughout the first growing season. In particular, the system may acquire an image feed of a crop (such as recorded by a satellite), detect fluorescent signals expressed by a set of sensitive plants in the crop and depicted in an image in the image feed, interpret the amount of nitrogen absorbed by the sensitive plants in the set of sensitive plants based on the fluorescent signals, and characterize plant health (such as across the entire crop and/or in a particular sub-area of the crop) based on the amount of nitrogen absorbed by the sensitive plants in the crop and the global target nitrogen content.

Over time, as the system collects additional data for sensitive plants in the crop, such as time series including nitrogen content, time series of nitrogen treatment data (e.g., frequency and amount of nitrogen applied to the soil), plant health data, and/or crop yield data, the system may focus on crop-specific and/or plant-specific target nitrogen content, such as by updating the universal nitrogen content based on the additional data collected over time. For example, during a first growing season, the system may collect surveys completed by users associated with the crop (such as at different times throughout the first growing season) and the surveys indicate plant health of the plants in the entire crop, such as specifying visual characteristics of the plants in the crop (e.g., color, wilt, height, fruit size, fruit growth), treatments applied to the crop (e.g., nitrogen, pesticides, fungicides, irrigation), crop losses, crop yield, and the like. Based on this data, in combination with the detected nitrogen content in the sensitive plants in the entire crop, the system can focus on the target nitrogen content corresponding to that particular crop and/or a particular sub-region of that crop. Over time, as the system continues to collect additional data for the crop, the system may continue to refine the target nitrogen content such that one or more users associated with the crop may apply nitrogen to the soil at a particular time in the growing season and/or in a particular sub-region of the crop according to the target nitrogen content defined for the particular crop and/or sub-region of the crop and configured to produce healthy plants in the crop.

Further, during this first growing season, the system may obtain an application amount of nitrogen specified by a user (e.g., farmer, agronomic) associated with the crop, such as soil applied to the crop and/or a particular sub-area of the crop, and characterize the uptake of nitrogen by plants in the crop (e.g., plants in the particular sub-area of the crop and/or substantially all plants across the crop) based on a difference between the application amount of nitrogen and the content of nitrogen detected at sensitive plants in the crop (e.g., based on fluorescent signals expressed by the sensitive plants).

For example, the system may obtain an initial amount of nitrogen applied to soil in the crop at an initial time corresponding to the beginning of a growing season. Then, at a first time, the system may acquire a first image of the crop recorded by the satellite, detect a first fluorescent signal expressed by the sensitive plant in a first sub-area of the crop, detect a second fluorescent signal expressed by the sensitive plant in a second sub-area of the crop, interpret a first amount of nitrogen consumed by the plant in the first sub-area (e.g., from soil) based on the first fluorescent signal, and interpret a second amount of nitrogen consumed by the plant in the second sub-area based on the second fluorescent signal. Then, for the first sub-region, the system may calculate a first ratio of the first nitrogen amount to the initial nitrogen application amount, calculate a duration between the first time and the initial time, and characterize the first nitrogen absorption (e.g., nitrogen consumption rate) based on the first ratio and the duration. Similarly, for the second subregion, the system can calculate a second ratio of the second nitrogen amount to the initial nitrogen application amount and characterize a second nitrogen absorption (e.g., nitrogen consumption rate) based on the second ratio and the duration. Thus, prior to subsequent application of nitrogen in soil in a crop, the system may derive a first nitrogen application amount for a first subregion of the crop, the first nitrogen application amount being predicted to produce nitrogen absorption corresponding to a target nitrogen content in plants in the first subregion, derive a second nitrogen application amount for a second subregion of the crop, the second nitrogen application amount being predicted to produce nitrogen absorption corresponding to a target nitrogen content in plants in the second subregion, generate a cue to apply the first nitrogen application amount and the second nitrogen application amount in the first subregion and the second subregion, respectively, at a second time (e.g., during a first growing season), and transmit the cue to a user or group of users associated with the crop.

