Crop Monitoring Research Articles

The Impact of AI on Agriculture and Farmers

Artificial Intelligence (AI) has emerged as a transformative force in the field of agriculture, offering innovative solutions to enhance productivity, sustainability, and efficiency. This research paper explores the multifaceted impact of AI on agriculture and farmers, encompassing various aspects such as precision farming, crop monitoring, livestock management, supply chain optimization, crop hybridization, and the development of AI tools and technology. Additionally, it delves into the opportunities AI presents for farmers and its potential role in advancing organic farming practices. Through a comprehensive analysis of existing literature and case studies, this paper aims to provide insights into the evolving landscape of agriculture facilitated by AI technologies.

REVIEWING THE ROLE OF AI IN DRONE TECHNOLOGY AND APPLICATIONS

This comprehensive review delves into the transformative impact of artificial intelligence (AI) on drone technology, examining its pivotal role in revolutionizing various applications. As drones continue to evolve from recreational gadgets to indispensable tools across industries, the integration of AI enhances their capabilities, enabling advanced functionalities and expanding their potential use cases. The convergence of AI and drone technology has given rise to a myriad of applications, transforming industries ranging from agriculture to surveillance. Machine learning algorithms empower drones with autonomous navigation capabilities, allowing them to navigate complex environments and adapt to dynamic scenarios. Computer vision technologies enable drones to perceive and analyze visual information, facilitating tasks such as object recognition, tracking, and environmental monitoring. These advancements significantly contribute to enhanced aerial surveying, precision agriculture, and disaster response efforts. In the realm of precision agriculture, AI-equipped drones aid in crop monitoring, disease detection, and yield estimation, optimizing resource allocation and boosting agricultural productivity. Drones with AI-driven capabilities are increasingly employed in environmental monitoring, wildlife conservation, and disaster response, providing real-time data for efficient decision-making. Recent trends in AI-infused drone technology highlight its dynamic evolution. Edge computing solutions empower drones to process data locally, reducing latency and enhancing real-time responsiveness. Reinforcement learning algorithms enable drones to learn from their experiences, adapting and optimizing their performance over time. Swarm intelligence, an emerging field in drone technology, leverages AI to enable coordinated and synchronized actions among multiple drones, expanding their capabilities for collaborative tasks. In conclusion, this review sheds light on the pivotal role of AI in transforming drone technology and expanding its applications. The synergy between AI and drones has unlocked new possibilities across various industries, ranging from agriculture to disaster response. As technology continues to advance, the collaborative integration of AI and drones promises to redefine the future of aerial technology, introducing unprecedented efficiencies and capabilities across diverse sectors.
 Keywords: Role, AI, Drone, Applications, Technology.

Drone‐based imaging sensors, techniques, and applications in plant phenotyping for crop breeding: A comprehensive review

AbstractOver the last decade, the use of unmanned aerial vehicles (UAVs) for plant phenotyping and field crop monitoring has significantly evolved and expanded. These technologies have been particularly valuable for monitoring crop growth and health and for managing abiotic and biotic stresses such as drought, fertilization deficiencies, disease, and bioaggressors. This paper provides a comprehensive review of the progress in UAV‐based plant phenotyping, with a focus on the current use and application of drone technology to gain information on plant growth, development, adaptation, and yield. We reviewed over 200 research articles and discuss the best tools and methodologies for different research purposes, the challenges that need to be overcome, and the major research gaps that remain. First, the review offers a critical focus on elucidating the distinct characteristics of UAV platforms, highlighting the diverse sensor technologies employed and shedding light on the nuances of UAV data acquisition and processing methodologies. Second, it presents a comprehensive analysis of the multiple applications of UAVs in field phenotyping, underscoring the transformative potential of integrating machine learning techniques for plant analysis. Third, it delves into the realm of machine learning applications for plant phenotyping, emphasizing its role in enhancing data analysis and interpretation. Furthermore, the paper extensively examines the open issues and research challenges within the domain, addressing the complexities and limitations faced during data acquisition, processing, and interpretation. Finally, it outlines the future trends and emerging technologies in the field of UAV‐based plant phenotyping, paving the way for innovative advancements and methodologies.

Energy and delay aware routing model for smart crop monitoring application using internet of things

The adoption of modern technology into farming has seen significant expansion to enhance the quality and quantity of crop production. In this research work, wireless sensor networks (WSNs) and the Internet of Things (IoTs) are integrated to provide a real-time crop monitoring system to farmers. Usually, battery-powered IoT devices equipped with sensors like temperature, humidity, motion sensors, etc. are placed across agriculture areas for real-time monitoring of crops and cattle. In improving energy efficiency and reducing delay clustering multi-hop routing has been used with good effect; However, the existing methods failed to enhance network lifetime and target coverage due to failure in addressing load-balancing and hotspot problems. In addressing research problems this paper presents an Energy and Delay Aware Routing (EDAR) scheme for heterogenous WSN-IoTs leveraging unequal grouping of networks and adoption of multipath routing for provisioning IoT applications. The simulation outcome shows the EDAR model achieves very good performance in terms of throughput and lifetime performance with minimal delay and communication overhead.

Revolutionizing Agriculture IoT and Random Forest Algorithm for Crop Monitoring and Disease Prediction

This research about presents a groundbreaking approach to revolutionize farming through the integration of Web of Things (IoT) innovation and progressed machine learning calculations. Centering on the improvement and execution of an IoT-based edit checking framework coupled with the Random Forest calculation for malady expectation, the ponder points to improve agrarian hones and relieve trim misfortunes caused by infections and natural components. Real-time information collection from IoT sensors sent in rural areas empowers comprehensive checking of vital natural parameters such as temperature, mugginess, soil dampness, and light concentrated. The Random Forest calculation analyzes this information to precisely foresee trim maladies, giving ranchers with significant bits of knowledge for proactive illness administration. Test comes about illustrate the adequacy of the proposed approach, with the Random Forest show accomplishing an exactness of 92%, exactness of 93%, review of 91%, and F1-score of 92%. These comes almost defeat customary methodologies and existing explore works, highlighting the potential of IoT and machine learning for optimizing alter proficiency and ensuring around the world food security.

The dominant pests (Coleoptera) of cereal crops, and population forecast for this

Goal. Create a forecast of the development of harmful organisms in cereal crops, to determine the economic feasibility of applying plant protection measures.
 Methods. Analysis of the phytosanitary state of cereal crops in Ukraine, where the main attention is paid to the dominant pest species. Analysis of the areas of distribution of these pests, population dynamics, their phenology and the state of populations in the context of natural and climatic zones (Steppe, Forest-steppe and Polissya). To assess the phytosanitary state of crops, and its dynamic changes, the following are used: — the results of phytosanitary monitoring of crops (according to generally accepted methods), which were carried out directly by the staff of the forecast laboratory of the Institute of Plant Protection of NAAS; — current reports of researchers from other laboratories of the Institute of Plant Protection of NAAS from the places of business trips; — materials of decadal reports of regional plant protection stations, as well as signaling and forecasting points; — information on the phytosanitary situation from regional state research stations and institutes of NAAS.
 Results. A study of the phytosanitary state of cereal crops on the territory of Ukraine was carried out, the dominant species of pests were identified, materials were prepared regarding the peculiarities of the phytosanitary state in the conditions of the year, and a long-term (annual) forecast of the development of pests for the next year was drawn up, based on the appropriate analysis of the data obtained.
 Conclusions. In recent years, climate change in Ukraine has manifested itself through an increase in the average annual temperature, and an increase in the sum of effective temperatures. A decrease in the zone of sufficient soil moisture was noted, its line shifted to the north. Under the influence of abiotic factors, pests constantly change the boundaries of their habitat and zones of damage, therefore reliable protection of crops is impossible without constant monitoring, constant clarification of the species composition of phytophages, and phytosanitary forecast. Improved methodological approaches for assessing the phytosanitary state of acrocyanoses and the promptness of obtaining relevant data will allow agricultural producers to make timely decisions on the economic feasibility of using certain plant protection products.

Enhancing Crop Productivity through Nanotechnology: A Comprehensive Review of Strategies and Results

Nanotechnology has emerged as a promising approach to address the challenges of increasing crop productivity and ensuring global food security. This comprehensive review examines the various strategies and results of applying nanotechnology in agriculture to enhance crop productivity. We discuss the use of nanomaterials, such as nanoparticles, nanofertilizers, nanopesticides, and nanosensors, in improving nutrient management, pest control, disease management, and crop monitoring. The review also highlights the potential of nanobiotechnology in crop improvement through targeted gene delivery, genetic engineering, and plant transformation. Furthermore, we explore the application of nanomaterials in seed priming, seed coating, and seed germination enhancement. The environmental and safety aspects of using nanotechnology in agriculture are also discussed, along with the challenges and future prospects. This review provides valuable insights into the current state-of-the-art and future directions of nanotechnology in enhancing crop productivity, promoting sustainable agriculture, and ensuring food security.

First report of cucurbit yellow stunting disorder virus infecting cucurbit crops in Jamaica.

The increasing prevalence of whitefly-transmitted viruses affecting cucurbit crops has emerged as a significant concern for global cucurbit production. Two of the most widely prevalent threats in the Americas are cucurbit yellow stunting disorder virus (CYSDV) and cucurbit chlorotic yellows virus (CCYV) (Crinivirus, Closteroviridae). These viruses induce similar foliar symptoms on cucurbit crops (Mondal et al., 2023) leading to loss of photosynthetic capability and decreased yields. Cantaloupe (Cucumis melo), watermelon (Citrullus lanatus), and cucumber (Cucumis sativus) are major cucurbit crops in St. Elizabeth, Jamaica, which is the principal fruit and vegetable producing region of the country. In August 2018, foliar symptoms were observed on cantaloupe, watermelon, and cucumber plants in several commercial farms in St. Elizabeth. These symptoms, mainly on the older leaves, consisted of severe yellowing or interveinal mottle and they appeared more pronounced on cantaloupe and cucumber plants compared to watermelon. Growers noticed the production of smaller than normal fruit. Disease incidence ranged from 10 to 100% and whiteflies (Bemisia tabaci Gennadius) were observed in the fields. To identify virus(es) associated with the disease, six plants (cantaloupe [n = 3], cucumber [n = 1] and watermelon [n = 2) exhibiting symptoms were sampled from four fields for preliminary screening. Total RNA was extracted from leaf tissues as described in Tamang et al. (2021) and samples tested by a multiplex reverse transcription RT-PCR method that targeted the RNA-dependent RNA polymerase (RdRp) of the whitefly transmitted viruses, CYSDV, CCYV, squash vein yellowing virus (SqVYV), and the aphid- transmitted cucurbit aphid-borne yellows virus (CABYV) (Mondal et al. 2023). RT-PCR amplified the expected 494-bp fragment of the CYSDV RdRp gene (Mondal et al., 2023) from two symptomatic plants; one cantaloupe, one cucumber, as well as from CYSDV-infected control plants but not from healthy controls. Further testing was conducted during the June-August 2020 growing season after similar symptoms were observed on additional farms in St. Elizabeth and two regions, Manchester and Clarendon, located to the east of St. Elizabeth. Twenty-one cucurbit leaf samples (11 cantaloupe, seven watermelon and two cucumber from St. Elizabeth and one cantaloupe from Clarendon) exhibiting foliar yellowing progressing from the crown outward, and mottling were collected. Whiteflies (5) from these fields in St. Elizabeth and 20 asymptomatic weed samples were also collected and sent to the USDA-ARS laboratory at Salinas, CA. Total RNA from leaf samples was extracted as described above and tested for CYSDV, CCYV, and CABYV. Total leaf DNA was also extracted (Mondal et al. 2016) and assayed with PCR (Gilbertson 2001) to detect the presence of the whitefly-transmitted cucurbit leaf crumple virus (CuLCrV), a begomovirus, commonly found in the southeastern United States (Gadhave et al., 2018; Keinath et al., 2018). Nineteen of the 21 cucurbit samples tested positive for the presence of CYSDV by RT-PCR (Mondal et al. 2023). Of the 19 CYSDV-positive samples, 13 cantaloupe, one cucumber, and five watermelon samples were singly infected with CYSDV, and one cantaloupe sample was infected with both CYSDV and CABYV. Amplicons of the Jamaica isolate from cantaloupe were sequenced (OR399555) and a 494 nt section of the RdRp gene was found to share 100% sequence identity to the Arizona 1 isolate (EF547827.1). The presence of CYSDV, was further confirmed using a second set of primers that amplified a 394-nt portion of the CYSDV coat protein gene (Polston et al., 2008). Among the weed samples, CABYV was detected in one sample from a Leonotis nepetifolia plant (Lamiaceae) and two Cleome sp. (Capparaceae) collected from St. Elizabeth. None of the crop and weed samples tested positive for CCYV or CuLCrV. DNA from whiteflies was extracted and assayed with PCR using species specific primers (Chen et al. 2016). All whiteflies were identified as B. tabaci cryptic species MEAM1, which is widely known an efficient vector of CYSDV (Berdiales, et al. 1999). This is the first report of CYSDV in Jamaica and its first known occurrence in these hosts within the country. Further monitoring of cucurbit crops and the whitefly vector is warranted to better understand the epidemiology.

Characteristics and risk assessment of arsenic contamination in a lead and zinc plant area in Yunnan Province

Taking a lead and zinc plant plot in Yunnan as the research object, the land use status and planting types of the region were investigated, the original enterprise distribution area and crop growing area of the plot were defined, and 67 surface soil samples and 14 columnar soil samples were systematically arranged in the plot for monitoring. Combined with the monitoring results and analysis, it is concluded that there is no definite basis that the high arsenic content in soil in the region is caused by the enterprise production, and the high arsenic content in the region may be caused by the background value. Based on the monitoring and investigation results, the risk assessment of the area was carried out. The results showed that the non-carcinogenic risk and carcinogenic hazard index of arsenic exceeded the prescribed acceptable level when the area was developed as the second type of construction land, and soil remediation should be carried out. At the same time, the collaborative distribution monitoring of regional crops showed that the arsenic content of crops was low, which met the requirements of food standards, possibly because the cultivated crops did not have strong adsorption and enrichment effects on the arsenic occurrence form in the regional soil.

Estimates of Crop Yield Anomalies for 2022 in Ukraine Based on Copernicus Sentinel-1, Sentinel-3 Satellite Data, and ERA-5 Agrometeorological Indicators.

The study explores the feasibility of adapting the EOStat crop monitoring system, originally designed for monitoring crop growth conditions in Poland, to fulfill the requirements of a similar system in Ukraine. The system utilizes satellite data and agrometeorological information provided by the Copernicus program, which offers these resources free of charge. To predict crop yields, the system uses several factors, such as vegetation condition indices obtained from Sentinel-3 Ocean and Land Color Instrument (OLCI) optical and Sea and Land Surface Temperature Radiometer (SLSTR). It also incorporates climate information, including air temperature, total precipitation, surface radiation, and soil moisture. To identify the best predictors for each administrative unit, the study utilizes a recursive feature elimination method and employs the Extreme Gradient Boosting regressor, a machine learning algorithm, to forecast crop yields. The analysis indicates a noticeable decrease in crop losses in 2022 in certain regions of Ukraine, compared to the previous year (2021) and the 5-year average (2017-2021), specifically for winter crops and maize. Considering the reduction in yield, it is estimated that the decline in production of winter crops in 2022 was up to 20%, while for maize, it was up to 50% compared to the decline in production.

A Raspberry Pi-Powered IoT Smart Farming System for Efficient Water Irrigation and Crop Monitoring

Water irrigation remain as a challenge to supply adequate amount of water to sustain the growth of plant and crops yield along the year in certain part of the world which are heavily affected by climate change. This scenario creates a huge risk toward the world food supply chain. Hence, the application of smart farming system is crucially important now to pave the way for a better the agriculture monitoring system to replace traditional manual monitoring labour by farmers. The smart farming system are usually equipped with environmental stimuli sensing system such as temperature, humidity, soil moisture, light intensity sensing sensors coupled with automation actuators to control the water irrigation rate for the crops in order to save water and at the same time provide adequate water supply for plant growth. The aim of using such smart farming system is to enable higher crops production and less human labour at the same time optimising resources available to minimize cost of farming. Hence, this paper aims to introduce a novel approach of a Raspberry Pi powered IoT smart farming system (ISFS) which can incorporate autonomous monitoring of plant irrigation, temperature, humidity, soil moisture and light intensity, to design a smartphone app that allows users to monitor plantation-related conditions in a user-friendly manner, and to enable automatic control of a drip irrigation system for plants based on data obtained on soil moisture, temperature and sunlight intensity. The proposed prototype with the functionality mentioned is aim to resolve the existing problem and to meet the demand of smart farming application in current era.

Crop Recommendation and Monitoring using AI

Abstract: Agriculture is crucial for India's economy, with over 50% relying on it for survival. Climate and weather variations pose risks to agriculture's health. AI can monitor crops by using machine learning methods. Crop monitoring includes Crop Recommendation, Weed Detection, Plant Disease Detection, Yield Prediction. The models are trained with Image and numerical datasets. A website will be developed to monitor crops and provide solutions. The optimal crop can be suggested based on the surrounding conditions by analysing important variables like composition of Nitrogen, Phosphorous and Potassium in the soil, its pH value, humidity, and rainfall using various models namely Gaussian Naive Bayes, Logistic Regression, Gradient boosting, Ensemble which fall under the domain of Machine Learning. ANN can be used for crop yield prediction. Weed and Plant disease can be detected using ResNet which can be utilized for deep neural networks. The intent of this project is to help farmers choose suitable crops, differentiate crops from weeds, detect diseases, provide remedies to protect crop. It enables to improve yield and productivity, Enhanced sustainability, Increased Profitability

Assessing the Potential of Multi-Temporal Conditional Generative Adversarial Networks in SAR-to-Optical Image Translation for Early-Stage Crop Monitoring

The incomplete construction of optical image time series caused by cloud contamination is one of the major limitations facing the application of optical satellite images in crop monitoring. Thus, the construction of a complete optical image time series via image reconstruction of cloud-contaminated regions is essential for thematic mapping in croplands. This study investigates the potential of multi-temporal conditional generative adversarial networks (MTcGANs) that use a single synthetic aperture radar (SAR) image acquired on a prediction date and a pair of SAR and optical images acquired on a reference date in the context of early-stage crop monitoring. MTcGAN has an advantage over conventional SAR-to-optical image translation methods as it allows input data of various compositions. As the prediction performance of MTcGAN depends on the input data composition, the variations in the prediction performance should be assessed for different input data combination cases. Such an assessment was performed through experiments using Sentinel-1 and -2 images acquired in the US Corn Belt. MTcGAN outperformed existing SAR-to-optical image translation methods, including Pix2Pix and supervised CycleGAN (S-CycleGAN), in cases representing various input compositions. In particular, MTcGAN was substantially superior when there was little change in crop vitality between the reference and prediction dates. For the SWIR1 band, the root mean square error of MTcGAN (0.021) for corn was significantly improved by 54.4% and 50.0% compared to Pix2Pix (0.046) and S-CycleGAN (0.042), respectively. Even when there were large changes in crop vitality, the prediction accuracy of MTcGAN was more than twice that of Pix2Pix and S-CycleGAN. Without considering the temporal intervals between input image acquisition dates, MTcGAN was found to be beneficial when crops were visually distinct in both SAR and optical images. These experimental results demonstrate the potential of MTcGAN in SAR-to-optical image translation for crop monitoring during the early growth stage and can serve as a guideline for selecting appropriate input images for MTcGAN.

Advancements in Precision Agriculture: Integrating Computer Vision for Intelligent Soil and Crop Monitoring in the Era of Artificial Intelligence

Precision Agriculture has witnessed significant advancements with the integration of computer vision and artificial intelligence (AI) technologies, marking a transformative era in modern farming practices. This research explores the synergies between computer vision and intelligent soil and crop monitoring in the context of precision agriculture. The study aims to contribute insights into the application of advanced technologies for optimizing agricultural processes, enhancing resource efficiency, and improving overall crop yield. Keywords— Precision Agriculture, Computer Vision, Artificial Intelligence, Soil Monitoring, Crop Monitoring, Image Processing, Machine Learning, Deep Learning, Agricultural Technology, Intelligent Farming, Data Analytics, Precision Farming, Sensor Technologies, Agricultural Innovation, Sustainable Agriculture.

Application of UAV Multispectral Imaging to Monitor Soybean Growth with Yield Prediction through Machine Learning

The application of remote sensing, which is non-destructive and cost-efficient, has been widely used in crop monitoring and management. This study used a built-in multispectral imager on a small unmanned aerial vehicle (UAV) to capture multispectral images in five different spectral bands (blue, green, red, red edge, and near-infrared), instead of satellite-captured data, to monitor soybean growth in a field. The field experiment was conducted in a soybean field at the Mississippi State University Experiment Station near Pontotoc, MS, USA. The experiment consisted of five cover crops (Cereal Rye, Vetch, Wheat, Mustard plus Cereal Rye, and native vegetation) planted in the winter and three fertilizer treatments (Fertilizer, Poultry Liter, and None) applied before planting the soybean. During the soybean growing season in 2022, eight UAV imaging flyovers were conducted, spread across the growth season. UAV image-derived vegetation indices (VIs) coupled with machine learning (ML) models were computed for characterizing soybean growth at different stages across the season. The aim of this study focuses on monitoring soybean growth to predict yield, using 14 VIs including CC (Canopy Cover), NDVI (Normalized Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), EVI2 (Enhanced Vegetation Index 2), and others. Different machine learning algorithms including Linear Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) are used for this purpose. The stage of the initial pod development was shown as having the best predictability for earliest soybean yield prediction. CC, NDVI, and NAVI (Normalized area vegetation index) were shown as the best VIs for yield prediction. The RMSE was found to be about 134.5 to 511.11 kg ha−1 in the different yield models, whereas it was 605.26 to 685.96 kg ha−1 in the cross-validated models. Due to the limited number of training and testing samples in the K-fold cross-validation, the models’ results changed to some extent. Nevertheless, the results of this study will be useful for the application of UAV remote sensing to provide information for soybean production and management. This study demonstrates that VIs coupled with ML models can be used in multistage soybean yield prediction at a farm scale, even with a limited number of training samples.

Referee-Meta-Learning for Fast Adaptation of Locational Fairness

When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases that sabotage the spatial fairness of the algorithm. This unfairness can easily introduce biases in subsequent decision-making given broad adoptions of learning-based solutions in practice. However, locational biases in AI are largely understudied. To mitigate biases over locations, we propose a locational meta-referee (Meta-Ref) to oversee the few-shot meta-training and meta-testing of a deep neural network. Meta-Ref dynamically adjusts the learning rates for training samples of given locations to advocate a fair performance across locations, through an explicit consideration of locational biases and the characteristics of input data. We present a three-phase training framework to learn both a meta-learning-based predictor and an integrated Meta-Ref that governs the fairness of the model. Once trained with a distribution of spatial tasks, Meta-Ref is applied to samples from new spatial tasks (i.e., regions outside the training area) to promote fairness during the fine-tune step. We carried out experiments with two case studies on crop monitoring and transportation safety, which show Meta-Ref can improve locational fairness while keeping the overall prediction quality at a similar level.

Enhancing Safety in IoT Systems: A Model-Based Assessment of a Smart Irrigation System Using Fault Tree Analysis

The agricultural industry has the potential to undergo a revolutionary transformation with the use of Internet of Things (IoT) technology. Crop monitoring can be improved, waste reduced, and efficiency increased. However, there are risks associated with system failures that can lead to significant losses and food insecurity. Therefore, a proactive approach is necessary to ensure the effective safety assessment of new IoT systems before deployment. It is crucial to identify potential causes of failure and their severity from the conceptual design phase of the IoT system within smart agricultural ecosystems. This will help prevent such risks and ensure the safety of the system. This study examines the failure behaviour of IoT-based Smart Irrigation Systems (SIS) to identify potential causes of failure. This study proposes a comprehensive Model-Based Safety Analysis (MBSA) framework to model the failure behaviour of SIS and generate analysable safety artefacts of the system using System Modelling Language (SysML). The MBSA approach provides meticulousness to the analysis, supports model reuse, and makes the development of a Fault Tree Analysis (FTA) model easier, thereby reducing the inherent limitations of informal system analysis. The FTA model identifies component failures and their propagation, providing a detailed understanding of how individual component failures can lead to the overall failure of the SIS. This study offers valuable insights into the interconnectedness of various component failures by evaluating the SIS failure behaviour through the FTA model. This study generates multiple minimal cut sets, which provide actionable insights into designing dependable IoT-based SIS. This analysis identifies potential weak points in the design and provides a foundation for safety risk mitigation strategies. This study emphasises the significance of a systematic and model-driven approach to improving the dependability of IoT systems in agriculture, ensuring sustainable and safe implementation.

Crop Leaf Phenotypic Parameter Measurement Based on the RKM-D Point Cloud Method.

Crop leaf length, perimeter, and area serve as vital phenotypic indicators of crop growth status, the measurement of which is important for crop monitoring and yield estimation. However, processing a leaf point cloud is often challenging due to cluttered, fluctuating, and uncertain points, which culminate in inaccurate measurements of leaf phenotypic parameters. To tackle this issue, the RKM-D point cloud method for measuring leaf phenotypic parameters is proposed, which is based on the fusion of improved Random Sample Consensus with a ground point removal (R) algorithm, the K-means clustering (K) algorithm, the Moving Least Squares (M) method, and the Euclidean distance (D) algorithm. Pepper leaves were obtained from three growth periods on the 14th, 28th, and 42nd days as experimental subjects, and a stereo camera was employed to capture point clouds. The experimental results reveal that the RKM-D point cloud method delivers high precision in measuring leaf phenotypic parameters. (i) For leaf length, the coefficient of determination (R2) surpasses 0.81, the mean absolute error (MAE) is less than 3.50 mm, the mean relative error (MRE) is less than 5.93%, and the root mean square error (RMSE) is less than 3.73 mm. (ii) For leaf perimeter, the R2 surpasses 0.82, the MAE is less than 7.30 mm, the MRE is less than 4.50%, and the RMSE is less than 8.37 mm. (iii) For leaf area, the R2 surpasses 0.97, the MAE is less than 64.66 mm2, the MRE is less than 4.96%, and the RMSE is less than 73.06 mm2. The results show that the proposed RKM-D point cloud method offers a robust solution for the precise measurement of crop leaf phenotypic parameters.

Technical Feasibility Analysis of Advanced Monitoring with a Thermal Camera on an Unmanned Aerial Vehicle and Pressure Chamber for Water Status in Vineyards

Water is a limiting factor and to adopt the most appropriate agronomic strategy it is necessary to know the water status. The objective is (i) analysing of the influence of different agronomic treatments on canopy temperature in vineyards with a thermal camera on an unmanned aerial vehicle (UAV), (ii) analysing of the influence of different agronomic treatments on vineyard water potentials with a pressure chamber, (iii) advanced technical feasibility analysis of vineyard crop monitoring. The control treatment (T07) in cv. Grenache consisted of applying 30% of reference evapotranspiration (ETo) with irrigation frequency every seven days and seven different treatments were proposed with different irrigation frequencies, pre-bud irrigation, and vine shoot distribution (T03, T15, T7A, T7V, T7P, T00, and T0P). As a result and in conclusion, the use of thermal cameras in UAVs and mid-day stem water potential allows differentiation between irrigated and unirrigated treatments, but no clear differences were shown between irrigation frequencies, pre-irrigation treatment, or vine shoot distribution. Comparing the thermal camera information in UAV and the stem water potential, certain patterns are identified with significant correlation values, the use of thermal cameras for the evaluation of plant water status is recommended, especially to obtain information in large areas.

Edge computing-oriented smart agricultural supply chain mechanism with auction and fuzzy neural networks

Powered by data-driven technologies, precision agriculture offers immense productivity and sustainability benefits. However, fragmentation across farmlands necessitates distributed transparent automation. We developed an edge computing framework complemented by auction mechanisms and fuzzy optimizers that connect various supply chain stages. Specifically, edge computing offers powerful capabilities that enable real-time monitoring and data-driven decision-making in smart agriculture. We propose an edge computing framework tailored to agricultural needs to ensure sustainability through a renewable solar energy supply. Although the edge computing framework manages real-time crop monitoring and data collection, market-based mechanisms, such as auctions and fuzzy optimization models, support decision-making for smooth agricultural supply chain operations. We formulated invisible auction mechanisms that hide actual bid values and regulate information flows, combined with machine learning techniques for robust predictive analytics. While rule-based fuzzy systems encode domain expertise in agricultural decision-making, adaptable training algorithms help optimize model parameters from the data. A two-phase hybrid learning approach is formulated. Fuzzy optimization models were formulated using domain expertise for three key supply chain decision problems. Auction markets discover optimal crop demand–supply balancing and pricing signals. Fuzzy systems incorporate domain knowledge into interpretable crop-advisory models. An integrated evaluation of 50 farms over five crop cycles demonstrated the high performance of the proposed edge computing-oriented auction-based fuzzy neural network model compared with benchmarks.