[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
Precision Agriculture and Sensor Systems—2nd Edition
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Precision Agriculture and Sensor Systems—2nd Edition

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Smart Agriculture".

Deadline for manuscript submissions: closed (3 August 2024) | Viewed by 6691

Special Issue Editors

Prof. Dr. Viacheslav Adamchuk

E-Mail Website
Guest Editor
Department of Bioresource Engineering, 21,111 Lakeshore Road, Ste-Anne-de-Bellevue, QC H9X 3V9, Canada
Interests: development of soil and plant sensor systems; geospatial data processing; navigation of agricultural vehicles; implementation of precision agriculture
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Abdul M. Mouazen

E-Mail Website
Guest Editor
Precision Soil and Crop Engineering (Precision Scoring), Faculty of Bioscience Engineering, Ghent University, Coupure Links 653, Blok B, 1st Floor, 9000 Gent, Belgium
Interests: proximal soil sensing; soil and water management; soil dynamics; tillage; traction; compaction; mechanical weeding; soil remediation and management and precision agriculture
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

You are invited to submit a manuscript to a special issue of Sensors. This issue will summarize cutting-edge research on the development and application of new sensor systems to support precision agriculture. We are especially interested in contributions on novel approaches to characterize soil, plants and animals as well as new ways to use sensor data to support the decision-making process.

Prof. Dr. Viacheslav Adamchuk
Prof. Dr. Abdul M. Mouazen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

21 pages, 29836 KiB  
Article
Sensorizing a Beehive: A Study on Potential Embedded Solutions for Internal Contactless Monitoring of Bees Activity
by Massimiliano Micheli, Giulia Papa, Ilaria Negri, Matteo Lancini, Cristina Nuzzi and Simone Pasinetti
Sensors 2024, 24(16), 5270; https://doi.org/10.3390/s24165270 - 14 Aug 2024
Viewed by 563
Abstract
Winter is the season of main concern for beekeepers since the temperature, humidity, and potential infection from mites and other diseases may lead the colony to death. As a consequence, beekeepers perform invasive checks on the colonies, exposing them to further harm. This [...] Read more.
Winter is the season of main concern for beekeepers since the temperature, humidity, and potential infection from mites and other diseases may lead the colony to death. As a consequence, beekeepers perform invasive checks on the colonies, exposing them to further harm. This paper proposes a novel design of an instrumented beehive involving color cameras placed inside the beehive and at the bottom of it, paving the way for new frontiers in beehive monitoring. The overall acquisition system is described focusing on design choices towards an effective solution for internal, contactless, and stress-free beehive monitoring. To validate our approach, we conducted an experimental campaign in 2023 and analyzed the collected images with YOLOv8 to understand if the proposed solution can be useful for beekeepers and what kind of information can be derived from this kind of monitoring, including the presence of Varroa destructor mites inside the beehive. We experimentally found that the observation point inside the beehive is the most challenging due to the frequent movements of the bees and the difficulties related to obtaining in-focus images. However, from these images, it is possible to find Varroa destructor mites. On the other hand, the observation point at the bottom of the beehive showed great potential for understanding the overall activity of the colony. Full article
(This article belongs to the Special Issue Precision Agriculture and Sensor Systems—2nd Edition)
►▼ Show Figures