6.2 Characterization of plant health

The system may characterize the health of plants in a particular crop based on a set of target plant conditions defined for that crop.

In particular, in this embodiment, the system may characterize plant health based on differences between a set of current plant conditions of the crop (such as derived from fluorescent signals expressed by sensitive plants in the crop and detected in an image of the crop) and a set of target plant conditions defined for the crop.

For example, the crop may include sensitive plants configured to signal nitrogen absorption in these sensitive plants (e.g., in the crop). In particular, each of a set of sensitive plants located in a crop may be configured to output a fluorescent signal within a target wavelength range that is indicative of an amount of nitrogen consumed by the sensitive plant (e.g., from soil). In this example, during a first period of time, the system may derive a target nitrogen content of soil in the crop (such as a target nitrogen dose defining a frequency of nitrogen application and an amount of nitrogen applied at each application) configured to produce plants in the particular crop that are "healthy" to the plant, such as characterized by a health score exceeding a threshold health score, and store the target nitrogen content in a crop profile generated for the crop.

Then, during a second time period after the first time period, the system may acquire an image feed of a sensitive plant in the crop recorded by an imaging system (e.g., a satellite, an optical sensor mounted on a drone, a tractor, or a wand mounted in the crop, or a camera on a mobile device) during the second time period, the imaging system configured to capture fluorescent signals output by the sensitive plant configured to output fluorescent signals within a target wavelength in response to various plant stressors, extract a first intensity of the fluorescent signals within the target wavelength range (e.g., a composite fluorescent signal output by a set of sensitive plants), and predict a current nitrogen level in the plant in the crop based on the first intensity of the fluorescent signals.

In the foregoing example, the system may then obtain a target nitrogen content defined for the particular crop that is stored in the crop profile, characterize a difference between the current nitrogen content and the target nitrogen content, and characterize the health of the plant (or "plant health") in the crop based on the difference. For example, the system may estimate a health score of a plant in a crop, such as represented by a percentage between 0% and 100%, a score between 0 and 10, a rating with poor health, medium health, good health, or excellent health, etc. In one example, in response to the difference exceeding an upper threshold difference defined for plants in the particular crop, the system may estimate a relatively low health score (e.g., "5%", "1/10", poor health condition) for the plants in the crop. Alternatively, in response to the difference falling below the upper threshold difference and exceeding the lower threshold difference, the system may estimate a relatively medium health score (e.g., "50%",5/10, medium health) for the plants in the crop. Alternatively, in response to the difference falling below the lower threshold difference, the system may estimate a relatively high health score (e.g., "95%",9/10, excellent health) for the plants in the crop.

6.2.1 Health Condition model

In one variation, the system may derive a plant health model configured to incorporate (interest) a set of current conditions detected for a particular sensitive plant or group of sensitive plants and output a prediction of the current plant health of the particular sensitive plant or group of sensitive plants.

For example, during a first growing season of a particular crop, the system may track a first set of plant conditions at a first set of sensitive plants located in a first sub-area of the crop, track a second set of plant conditions at a second set of sensitive plants located in a second sub-area of the crop, obtain a first set of plant surveys completed by a user or users associated with the crop, the first set of plant surveys indicating health of plants in the first sub-area throughout the first growing season, obtain a second set of surveys completed by a user or users associated with the crop, the second set of surveys indicating health of plants in the second sub-area throughout the first growing season, and/or obtain a first set of crop data collected for the crop during the first growing season, such as including weather data, crop yield data (e.g., crop yield data for the entire crop and/or sub-area of the crop), crop treatment data (e.g., crop treatment data for the entire crop and/or sub-area of the crop), and the like.

The system may then derive a first health model configured to predict health of plants in the first sub-area of the crop based on the first set of plant conditions, the first set of plant surveys, and the first set of crop data, the first health model configured to predict health of plants in the first sub-area of the crop based on plant conditions at the sensitive plants in the first sub-area, and derive the first health model based on the second set of plant conditions, the second set of plant surveys, and the first set of crop data, the first health model configured to predict health of plants in the first sub-area of the crop based on plant conditions at the sensitive plants in the first sub-area.

Then, during a subsequent growing season, the system may acquire a first image depicting plants in a first sub-region of the crop, interpret a first set of plant conditions based on fluorescence signals extracted from the first image, and characterize health of the plants in the first sub-region, such as represented by a first plant health score, based on the first set of plant conditions and the first health model. Further, the system may obtain a second image depicting plants in a second sub-area of the crop, interpret a second set of plant conditions based on fluorescence signals extracted from the second image, and characterize health conditions of plants in the second sub-area, such as represented by a second plant health score, based on the second set of plant conditions and a second health model. In this example, the system may then select a particular treatment pathway for implementation in each sub-region of the crop, thereby enabling the treatment of the plants in each sub-region to be tailored based on the changes in the health of the plants in those sub-regions.

In one example, the system may derive a health model configured to output a health score representative of a health of plants in a particular sub-area of the crop based on a magnitude of nitrogen consumption detected in sensitive plants in the particular sub-area, a magnitude of moisture consumption detected in sensitive plants in the particular sub-area, a magnitude of fungal pressure detected in the particular sub-area, and/or a magnitude of insect pressure detected in the particular sub-area.

6.3 Targeted treatment

The system may use the difference between a set of target conditions defined for a crop and the (currently) detected conditions in the crop to suggest that a targeting treatment be performed on the plants in the crop.

In particular, the system may selectively suggest treatments (such as to a farmer or agronomic associated with the crop) configured to offset current conditions within the crop toward a set of target conditions defined for the crop and/or for a particular subset of plants in the crop (e.g., in a particular sub-area).

Thus, the system may acquire an image or images of sensitive plants in a crop, extract fluorescent signals representative of first conditions of the sensitive plants (such as the magnitude of fungal stressors present at the sensitive plants or the amount of nitrogen consumed by the sensitive plants) using a reporter model defined for the sensitive plants, acquire target conditions defined for the plants in the crop and corresponding to the first conditions, such as a threshold magnitude (e.g., a maximum magnitude) of fungal stressors that are tolerable to the plants in the crop or a target nitrogen content configured to maximize plant health or growth (e.g., within a target range), characterize a difference between the first conditions and the target conditions, and select a treatment pathway for the plants in the crop configured to adjust the first conditions toward the target conditions based on the difference. The system may then prompt a user associated with the crop to implement the treatment pathway and/or automatically trigger the implementation of the treatment pathway, such as via an automated treatment system.

Furthermore, by utilizing signals generated by sensitive plants distributed throughout the crop, the system can selectively suggest different treatment types and/or doses of treatments in different areas within the particular crop. Thus, the system may enable targeted treatment of plants within a particular crop and/or geographic area (e.g., across multiple crops) based on conditions within each of these different areas.

For example, the system may obtain an image feed of a population of sensitive plants including a first set of sensitive plants sown in a first sub-region of the crop and a second set of sensitive plants arranged in a second sub-region of the crop, interpret a first set of conditions at the plants in the first sub-region based on a first subset of features (such as fluorescence intensity in a first wavelength range) extracted from the first image in the image feed, obtain a set of target conditions defined for the plants in the crop, characterize a first difference between the first set of conditions and the set of target conditions, and select a first treatment pathway for application in the plants in the first sub-region in response to the first difference exceeding a threshold difference. The system may also interpret a second set of conditions at the plant in the second sub-region based on a second subset of features extracted from the first image (such as fluorescence intensity in the first wavelength range), characterize a second difference between the second set of conditions and the set of target conditions, and select a second treatment pathway for application in the plant in the second sub-region in response to the second difference exceeding a threshold difference. The system may then generate a notification including a prompt to implement the first treatment pathway in the first sub-area and the second treatment pathway in the second sub-area, and send the prompt to a farmer associated with the crop.

6.3.1 Treatment diagrams

In one variation, the system may derive a treatment map for a particular crop based on a set of target conditions defined for that crop. In particular, in this variation, the system may integrate a treatment map based on the treatment pathways selected for the individual sub-regions of the crop, the treatment map specifying the location and magnitude (e.g., frequency and/or amount) of application for each treatment pathway selected for the crop.

