Search

This paper presents a machine learning (ML)-based approach for the intelligent control of Autonomous Vehicles (AVs) utilized in solar panel cleaning systems, aiming to mitigate challenges arising from uncertainties, disturbances, and dynamic environments. Solar panels, predominantly situated in dedicated lands for solar energy production (e.g., agricultural solar farms), are susceptible to dust and debris accumulation, leading to diminished energy absorption. Instead of labor-intensive manual cleaning, robotic cleaners offer a viable solution. AVs equipped to transport and precisely position these cleaning robots are indispensable for the efficient navigation among solar panel arrays. However, environmental obstacles (e.g., rough terrain), variations in solar panel installation (e.g., height disparities, different angles), and uncertainties (e.g., AV and environmental modeling) may degrade the performance of traditional controllers. In this study, a biologically inspired method based on Brain Emotional Learning (BEL) is developed to tackle the aforementioned challenges. The developed controller is implemented numerically using MATLAB-SIMULINK. The paper concludes with a comparative analysis of the AVs’ performance using both PID and developed controllers across various scenarios, highlighting the efficacy and advantages of the intelligent control approach for AVs deployed in solar panel cleaning systems within agricultural solar farms. Simulation results demonstrate the superior performance of the ML-based controller, showcasing significant improvements over the PID controller.

The use of unmanned aerial vehicles (UAVs) for pesticide application has increased substantially. However, there is a lack of technical information regarding the optimal operational parameters. The aim of this study was to evaluate the quality of pesticide application on a soybean crop using a UAV employing different spray nozzles. The experiments were conducted using a completely randomized design with four treatments and eight repetitions. The trial was conducted in a soybean growing area during the soybean reproductive stage (1.1 m tall). The treatments included aerial application (rate: 10 L hm−2) using an Agras MG1-P UAV with XR 11001 (flat fan), AirMix 11001 (air-induction flat fan), and COAP 9001 (hollow cone spray) nozzles; for comparison, ground application (rate of 100 L hm−2) using a constant pressure knapsack sprayer with an XR 110015 (flat fan) nozzle was performed. The deposition was evaluated by quantifying a tracer (brilliant blue) using spectrophotometry and analyzing the droplet spectrum using water-sensitive paper. Furthermore, the application quality was investigated using statistical process control methodology. The best deposition performance was exhibited by the application via UAV using the COAP 9001 and AirMix 11001 nozzles. For all the treatments, the process remained under statistical control, indicating commendable adherence to quality standards. The aerial application provided greater penetration of the spray into the crop canopy. With the use of the UAV, the coverage on the water-sensitive paper was

Accurately identifying the boundaries of agricultural land is critical to the effective management of its resources. This includes the determination of property and land rights, the prevention of non-agricultural activities on agricultural land, and the effective management of natural resources. There are various methods for accurate boundary detection, including traditional measurement methods and remote sensing, and the choice of the best method depends on specific objectives and conditions. This paper proposes the use of convolutional neural networks (CNNs) as an efficient and effective tool for the automatic recognition of agricultural land boundaries. The objective of this research paper is to develop an automated method for the recognition of agricultural land boundaries using deep neural networks and Sentinel 2 multispectral imagery. The Buinsky district of the Republic of Tatarstan, Russia, which is known to be an agricultural region, was chosen for this study because of the importance of the accurate detection of its agricultural land boundaries. Linknet, a deep neural network architecture with skip connections between encoder and decoder, was used for semantic segmentation to extract arable land boundaries, and transfer learning using a pre-trained EfficientNetB3 model was used to improve performance. The Linknet + EfficientNetB3 combination for semantic segmentation achieved an accuracy of 86.3% and an f1 measure of 0.924 on the validation sample. The results showed a high degree of agreement between the predicted field boundaries and the expert-validated boundaries. According to the results, the advantages of the method include its speed, scalability, and ability to detect patterns outside the study area. It is planned to improve the method by using different neural network architectures and prior recognized land use classes.

Machine Learning (ML) has enabled many image-based object detection and recognition-based solutions in various fields and is the state-of-the-art method for these tasks currently. Therefore, it is of interest to apply this technique to different questions. In this paper, we explore whether it is possible to classify apple cultivars based on fruits using ML methods and images of the apple in question. The goal is to develop a tool that is able to classify the cultivar based on images that could be used in the field. This helps to draw attention to the variety and diversity in fruit growing and to contribute to its preservation. Classifying apple cultivars is a certain challenge in itself, as all apples are similar, while the variety within one class can be high. At the same time, there are potentially thousands of cultivars indicating that the task becomes more challenging when more cultivars are added to the dataset. Therefore, the first question is whether a ML approach can extract enough information to correctly classify the apples. In this paper, we focus on the technical requirements and prerequisites to verify whether ML approaches are able to fulfill this task with a limited number of cultivars as proof of concept. We apply transfer learning on popular image processing convolutional neural networks (CNNs) by retraining them on a custom apple dataset. Afterward, we analyze the classification results as well as possible problems. Our results show that apple cultivars can be classified correctly, but the system design requires some extra considerations.

Developing different robotic platforms for farm operations is vital to addressing the increasing world population. A harvesting robot significantly increases a farm’s productivity while farmers focus on other relevant farm operations. From the literature, it could be summarized that the design concepts of the harvesting mechanisms were categorized as grasping and cutting, vacuum suction plucking systems, twisting and plucking mechanisms, and shaking and catching. Meanwhile, robotic system components include the mobile platform, manipulators, and end effectors, sensing and localization, and path planning and navigation. The robotic system must be cost-effective and safe. The findings of this research could contribute to the design process of developing a harvesting robot or developing a harvesting module that can be retrofitted to a commercially available mobile platform. This paper provides an overview of the most recent harvesting robots’ different concept designs and system components. In particular, this paper will highlight different agricultural ground mobile platforms and their associated mechanical design, principles, challenges, and limitations to characterize the crop environment relevant to robotic harvesting and to formulate directions for future research and development for cotton harvesting platforms.

In the past few decades, fruits have been increasingly consumed, leading to an increase in global fruit production. However, fresh produce is susceptible to large losses during production and preservation. In the postharvest preservation stage, fruits undergo various technical treatments for maintaining their quality. A widely adopted technology is the application of edible coatings, which can be applied to a diverse range of fruits to regulate the exchange of moisture and gases between the fruit and its environment. In addition, edible coatings provide a significant benefit by allowing the integration of different active ingredients into the coating’s matrix, meaning that these substances will associate with and possibly be eaten together with the fruit. This would help improve the organoleptic and nutritional qualities of the fruit as well as the shelf life. This paper provides an overview of the available data on the typical components used in coating matrix, focusing on the effect of the material combinations and application techniques to fruit properties. The processors can use this knowledge in choosing a suitable coating material and concentration for various fresh and fresh-cut fruits. Additionally, this paper reviews recent developments and limitations in utilizing edible coatings for prolonging the shelf-life of fruits.