Figure 1

Figure 1
<p>Example of the liquid lenses sweep actuation. Red areas depict focal lengths for which the image is completely out of focus, yellow areas depict focal lengths for which the image is still out of focus but objects are distinguishable from the background, and finally, green areas depict focal lengths for which the output image is in focus.</p> Full article ">Figure 2
<p>Scheme of the proposed set-up presenting the wiring of electrical components. Images of the mechanical mounting are also shown for both cameras (“Frame” and “Bottom”).</p> Full article ">Figure 3
<p>Scheme of the multi-process software that deals with frames acquisition and saving. In this example, only two cameras are shown; however, the software works with up to 4 devices (due to USB bandwidth limitations).</p> Full article ">Figure 4
<p>Representation of images subdivision into out-of-focus and in-focus according to the custom thresholding developed. (<b>a</b>) The 2D t-SNE visualization. (<b>b</b>) The 3D t-SNE visualization.</p> Full article ">Figure 5
<p>Example of the bounding boxes coordinate system with respect to the image coordinate system. Every parameter is expressed in pixels. The bounding box is depicted in yellow.</p> Full article ">Figure 6
<p>Examples taken from the “Frame detector” dataset. (<b>a</b>) The left bee is labeled as “blurred_bee”, and the right bee as “bee” (in-focus). (<b>b</b>) Example of a “bee” class fully visible. (<b>c</b>) Example of several “blurred_bee” not fully visible. (<b>d</b>) Example of a true negative image where no boxes are drawn. A bee or two seem to appear on the right; however, they are so blurred that a confident detection is impossible even for an expert.</p> Full article ">Figure 7
<p>Examples taken from the “Bottom detector” dataset. The visible bees are mostly located on the right (red spot), inside the frames. (<b>a</b>) An “occluded_bee” is seen at the bottom center. (<b>b</b>) A couple of “occluded_bees” are at the top center. (<b>c</b>) Example of a visible “bee” on the left area between the frames. (<b>d</b>) Example of a visible “bee” on the right almost outside the frames.</p> Full article ">Figure 8
<p>Labels correlogram computed on the “Frame detector” dataset. The diagonal shows the histograms corresponding to the bounding boxes’ coordinates (<math display="inline"><semantics> <msub> <mi>C</mi> <mi>X</mi> </msub> </semantics></math>, <math display="inline"><semantics> <msub> <mi>C</mi> <mi>Y</mi> </msub> </semantics></math>, <span class="html-italic">W</span>, <span class="html-italic">H</span>) respectively. The off-diagonal graphs show the relationship between the four coordinates accordingly.</p> Full article ">Figure 9
<p>Confusion matrix of the “Frame detector” model computed on resulted data of test sub-dataset. Row-wise and column-wise statistics are shown on the right and at the bottom of the confusion matrix. Values inside the confusion matrix are normalized over the total observations in the test sub-dataset.</p> Full article ">Figure 10
<p>Labels correlogram computed on the “Bottom detector” dataset. The diagonal shows the histograms corresponding to the bounding boxes’ coordinates (<math display="inline"><semantics> <msub> <mi>C</mi> <mi>X</mi> </msub> </semantics></math>, <math display="inline"><semantics> <msub> <mi>C</mi> <mi>Y</mi> </msub> </semantics></math>, <span class="html-italic">W</span>, <span class="html-italic">H</span>) respectively. The off-diagonal graphs show the relationship between the four coordinates accordingly.</p> Full article ">Figure 11
<p>Confusion matrix of the “Bottom detector” model computed on resulted data of test sub-dataset. Row-wise and column-wise statistics are shown on the right and at the bottom of the confusion matrix. Values inside the confusion matrix are normalized over the total observations in the test sub-dataset.</p> Full article ">Figure 12
<p>(<b>a</b>–<b>d</b>) Examples of potential <span class="html-italic">Varroa destructor</span> mites taken from the “Frame” dataset highlighted with a red circle on top of the original image.</p> Full article ">Figure 13
<p>Top view of the set-up depicting the inside of the <span class="html-italic">honey super</span>, where the third camera and electronic components are placed. This configuration is still in development.</p> Full article ">
17 pages, 3815 KiB  
Article
Site-Independent Mapping of Clay Content in Vineyard Soils via Mobile Proximal Gamma-Ray Spectrometry and Machine Learning Calibrations
by Ralf Wehrle and Stefan Pätzold
Sensors 2024, 24(14), 4528; https://doi.org/10.3390/s24144528 - 12 Jul 2024
Viewed by 506
Abstract
Vineyards hold considerable soil variability between regions and plots, and there is frequently large soil heterogeneity within plots. Clay content in vineyard soils is of interest with respect to soil management, environmental monitoring, and wine quality. However, spatially resolved clay mapping is laborious [...] Read more.
Vineyards hold considerable soil variability between regions and plots, and there is frequently large soil heterogeneity within plots. Clay content in vineyard soils is of interest with respect to soil management, environmental monitoring, and wine quality. However, spatially resolved clay mapping is laborious and expensive. Gamma-ray spectrometry (GS) is a suitable tool for predicting clay content in precision agriculture when locally calibrated, but it has scarcely been tested site-independently and in vineyards. This study evaluated GS to predict clay content with a site-independent calibration and four machine learning algorithms (Support Vector Machines, Random Forest, k-Nearest Neighbors, and Bayesian regulated neuronal networks) in eight vineyards from four German vine-growing regions. Clay content in the studied soils ranged from 62 to 647 g kg−1. The Random Forest calibration was most suitable. Test set evaluation revealed good model performance for the entire dataset with RPIQ = 4.64, RMSEP = 56.7 g kg−1, and R2 = 0.87; however, prediction quality varied between the sites. Overall, GS with the Random Forest model calibration was appropriate to predict the clay content and its spatial distribution, even for heterogeneous geopedological settings and in individual plots. Therefore, GS is considered a valuable tool for soil mapping in vineyards, where clay content and product quality are closely linked. Full article
(This article belongs to the Special Issue Precision Agriculture and Sensor Systems—2nd Edition)
►▼ Show Figures

Figure 1

Figure 1
<p>Tractor-mounted gamma spectrometer.</p> Full article ">Figure 2
<p>Clay content (g kg<sup>−1</sup>) versus gamma ROIs for the entire dataset: (<b>a</b>) total counts (cps); (<b>b</b>) K-40 (cps); (<b>c</b>) Th-232 (cps); (<b>d</b>) Th-232/K-40-ratios.</p> Full article ">Figure 3
<p>Predicted and observed values of cross-validation (cal) and test set validation (val) for clay content from site-independent regression models. SVM: Support Vector Machine; KNN: k-Nearest Neighbor, BNN: Bayesian regularized neuronal network; RF: Random Forest.</p> Full article ">Figure 4
<p>Prediction results of the site-independent RF calibration model when separately applied to individual vineyards.</p> Full article ">Figure 5
<p>(<b>a</b>) Total counts (cps) of on-the-go gamma spectrometric measurements and ground truth sampling points of the examined vineyards. (<b>b</b>) Total counts (cps) of on-the-go gamma spectrometric measurements and ground truth sampling points of the examined vineyards.</p> Full article ">Figure 5 Cont.
<p>(<b>a</b>) Total counts (cps) of on-the-go gamma spectrometric measurements and ground truth sampling points of the examined vineyards. (<b>b</b>) Total counts (cps) of on-the-go gamma spectrometric measurements and ground truth sampling points of the examined vineyards.</p> Full article ">Figure 6
<p>Gamma spectrometric on-the-go predicted soil clay maps of Random Forest model and ground truth data (large dots) for the vineyards in (<b>a</b>) Leiw H, (<b>b</b>) Leiw K, (<b>c</b>) Sieb N, and (<b>d</b>) Spre B.</p> Full article ">
17 pages, 2879 KiB  
Article
Prediction Accuracy of Soil Chemical Parameters by Field- and Laboratory-Obtained vis-NIR Spectra after External Parameter Orthogonalization
by Konrad Metzger, Frank Liebisch, Juan M. Herrera, Thomas Guillaume and Luca Bragazza
Sensors 2024, 24(11), 3556; https://doi.org/10.3390/s24113556 - 31 May 2024
Viewed by 3079
Abstract
One challenge in predicting soil parameters using in situ visible and near infrared spectroscopy is the distortion of the spectra due to soil moisture. External parameter orthogonalization (EPO) is a mathematical method to remove unwanted variability from spectra. We created two different EPO [...] Read more.
One challenge in predicting soil parameters using in situ visible and near infrared spectroscopy is the distortion of the spectra due to soil moisture. External parameter orthogonalization (EPO) is a mathematical method to remove unwanted variability from spectra. We created two different EPO correction matrices based on the difference between spectra collected in situ and, respectively, spectra collected from the same soil samples after drying and sieving and after drying, sieving and finely grinding. Spectra from 134 soil samples recorded with two different spectrometers were split into calibration and validation sets and the two EPO corrections were applied. Clay, organic carbon and total nitrogen content were predicted by partial least squares regression for uncorrected and EPO-corrected spectra using models based on the same type of spectra (“within domain”) as well as using laboratory-based models to predict in situ collected spectra (“cross-domain”). Our results show that the within-domain prediction of clay is improved with EPO corrections only for the research grade spectrometer, with no improvement for the other parameters. For the cross-domain predictions, there was a positive effect from both EPO corrections on all parameters. Overall, we also found that in situ collected spectra provided an equally successful prediction as laboratory-based spectra. Full article
(This article belongs to the Special Issue Precision Agriculture and Sensor Systems—2nd Edition)
►▼ Show Figures