For example, the system may acquire an image of a crop recorded by a satellite at a first time, the image depicting a set of fluorescent signals expressed by sensitive plants in the crop, interpret a first nitrogen content in plants in a first sub-area of the crop based on a first fluorescent signal in the set of fluorescent signals, interpret a second nitrogen content in plants in a second sub-area of the crop based on a second fluorescent signal in the set of fluorescent signals, and interpret a third nitrogen content in plants in a third sub-area of the crop based on a third fluorescent signal in the set of fluorescent signals. Then, for a first subregion of the crop, the system may obtain a first target nitrogen content corresponding to plants in the first subregion from a set of target nitrogen contents derived for the crop, characterize a difference between the first nitrogen content and the first target nitrogen content, and derive a first nitrogen application amount for application to soil in the first subregion at a second time that is subsequent to the first time based on the difference. The system may similarly repeat the process for the second sub-region and the third sub-region to derive a second nitrogen application rate for application to soil in the second sub-region at the second time and a third nitrogen application rate for application to soil in the third sub-region at the second time. The system may then derive a treatment map for implementation at about the second time, the treatment map indicating the first, second, and third amounts of applied nitrogen to be applied in the first, second, and third sub-regions of the crop, respectively, and send the treatment map to the user for implementation in the crop at about the second time. Additionally and/or alternatively, in this example, the system can upload the treatment map to an autonomous vehicle (e.g., an autonomous tractor or drone) configured to autonomously traverse the crop and apply nitrogen to soil in the crop according to the treatment map.

In one embodiment, the system may derive a treatment map specifying treatment types and treatment doses (e.g., amounts and/or durations of treatments) for application in a particular area of a crop and/or within a geographic area. For example, the system may interpret a first pressure of a first stressor in a first region of a crop based on features extracted from a first portion of a first image depicting sensitive plants in the first region, interpret a second pressure of the first stressor in a second region of the crop based on features extracted from a second portion of the first image depicting sensitive plants in the second region, select a first mitigation technique (e.g., apply pesticide or fungicide, water plants, fertilize plants) configured to mitigate the pressure of the first stressor in the crop, define a dose gradient for applying the first mitigation technique on the crop based on the first pressure and the second pressure, and generate a treatment map based on the first mitigation technique and the dose gradient. For example, the system may generate a treatment map defining a first dose of a first relief action in a first region of the crop and a second dose of the first relief action in a second region of the crop that is less than the first dose in response to the second pressure dropping below the first pressure.

6.4 Stress resistance of crops

In one variation, the system can characterize crop stress resistance of a particular crop to a set of plant stressors (e.g., abiotic stressors and/or biotic stressors), such as drought, overheating, nutrient deficiency (e.g., nitrogen deficiency, phosphorus deficiency), excessive watering, salinity, soil pH, soil pollution, insects, fungi, weed growth, and the like.

In particular, in this embodiment, the system may characterize the stress resistance of the crop to a particular stressor in the set of plant stressors based on a target plant condition defined for the crop that is associated with the particular stressor. For example, the system can quantify stress resistance of a plant in a crop to nitrogen deficiency as an inverse function of a target nitrogen content defined for the plant in the crop. More specifically, in this example, if the target nitrogen content defined for plants in a crop is relatively low, the system may quantify the stress resistance of these plants to nitrogen deficiency as relatively high. Alternatively, in this example, if the target nitrogen content defined for plants in the crop is relatively high, the system may quantify the stress resistance of these plants to nitrogen deficiency as relatively low.

Additionally and/or alternatively, in another embodiment, the system can characterize stress tolerance of a crop to a particular stressor in the set of plant stressors based on sensitivity of the plant in the crop to deviations from a target plant condition associated with the particular stressor. For example, the system can interpret the sensitivity of a plant in a crop to nitrogen deficiency (such as below a target nitrogen content defined for the plant in the crop) based on observed changes in plant health, and quantify stress resistance of the plant in the crop to nitrogen deficiency as an inverse function of the sensitivity. The system may similarly repeat the process for each stressor in the set of plant stressors to characterize stress resistance of the crop or plant in the particular crop to the set of plant stressors.

The systems and methods described herein may be at least partially embodied and/or implemented as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions may be executed by a computer-executable component integrated with an application, applet, host, server, network, website, communication service, communication interface, hardware/firmware/software element of a user computer or mobile device, wristwatch, smart phone, or any suitable combination thereof. Other systems and methods of embodiments may be at least partially embodied and/or implemented as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions may be executed by a computer-executable component integrated with a device and network of the type described above. The computer readable medium may be stored on any suitable computer readable medium such as RAM, ROM, flash memory, EEPROM, an optical device (CD or DVD), a hard disk drive, a floppy disk drive, or any suitable device. The computer-executable components may be processors, but any suitable special purpose hardware devices may (alternatively or additionally) execute the instructions.

As will be recognized by those skilled in the art from the foregoing detailed description and from the accompanying drawings and claims, modifications and changes may be made to the embodiments of the invention without departing from the scope of the invention as defined in the appended claims.

Claims (20)

1. A method, comprising:

-acquiring an image feed of sensitive plants of a sensitive plant type sown in a set of farmlands within a geographical area, the image feed being recorded during a first period of time, the sensitive plants of the sensitive plant type being configured to signal the presence of a set of stressors at the sensitive plants;

-interpreting a first pressure of a first stressor of the set of stressors in a first sub-region within the geographical area based on features extracted from a first subset of images of sensitive plants in the first sub-region depicted in the image feed;

-interpreting a second pressure of the first stressor in a second sub-region within the geographical area based on features extracted from a second subset of images of sensitive plants in the second sub-region depicted in the image feed;

-deriving a first pressure map of the geographical area based on the first pressure and the second pressure, the first pressure map representing the presence of the set of stressors within the geographical area during the first period of time;

-obtaining a yield model relating the pressure of the set of stressors within the geographical area to the crop yield of a set of crop types of crops in a target area, and

-Predicting a first crop yield of crops of a first crop type of the set of crop types in the geographical area based on the first pressure map and the yield model.

2. The method according to claim 1:

Wherein predicting the first crop yield of the crop of the first crop type based on the first pressure map and the yield model comprises predicting the first crop yield of the crop of the first crop type based on a first subset of features extracted from an area of the first pressure map corresponding to the crop of the first crop type and the yield model, and

-Further comprising:

Predicting a second crop yield of a crop of a second crop type in the geographic region based on a second subset of features extracted from a region of the first pressure map corresponding to the crop of the second crop type in the set of crop types and the yield model, and

-Generating a first yield profile in a set of yield profiles in relation to the geographical area based on the first crop yield of the crop of the first crop type and the second crop yield of the crop of the second crop type.

3. The method according to claim 1:

-wherein deriving the first pressure map comprises:

Predicting a third pressure of the first stressor at a third sub-region within the geographical region based on the first pressure of the first stressor in the first sub-region and the second pressure of the first stressor in the second sub-region, and

-Deriving said first pressure map of said geographical area based on said first pressure, said second pressure and said third pressure, and

-Wherein predicting the first crop yield of the crop of the first crop type in the geographic area comprises predicting the first crop yield of the crop of the first crop type in the geographic area comprising:

-a first crop of said first crop type located in said first sub-area and comprising a first group of sensitive plants of said sensitive plant type;

-a second crop of said first crop type located in said second sub-area and comprising a second group of sensitive plants of said sensitive plant type, and

-A third crop of said first crop type located in said third sub-area.

4. The method according to claim 1:

-further comprising:

-interpreting a third pressure in the first sub-region of a second stressor of the set of stressors based on features extracted from the first subset of images, and

-Interpreting a fourth pressure of the second stressor in the second sub-region in the set of stressors based on features extracted from the second subset of images, and

-Wherein deriving the first pressure map of the geographical area based on the first pressure and the second pressure comprises deriving the first pressure map of the geographical area based on the first pressure of the first stressor, the second pressure of the first stressor, the third pressure of the second stressor and the fourth pressure of the second stressor.

5. The method according to claim 4:

-wherein interpreting the first pressure of the first stressor in the first sub-region based on features extracted from the first subset of images comprises:

-extracting a first set of fluorescence measurements in a first wavelength range from said first subset of images, and

-Interpreting said first pressure of said first stressor in said first sub-region based on said first set of fluorescence measurements, and

-Wherein interpreting the third pressure of the second stressor in the first sub-region based on features extracted from the first subset of images comprises:

-extracting a second set of fluorescence measurements in a second wavelength range from said first subset of images, and

-Interpreting said third pressure of said second stressor in said first sub-region based on said second set of fluorescence measurements.

6. The method of claim 1, further comprising, during the initial period:

-for each growth phase of a series of growth phases within the initial period:

-recording a time series of pressure data representing the pressure of the set of stressors within the geographical area throughout the growth period;

-recording the final crop yield of the crop type of crop in the geographical area, and

-Storing the time series of pressure data and the final crop yield in one of a series of growth period groups, and

-Deriving a model relating the pressure of the set of stressors within the geographical area to the crop yield of the crop type within the geographical area based on the series of growing period groupings.

7. The method according to claim 1:

-further comprising acquiring a time sequence of weather data recorded for the geographical area during the first time period, and

-Wherein predicting the first crop yield based on the first pressure map and the yield model comprises predicting the first crop yield based on the first pressure map, a time series of the weather data and the yield model.

8. The method of claim 1, further comprising:

-predicting a third pressure of the first stressor in the first sub-region at a second time subsequent to the first time based on the first pressure map;

-predicting a fourth pressure of the first stressor in the second sub-region at the second time based on the first pressure map;

-deriving a second pressure map of the geographical area based on the third pressure of the first stressor and the fourth pressure of the first stressor;

generating a processing map for implementation at said second time based on said second pressure map, and

-Sending the treatment map to a group of users associated with crops in the geographical area.

9. The method according to claim 8:

-wherein generating the processing graph comprises:

-selecting a first mitigation technique from a set of mitigation techniques, the first mitigation technique configured to mitigate stress of the first stressor in the geographic region, and

Defining a dose gradient based on the first pressure map, the dose gradient including an array of doses for administering the first mitigation technique across the geographic area, and

-Wherein transmitting the treatment map to the group of users associated with crops in the geographical area comprises:

-transmitting the treatment map to a first subset of users of the group of users associated with applying the first mitigation technique within the geographic area, and

-Sending the treatment map to a second subset of users of the group of users associated with the manufacture of chemicals associated with the first mitigation technique.

10. The method of claim 1, further comprising:

-acquiring a target pressure range defined for the pressure of the first stressor in the first sub-region;

-characterizing the difference between the first pressure and the target pressure range, and

-In response to the difference exceeding a threshold difference:

-selecting a first relief action from a set of relief actions, the first relief action being configured to relieve stress of the first stressor;

-selecting a first dose of the relief action based on the difference;

-generating a cue for performing said first relief action at said first dose in a crop of said crop type within said first sub-area, and

-Sending the prompt to a group of users associated with crops in the first sub-area.

11. The method of claim 1, further comprising:

-at a second time after the first time, in response to harvesting the crop of the crop type within the geographic area, obtaining a final crop yield of the crop type harvested within the growing period;

obtaining a time series of pressure maps derived for said geographical area during said growth period, said time series of pressure maps comprising said first pressure map, and

-Modifying the yield model based on the time series of the pressure map and the final crop yield.

12. The method of claim 1, further comprising:

-based on the first pressure map:

-selecting a first relief action from a set of relief actions, the first relief action being configured to relieve stress of the first stressor;

-generating a first prompt to effect the first mitigation action in the crop of the one crop type within the geographic area during a second time period subsequent to the first time period, and

-Sending the first prompt to a group of users associated with crops of the crop type in the geographical area;

-interpreting a third pressure of the first stressor in the first sub-region based on features extracted from a third subset of images of sensitive plants depicted in the first sub-region in the image feed;

-interpreting a fourth pressure of the first stressor in the second sub-region based on features extracted from a fourth subset of images of sensitive plants depicted in the second sub-region in the image feed;

-characterizing a first difference between the third pressure and the first pressure in the first sub-zone;

-characterizing a second difference between the second pressure and the fourth pressure in the second sub-zone;

-in response to the first difference exceeding a threshold difference:

-generating a second cue to effect the first mitigation action in the crop of the crop type within the first sub-area during a third time period subsequent to the second time period, and

-Sending the second prompt to a first subset of users of the group of users associated with the crop of the crop type in the first sub-area, and

-In response to the second difference falling below the threshold difference:

-selecting a second relief action in the set of relief actions to replace the first relief action, and the second relief action is configured to relieve stress of the first stressor;

-generating a third cue to effect the second mitigation action in the crop of the crop type within the second sub-area during the third period of time, and

-Sending the third prompt to a second subset of users of the group of users associated with the crop of the crop type in the second sub-area.

13. The method according to claim 1:

-wherein acquiring the image feed of a sensitive plant comprises acquiring the image feed of a sensitive plant of the sensitive plant type, the sensitive plant being configured to:

Selectively outputting fluorescent signals across a set of wavelength ranges based on the set of stressors, and

-Outputting a baseline fluorescence signal in a target wavelength range associated with the crop of the crop type, the wavelengths in the target wavelength range being outside the set of wavelength ranges;

-wherein interpreting the first pressure of the first stressor in the first sub-region based on features extracted from the first subset of images comprises:

-identifying a first group of crops of said crop type within said first sub-area based on detection of said baseline fluorescence signals within said first subset of images, and

Interpreting the first pressure of the first stressor in the first set of crops based on detection of fluorescent signals within the first subset of images spanning the set of wavelength ranges, and

-Wherein interpreting the second pressure of the first stressor in the second sub-region based on features extracted from the second subset of images comprises:

-identifying a second set of crops of said crop type within said second sub-area based on detection of said baseline fluorescence signals within said second subset of images, and

-Interpreting the second pressure of the first stressor in the second set of crops based on detection of fluorescent signals within the second subset of images across the set of wavelength ranges.

14. The method of claim 1, wherein obtaining the image feed of the sensitive plant type comprises obtaining the image feed of the sensitive plant type comprising:

A first promoter of a set of promoters, said first promoter being configured to activate in response to the stress of said first stressor, and

-A first reporter of a set of reporters associated with the first promoter and configured to express a detectable fluorescent signal responsive to activation of the first promoter and corresponding to the stress of the first stressor.

15. The method according to claim 1:

-wherein interpreting the first stress of the first stressor comprises interpreting a first magnitude of nitrogen absorption in plants in the first sub-region;

Wherein interpreting the second stress of the first stressor comprises interpreting a second magnitude of nitrogen absorption in plants in the second sub-region, and

-Wherein predicting the total crop yield comprises:

-obtaining a target nitrogen uptake defined for plants in the geographical area;

-predicting a first health score of the plant in the first sub-region based on the first magnitude of nitrogen absorption and the target nitrogen absorption;

Predicting a second health score for the plant in the second sub-region based on the second magnitude of nitrogen absorption and the target nitrogen absorption, and

-Predicting the total crop yield for the geographic area based on the first health score, the second health score, and the yield model.

16. A method, comprising:

-acquiring an image feed of a population of sensitive plants of one crop type sown in a farmland, said image feed being recorded by an aerial sensor during a first period of time, said population of sensitive plants being configured to signal the presence of a set of conditions and comprising a first set of sensitive plants arranged in a first area of said farmland;

-interpreting a first set of conditions at the plants in the first area based on features extracted from a first subset of images of sensitive plants depicted in the first area in the image feed;

-obtaining a set of target conditions defined for plants in the first area of the farmland;

-predicting a first health score of plants in the first area based on a first difference between the first set of conditions and the set of target conditions;

-selecting a first treatment pathway for plants in the first area in a set of treatment pathways based on the first health score, the first treatment pathway configured to drive conditions of plants in the farmland towards the set of target conditions;

Generating a prompt to implement the first processing pathway during a second time period subsequent to the first time period, and

-Sending the prompt to a user associated with the farmland.

17. The method according to claim 16:

-wherein obtaining the image feed of the sensitive plant population comprising the first set of sensitive plants in the first area comprises obtaining the image feed of the sensitive plant population comprising the first set of sensitive plants arranged in the first area and a second set of sensitive plants arranged in a second area of the farmland;

-further comprising:

-interpreting a second set of conditions at the plants in the second area based on a second set of signals detected in a second subset of images in the image feed depicting sensitive plants in the second area;

-obtaining a second set of target conditions defined for plants in said second area;

Predicting a second health score for plants in the second area of the farmland based on a second difference between the second set of conditions and the second set of target conditions, and

-Selecting a second treatment pathway for plants in the second area based on the second health score, and

-Wherein generating the hint that the first processing pathway was implemented during the second time period comprises generating the hint that the first processing pathway was implemented in the first area and the second processing pathway was implemented in the second area during the second time period.

18. The method according to claim 17:

-wherein selecting the first treatment pathway for plants in the first region based on the first health score comprises selecting the first treatment pathway for plants in the first region in response to the first health score falling below a threshold health score, and

-Wherein selecting the second treatment pathway for plants in the second sub-region based on the second health score comprises selecting the second treatment pathway for plants in the first sub-region in response to the second health score exceeding the threshold health score, the second treatment pathway configured to maintain the second set of plant conditions in plants in the second sub-region.

19. The method according to claim 16:

-wherein obtaining the image feed of the sensitive plant population comprising the first set of sensitive plants in the first sub-area comprises obtaining the image feed of a sensitive plant population comprising the first set of sensitive plants arranged in the first area and a second set of sensitive plants arranged in a second area of the farmland;

Wherein interpreting the first set of conditions at the plant in the first region comprises interpreting a first pressure of a first stressor in the plant in the first region in a set of stressors and a second pressure of a second stressor in the plant in the first region in the set of stressors, and

-Further comprising:

-interpreting a second set of conditions at the plants in the second area based on features extracted from a second subset of images of sensitive plants depicted in the second area in the image feed, the second set of conditions comprising a third pressure of the first stressor in the plants in the second area;

-obtaining a second set of target conditions defined for plants in the second area;

-predicting a second health score for plants in the second area of the farmland based on a second difference between the second set of conditions and the second set of target conditions;

-obtaining a yield model relating plant health of crops of said crop type in said crop field to crop yield;

And

-Predicting a first crop yield of a crop of the crop type based on the first health score, the second health score, and the yield model.

20. A method, comprising:

-acquiring an image feed of a population of sensitive plants in a crop of one crop type sown in a target area, and the population of sensitive plants being configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first period of time;

-interpreting a first time sequence of pressure data of plants in a first sub-region of a set of sub-regions of the target region, based on features extracted from a first subset of images in the image feed captured during a first time period, the first time sequence of pressure data representing changes in pressure of a set of stressors at plants in the first sub-region during the first time period;

-interpreting a second time sequence of pressure data of plants in a second sub-region of the set of sub-regions of the target region, based on features extracted from a second subset of images in the image feed captured during the first time period, the second time sequence of pressure data representing changes in pressure of the set of stressors at plants in the second sub-region during the first time period;

-obtaining a yield model relating the pressure of the set of stressors in the target area to the crop yield of the crop of the one crop type in the target area, and

-Predicting a first crop yield of crops of said one crop type of said set of crop types in said target area during a target harvest time period after said first time period based on said first time sequence of pressure data, said second time sequence of pressure data and said yield model.