Climate change has drawn the attention not only of scientists but of politicians and societies worldwide. The aim of this paper is to present a method for selecting research studies on climate change, waste management and the role of microbes in the recycling of organic matter in soil that analyze the role of organic agriculture as the main connection between agricultural losses and climate change. VOSviewer version 1.6.18 free software tool was used in this study in order to achieve the bibliometric and mapping approach for studies on the effects of climate change in terms of soil recycled organic matter and microbe interaction. Scopus database (accessed 29 September 2022) indexed a total of 1,245,809 bibliographic items classified into paradigms. The presented documents were downloaded from Scopus as graph-based maps and as distance-based maps in order to reflect the strength of the relation between the items. Climate change includes changes in soil and soil microorganisms as affected by natural climate variations and local weather, which have beneficial or negative effects on soil organic matter. From the examination of the selected papers, it was concluded that climate change and changing precipitation patterns are having an impact on microorganisms, particularly bacterial groups, and thus ecosystem function.

Chemical spraying is one of the most important and frequently performed intercultural agricultural operations. It is imperative to select the appropriate spraying technology as a selection of ineffective one leads to the wastage of a considerable volume of applied chemicals to the non-target area. Many precision technologies have been developed in the past few decades, such as image processing based on real-time variable-rate chemical spraying systems, autonomous chemical sprayers using machine vision and nozzle control, and use of unmanned aerial and ground vehicles. Cotton defoliation is a natural physiological process, but untimely and inadequate leaf defoliation by natural process hinders the mechanical cotton harvest. Induced defoliation is practiced by applying defoliants to address the issue with the natural process of defoliation. This paper covers spraying technologies in agriculture, cotton plants, cotton defoliation, new defoliant spraying systems, and the recent field test. The new spraying system attached to an autonomous mobile robot aims to improve the delivery of defoliant chemicals by adding a spray unit on the side of the plant. Preliminary results of the water-sensitive paper test at the field showed adequate penetration with low flow rates. This is a huge development as there is a huge potential to save on the cost of applying defoliant chemicals.

UAV may be limited by its flight height and camera resolution when aerial photography of a tea garden is carried out. The images of the tea garden contain trees and weeds whose vegetation information is similar to tea tree, which will affect tea tree extraction for further agricultural analysis. In order to obtain a high-definition large field-of-view tea garden image that contains tea tree targets, this paper (1) searches for the suture line based on the graph cut method in the image stitching technology; (2) improves the energy function to realize the image stitching of the tea garden; and (3) builds a feature vector to accurately extract tea tree vegetation information and remove unnecessary variables, such as trees and weeds. By comparing this with the manual extraction, the algorithm in this paper can effectively distinguish and eliminate most of the interference information. The IOU in a single mosaic image was more than 80% and the omissions account was 10%. The extraction results in accuracies that range from 84.91% to 93.82% at the different height levels (30 m, 60 m and 100 m height) of single images. Tea tree extraction accuracy rates in the mosaic images are 84.96% at a height of 30 m, and 79.94% at a height of 60 m.

Crown rot disease is caused by Fusarium pseudograminearum and is one of the major stubble-soil fungal diseases threatening the cereal industry globally. It causes failure of grain establishment, which brings significant yield loss. Screening crops affected by crown rot is one of the key tools to manage crown rot, because it is necessary to understand disease infection conditions, identify the severity of infection, and discover potential resistant varieties. However, screening crown rot is challenging as there are no clear visible symptoms on leaves at early growth stages. Hyperspectral imaging (HSI) technologies have been successfully used to better understand plant health and disease incidence, including light absorption rate, water and nutrient distribution, and disease classification. This suggests HSI imaging technologies may be used to detect crown rot at early growing stages, however, related studies are limited. This paper briefly describes the symptoms of crown rot disease and traditional screening methods with their limitations. It, then, reviews state-of-art imaging technologies for disease detection, from color imaging to hyperspectral imaging. In particular, this paper highlights the suitability of hyperspectral-based screening methods for crown rot disease. A hypothesis is presented that HSI can detect crown-rot-infected plants before clearly visible symptoms on leaves by sensing the changes of photosynthesis, water, and nutrients contents of plants. In addition, it describes our initial experiment to support the hypothesis and further research directions are described.

Recent advances in light emitting diode (LED) technology have provided exciting opportunities for plant lighting applications, and it is expected that LED lighting will soon overtake the still common use of high-intensity discharge (HID) lighting technology. Because LED lighting offers novel capabilities, extensive research is needed to identify optimal lighting practices for the large number of crops grown by commercial greenhouse growers. Plant scientists and growers facing decisions about plant lighting systems do not always have sufficient information about lamp performance characteristics. In this paper, we reported on various technical performance characteristics for 18 lamp types commonly used for plant production, and compared these characteristics with the characteristics of sunlight. The results showed a substantial range of performance characteristics, highlighting the importance of a careful assessment before selecting a light source for horticultural applications. The data presented in this paper can be used to assess the suitability of a specific light source for a particular horticultural application.

The objective of this paper was to quantify the economic and environmental effects of changing a dairy farm’s milking start times. Changing morning and evening milking start times could reduce both electricity costs and farm electricity related CO2 emissions. However, this may also involve altering farmer routines which are based on practical considerations. Hence, these changes need to be quantified both in terms of profit/emissions and in terms of how far these milking start times deviate from normal operations. The method presented in this paper optimized the combination of dairy farm infrastructure setup and morning and evening milking start times, based on a weighting variable (α) which assigned relative importance to labor utilization, farm net profit and farm electricity related CO2 emissions. Multi-objective optimization was utilized to assess trade-offs between labor utilization and net profit, as well as labor utilization and electricity related CO2 emissions. For a case study involving a 195 cow Irish dairy farm, when the relative importance of maximizing farm net profit or minimizing farm electricity related CO2 emissions was high, the least common milking start times (06:00 and 20:00) were selected. When the relative importance of labor utilization was high, the most common milking start times (07:00 and 17:00) were selected. The 195 cow farm saved €137 per annum when milking start times were changed from the most common to the least common. Reductions in electricity related CO2 emissions were also seen when the milking start times were changed from most common to least common. However, this reduction in emissions was primarily due to the addition of efficient and renewable technology to the farm. It was deduced that the monetary and environmental benefits of altering farmer milking routines were unlikely to change normal farm operating procedures.

Spraying pesticides using air induction nozzles is a well-known method to reduce drift. These drift-reducing nozzles have been tested on many different tree crops (such as apples, citrus, and grapes), but we are still lacking information on their utilization on hazelnut (Corylus avellana L.) groves, although hazelnut is a major nut crop in Italy, and in recent years its cultivated area has been constantly growing. This paper reports a comparison between treatments carried out with cone and flat-fan low-drift nozzles versus two conventional nozzles. The distribution quality, the number of droplets per cm2 of the target area, and the drift in non-target trees adjacent to those treated were evaluated by analyzing the impact of the droplets on water-sensitive papers placed on the tree canopies. The results show that because no significative differences in terms of application quality were found between the tested nozzles, low-drift nozzles can be a good alternative to the standard nozzles to reduce the drift of pesticide applications in hazelnuts without altering the chosen distribution of the pesticide.

In the business of growing and selling ornamental plants, it is important to keep track of plants from nursery to distribution. Radio Frequency Identification (RFID) technology provides an easier tracking method for inventories of plants by attaching tags with unique identifiers. Due to the vast area of most nurseries, there is a need to have an efficient method of scanning RFID tags. This paper investigates the use of drones and RFID, specifically, the effects of RFID reader power and flight altitude on tag counts. The experimental setup evaluated three RFID reader power levels (15 dBm, 20 dBm, and 27 dBm), three flight altitudes (3 m, 5 m, and 7 m), the number of passes (one or two), and two plant types (‘Green Giant’ arborvitae and ‘Sky Pencil’ holly). For RFID tags, four types were used (L5, L6, L8, and L9), with two antenna types (dog-bone and square-wave) and two attachment types (loop-lock and stake). For each power level, the UAV was flown to three different altitudes of 3 m, 5 m, and 7 m above the ground. At each altitude, two scan passes were performed at a constant speed of approximately 1.5 m/s. Each plot of plants (two in total) was randomly tagged with a total of 40 RFID tags per plot. Field data were collected from September to December 2023 (on a total of eight dates). The data showed that a power level of 15 dBm and an altitude of 3 m yielded a tag count of 53%, while counts of 34% and 16% were achieved at 5 m and 7 m, respectively. At 20 dBm and an altitude of 3 m, the count accuracy across all tag types and both plants was 90%. When the altitude was increased to 5 m and 7 m, tag-count accuracy dropped to 75% and 33%, respectively. The highest count accuracy was observed at 27 dBm and an altitude of 3 m, with a reading accuracy of 98%. Tag types L6 and L9 performed better at any power level and altitude, while L5 and L8 performed well at a higher power level and lower altitude. In this experiment, canopy properties (size and shape) had no effect on the number of tags read. This study aimed to evaluate the RFID power and UAV altitude achieving the highest accuracy in scanning the RFID tags. Furthermore, it also assessed the effects of plant growth on the scanning efficiency and accuracy of the system.

Numerical investigations on the flowability of pulverized biomass are crucial for agriculture, aiding in optimizing biomass use, crop residue management, soil health improvement, and environmental impact mitigation. Rising interest in biomass and conversion processes necessitates deeper property understanding and technological process optimization. Moisture content is a key parameter influencing biomass quality. In this paper, computer simulations of shear tests depending on the moisture content using the discrete element method were carried out and compared with experimental results. An experimental study and modeling for Jenike’s direct shearing apparatus was carried out. A swelling bed model was proposed to account for the effect of moisture. The swelling bed model assumed an increase in biomass grain vorticity proportional to the moisture content. The model was solved using the discrete element method (DEM). The model considers the effect of moisture on the values of Young’s and Kirchoff’s moduli for biomass grains. The model assumed that moisture is not present in surface form, the total amount of moisture is absorbed into the interior of the material grains, and the volume of a single grain increases linearly with an increase in the volume of the absorbed moisture. The tested materials were pulverized sunflower husks, apple pomace, distiller’s dried grains with solubles (DDGS), meat and bone meal (MBM), and sawdust. Samples with moisture contents of 0%, 10%, 20%, and 30% were tested. The best agreement of the model with the experimental data was observed for the most absorbent materials in which moisture was not present in surface form, such as apple pomace, DDGS, and sawdust. Research data are important for the proper design of biomass storage, transportation equipment, and utilization as feedstock for bioenergy production or soil enrichment.

This paper deals with the problem of predetermining the spray angle and uniformity of the flat fan sprayer with a semicircular impact surface for the intra-soil application of liquid mineral fertilizers. The jet impact on a round splash plate and radial atomization properties are investigated theoretically, the formation features of the spray with an obtuse angle are studied in a geometrical way, and the design search of the nozzle shape and optimization calculations are performed using computational fluid dynamics (CFD) simulations and then verified experimentally. It was revealed that the spray rate and spray angle can be adjusted by changing the parameter s, and when the spray angle is within s = 0–0.2 mm, it forms spray angles with range of 140°–175°. The spraying angle, in turn, shows the potential length of the tillage knife in accordance with the undersoil cavity dimensions. A spray uniformity of up to 74% was achieved, which is sufficient for applied studies and for intra-soil application operations. According to the investigations and field experiments, it can be concluded that the designed nozzle is applicable for the intra-soil application of liquid mineral fertilizers. The use of flat fan nozzles that form a spraying band under the soil cavity and along the entire length of the tillage knife ensures a highly efficient mixing process, the liquid mineral fertilizers with treated soil (particles) positively contributing to plant maturation.

Satellite remote sensing data expedite crop yield estimation, offering valuable insights for farmers’ decision making. Recent forecasting methods, particularly those utilizing machine learning algorithms like Random Forest and Artificial Neural Networks, show promise. However, challenges such as validation performances, large volume of data, and the inherent complexity and inexplicability of these models hinder their widespread adoption. This paper presents a simpler approach, employing linear regression models fitted from vegetation indices (VIs) extracted from MODIS sensor data on the Terra and Aqua satellites. The aim is to forecast cotton yields in key areas of the Brazilian Cerrado. Using data from 281 commercial production plots, models were trained (167 plots) and tested (114 plots), relating seed cotton yield to nine commonly used VIs averaged over 15-day intervals. Among the evaluated VIs, Enhanced Vegetation Index (EVI) and Triangular Vegetation Index (TVI) exhibited the lowest root mean square errors (RMSE) and the highest determination coefficients (R2). Optimal periods for in-season yield prediction fell between 90 and 105 to 135 and 150 days after sowing (DAS), corresponding to key phenological phases such as boll development, open boll, and fiber maturation, with the lowest RMSE of about 750 kg ha−1 and R2 of 0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time series) for EVI and TVI, which occurred around 80–90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps, and their respective VIs.

Potential soil production is closely related to the physical and mechanical properties. The aim of this paper was to evaluate the effect of different levels of soil compaction created by tractor chassis. The total area of the experimental plot was 13.22 ha. Up until 2019, a conventional tillage system had been used. The measurements were carried out with an innovative measuring device that allows for the continuous measurement of the horizontal penetrometry for comparative measurements while driving, which was designed at the Slovak University of Agriculture in Nitra. The measuring device measured the soil resistance in the tire track (On-track) and out of track (Off-track) as well as in three (50 s) sequences within one tractor pass. Three lines were chosen, where in each a pair of combinations was made. The results were subjected, in addition to graphical evaluation, to single factor ANOVA analysis. When comparing individual passes (PH1 to PH6), the statistical analysis showed that the results of the horizontal resistance measurements proved to be statistically significant (p < 0.05) with respect to the weight, number of passes, and tire underinflation. The highest compaction was caused by the first pass, while the higher weight of the tractor during the next pass had a smaller effect. Underinflating the tires ensured a reduction in compaction. Reducing the tractor tire pressure to 0.15 MPa resulted in a reduction in soil compaction of up to 16%.

The paper presents research on measuring and the possibility of prediction of noise levels on the left and right sides of the operator within the cabin of an agricultural tractor when moving across various agrotechnical surfaces, considering movement velocity and tire pressures while employing machine learning techniques. Noise level measurements were conducted on a LANDINI POWERFARM 100 type tractor, and aligned with standards (HRN ISO 5008, HRN ISO 6396 and HRN ISO 5131). The obtained noise values were divided into two data sets (left and right set) and processed using multiple linear regression (mlr) and three machine learning methods (gradient boosting machine (gbm); support vector machine using radial basis function kernel (svmRadial); monotone multi-layer perceptron neural network (monmlp)). The most accurate method, considering surfaces, from the left side data set—(R2 0.515–0.955); (RMSE 0.302–0.704); (MAE 0.225–0.488)—and the right side—(R2 0.555–0.955); (RMSE 0.180–0.969); (MAE 0.139–0.644)—was monmlp predominantly, and to a lesser extent svmRadial. On analyzing the total data sets from the left and right sides regarding surfaces, gbm emerged as the most accurate method. The application of machine learning methods demonstrated data accuracy, yet in future research, measurements on certain surfaces may need to be repeated multiple times potentially to improve accuracy further.

Over the years, agricultural management practices are being improved as they integrate Information and Communication Technologies (ICT) and Precision Agriculture tools. Regarding sugarcane crop production, this integration aims to reduce production cost, enhance input applications, and allow communication among different hardware and datasets, improving system sustainability. Sugarcane mechanization has some particularities that mandate the development of custom solutions based on digital tools, which are being applied globally in different crops. Digital mechanization can be conceived as the application of digital tools on mechanical operation. This review paper addresses different digital solutions that have contributed towards the mechanization of sugarcane crop production. The process of digitalization and transformation in agriculture and its related operations to sugarcane are presented, highlighting important ICT applications such as real-time mechanical operations monitoring and integration among operations, demonstrating their contributions and limitations regarding management efficiency. In addition, this article presents the major challenges to overcome and possible guidance on research to address these issues, i.e., poor communication technologies available, need for more focus on field and crop data, and lack of data interoperability among mechanized systems.

Pine wilt disease causes huge economic losses to pine wood forestry because of its destructiveness and rapid spread. This paper proposes a detection and location method of pine wood nematode disease at a large scale adopting UAV (Unmanned Aerial Vehicle) remote sensing and artificial intelligence technology. The UAV remote sensing images were enhanced by computer vision tools. A Faster-RCNN (Faster Region Convolutional Neural Networks) deep learning framework based on a RPN (Region Proposal Network) network and the ResNet residual neural network were used to train the pine wilt diseased dead tree detection model. The loss function and the anchors in the RPN of the convolutional neural network were optimized. Finally, the location of pine wood nematode dead tree was conducted, which generated the geographic information on the detection results. The results show that ResNet101 performed better than VGG16 (Visual Geometry Group 16) convolutional neural network. The detection accuracy was improved and reached to about 90% after a series of optimizations to the network, meaning that the optimization methods proposed in this paper are feasible to pine wood nematode dead tree detection.

Within the transition from precision agriculture (task-specific approach) to smart farming (system-specific approach) there is a need to build and evaluate robotic systems that are part of an overall integrated system under a continuous two-way connection and interaction. This paper presented an initial step in creating an integrated system for agri-robotics, enabling two-way communication between an unmanned ground vehicle (UGV) and a farm management information system (FMIS) under the general scope of smart farming implementation. In this initial step, the primary task of route-planning for the agricultural vehicles, as a prerequisite for the execution of any field operation, was selected as a use-case for building and evaluating this integration. The system that was developed involves advanced route-planning algorithms within the cloud-based FMIS, a comprehensive algorithmic package compatible with agricultural vehicles utilizing the Robot Operating System (ROS), and a communicational and computational unit (CCU) interconnecting the FMIS algorithms, the corresponding user interface, and the vehicles. Its analytical module provides valuable information about UGVs’ performance metrics, specifically performance indicators of working distance, non-working distance, overlapped area, and field-traversing efficiency. The system was demonstrated via the implementation of two robotic vehicles in route-execution tasks in various operational configurations, field features, and cropping systems (open field, row crops, orchards). The case studies showed variability in the operational performance of the field traversal efficiency to be between 79.2% and 93%, while, when implementing the optimal route-planning functionality of the system, there was an improvement of up to 9.5% in the field efficiency. The demonstrated results indicate that the user can obtain better control over field operations by making alterations to ensure optimum field performance, and the user can have complete supervision of the operation.

In the field of agriculture, measuring the leaf area is crucial for the management of crops. Various techniques exist for this measurement, ranging from direct to indirect approaches and destructive to non-destructive techniques. The non-destructive approach is favored because it preserves the plant’s integrity. Among these, several methods utilize leaf dimensions, such as width and length, to estimate leaf areas based on specific models that consider the unique shapes of leaves. Although this approach does not damage plants, it is labor-intensive, requiring manual measurements of leaf dimensions. In contrast, some indirect non-destructive techniques leveraging convolutional neural networks can predict leaf areas more swiftly and autonomously. In this paper, we propose a new direct method using 3D point clouds constructed by semantic RGB-D (Red Green Blue and Depth) images generated by a semantic segmentation neural network and RGB-D images. The key idea is that the leaf area is quantified by the count of points depicting the leaves. This method demonstrates high accuracy, with an R2 value of 0.98 and a RMSE (Root Mean Square Error) value of 3.05 cm2. Here, the neural network’s role is to segregate leaves from other plant parts to accurately measure the leaf area represented by the point clouds, rather than predicting the total leaf area of the plant. This method is direct, precise, and non-invasive to sweet pepper plants, offering easy leaf area calculation. It can be implemented on laptops for manual use or integrated into robots for automated periodic leaf area assessments. This innovative method holds promise for advancing our understanding of plant responses to environmental changes. We verified the method’s reliability and superior performance through experiments on individual leaves and whole plants.

Photosynthetically Active Radiation (PAR) is an important parameter in the plant photosynthesis process, which can relate to plant growth, crop water use, and leaf gas exchange. Previously, many researchers utilized commercially available sensors to monitor PAR. The high cost of the commercially available PAR sensors has limited researchers, agricultural professionals, and farmers to use and expand PAR monitoring in agricultural lands. Thus, this paper focuses on designing an affordable Internet of Things (IoT)-based PAR sensor monitoring system including 3D-printed enclosures (waterproof) for the sensors, performance evaluation of multiple light sensors, solar powering configuration, cloud setup, and cost analysis. Three sensors, including VTB8440BH photodiode, SI 1145, and LI-190R sensors, were evaluated. The 3D-printed waterproof enclosures were designed for the photodiode and SI 1145. Particle Boron was used for recording and sending the sensor data to the IoT webserver. Both the photodiode and SI 1145 were compared to LI-190R, which is the industry standard. In the calibration process, the R2 values of the photodiode and SI 1145 with LI-190R were 0.609 and 0.961, respectively. Field validation data shows that SI 1145 had a strong correlation with LI-190R. In addition, the performance evaluation data shows the photodiode had a weaker correlation with LI-190R than SI 1145. In conclusion, the study successfully developed and designed affordable and reliable IoT-based PAR sensor monitoring systems, including a 3D-printed housing, hardware, programming, and IoT website. SI 1145 with a glass filter is an alternative sensor to monitor PAR at a low cost and has the advantage of being connected to IoT microcontrollers.

One of the most delicate operations in the sugar beet harvesting process is removing the tops from the heads of the root crops without any mechanical damages. The aim of this study is to improve the design of the conveying and unloading system of the sugar beet topper machine. In this paper, a mathematical model of the motion of a cut beet tops particle M, along the conveying and unloading system, has been developed to support the evaluation of kinematic and design parameters, depending on the rotational speed of the thrower blade, the air flow speed, the required ejection speed of particle M, and the position of the trailer that moves alongside the harvester. It has been established that increasing the speed Va of the top particle M, which has left the end of the blade of the thrower, leads to an increase in the arc coordinate S(t) of its movement along the cylindrical section of the casing. Within the range of the speed change from 4 m·s–1 to 8 m·s–1, the value of the arc coordinate S(t) increases by 1.4 times during time t = 0.006 s. Moreover, a rapid decrease in speed V is observed with an increase in the length x of the discharge chute.

Early detection of plant leaf diseases is a major necessity for controlling the spread of infections and enhancing the quality of food crops. Recently, plant disease detection based on deep learning approaches has achieved better performance than current state-of-the-art methods. Hence, this paper utilized a convolutional neural network (CNN) to improve rice leaf disease detection efficiency. We present a modified YOLOv8, which replaces the original Box Loss function by our proposed combination of EIoU loss and α-IoU loss in order to improve the performance of the rice leaf disease detection system. A two-stage approach is proposed to achieve a high accuracy of rice leaf disease identification based on AI (artificial intelligence) algorithms. In the first stage, the images of rice leaf diseases in the field are automatically collected. Afterward, these image data are separated into blast leaf, leaf folder, and brown spot sets, respectively. In the second stage, after training the YOLOv8 model on our proposed image dataset, the trained model is deployed on IoT devices to detect and identify rice leaf diseases. In order to assess the performance of the proposed approach, a comparative study between our proposed method and the methods using YOLOv7 and YOLOv5 is conducted. The experimental results demonstrate that the accuracy of our proposed model in this research has reached up to 89.9% on the dataset of 3175 images with 2608 images for training, 326 images for validation, and 241 images for testing. It demonstrates that our proposed approach achieves a higher accuracy rate than existing approaches.

The rise of mechanical automation in orchards has sparked research interest in developing robots capable of autonomous tree pruning operations. To achieve accurate pruning outcomes, these robots require robust perception systems that can reconstruct three-dimensional tree characteristics and execute appropriate pruning strategies. Three-dimensional modeling plays a crucial role in enabling accurate pruning outcomes. This paper introduces a specialized tree modeling approach using the space colonization algorithm (SCA) tailored for pruning. The proposed method extends SCA to operate in three-dimensional space, generating comprehensive cherry tree models. The resulting models are exported as normalized point cloud data, serving as the input dataset. Multiple criteria decision analysis is utilized to guide pruning decisions, incorporating various factors such as tree species, tree life cycle stages, and pruning strategies during real-world implementation. The pruning task is transformed into a point cloud neural network segmentation task, identifying the trunks and branches to be pruned. This approach reduces the data acquisition time and labor costs during development. Meanwhile, pruning training in a virtual environment is an application of digital twin technology, which makes it possible to combine the meta-universe with the automated pruning of fruit trees. Experimental results demonstrate superior performance compared to other pruning systems. The overall accuracy is 85%, with mean accuracy and mean Intersection over Union (IoU) values of 0.83 and 0.75. Trunks and branches are successfully segmented with class accuracies of 0.89 and 0.81, respectively, and Intersection over Union (IoU) metrics of 0.79 and 0.72. Compared to using the open-source synthetic tree dataset, this dataset yields 80% of the overall accuracy under the same conditions, which is an improvement of 6%.

In Mediterranean farming systems, the semi-arid conditions and agricultural ecosystems have made site-specific management an important approach. This method aims to understand and handle the variability of soil properties and crop management, particularly through the utilization of geospatial information and accessible technology. Over three years in a 30 ha experimental field located in the Alentejo region (Portugal), crop establishment was monitored using data from soil apparent electrical conductivity (ECa), remote sensing (Sentinel-2), and in situ soil sampling. The procedure began with Step 1, involving the acquisition of soil spatial information and spatial interpolation. Subsequently, in Step 2, management zones (MZs) for soil characteristics were delineated using a combination of ECa measurements and soil analysis, and Step 3 spanned over three years of gathering meteorological data and crop remote sensing measurements. In Step 4, site-specific crop MZs were delineated by vegetation indexes (VIs). This article aims to increase the importance of in situ and remote assessments to more accurately identify areas with different productive potential. Results showed three MZs based on the percentage of sand, ECa, altimetry, exchangeable calcium, and exchangeable calcium properties, validated by crop VIs (Normalized Difference Vegetation Index (NDVI), Normalized Difference Red-Edge Index (NDRE), and Normalized Difference Moisture Index (NDMI)) over time. Although there are many sensorial techniques available for site-specific management, this paper emphasizes a methodology for the farmer to identify different MZs combining remote and in situ evaluations, supporting new opportunities for a more rational use of natural resources. Based on soil parameters, three site-specific management areas could be selected. NDMI was the index that best explained the MZs created according to soil properties.

Climate-change-induced unpredictable weather patterns are adversely affecting global agricultural productivity, posing a significant threat to sustainability and food security, particularly in developing regions. Wealthier nations can invest substantially in measures to mitigate climate change’s impact on food production, but economically disadvantaged countries face challenges due to limited resources and heightened susceptibility to climate change. To enhance climate resilience in agriculture, technological solutions such as the Internet of Things (IoT) are being explored. This paper introduces a digital twin as a technological solution for monitoring and controlling temperatures in a greenhouse tunnel situated in Stellenbosch, South Africa. The study incorporates an aeroponics trial within the tunnel, analysing temperature variations caused by the fan and wet wall temperature regulatory systems. The research develops an analytical model and employs a support vector regression algorithm as an empirical model, successfully achieving accurate predictions. The analytical model demonstrated a root mean square error (RMSE) of 2.93 °C and an R2 value of 0.8, while the empirical model outperformed it with an RMSE of 1.76 °C and an R2 value of 0.9 for a one-hour-ahead simulation. Potential applications and future work using these modelling techniques are then discussed.

Machine learning (ML) within the edge internet of things (IoT) is instrumental in making significant shifts in various industrial domains, including smart farming. To increase the efficiency of farming operations and ensure ML accessibility for both small and large-scale farming, the need for a low-cost ML-enabled framework is more pressing. In this paper, we present an end-to-end solution that utilizes tiny ML (TinyML) for the low-cost adoption of ML in classification tasks with a focus on the post-harvest process of olive fruits. We performed dataset collection to build a dataset that consists of several varieties of olive fruits, with the aim of automating the classification and sorting of these fruits. We employed simple image segmentation techniques by means of morphological segmentation to create a dataset that consists of more than 16,500 individually labeled fruits. Then, a convolutional neural network (CNN) was trained on this dataset to classify the quality and category of the fruits, thereby enhancing the efficiency of the olive post-harvesting process. The goal of this study is to show the feasibility of compressing ML models into low-cost edge devices with computationally constrained settings for tasks like olive fruit classification. The trained CNN was efficiently compressed to fit into a low-cost edge controller, maintaining a small model size suitable for edge computing. The performance of this CNN model on the edge device, focusing on metrics like inference time and memory requirements, demonstrated its feasibility with an accuracy of classification of more than 97.0% and minimal edge inference delays ranging from 6 to 55 inferences per second. In summary, the results of this study present a framework that is feasible and efficient for compressing CNN models on edge devices, which can be utilized and expanded in many agricultural applications and also show the practical insights for implementing the used CNN architectures into edge IoT devices and show the trade-offs for employing them using TinyML.

The objectives set in the European Green Deal constitute the starting point of this review, which then focuses on the current implementation gap between agro-industrial wastes as resources for large-scale bioprocesses (e.g., baker’s yeast, bioethanol, citric acid, and amino acids). This review highlights the current lack of sustainability of the post-harvest processing of grapes and apples. In light of the European Green Deal, industrial biotechnology often lacks sustainability as well. We reviewed the recent progress reported in the literature to enhance the valorization of grape and apple pomace and the current failure to implement this research in technical processes. Nevertheless, selected recent papers show new perspectives to bridge this gap by establishing close collaborations between academic teams and industrial partners. As a final outcome, for the first time, we drew a circular flow diagram that connects agriculture post-harvest transformation with the industrial biotechnology and other industries through the substantial valorization of apple and grape pomace into renewable energy (solid biofuels) and sugar extracts as feedstock for large-scale bioprocesses (production of baker’s yeast industry, citric acid, bioethanol and amino acids). Finally, we discussed the requirements needed to achieve the successful bridging of the implementation gap between academic research and industrial innovation.

Plastic contamination in cotton lint poses significant challenges to the U.S. cotton industry, with plastic wrap from John Deere round module harvesters being a primary contaminant. Despite efforts to manually remove this plastic during module unwrapping, some inevitably enters the cotton gin’s processing system. To address this, a machine-vision detection and removal system has been developed. This system uses inexpensive color cameras to identify plastic on the gin stand feeder apron, triggering a mechanism that expels the plastic from the cotton stream. However, the system, composed of 30–50 Linux-based ARM computers, requires substantial effort for calibration and tuning and presents a technological barrier for typical cotton gin workers. This research aims to transition the system to a more user-friendly, plug-and-play model by implementing an auto-calibration function. The proposed function dynamically tracks cotton colors while excluding plastic images that could hinder performance. A critical component of this auto-calibration algorithm is the hand intrusion detector, or “HID”, which is discussed in this paper. In the normal operation of a cotton gin, the gin personnel periodically have to clear the machine, which entails running a stick or their arm/hand under the detection cameras. This results in the system capturing a false positive, which interferes with the ability of auto-calibration algorithms to function correctly. Hence, there is a critical need for an HID to remove these false positives from the record. The anticipated benefits of the auto-calibration function include reduced setup and maintenance overhead, less reliance on skilled personnel, and enhanced adoption of the plastic removal system within the cotton ginning industry.

This paper presents the implementation of statistical and remote sensing techniques to analyze the spectral response, grain yield, and infestation of fall armyworm (Spodoptera frugiperda) in corn (Zea mays) based on the application of edaphic and foliar treatments with silicon, comparing the results with those reported in the literature where it has been demonstrated that the incorporation of this nutrient in different crops improves the activity of the enzyme nitrate reductase and dry matter weight gain. The results show that the foliar application of silicon tends to increase grain production in the crop, while the soil treatment does not improve yield. Similarly, foliar silicon application improves the Normalized Difference Vegetation Index, which improves plant health and could be correlated with higher grain yield of the crop. An inverse correlation was detected between the use of foliar silicon and the Normalized Difference Water Index and a direct relationship in the case of direct field application. As for the analysis of the data to verify the influence of the use of silicon on fall armyworm infestation, no statistically significant evidence was found that would lead to the conclusion that the application of this element, whether in soil or foliar form, could lead to a decrease in crop infestation.

Gum rosin is an important agricultural commodity which is widely used as a raw material for various industries. However, gum rosin has low stability, crystallizes easily, and tends to oxidize. This is due to carboxyl groups and conjugated double bonds in gum rosin’s structure. Therefore, to reduce these weaknesses, it is necessary to modify the rosin compound to achieve better stability via the esterification process. This paper surveys esterification agents such as glycerol, pentaerythritol, methanol, ethylene glycol, polyethylene glycol (PEG), allyl group, and starch Rosin ester. The product is used in the manufacture of pressure-sensitive adhesives, drug delivery, solder flux for electronic devices, as a plasticizer, and as a coating agent in fertilizers. In general, the esterification reaction between alcohols and carboxylic acids is very slow without a catalyst. Heterogeneous catalysts have the advantage of controlling size, structure, spatial distribution, surface composition, thermal-chemical stability, and selectivity. Among the catalysts for gum rosin esterification are ZSM-5, Fe3O4, ZnO, Calcium, TiO2, Kaolin, and Al2O3, among others. Different catalysts and esterification agents can produce various physical and chemical properties of rosin ester and will result in specific rosin ester products, such as glycerol ester, pentaerythritol ester, methyl ester, glycol ester, allyl ester, and acid starch-based rosin.

The occurrence of late spring frosts due to climate change causes great damage to plantation production worldwide. The main objective of the paper is to provide a comprehensive overview of the problem and to outline effective protective measures against late spring frosts. The nature of frost depends on regional, altitudinal, and geographic differences, but they all share a common problem: they remove heat, resulting in the freezing of new plant growth and flowers. Tissue freezing is affected by critical temperatures and the frost type, intensity, and duration. Protection against late spring frosts can be broadly divided into three categories: active, passive, and chemical measures. In the field of agricultural engineering, various techniques have been thoroughly researched, and their effectiveness has been confirmed by research. These include various sprinkler systems, different heating devices, and large-diameter fans. Conclusive findings are being made on the performance of these systems in sub-zero temperatures and their cost-effectiveness. Climate change increases the importance of protecting permanent crops from late spring frosts and requires advances in agricultural technology to meet changing production demands and challenges.

Promotion of research and development in advanced technology must be implemented in agriculture to increase production in the current challenging environment where the demand for manual farming is decreasing due to the unavailability of skilled labor, high cost, and shortage of labor. In the last two decades, the demand for fruit harvester technologies, i.e., mechanized harvesting, manned and unmanned aerial systems, and robotics, has increased. However, several industries are working on the development of industrial-scale production of advanced harvesting technologies at low cost, but to date, no commercial robotic arm has been developed for selective harvesting of valuable fruits and vegetables, especially within controlled strictures, i.e., greenhouse and hydroponic contexts. This research article focused on all the parameters that are responsible for the development of automated robotic arms. A broad review of the related research works from the past two decades (2000 to 2022) is discussed, including their limitations and performance. In this study, data are obtained from various sources depending on the topic and scope of the review. Some common sources of data for writing this review paper are peer-reviewed journals, book chapters, and conference proceedings from Google Scholar. The entire requirement for a fruit harvester contains a manipulator for mechanical movement, a vision system for localizing and recognizing fruit, and an end-effector for detachment purposes. Performance, in terms of harvesting time, harvesting accuracy, and detection efficiency of several developments, has been summarized in this work. It is observed that improvement in harvesting efficiency and custom design of end-effectors is the main area of interest for researchers. The harvesting efficiency of the system is increased by the implementation of optimal techniques in its vision system that can acquire low recognition error rates.

The production of food generated by agriculture has been essential for civilizations throughout time. Tillage of fields has been supported by great technological advances in several areas of knowledge, which have increased the amount of food produced at lower costs. The use of technology applied to modern agriculture has generated a research area called precision agriculture, which has providing crops with resources in an exact amount at a precise moment as one of its most relevant objectives The data analysis process in precision agriculture systems begins with the filtering of the information available, which can come from sources such as images, videos, and spreadsheets. When the information source is digital images, the process is known as segmentation, which consists of assigning a category or label to each pixel of the analyzed image. In recent years, different algorithms of segmentation have been developed that make use of different pixel characteristics, such as color, texture, neighborhood, and superpixels. In this paper, a method to segment images of leaves and fruits of tomato plants is presented, which is carried out in two stages. The first stage is based on the dominance of one of the color channels over the other two, using the RGB color model. In the case of the segmentation of the leaves, the green channel dominance is used, whereas the dominance of red channel is used for the fruits. In the second stage, the false positives generated during the previous stage are eliminated by using thresholds calculated for each pixel that meets the condition of the first stage. The results are measured by applying performance metrics: Accuracy, Precision, Recall, F1-Score, and Intersection over Union. The results for segmentation of the fruit and leaves of the tomato plants with the highest metrics is Accuracy with 98.34% for fruits and Recall with 95.08% for leaves.

The present study aimed to investigate an alternative evaporative cooling pad material made from mangosteen peel (MP) waste. Mangosteen peels were used to fill a 150 mm thick mesh container with a packing density of 180 kg/m3. A wind tunnel was constructed and utilized to experimentally evaluate the cooling performance of this organic-waste-based pad under hot and humid conditions (31–34 °C and 55–70% RH). The performance parameters assessed included pressure drop, temperature drop, saturation effectiveness, cooling capacity, and coefficient of performance (COP). The influence of air velocity (0.7, 1.0, 1.4, and 1.8 m/s) on these parameters was also examined. The results revealed that the saturation effectiveness of the MP pad ranged from 53% to 77% within the considered air velocity range. The maximum temperature drop (4.6 °C), saturation effectiveness (77%), cooling capacity (0.6 kW), and COP (3.5) were achieved when the system operated at 1.4 m/s. A comparative study showed that, at this velocity, the MP pad provided performance nearly equivalent to that of the commercial cellulose paper pad, except for the pressure drop. This result affirms the potential of mangosteen peels as a suitable wet medium for evaporative cooling applications.

Tropical climate conditions favor landscape evolution and the formation of highly weathered soils under different pedogenic processes due to certain differential properties. Traditional analysis coupled with VNIR-SWIR reflectance spectroscopy and X-ray diffractometry (XRD) analyses can reveal such characteristics. Several researchers cited throughout this study already discussed the possible applications of analyses in this field. All agree that integrated knowledge (holistic) can drive the future of the soil sciences. However, few refer to the potential of soil spectroscopy in deriving pedogenetic information. Thus, this paper aimed to assess pedomorphogeological relationships in a representative toposequence of the Brazilian Midwest using traditional analyses and geotechnologies. We performed landscape observations and soil sampling in the field. The laboratory’s physical, chemical, spectral, and mineralogical determinations supported the soil classification according to the World Reference Basis (WRB/FAO) system. Based on the analysis results, we divided five profiles into two soil groups (highly and slightly weathered soils) using Pearson’s correlation and hierarchical clustering analysis (HCA). Traditional analyses determined the diagnostic attributes. Spectroscopic readings from 0.35 to 2.5 µm wavelengths and XRD supported identifying soil attributes and properties. Finally, all soil classes were correlated according to correspondent reflectance spectra and primary pedological attributes. There was a strong correlation between spectral oxide features and X-ray diffraction peaks. The HCA based on oxide content and mineral composition validated the previous soil grouping. Thus, we could assess the pedomorphogeological relationships through VNIR-SWIR spectroscopy, XRD, and traditional analyses concerning pedogenic processes through their correlation with soil properties resulting from these processes. However, periodic measurements are required, making orbital sensing a continuous data source for soil monitoring.

The delineation of management zones is one of the ways to enable the spatially differentiated management of plots using precision agriculture tools. Over the years, the spatial variability of data collected from soil and plant sampling started to be replaced by data collected by proximal and orbital sensors. As a result, the variety and volume of data have increased considerably, making it necessary to use advanced computational tools, such as machine learning, for data analysis and decision-making support. This paper presents a methodology used to establish management zones (MZ) in precision agriculture by analyzing data obtained from soil sampling, proximal sensors and orbital sensors, in experiments carried out in four plots featuring soybean–cotton and soybean–corn crops, in Mato Grosso and Paraná states, Brazil. Four procedures were evaluated, using different input data sets for the MZ delineation: (I) soil attributes, including clay content, apparent electrical conductivity or fertility, along with elevation, yield maps and vegetation indices (VIs) captured during the peak crop biomass period; (II) soil attributes in conjunction with VIs demonstrating strong correlations; (III) solely VIs exhibiting robust correlation with soil attributes and yield; (IV) VIs selected via random forests to identify the importance of the variable for estimating yield. The results showed that the VIs derived from satellite images could effectively replace other types of data. For plots where the natural spatial variability can be easily identified, all procedures favor obtaining MZ maps that allow reductions of 40% to 70% in yield variance, justifying their use. On the other hand, in plots with low natural spatial variability and that do not have reliable yield maps, different data sets used as input do not help in obtaining feasible MZ maps. For areas where anthropogenic activities with spatially differentiated treatment are already present, the exclusive use of VIs for the delineation of MZs must be carried out with reservations.

Many farms utilize closed-type livestock systems to enhance productivity and facilitate effective environmental management. However, the confined nature of these closed spaces poses an increased risk of exposure to harmful gases and organic dust for both workers and livestock. Additionally, the introduction of outside air through ventilation systems can lead to temperature fluctuations within the breeding environment, resulting in potential productivity issues. This research paper employs computational fluid dynamics (CFD) to develop ventilation operation management plans that address both the working environment and the breeding environment simultaneously. The proposed plans are designed to be easily implemented in practical farm settings. The findings of this study, based on the simulation analysis, indicate that while ventilation is effective in reducing harmful gases and improving the working environment, its efficiency decreases after the initial 3 min of operation. Furthermore, uncontrolled ventilation can cause sudden temperature changes, which may adversely affect the well-being of the livestock. However, when upgraded ventilation structures are implemented, significant improvements in the working environment (an average of 27.3% improvement) can be achieved while maintaining temperature stability for the livestock. These results highlight the importance of referring to the provided ventilation operation management table before commencing work, as it enables workers to improve the working environment while minimizing the potential impact of ventilation on the breeding environment.

Timely detection of pests and diseases in crops is essential to mitigate severe damage and economic losses, especially in the context of climate change. This paper describes a method for detecting the presence of coffee leaf rust (CLR) using two databases: RoCoLe and a database obtained from an unmanned aerial vehicle (UAV) equipped with an RGB camera. The developed method follows a two-stage approach. In the first stage, images are processed using ImageJ software, while, in the second phase, Python is used to implement morphological filters and the Hough transform for rust identification. The algorithm’s performance is evaluated using the chi-square test, and its discriminatory capacity is assessed through the generation of a Receiver Operating Characteristic (ROC) curve. Additionally, Cohen’s kappa method is used to assess the agreement among observers, while Kendall’s rank correlation coefficient (KRCC) measures the correlation between the criteria of the observers and the classifications generated by the method. The results demonstrate that the developed method achieved an efficiency of 97% in detecting coffee rust in the RoCoLe dataset and over 93.5% in UAV images. These findings suggest that the developed method has the potential to be implemented in the future on a UAV for rust detection.

The aim of this work was to elaborate a new methodology that can allow for the identification of the topsoil homogeneous area (tSHA) distribution along land parcels, supporting farmers in keeping low-cost, sustainable, and light logistic management of precision agriculture (PA) practices. This paper shows the assessment of tSHA variability over two production units (PUs), considering radiometric response (optical camera), physicochemical (texture, pH, electrical conductivity), and statistical and geostatistical data analysis. By using unmanned aircraft systems (UASs) and laboratory analysis, our results revealed that the integration between UAS-RGB and physicochemical data can improve the estimation accuracy of tSHA distribution. Firstly, the UAS-RGB dataset was used to isolate bare soil from the vegetative radiometric contribution. Secondly, starting from statistical approaches (correlation matrices), the highest correlation with UAS-RGB and physicochemical data was stated. Thirdly, by using a geostatistical approach (ordinary cokriging), the map representing the tSHA variability was finally obtained.

This paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of vegetal species were applied to convolutional neural networks (CNNs) and support vector machine (SVM) classifiers. We focused on okra as the target vegetal species and classified it into two quality types. However, our approach could also be applied to other species. The machine learning solution consists of several components, and each design process and its combinations are essential for classification quality. Therefore, we carefully investigated their effects on classification accuracy. Through our experimental evaluation, we confirmed the following: (1) in color space selection, HLG (hue, lightness, and green) and HSL (hue, saturation, and lightness) are essential for vegetal species; (2) suitable preprocessing techniques are required owing to the complexity of the data and noise load; and (3) the diversity extension of learning image data by mixing different datasets obtained under different conditions is quite effective in reducing the overfitting possibility. The results of this study will assist AI practitioners in the design and development of post-harvest classifications based on machine learning.

Glyphosate is the most widely used herbicide for weed control in citrus orchards in Brazil; therefore, it is likely that several species have gained resistance to this herbicide and that more than one resistant species can be found in the same orchard. The objective was to identify weeds resistant to glyphosate in citrus orchards from different regions of the São Paulo State (SP) and determine how many resistant species are present within the same orchard. Seeds of Amaranthus deflexus, A. hybridus, Bidens pilosa, Chloris elata, Conyza bonariensis, Digitaria insularis, Solanum Americanum, and Tridax procumbens, which, as reported by growers, are suspected to be resistant to glyphosate, were collected from plants that survived the last application of this herbicide (>720 g of acid equivalent [ae] ha–1) in sweet orange and Tahiti acid lime orchards. Based on dose–response and shikimic acid accumulation assays, all populations of A. deflexus, A. hybridus, B. pilosa, and T. procumbens were sensitive to glyphosate. However, populations of B. pilosa from the Olimpia region (R-NS, R-PT and R-OdA) showed signs of resistance based on plant mortality rates by 50% within a population (LD50 = 355–460 g ae ha−1). All populations of C. bonariensis, C. elata, and D. insularis were resistant to glyphosate, presenting resistance ratios from 1.9 to 27.6 and low shikimate accumulation rates. Solanum americanum also showed resistance, with resistance ratios ranging from 4.3 to 25.4. Most of the citrus orchards sampled presented the occurrence of more than one species resistant to glyphosate: Nossa Senhora—one species; Olhos D’agua and Passatempo—two species; Araras—four species; and Cordeiropolis and Mogi-Mirim—up to five species. The results reported in this paper provide evidence of multiple species in citrus orchards from São Paulo that have exhibited resistance to glyphosate. This underscores the difficulties in managing glyphosate-resistant weeds which are prevalent throughout the country, such as C. bonariensis and D. insularis. The presence of these resistant species further complicates the control of susceptible species that may also develop resistance. In addition, the glyphosate resistance of S. americanum was identified for the first time.

Accurate estimates of pasture biomass in grazing lands are currently a time-consuming and resource-intensive task. The process generally includes physically cutting, bagging, labelling, drying, and weighing grass samples using multiple “quadrats” placed on the ground. Quadrats vary in size but are typically in the order of 0.25 m2 (i.e., 0.5 m × 0.5 m) up to 1.0 m2. Measurements from a number of harvested quadrats are then averaged to get a site estimate. This study investigated the use of photographs and ‘machine learning’ to reduce the time factor and difficulty in taking pasture biomass measurements to potentially make the estimations more accessible through the use of mobile phone cameras. A dataset was created from a pre-existing archive of quadrat photos and corresponding hand-cut pasture biomass measurements taken from a diverse range of field monitoring sites. Sites were clustered and one was held back per model for testing. The models were based on DenseNet121. Individual quadrat errors were large but more promising results were achieved when estimating the site mean pasture biomass. Another two smaller additional datasets were created post-training which were used to further assess the ensemble; they provided similar absolute errors to the original dataset, but significantly larger relative errors. The first was made from harvested quadrats, and the second was made using a pasture height meter in conjunction with a mobile phone camera. The models performed well across a variety of situations and locations but underperformed when assessed on some sites with very different vegetation. More data and refinement of the approach outlined in the paper will reduce the number of models needed and help to correct errors. These models provide a promising start, but further investigation, refinement, and data are needed before becoming a usable application.

This paper explores the potential of infrared thermography and geostatistics in animal production and presents the results of the application of the combination of these techniques, contributing significantly to efforts to obtain animals’ responses to the environments in which they are located and thereby ensuring improvements in productivity and animal welfare. The objective was to verify the variability in surface temperature in pigs submitted to different climate control systems using geostatistics. Three growing animals per stall were selected. Dry bulb temperature (Tbd, °C), relative humidity (RH, %) and thermal images were recorded at 08:00 and 12:00 h. To analyze the data, semivariograms were made, the theoretical model was validated and kriging maps were constructed. The mean temperature of the pigs in the pen with adiabatic evaporative cooling (AEC) ranged from 32.40 to 36.25 °C; for the pigs in the forced ventilation (FV) pen, the range of variation was from 32.51 to 36.81 °C. In the control group (Con), with natural ventilation, the average temperature was 37.51 to 38.45 °C. The geostatistical analysis provided a mathematical model capable of illustrating the variation in temperature in the caudal–dorsal regions of the pigs according to the environments to which the animals were subjected.

Including the correct combination of factors for the application technology of pesticides can improve their distribution on their targets. The aim of this work was to use multivariate analysis to study the effect size and the order of influence of three factors that interfere with pesticide application technology in corn crops. A 2 × 2 × 3 factorial experiment was conducted with two droplet size classes (fine and coarse), two application rates (80 and 150 L ha−1), and the presence of adjuvants (mineral oil one and two, and no adjuvant). A knapsack boom sprayer was used for the applications. Droplet deposition on the corn leaves was evaluated by detecting a tracer added to the spray via spectrophotometry and the droplet spectrum by analyzing water-sensitive papers. Univariate and multivariate statistical analyses were performed to integrate the variables analyzed. Droplet size has proven to be the most important factor in spraying planning, and the second factor is the application rate. With the association between fine droplets and higher application rates, a better performance was obtained in coverage, droplet density, and droplet deposition.