Figure 1

Figure 1
<p>Scanning setup for in situ spectra acquisition with the NeoSpectra Scanner (<b>a</b>) and with the PSR+3500 contact probe (<b>b</b>). The setup for laboratory spectra acquisition of only sieved (lab_sieved) soil samples (<b>c</b>) and finely ground (lab_fine) soil sample (<b>d</b>) with the PSR+3500 bare fiber.</p> Full article ">Figure 2
<p>Visualization of the first two principal components (PC1 and PC2) of the dataset with the calibration (red dot) and the validation (circle) samples as selected by the Kennard–Stone algorithm for the PSR spectrometer. The ratio calibration/validation was of 70/30.</p> Full article ">Figure 3
<p>Overview of the EPO correction and the models created with the EPO-corrected spectra. This scheme applies to the spectra collected with both the spectrometers. See the main text for abbreviations.</p> Full article ">Figure 4
<p>Raw absorbance spectra (<b>a</b>,<b>c</b>) and EPO-corrected absorbance spectra (<b>b</b>,<b>d</b>) from an exemplary soil sample for the PSR spectrometer (<b>a</b>,<b>b</b>) and the NEO spectrometer (<b>c</b>,<b>d</b>) for the sieved-only (lab: green) and in situ (field: red) scans. In (<b>a</b>,<b>c</b>), absorption peaks of H<sub>2</sub>O are clearly visible around 1400 nm, 1900 nm and 2250 nm. Note the difference scale of the <span class="html-italic">y</span>-axis.</p> Full article ">Figure 5
<p>Laboratory versus predicted values from the validation set for the within-domain predictions for clay (<b>a</b>,<b>d</b>), SOC (<b>b</b>,<b>e</b>) and Ntot (<b>c</b>,<b>f</b>) for the PSR (<b>a</b>–<b>c</b>) and the NEO (<b>d</b>–<b>f</b>) spectrometer including the 1:1 line. The predicted values for the field-obtained (=field moist) model are displayed in red, for the lab_fine in black and for the lab_sieved in blue. For an overview of the modeling process, see <a href="#sensors-24-03556-f003" class="html-fig">Figure 3</a>. For the level of accuracy of prediction, see <a href="#sensors-24-03556-t003" class="html-table">Table 3</a> for the modelling “field moist”, “lab_sieved” and “lab_fine” for the two spectrometers and the three parameters.</p> Full article ">Figure 6
<p>RPIQ values for uncorrected (raw) spectra (grey) and correspondent EPO-corrected spectra (black) for within domain predictions (field_f and field_s) and cross-domain predictions (lab_f-field_f and lab_s-field_s) for the PSR (<b>a</b>–<b>c</b>) and the NEO (<b>d</b>–<b>f</b>) spectrometers and for clay (<b>a</b>,<b>d</b>), SOC (<b>b</b>,<b>e</b>) and Ntot (<b>c</b>,<b>f</b>). The values of the raw field-obtained spectra (field_s and field_f) are the same and repeated for a better comparison.</p> Full article ">Figure 7
<p>Laboratory versus predicted values from the validation set for the cross-domain predictions for clay (<b>a</b>,<b>d</b>), SOC (<b>b</b>,<b>e</b>) and Ntot (<b>c</b>,<b>f</b>) for the PSR (<b>a</b>–<b>c</b>) and the NEO (<b>d</b>–<b>f</b>) spectrometers including the 1:1 line. The predicted values for the uncorrected predictions are displayed in red for the <span class="html-italic">lab_sieved-field moist</span> model and in orange for the <span class="html-italic">lab_fine-field moist</span> model, whereas for the EPO-corrected models the predicted values are in dark blue for the <span class="html-italic">sieved_EPO_s-field_EPO_</span>s model and in light blue for the <span class="html-italic">fine_EPO_f-field_EPO_f</span> model. For an overview over the modeling process, see <a href="#sensors-24-03556-f003" class="html-fig">Figure 3</a> and <a href="#sensors-24-03556-t003" class="html-table">Table 3</a>.</p> Full article ">
19 pages, 5382 KiB  
Article
Development of a Quick-Install Rapid Phenotyping System
by Roberto M. Buelvas, Viacheslav I. Adamchuk, John Lan, Valerio Hoyos-Villegas, Arlene Whitmore and Martina V. Stromvik
Sensors 2023, 23(9), 4253; https://doi.org/10.3390/s23094253 - 25 Apr 2023
Viewed by 1705
Abstract
In recent years, there has been a growing need for accessible High-Throughput Plant Phenotyping (HTPP) platforms that can take measurements of plant traits in open fields. This paper presents a phenotyping system designed to address this issue by combining ultrasonic and multispectral sensing [...] Read more.
In recent years, there has been a growing need for accessible High-Throughput Plant Phenotyping (HTPP) platforms that can take measurements of plant traits in open fields. This paper presents a phenotyping system designed to address this issue by combining ultrasonic and multispectral sensing of the crop canopy with other diverse measurements under varying environmental conditions. The system demonstrates a throughput increase by a factor of 50 when compared to a manual setup, allowing for efficient mapping of crop status across a field with crops grown in rows of any spacing. Tests presented in this paper illustrate the type of experimentation that can be performed with the platform, emphasizing the output from each sensor. The system integration, versatility, and ergonomics are the most significant contributions. The presented system can be used for studying plant responses to different treatments and/or stresses under diverse farming practices in virtually any field environment. It was shown that crop height and several vegetation indices, most of them common indicators of plant physiological status, can be easily paired with corresponding environmental conditions to facilitate data analysis at the fine spatial scale. Full article
(This article belongs to the Special Issue Precision Agriculture and Sensor Systems—2nd Edition)
►▼ Show Figures

Figure 1

Figure 1
<p>Picture of handheld setup.</p> Full article ">Figure 2
<p>Block diagram of the electronic subsystem of the HTPP platform.</p> Full article ">Figure 3
<p>Picture of built prototype of vehicle-mounted HTPP setup.</p> Full article ">Figure 4
<p>Screenshot of GUI (main window).</p> Full article ">Figure 5
<p>Diagram of variables collected in experiments and used to build models.</p> Full article ">Figure 6
<p>Example histogram of NDVI at last date for a plot and estimated threshold that separates bimodal distribution.</p> Full article ">Figure 7
<p>Results of repeated measurements ANOVA over time.</p> Full article ">Figure 8
<p>Map of plot locations highlighting plots of example varieties.</p> Full article ">Figure 9
<p>Map of NDRE at first date using maximum for aggregation highlighting example varieties.</p> Full article ">Figure 10
<p>Map of NDVI at first date using average for aggregation highlighting example varieties.</p> Full article ">Figure 11
<p>Map of air temperature in °C at first date highlighting example varieties.</p> Full article ">Figure 12
<p>Evolution of phenotypical data for example varieties.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop