CN118410081A - Forestry seedling optimization method based on big data - Google Patents
Forestry seedling optimization method based on big data Download PDFInfo
- Publication number
- CN118410081A CN118410081A CN202410855316.2A CN202410855316A CN118410081A CN 118410081 A CN118410081 A CN 118410081A CN 202410855316 A CN202410855316 A CN 202410855316A CN 118410081 A CN118410081 A CN 118410081A
- Authority
- CN
- China
- Prior art keywords
- growth
- forest
- parameters
- seedling
- key
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Human Resources & Organizations (AREA)
- Genetics & Genomics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Biomedical Technology (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Physiology (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of big data forestry optimization, in particular to a big data-based forestry seedling optimization method. According to the invention, the optimization level of the forest seedling raising process is remarkably improved by utilizing a data analysis technology, the histories and real-time information of forest growth, weather and soil are deeply analyzed, so that the growth mode is accurately revealed, a forest growth basic data set is generated, key nodes of a seedling raising period are identified by time sequence analysis, key growth parameters are selected and optimized, the seedling raising condition is effectively improved, in addition, the application of a dynamic ecological network model enables the forest growth dynamic model to more accurately reflect the interaction of the forest and the environment, and the scientificity and effect evaluation capability of forest field management measures are improved.
Description
Technical Field
The invention relates to the technical field of big data forestry optimization, in particular to a method for optimizing forestry seedling based on big data.
Background
The technical field of big data forestry optimization relates to the application of big data analysis and processing technology in the forestry management and seedling raising process, and aims to optimize the efficiency and the effect of forestry seedling raising by collecting and analyzing a large amount of data related to forestry. The technical field integrates computer science, data science and forestry science, and aims to solve various problems encountered in forestry seedling culture, such as seedling selection, pest and disease prevention, growth condition optimization and the like through advanced data analysis technologies, such as machine learning, artificial intelligence, statistical analysis and the like. By analyzing a large amount of data such as climate data, soil characteristics, moisture conditions, plant diseases and insect pests occurrence records and the like, the optimal condition of seedling culture can be predicted more accurately, so that the success rate of seedling culture and the growth efficiency are improved.
The method for optimizing the seedling raising based on the big data is a method for analyzing and guiding the seedling raising process by utilizing the big data technology. The key aim of the method is to find out the key factors of successful seedling raising by analyzing a large-scale data set, so as to optimize the planting scheme and the management strategy and realize higher seedling raising efficiency and better plant growth performance. The method tries to reduce trial-and-error cost through data-driven decision, realizes efficient utilization of resources, and finally achieves the effects of improving the quality of the forest and increasing the forestry output. Not only a single growth factor is of interest, but a plurality of influencing factors, such as environmental conditions, biological characteristics, external intervention, etc., are taken into consideration in combination to ensure optimization of the seedling process.
The traditional forestry seedling raising and management method has obvious defects in the aspect of treating complex growth factors. Depending on experience judgment and local data analysis, the comprehensive and accurate analysis of factors such as environmental changes, biological characteristics, external intervention and the like is lacking. Limitations of this approach are manifested by insufficient data processing and analysis depth, failure to precisely control and optimize growth conditions, resulting in limited seedling success rates and growth efficiencies. If the disease and insect pest prediction and control are insufficient, the conditions such as illumination, moisture and the like are not scientifically adjusted, so that seedling raising fails or growth is slow, further the quality and yield of the forest are affected, and the economic and ecological values of the forestry are reduced.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a large data-based forestry seedling optimization method.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the forestry seedling optimization method based on big data comprises the following steps:
S1: the method comprises the steps of obtaining a forest growth basic data set by collecting historical and real-time information of forest growth, weather and soil, and performing correlation analysis to reveal a growth mode;
S2: using the forest growth basic data set, analyzing and identifying key nodes including sprouting, branching and maturing through time sequence, and dividing seedling period to obtain a segmented seedling period index;
s3: based on the segmented seedling period index, selecting illumination, air and soil humidity as key parameters, determining key growth parameters of each stage, and obtaining an optimized parameter list;
s4: optimizing multi-stage parameters by global and local searching by utilizing the optimized parameter list, optimizing seedling conditions, and generating an optimized parameter scheme;
S5: applying the optimized parameter scheme to a seedling raising process, adjusting illumination, watering, fertilizing, monitoring and recording results, and analyzing to obtain a seedling raising effect evaluation result;
s6: analyzing the interaction between the forest and the environment through the dynamic ecological network model by using the seedling effect evaluation result, updating model parameters, mapping ecological states and constructing a forest growth dynamic model;
S7: and simulating forestry management measures including forest thinning, irrigation and fertilization by using the forest growth dynamic model, evaluating the measure effect, and making a forest farm management optimization scheme.
As a further scheme of the invention, the forest growth basic data set comprises tree growth speed, leaf color change, trunk diameter, temperature, humidity, rainfall, soil pH value, water content and nutritional ingredients, the segmented seedling raising period indexes comprise key growth stage characteristics of sprouting period duration, branching period growth rate and mature period fruit size, the optimized parameter list comprises illumination intensity range, air humidity, soil humidity, fertilizer type and application frequency, the optimized parameter scheme comprises multi-stage illumination regulation, irrigation schedule, fertilization plan and temperature and humidity control strategy, the seedling raising effect evaluation result comprises growth speed, plant health condition, fruit yield and quality analysis data, the forest growth dynamic model comprises an interaction network of forest competition, environmental response and management measure effect, and the forest management optimization scheme comprises a forest optimal time, an irrigation and fertilization optimal plan and a target climate condition response strategy.
As a further scheme of the invention, the forest growth basic data set is used, key nodes including germination, branching and maturation are identified through time sequence analysis, and the seedling period is divided, so that the step of obtaining the segmented seedling period index is specifically as follows:
S201: based on the forest growth basic data set, screening time points of sprouting, branching and maturing stages in the time series data by adopting a time series analysis method, sequencing and marking the time points, and extracting growth rate data to obtain a preliminary growth cycle frame;
S202: subdividing the start-stop time of each key growth stage based on the preliminary growth period frame, analyzing the growth rate change of adjacent time points, identifying the time points with prominent change based on the growth rate, marking the time points as key growth nodes, and obtaining a refined key growth node time table;
s203: calculating duration time of multiple growth stages based on the refined key growth node time table, comparing duration time of differential stages with growth characteristics, determining time span of each stage, and forming optimized seedling period stage division;
S204: and on the basis of the optimized seedling raising period stage division, formulating management measures of each growth stage, including moisture management, illumination adjustment and nutrition replenishment, and formulating a time schedule and a management strategy for each stage to obtain the segmented seedling raising period index.
As a further aspect of the present invention, the time series analysis method employs the formula:；
Wherein, In order for the adjusted growth amount to change,To at the point of timeIs used for the growth of the seed,To at the point of timeIs used for the growth of the seed,As the weight coefficient of the light-emitting diode,As a result of the climate factor,Is used for the quality index of the soil,In order to be able to use the water resource,Human intervention.
As a further scheme of the invention, based on the segmented seedling period index, the illumination, air and soil humidity and fertilizer are selected as key parameters, key growth parameters of each stage are determined, and the steps for acquiring an optimized parameter list are specifically as follows:
s301: based on the segmented seedling period index, collecting multi-stage illumination intensity, air humidity, soil humidity and fertilizer consumption data, analyzing the influence of multiple parameters on growth, identifying driving parameters of multi-stage growth, and generating a preliminary key parameter list;
s302: based on the preliminary key parameter list, comprehensively referring to the influence of illumination, air humidity, soil humidity and fertilizer consumption on growth, and selecting multi-stage optimal parameter configuration through comparative analysis to obtain optimized key parameter configuration;
S303: and adjusting the irrigation frequency according to the set threshold value of the soil humidity based on the optimized key parameter configuration, adjusting the fertilizer type and the application amount according to the soil nutrients, adjusting the illumination intensity, and obtaining an optimized parameter list.
As a further scheme of the invention, the optimized parameter list is utilized to optimize multi-stage parameters through global and local search, the seedling conditions are optimized, and the steps for generating the optimized parameter scheme are specifically as follows:
S401: based on the optimized parameter list, detecting potential conflicts among parameters, adjusting the conflict parameters to balance points, ensuring that the cooperation among the parameters promotes plant growth, analyzing the influence of the parameters one by one, performing parameter tuning, and generating a parameter conflict adjustment list;
S402: based on the parameter conflict adjustment list, analyzing environmental condition changes in multiple growth stages, including adjustment requirements of soil humidity along with seasonal changes, refining and optimizing configuration of illumination, moisture and fertilizer parameters to obtain local optimization parameter configuration;
s403: and based on the local optimization parameter configuration, applying the adjusted parameters, and referring to the environmental change of the whole growth period, unifying the optimization parameters to obtain an optimization parameter scheme.
As a further scheme of the invention, by using the seedling effect evaluation result, the interaction between the forest and the environment is analyzed through a dynamic ecological network model, model parameters are updated, ecological states are mapped, and the step of constructing the forest growth dynamic model is specifically as follows:
s601: recording tree growth data by analyzing the seedling effect evaluation result, and calculating through a Pearson correlation coefficient and a Spearman rank correlation coefficient to identify the correlation between key environmental factors of soil humidity and temperature and tree growth so as to obtain an ecological factor identification result;
S602: the ecological factor recognition result is adopted, relation parameters of the growth rate, the survival rate and the environmental factors of the forest in the model are adjusted, actual interaction between the growth of the forest and the environment is mapped, and a parameter updating model is generated;
s603: and simulating a plurality of growth stages from seedling to maturity of the forest by using the parameter updating model, and recording interaction between the forest state in the differential growth period and environmental change to obtain a forest growth dynamic model.
As a further aspect of the present invention, the Pearson correlation coefficient uses the formula:；
The Spearman rank correlation coefficient employs the formula: ；
Wherein, AndFor improved Pearson correlation coefficients and Spearman rank correlation coefficients,AndAs an observation of the original environment and the growth data,For additional environmental impact parameters, including soil nutrient content,AndRespectively is withAndThe associated additional parameters, including average light intensity and rainfall over the target period,In order for the rank to be poor,In order to be able to measure the number of observations,Is a weight coefficient used for adjusting the weight of the influence of the additional parameter on the original data,For the additional introduction of the ranking difference parameter,The number of observations that are additional references.
Compared with the prior art, the invention has the advantages and positive effects that:
According to the invention, the optimization level of the forestry seedling raising process is remarkably improved by utilizing a data analysis technology. And deeply analyzing the historical and real-time information of the forest growth, weather and soil, thereby accurately revealing the growth mode and generating a forest growth basic data set. And the key nodes of the seedling raising period are identified through time sequence analysis, key growth parameters are selected and optimized, and the seedling raising conditions are effectively improved. In addition, by the application of the dynamic ecological network model, the forest growth dynamic model can more accurately reflect the interaction between the forest and the environment, and the scientificity and effect evaluation capability of forest farm management measures are improved.
Drawings
FIG. 1 is a schematic diagram of the main steps of the present invention;
FIG. 2 is a detailed schematic of the S1 of the present invention;
FIG. 3 is a schematic diagram of an S2 refinement of the present invention;
FIG. 4 is a schematic diagram of an S3 refinement of the present invention;
FIG. 5 is a schematic diagram of an S4 refinement of the present invention;
FIG. 6 is a schematic diagram of an S5 refinement of the present invention;
FIG. 7 is a schematic diagram of an S6 refinement of the present invention;
fig. 8 is a schematic diagram of the S7 refinement of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Embodiment referring to fig. 1, the present invention provides a technical solution: the forestry seedling optimization method based on big data comprises the following steps:
S1: the method comprises the steps of obtaining a forest growth basic data set by collecting historical and real-time information of forest growth, weather and soil, and performing correlation analysis to reveal a growth mode;
s2: using a forest growth basic data set, analyzing and identifying key nodes including germination, branching and maturation through time sequence, and dividing seedling period to obtain a segmented seedling period index;
S3: based on the segmented seedling period index, selecting illumination, air and soil humidity and fertilizer as key parameters, determining key growth parameters of each stage, and obtaining an optimized parameter list;
S4: optimizing multi-stage parameters by global and local searching by utilizing an optimized parameter list, optimizing seedling conditions, and generating an optimized parameter scheme;
s5: applying the optimized parameter scheme to the seedling raising process, adjusting illumination, watering and fertilizing, monitoring and recording the result, and analyzing to obtain a seedling raising effect evaluation result;
S6: analyzing the interaction between the forest and the environment through a dynamic ecological network model by using the seedling effect evaluation result, updating model parameters, mapping ecological states, and constructing a forest growth dynamic model;
s7: and simulating forestry management measures including forest thinning, irrigation and fertilization by using the forest growth dynamic model, evaluating the measure effect, and making a forest farm management optimization scheme.
The tree growth basic data set comprises tree growth speed, leaf color change, trunk diameter, temperature, humidity, rainfall, soil pH value, water content and nutritional ingredients, the segmented seedling period index comprises key growth stage characteristics of sprouting period duration, branching period growth rate and mature period fruit size, the optimized parameter list comprises illumination intensity range, air humidity, soil humidity, fertilizer type and application frequency, the optimized parameter scheme comprises multi-stage illumination adjustment, irrigation schedule, fertilization plan and temperature and humidity control strategy, the seedling effect evaluation result comprises growth speed, plant health condition, fruit yield and quality analysis data, the tree growth dynamic model comprises interaction network of inter-tree competition, environmental response and management measure effect, the forest management optimization scheme comprises optimal forest dredging time, optimal irrigation and fertilization plan and target climate condition coping strategy.
Referring to fig. 2, by collecting the history and real-time information of the forest growth, weather and soil, the correlation analysis reveals the growth mode, and the step of generating the forest growth basic data set specifically comprises:
S101: positioning a forest region by adopting a geographic information system, collecting forest growth history data by a remote sensing technology, acquiring current meteorological conditions by utilizing data provided by a meteorological station, obtaining soil characteristics by using soil sampling analysis, and establishing a forest growth environment database;
based on a geographic information system, positioning a forest region, collecting forest growth history data by adopting a remote sensing technology, collecting current meteorological conditions by utilizing meteorological station data, obtaining soil characteristics by using soil sampling analysis, accurately mapping the geographic position of the forest region, adopting ArcGIS software, defining the position of the forest region by a coordinate system, utilizing satellite remote sensing images, analyzing the forest growth condition by NDVI index, collecting meteorological station data, reading the current meteorological conditions by utilizing temperature and humidity sensors, utilizing soil sampling, analyzing the soil components by utilizing a mass spectrometer, and generating a forest growth environment database.
S102: extracting key variables from a forest tree growth environment database by a data screening technology, wherein the key variables comprise sunlight duration, annual average temperature and soil water content, and obtaining a growth mode key index set by statistical analysis and identification of a growth mode;
The method comprises the steps of extracting key variables from a forest growth environment database based on a data screening technology, carrying out statistical analysis on the key variables including sunlight duration, annual average temperature and soil water content, identifying a growth mode, adopting a Pandas library of Python to carry out data screening, storing environment variable data through a DATAFRAME structure, carrying out statistical analysis by utilizing a SciPy library, analyzing the relation between the variables and the growth of the forest through a linear regression model, identifying key factors influencing the growth of the forest, and generating a growth mode key index set.
S103: and combining the growth mode key index set with real-time meteorological data, carrying out trend analysis, predicting the growth condition of the future forest, and establishing a forest growth basic data set.
Based on a key index set of a growth mode and real-time meteorological data, trend analysis is carried out, future forest growth conditions are predicted, a forest growth basic data set is established, a machine learning method is adopted, a random forest model is established by utilizing Sklearn libraries, model training is carried out by taking historical growth data and real-time meteorological data as inputs, future forest growth trends are predicted by utilizing the model, and a forest growth basic data set is generated.
Referring to fig. 3, using a tree growth basic data set, identifying key nodes including sprouting, branching and maturing through time series analysis, and dividing a seedling period to obtain a segmented seedling period index specifically includes:
S201: based on a forest growth basic data set, screening time points of sprouting, branching and maturing stages in the time series data by adopting a time series analysis method, sequencing and marking the time points, and extracting growth rate data to obtain a preliminary growth cycle frame;
Based on a forest growth basic data set, a time sequence analysis method is adopted, a Pandas library of Python is utilized to process data, time points of sprouting, branching and maturing stages in the time sequence data are screened, the time points are ordered and marked, a sort_values () function is adopted to be arranged according to time ascending order, a label () function is used to carry out staged marking, growth rate data are extracted, and growth quantity change of adjacent time points is calculated through a diff () function, so that a preliminary growth period framework is obtained.
The time series analysis method adopts the formula:；
Wherein, In order for the adjusted growth amount to change,For the amount of growth at time point t,To at the point of timeIs used for the growth of the seed,As the weight coefficient of the light-emitting diode,As a result of the climate factor,Is used for the quality index of the soil,In order to be able to use the water resource,Human intervention.
By introducing external factors such as climate change, soil quality, water resource availability and human intervention degree, the change of the growth rate of the forest is more accurately simulated, and each newly introduced parameter is adjusted through a corresponding weight coefficient so as to ensure that the actual influence of each factor on the growth rate is accurately reflected. The method of validating these weighting coefficients involves regression analysis of the historical data, with statistical analysis to determine the optimal value for each coefficient to minimize the difference between the model predicted growth rate and the actual observed value. Therefore, the improved model is based on historical growth data, and the comprehensive influence of environment and human factors is considered, so that the prediction accuracy is improved.
S202: subdividing the start-stop time of each key growth stage based on a preliminary growth period frame, analyzing the growth rate change of adjacent time points, identifying the time points with prominent change based on the growth rate, marking the time points as key growth nodes, and obtaining a refined key growth node time table;
Subdividing the start-stop time of each key growth stage based on a preliminary growth period framework, analyzing the growth rate change of adjacent time points, adopting a sliding window method, creating a sliding window by utilizing NumPy library to perform local growth rate calculation, identifying the time points with outstanding change based on the growth rate, using an argmax () function to find the time point with the maximum change rate, marking the time points as key growth nodes, and obtaining a refined key growth node schedule.
S203: calculating duration of multiple growth stages based on a refined key growth node schedule, comparing the duration of differentiated stages with growth characteristics, determining time span of each stage, and forming optimized seedling period stage division;
Based on the refined key growth node time table, calculating the duration of multiple growth stages, comparing the duration of differentiated stages with the growth characteristics, adopting a time difference calculation method, converting a time format by utilizing a (to_ datetime) function of Pandas, calculating the duration between stages by utilizing a (diff) function, determining the time span of each stage, and forming the optimized seedling period stage division.
S204: based on the optimized seedling period stage division, management measures of each growth stage are formulated, including moisture management, illumination adjustment and nutrition replenishment, and a time table and a management strategy are formulated for each stage to obtain the segmented seedling period index.
Based on the optimized seedling period stage division, the management measures of each growth stage are formulated, including moisture management, illumination adjustment and nutrition replenishment, a decision tree model is adopted, a decision tree is built by utilizing Sklearn libraries, a time table and a management strategy are formulated for each stage by taking stage characteristics as input variables, and model training is performed by using a fit () function, so that the segmented seedling period index is obtained.
Referring to fig. 4, based on the periodical indexes of the segmented seedling, the illumination, air and soil humidity and fertilizer are selected as key parameters, and the key growth parameters of each stage are determined, so that the steps for obtaining the optimized parameter list are specifically as follows:
S301: based on the segmented seedling period index, collecting multi-stage illumination intensity, air humidity, soil humidity and fertilizer consumption data, analyzing the influence of multiple parameters on growth, identifying driving parameters of multi-stage growth, and generating a preliminary key parameter list;
Based on the segmented seedling period index, multi-stage illumination intensity, air humidity, soil humidity and fertilizer consumption data are collected, influence analysis is carried out on multiple parameters, driving parameters of multi-stage growth are identified, a multiple linear regression analysis method is adopted, a Statsmodels library of Python is utilized, parameter estimation is carried out through a Ordinary Least Squares (OLS) model, independent variables are set to be illumination intensity, air humidity, soil humidity and fertilizer consumption, regression analysis is carried out on the independent variables to be plant growth rate, parameters with obvious influence on growth are identified, and a preliminary key parameter list is generated.
S302: based on the preliminary key parameter list, comprehensively referring to the influence of illumination, air humidity, soil humidity and fertilizer consumption on growth, and selecting multi-stage optimal parameter configuration through comparative analysis to obtain optimized key parameter configuration;
Based on the preliminary key parameter list, comprehensively referring to the influence of illumination, air humidity, soil humidity and fertilizer consumption on growth, selecting multi-stage optimal parameter configuration through comparative analysis, adopting a genetic algorithm optimization strategy, setting a fitness function to maximize plant growth rate by utilizing a DEAP (Distributed Evolutionary Algorithms in Python) library of Python, and searching optimal illumination intensity, air humidity, soil humidity and fertilizer consumption configuration through selection, crossing and mutation operation of the genetic algorithm to obtain the optimized key parameter configuration.
S303: based on the optimized key parameter configuration, the irrigation frequency is adjusted according to a set threshold value of soil humidity, the fertilizer type and the application amount are adjusted according to soil nutrients, the illumination intensity is adjusted, and an optimized parameter list is obtained.
Based on the optimized key parameter configuration, the irrigation frequency is adjusted according to a set threshold value of soil humidity, the type and the application amount of fertilizer are adjusted according to soil nutrients, the illumination intensity is adjusted, a threshold value adjusting method is adopted, an Arduino microcontroller and a sensor are utilized, a soil humidity threshold value is set by writing C++ codes, an irrigation system is started when the soil humidity is lower than the threshold value, data are read through a soil nutrient sensor, the application amount and the type of fertilizer are automatically adjusted according to the nutrient deficiency condition, meanwhile, illumination is automatically adjusted through an LED light source adjusting system according to the optimized illumination intensity configuration, and an optimized parameter list is obtained.
Referring to fig. 5, the steps of optimizing seedling conditions by using the optimized parameter list and optimizing multi-stage parameters through global and local search, and generating an optimized parameter scheme are specifically as follows:
s401: based on the optimized parameter list, detecting potential conflict among parameters, adjusting the conflict parameters to balance points, ensuring that the cooperation among the parameters promotes plant growth, analyzing the influence of the parameters one by one, performing parameter tuning, and generating a parameter conflict adjustment list;
Based on an optimized parameter list, potential conflict among parameters is detected, the conflict parameters are adjusted to balance points, cooperation among the parameters is guaranteed to promote plant growth, the influence degree of the parameters is analyzed one by one, parameter tuning is carried out, a multi-objective optimization method is adopted, modeling is carried out by utilizing a Pyomo library of Python, a multi-objective optimization problem is set, an objective function comprises maximizing plant growth rate and minimizing conflict degree among the parameters, genetic algorithm is used for solving, balance points among a plurality of parameters are found through crossover, mutation and selection operation, weight of each parameter is adjusted, cooperation on plant growth is guaranteed, and a parameter conflict adjustment list is generated.
S402: based on the parameter conflict adjustment list, analyzing environmental condition changes in multiple growth stages, including adjustment requirements of soil humidity along with seasonal changes, refining and optimizing configuration of illumination, moisture and fertilizer parameters to obtain local optimization parameter configuration;
Based on the parameter conflict adjustment list, analyzing environmental condition changes in multiple growth stages, including adjustment requirements of soil humidity along with seasonal changes, refining and optimizing configuration of parameters of illumination, moisture and fertilizer, adopting a time sequence analysis method, carrying out seasonal analysis by utilizing a Pandas library of Python, identifying modes of soil humidity along with seasonal changes through a time sequence decomposition method, then adjusting the parameter configuration of illumination, moisture and fertilizer based on the modes so as to adapt to the requirements of different seasons, adopting an ARIMA model to predict environmental conditions of each season in the future, refining the parameter configuration according to a prediction result, and obtaining the local optimization parameter configuration.
S403: based on the local optimization parameter configuration, the adjusted parameters are applied, and the parameters are optimized uniformly by referring to the environmental change of the whole growth period, so that an optimized parameter scheme is obtained.
Based on local optimization parameter configuration, the adjusted parameters are applied, the environment change of the whole growth period is referred, the parameters are optimized uniformly, a dynamic programming method is adopted, the SciPy library of Python is utilized for solving, the state variable is set to be the environment parameter configuration of each growth stage by establishing an optimization model comprising each stage of the whole growth period, the action variable is the decision of the adjustment parameters, the reward function is the improvement of the plant growth efficiency, and the optimal decision strategy of each stage is solved step by a dynamic programming algorithm, so that the parameter configuration of the whole growth period is adjusted, and an optimized parameter scheme is obtained.
Referring to fig. 6, applying the optimized parameter scheme to the seedling raising process, adjusting illumination, watering, fertilizing, monitoring and recording results, and analyzing to obtain the seedling raising effect evaluation result specifically includes the following steps:
s501: based on an optimized parameter scheme, adjusting the illumination intensity to a recommended value, if the plant growth speed does not reach the standard, increasing the illumination time length, synchronously increasing the fertilizer supply, ensuring nutrition and illumination to support healthy growth of plants, and generating adjusted illumination and fertilizer supply parameters;
Based on an optimized parameter scheme, adjusting illumination intensity to a recommended value, if the plant growth speed does not reach a standard, increasing illumination time, synchronously increasing fertilizer supply, guaranteeing nutrition and supporting healthy growth of plants by using a PID control algorithm, utilizing an Arduino platform to monitor in real time, detecting illumination intensity by a photosensitive sensor, detecting soil humidity by a soil humidity sensor, automatically adjusting the intensity of an LED light source and starting an irrigation system according to a detection result, setting PID controller parameters P, I, D to respectively correspond to the illumination intensity, the fertilizer supply rate and the adjustment speed of water supply so as to ensure that illumination and nutrition supply reach the optimal state of plant growth, and generating adjusted illumination and fertilizer supply parameters.
S502: based on the adjusted illumination and fertilizer supply parameters, regularly recording the growth data of plant height and leaf number, if the growth acceleration is monitored, maintaining parameter setting, otherwise, fine-tuning according to the situation, and optimizing the growth condition to obtain a growth monitoring record;
Based on the adjusted illumination and fertilizer supply parameters, the growth data of plant height and leaf number are recorded regularly, if the growth acceleration is monitored, parameter setting is maintained, otherwise, data recording and analysis software such as Pandas library of Excel or Python is adopted for recording and analyzing the growth data according to the situation, regular recording intervals such as once a week are set, the data of plant height, leaf number and the like are recorded, a data visualization tool such as Matplotlib is used for drawing a growth curve graph, the growth trend is analyzed, the illumination intensity and fertilizer supply are subjected to fine adjustment according to the growth data and the trend, and the growth condition is optimized, so that the growth monitoring record is obtained.
S503: based on the growth monitoring record, analyzing the growth rate and the plant health condition, comparing the actual growth data with an expected target, and evaluating the seedling cultivation strategy effect to obtain a seedling cultivation effect evaluation result.
Based on the growth monitoring record, analyzing the growth rate and the plant health condition, comparing the actual growth data with an expected target, adopting a difference analysis method, utilizing Pandas and NumPy libraries of Python to perform data processing and mathematical operation, calculating the difference between the actual growth data (such as plant height and leaf number) and the expected target, evaluating standard deviation and mean value, determining the degree of dispersion and deviation of the growth data, using Matplotlib libraries to draw a comparison chart of the growth data and the expected target, intuitively displaying the deviation between the growth trend and the target, evaluating the effect of a seedling cultivation strategy according to the analysis result of the difference, examining the influence of management measures such as illumination, moisture, fertilizer and the like on the plant growth rate and the health condition, adjusting the management measures which do not accord with the expected target, optimizing the growth condition and the seedling cultivation strategy, acquiring the seedling cultivation effect evaluation result, and generating a comprehensive evaluation report.
Referring to fig. 7, using the seedling effect evaluation result, the steps of analyzing the interaction between the forest and the environment through the dynamic ecological network model, updating the model parameters, mapping the ecological state, and constructing the forest growth dynamic model are specifically as follows:
S601: recording tree growth data by analyzing a seedling effect evaluation result, and calculating through a Pearson correlation coefficient and a Spearman rank correlation coefficient to identify the correlation between key environmental factors of soil humidity and temperature and tree growth so as to obtain an ecological factor identification result;
Based on the seedling effect evaluation result, the forest growth data are recorded, the correlation between the key environmental factors of soil humidity and temperature and the forest growth is identified, a correlation analysis method is adopted, a SciPy library of Python is utilized, the calculation is carried out through a Pearson correlation coefficient and a Spearman rank correlation coefficient, input parameters are the environmental data of soil humidity and temperature and the growth data of the forest growth rate, survival rate and the like, the correlation strength and direction between the environmental factors and the forest growth are determined through a statistical analysis method, the obvious correlation between the environmental factors and the forest growth is evaluated, the ecological factor identification result is obtained, and the environmental factor and forest growth correlation report is generated.
The Pearson correlation coefficient uses the formula:；
The Spearman rank correlation coefficient uses the formula: ；
Wherein, AndFor improved Pearson correlation coefficients and Spearman rank correlation coefficients,AndAs an observation of the original environment and the growth data,For additional environmental impact parameters, including soil nutrient content,AndRespectively is withAndThe associated additional parameters, including average light intensity and rainfall over the target period,In order for the rank to be poor,In order to be able to measure the number of observations,Is a weight coefficient used for adjusting the weight of the influence of the additional parameter on the original data,For the additional introduction of the ranking difference parameter,The number of observations that are additional references.
First, environmental data is collectedAnd forest growth dataThese data are the basis for analysis, whereIncluding soil moisture, temperature, etcIncluding the growth rate, survival rate, etc. of the forest tree, followed by the introduction of additional environmental impact parametersSuch as soil nutrient content, which are intended to provide more information about the growth conditions of the forest, and then, to consider and considerAndRelated additional parametersAndRepresenting the average illumination intensity and rainfall in a specific time period respectively, so that more factors affecting the growth of the forest tree can be captured, and then, the quantity of the observed values is calculatedConfirming the size of the data set, simultaneous importationAs an additional consideration of the number of observations to consider a broader data set. Next, a ranking difference is calculatedThis step is necessary to calculate the Spearman correlation coefficient, introducedAs an additionally introduced ranking difference parameter to take into account ranking differences between additional factors, a weighting coefficient is then setThese coefficients are used to adjust the weight of the influence of the additional parameters on the raw data, which may be determined based on historical data analysis or expert experience. Finally, when executing formula calculation, firstly substituting all relevant parameters and weight coefficients according to an improved Pearson formula or Spearman formula, and calculating improved relevant coefficients for PearsonRequiring integration of raw environment and growth data observations、Additional environmental impact parametersAnd associated additional parameters、And by weight、Adjusting influence, for Spearman, by weighting rank differencesAnd additional ranking difference parametersAnd weight ofTo calculate improved correlation coefficients。
S602: adopting an ecological factor identification result, adjusting relation parameters of the growth rate, the survival rate and environmental factors of the forest in the model, mapping actual interaction between the growth of the forest and the environment, and generating a parameter updating model;
The method comprises the steps of adopting an ecological factor identification result, adjusting relation parameters of forest growth rate, survival rate and environmental factors in a model, mapping actual interaction between forest growth and environment, adopting a machine learning algorithm, such as a random forest, constructing the model by utilizing a Scikit-learn library of Python, inputting the identified key environmental factors and forest growth data, adjusting model parameters to optimally reflect the influence of the environmental factors on the forest growth and the survival rate, optimizing model parameters through a cross verification method, ensuring that the model can accurately map actual relation between the forest growth and the environmental factors, and generating a parameter updating model.
S603: and simulating a plurality of growth stages from seedling to maturity of the forest by using the parameter updating model, and recording interaction between the state of the forest in the differential growth period and environmental change to obtain a dynamic model of growth of the forest.
The method comprises the steps of using a parameter updating model to simulate a plurality of growth stages from seedlings to maturity of a forest, recording interaction between the states of the forest in a differential growth period and environmental changes, adopting a dynamic simulation technology, using Python programming to realize, simulating response of the forest in different growth stages to the environmental changes through the model, recording indexes such as growth rate, leaf area increase and the like of the forest growth state in the simulation process, and environmental condition changes such as soil humidity and temperature fluctuation, and using a visualization technology such as Matplotlib library to draw dynamic diagrams of the growth stages and environmental factor changes to obtain a forest growth dynamic model, and generating a dynamic simulation report of the forest growth and environmental interaction.
Referring to fig. 8, using a forest growth dynamic model, simulating forest management measures including forestation, irrigation, fertilization, and evaluating measure effects, and making a forest farm management optimization scheme specifically includes the following steps:
S701: collecting the types, growth states, soil types and moisture conditions of the forest in a forest farm by utilizing a forest growth dynamic model and adopting field investigation and remote sensing data, and recording the ecological environment of the forest farm and the basic growth condition of the forest to obtain a basic forest Kuang Shuju;
And collecting the forest types, growth states, soil types and moisture conditions of the forest by using a forest growth dynamic model and adopting field investigation and remote sensing data, and recording the ecological environment of the forest and the basic growth condition of the forest to obtain basic forest condition data. In the process, a Geographic Information System (GIS) technology is adopted, data superposition analysis is performed through ArcGIS software operation, layer attribute query parameters are set to be tree types, growth states, soil types and moisture conditions, a remote sensing image analysis tool such as an ISODATA clustering algorithm of ENVI software is utilized to classify the soil types and the moisture conditions, the operation comprises the steps of setting the number of clustering centers to be 10, the maximum iteration number to be 20, and calculating tree coverage and growth state indexes through a space analysis tool to generate a basic forest condition data set.
S702: based on the basic forest condition data, setting a simulation scene comprising a forest density, an irrigation level and a fertilization scheme, simulating the influence of management measures of forest, irrigation and fertilization on the growth of the forest, and obtaining a management measure simulation result;
Based on the basic forest condition data, setting a simulation scene comprising a forest density, an irrigation level and a fertilization scheme, simulating the influence of management measures of forest, irrigation and fertilization on the growth of the forest, and obtaining a management measure simulation result. In the process, ecological system simulation software Forest Growth Simulator (FGS) is adopted to configure simulation parameters, the simulation parameters comprise that the density of the forests is set to 300 plants per hectare, the irrigation level is set to 50mm per month, the fertilizing amount is set to 150kg of nitrogenous fertilizer per hectare, simulation operation commands are executed, the operations comprise that climate variable data input such as annual average temperature and precipitation amount are adjusted, multiple simulation iterations are carried out by using a growth model algorithm built in FGS, and a management measure simulation data set is generated.
S703: based on the simulation result of the management measures, analyzing the influence of the differential management measures on the growth rate and ecological adaptability of the forest, and identifying the optimal management measures for promoting the growth of the forest to obtain an analysis result of the optimal measures;
Based on the simulation result of the management measures, the influence of the differential management measures on the growth rate and ecological adaptability of the forest is analyzed, and the optimal management measures for promoting the growth of the forest are identified to obtain the analysis result of the optimization measures. In the process, data analysis software R is adopted, a script is written by using R language to execute statistical analysis, analysis orders are set to include performing variance analysis by using anova functions, lm functions are subjected to linear regression analysis, independent variables are set to be forest density, irrigation level and fertilization scheme, dependent variables are tree growth rate and ecological adaptability indexes, an analysis chart is drawn through ggplot packets, and an optimization measure analysis report is generated.
S704: based on the analysis result of the optimization measures, current management data of a forest farm is collected, wherein the current management data comprise density, irrigation frequency and fertilization type and amount of the forest, the distance between the forests is adjusted according to the growth condition and ecological requirements of the forest, an irrigation plan is optimized, and a fertilization scheme is refined to form a forest farm management optimization scheme.
Based on the analysis result of the optimization measures, current management data of a forest farm is collected, wherein the current management data comprise density, irrigation frequency and fertilization type and amount of the forest, the distance between the forests is adjusted according to the growth condition and ecological requirements of the forest, an irrigation plan is optimized, and a fertilization scheme is refined to form a forest farm management optimization scheme. In the process, project tasks are defined by project management software Microsoft Project, including setting a forest gap to be adjusted to 5 meters, adjusting irrigation frequency to be once every two weeks, adjusting a fertilization scheme to apply slow release fertilizer, inputting task duration and resource allocation, such as allocating specific staff and equipment to different management tasks, executing a scheduling algorithm to perform time and resource optimization, performing construction period calculation by using a Critical Path Method (CPM), performing resource balance analysis, and generating a forest management optimization plan.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (8)
1. The forestry seedling optimization method based on big data is characterized by comprising the following steps of:
The method comprises the steps of obtaining a forest growth basic data set by collecting historical and real-time information of forest growth, weather and soil, and performing correlation analysis to reveal a growth mode;
Using the forest growth basic data set, analyzing and identifying key nodes including sprouting, branching and maturing through time sequence, and dividing seedling period to obtain a segmented seedling period index;
Based on the segmented seedling period index, selecting illumination, air and soil humidity as key parameters, determining key growth parameters of each stage, and obtaining an optimized parameter list;
Optimizing multi-stage parameters by global and local searching by utilizing the optimized parameter list, optimizing seedling conditions, and generating an optimized parameter scheme;
Applying the optimized parameter scheme to a seedling raising process, adjusting illumination, watering, fertilizing, monitoring and recording results, and analyzing to obtain a seedling raising effect evaluation result;
Analyzing the interaction between the forest and the environment through the dynamic ecological network model by using the seedling effect evaluation result, updating model parameters, mapping ecological states and constructing a forest growth dynamic model;
And simulating forestry management measures including forest thinning, irrigation and fertilization by using the forest growth dynamic model, evaluating the measure effect, and making a forest farm management optimization scheme.
2. The method of claim 1, wherein the basic forest growth data set comprises tree growth speed, leaf color change, trunk diameter, temperature, humidity, rainfall, soil ph, water content and nutrient content, the segmented seedling period index comprises key growth stage characteristics of sprouting period duration, branching period growth rate and mature period fruit size, the optimized parameter list comprises illumination intensity range, air humidity, soil humidity, fertilizer type and application frequency, the optimized parameter scheme comprises multi-stage illumination adjustment, irrigation schedule, fertilization plan and temperature and humidity control strategies, the seedling effect evaluation result comprises growth speed, plant health condition, fruit yield and quality analysis data, the forest growth dynamic model comprises interaction network of inter-forest, environmental response and management measure effects, and the forest management optimization scheme comprises optimal forest time, optimal irrigation and fertilization plan and target climate condition coping strategies.
3. The method for optimizing forestry seedling raising based on big data according to claim 1, wherein the step of using the forest growth basic data set to identify key nodes through time sequence analysis includes sprouting, branching and maturing, and dividing seedling raising period to obtain a segmented seedling raising period index specifically comprises the steps of:
Based on the forest growth basic data set, screening time points of sprouting, branching and maturing stages in the time series data by adopting a time series analysis method, sequencing and marking the time points, and extracting growth rate data to obtain a preliminary growth cycle frame;
Subdividing the start-stop time of each key growth stage based on the preliminary growth period frame, analyzing the growth rate change of adjacent time points, identifying the time points with prominent change based on the growth rate, marking the time points as key growth nodes, and obtaining a refined key growth node time table;
calculating duration time of multiple growth stages based on the refined key growth node time table, comparing duration time of differential stages with growth characteristics, determining time span of each stage, and forming optimized seedling period stage division;
and on the basis of the optimized seedling raising period stage division, formulating management measures of each growth stage, including moisture management, illumination adjustment and nutrition replenishment, and formulating a time schedule and a management strategy for each stage to obtain the segmented seedling raising period index.
4. A big data based method of optimizing seedling raising as claimed in claim 3, wherein said time series analysis method uses the formula；
Wherein,In order for the adjusted growth amount to change,To at the point of timeIs used for the growth of the seed,To at the point of timeIs used for the growth of the seed,As the weight coefficient of the light-emitting diode,As a result of the climate factor,Is used for the quality index of the soil,In order to be able to use the water resource,Human intervention.
5. The method for optimizing forestry seedling raising based on big data according to claim 1, wherein the step of selecting illumination, air and soil humidity and fertilizer as key parameters based on the segment seedling raising period index, determining key growth parameters of each stage, and obtaining an optimized parameter list comprises the following steps:
Based on the segmented seedling period index, collecting multi-stage illumination intensity, air humidity, soil humidity and fertilizer consumption data, analyzing the influence of multiple parameters on growth, identifying driving parameters of multi-stage growth, and generating a preliminary key parameter list;
Based on the preliminary key parameter list, comprehensively referring to the influence of illumination, air humidity, soil humidity and fertilizer consumption on growth, and selecting multi-stage optimal parameter configuration through comparative analysis to obtain optimized key parameter configuration;
And adjusting the irrigation frequency according to the set threshold value of the soil humidity based on the optimized key parameter configuration, adjusting the fertilizer type and the application amount according to the soil nutrients, adjusting the illumination intensity, and obtaining an optimized parameter list.
6. The method of optimizing seedling raising based on big data according to claim 1, wherein the step of optimizing seedling raising conditions by global and local search optimizing multi-stage parameters by using the optimizing parameter list to generate an optimizing parameter scheme specifically comprises:
Based on the optimized parameter list, detecting potential conflicts among parameters, adjusting the conflict parameters to balance points, ensuring that the cooperation among the parameters promotes plant growth, analyzing the influence of the parameters one by one, performing parameter tuning, and generating a parameter conflict adjustment list;
Based on the parameter conflict adjustment list, analyzing environmental condition changes in multiple growth stages, including adjustment requirements of soil humidity along with seasonal changes, refining and optimizing configuration of illumination, moisture and fertilizer parameters to obtain local optimization parameter configuration;
and based on the local optimization parameter configuration, applying the adjusted parameters, and referring to the environmental change of the whole growth period, unifying the optimization parameters to obtain an optimization parameter scheme.
7. The method for optimizing seedling raising based on big data according to claim 1, wherein the steps of analyzing the interaction between the forest and the environment through the dynamic ecological network model, updating model parameters, mapping ecological state, and constructing the dynamic model of the growth of the forest by using the seedling raising effect evaluation result are specifically as follows:
recording tree growth data by analyzing the seedling effect evaluation result, and calculating through a Pearson correlation coefficient and a Spearman rank correlation coefficient to identify the correlation between key environmental factors of soil humidity and temperature and tree growth so as to obtain an ecological factor identification result;
The ecological factor recognition result is adopted, relation parameters of the growth rate, the survival rate and the environmental factors of the forest in the model are adjusted, actual interaction between the growth of the forest and the environment is mapped, and a parameter updating model is generated;
and simulating a plurality of growth stages from seedling to maturity of the forest by using the parameter updating model, and recording interaction between the forest state in the differential growth period and environmental change to obtain a forest growth dynamic model.
8. The method of optimizing forestry seedling based on big data according to claim 7, wherein the Pearson correlation coefficient uses the formula:；
The Spearman rank correlation coefficient employs the formula: ；
Wherein, AndFor improved Pearson correlation coefficients and Spearman rank correlation coefficients,AndAs an observation of the original environment and the growth data,For additional environmental impact parameters, including soil nutrient content,AndRespectively is withAndThe associated additional parameters, including average light intensity and rainfall over the target period,In order for the rank to be poor,In order to be able to measure the number of observations,Is a weight coefficient used for adjusting the weight of the influence of the additional parameter on the original data,For the additional introduction of the ranking difference parameter,The number of observations that are additional references.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410855316.2A CN118410081B (en) | 2024-06-28 | 2024-06-28 | Forestry seedling optimization method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410855316.2A CN118410081B (en) | 2024-06-28 | 2024-06-28 | Forestry seedling optimization method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118410081A true CN118410081A (en) | 2024-07-30 |
| CN118410081B CN118410081B (en) | 2024-08-23 |
Family
ID=92032483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410855316.2A Active CN118410081B (en) | 2024-06-28 | 2024-06-28 | Forestry seedling optimization method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118410081B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118840224A (en) * | 2024-09-23 | 2024-10-25 | 广东力生智能有限公司 | Tobacco seedling full-period monitoring management system and method based on Internet of things |
| CN118901368A (en) * | 2024-09-09 | 2024-11-08 | 中国热带农业科学院热带作物品种资源研究所 | Orchard water and fertilizer regulation and control method and system |
| CN119250760A (en) * | 2024-12-03 | 2025-01-03 | 广州市林业和园林科学研究院 | A tree planting and adoption service system and method |
| CN119273951A (en) * | 2024-09-04 | 2025-01-07 | 广东省农业科学院果树研究所 | Litchi growth balance control method and system based on intelligent water and fertilizer integration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2011138109A (en) * | 2011-09-16 | 2013-05-10 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Брянская государственная инженерно-технологическая академия" | METHOD FOR COMPREHENSIVE ASSESSMENT OF THE STATE OF FOREST ECOSYSTEMS IN THE AREAS OF TECHNOGENIC INFLUENCE OF INDUSTRIAL OBJECTS |
| CN105104049A (en) * | 2015-03-23 | 2015-12-02 | 宁波市鄞州区天童林场 | Pseudolarix kaempferi seedling naturally breeding method |
| CN115443826A (en) * | 2022-09-05 | 2022-12-09 | 江苏里下河地区农业科学研究所 | Fine light control method and system for healthy seedling cultivation |
| CN117196249A (en) * | 2023-09-27 | 2023-12-08 | 青海省交控建设工程集团有限公司 | Vegetation greening method for high-cold high-altitude areas |
-
2024
- 2024-06-28 CN CN202410855316.2A patent/CN118410081B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2011138109A (en) * | 2011-09-16 | 2013-05-10 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Брянская государственная инженерно-технологическая академия" | METHOD FOR COMPREHENSIVE ASSESSMENT OF THE STATE OF FOREST ECOSYSTEMS IN THE AREAS OF TECHNOGENIC INFLUENCE OF INDUSTRIAL OBJECTS |
| CN105104049A (en) * | 2015-03-23 | 2015-12-02 | 宁波市鄞州区天童林场 | Pseudolarix kaempferi seedling naturally breeding method |
| CN115443826A (en) * | 2022-09-05 | 2022-12-09 | 江苏里下河地区农业科学研究所 | Fine light control method and system for healthy seedling cultivation |
| CN117196249A (en) * | 2023-09-27 | 2023-12-08 | 青海省交控建设工程集团有限公司 | Vegetation greening method for high-cold high-altitude areas |
Non-Patent Citations (1)
| Title |
|---|
| 张秀珍;: "林业病虫害防治有效方法的思考", 农村实用技术, no. 06, 11 June 2020 (2020-06-11) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119273951A (en) * | 2024-09-04 | 2025-01-07 | 广东省农业科学院果树研究所 | Litchi growth balance control method and system based on intelligent water and fertilizer integration |
| CN118901368A (en) * | 2024-09-09 | 2024-11-08 | 中国热带农业科学院热带作物品种资源研究所 | Orchard water and fertilizer regulation and control method and system |
| CN118901368B (en) * | 2024-09-09 | 2025-03-07 | 中国热带农业科学院热带作物品种资源研究所 | Orchard water and fertilizer regulation and control method and system |
| CN118840224A (en) * | 2024-09-23 | 2024-10-25 | 广东力生智能有限公司 | Tobacco seedling full-period monitoring management system and method based on Internet of things |
| CN118840224B (en) * | 2024-09-23 | 2025-02-07 | 广东力生智能有限公司 | Tobacco seedling full cycle monitoring management system and method based on Internet of Things |
| CN119250760A (en) * | 2024-12-03 | 2025-01-03 | 广州市林业和园林科学研究院 | A tree planting and adoption service system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118410081B (en) | 2024-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118410081B (en) | Forestry seedling optimization method based on big data | |
| CN112906298B (en) | Blueberry yield prediction method based on machine learning | |
| CN118097438A (en) | A fertilization method and system based on big data | |
| CN117893346A (en) | AI intelligent agriculture harvesting management system based on Internet of things and application thereof | |
| CN118348900B (en) | Internet of things-based field environment control method and device | |
| CN117669885A (en) | Intelligent tobacco planting management system and method | |
| KR20210114751A (en) | Method and apparatus for estimating crop growth quantity | |
| CN115292753A (en) | Agricultural greenhouse data tracing and management method based on block chain | |
| Zhang et al. | Artificial intelligence in soil management: The new frontier of smart agriculture | |
| CN118586549A (en) | Seedling growth monitoring and management system | |
| Parashar et al. | ENHANCING CROP YIELD PREDICTION IN PRECISION AGRICULTURE THROUGH SUSTAINABLE BIG DATA ANALYTICS AND DEEP LEARNING TECHNIQUES. | |
| Khatraty et al. | Smart Digital-Twin hub Concept for Rice yield prediction and monitoring from multivariate time series data | |
| Goldenits et al. | Current applications and potential future directions of reinforcement learning-based Digital Twins in agriculture | |
| Carrasquilla-Batista et al. | IoT applications: On the path of Costa Rica's commitment to becoming carbon-neutral | |
| CN119003985A (en) | Unmanned aerial vehicle-based litchi full-growth-period nutrition accurate regulation and control method | |
| CN119151052A (en) | Sugarcane yield prediction method and system based on machine learning | |
| Abidi et al. | Elucidation of intelligent classification framework for hydroponic lettuce deficiency using enhanced optimization strategy and ensemble multi-dilated adaptive networks | |
| Shermila et al. | Optimization of Agriculture Using Data Science and Machine Learning | |
| Tsvetkova et al. | The use of digital technologies in agricultural management | |
| Chen et al. | Artificial intelligence-driven gene editing and crop breeding: Technological innovations and application prospects | |
| KR102720660B1 (en) | Design method of smart farm cooling package optimal design support system | |
| CN118350850B (en) | A method and system for supporting decision making of thermal analysis of agricultural products | |
| Fondaj et al. | Proposal of Prediction Model for Smart Agriculture Based on IoT Sensor Data | |
| Sharaf | AI and Robotic Innovations for Optimizing Cucumber Harvesting Time and Improving Resource Efficiency in Vertical Farming by 2028 | |
| Kumar | Chapter-2 Internet of Things (IoT) for Adoption of Precision Agriculture Practices among Indian Row-crop Producers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |