Computers and Electronics in Agriculture最新文献

{"title":"Deep convolutional networks based on lightweight YOLOv8 to detect and estimate peanut losses from images in post-harvesting environments","authors":"Armando Lopes de Brito Filho ,&nbsp;Franciele Morlin Carneiro ,&nbsp;Vinicius dos Santos Carreira ,&nbsp;Danilo Tedesco ,&nbsp;Jarlyson Brunno Costa Souza ,&nbsp;Marcelo Rodrigues Barbosa Júnior ,&nbsp;Rouverson Pereira da Silva","doi":"10.1016/j.compag.2025.110282","DOIUrl":"10.1016/j.compag.2025.110282","url":null,"abstract":"<div><div>Peanut losses detection is key to monitor operational quality during mechanical harvesting. Current manual assessments faces practical limitations in the field, as they tend to be exhaustive, time-consuming, and susceptible to errors, especially after long work periods. Therefore, the main objective of this study was to develop an automated image processing framework to detect, count, and estimate peanut pod losses during the harvesting operation. We proposed a robust approach encompassing different environmental conditions and training detection algorithms, specifically based on lightweight YOLOv8 architecture, with images acquired with a mobile smartphone at six different times of the day (10 a.m., 11 a.m., 1 p.m., 2 p.m., 3 p.m., and 4 p.m.). The experimental results showed that detecting two-seed peanut pods was more effective than one-seed pods, with higher precision, recall, and mAP50 values. The best results for image acquisition were between 10 a.m. and 2 p.m. The study also compared manual and automated counting methods, revealing that the best scenarios for counting achieved an R² above 0.80. Furthermore, georeferenced maps of peanut losses revealed significant spatial variability, providing critical insights for targeted interventions. These findings demonstrate the potential to enhance mechanized harvesting efficiency and lay the groundwork for future integration into fully automated systems. By incorporating this method into harvesting machinery, real-time monitoring and accurate loss quantification can be achieved, substantially reducing the need for labor-intensive manual assessments.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110282"},"PeriodicalIF":7.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143644333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-destructive and efficient prediction of intramuscular fat in live pigs based on ultrasound images and machine learning","authors":"Jian Wu ,&nbsp;Yingying Yang ,&nbsp;Wen Yang ,&nbsp;Chengwan Zha ,&nbsp;Liming Hou ,&nbsp;Sanqin Zhao ,&nbsp;Wangjun Wu ,&nbsp;Yutao Liu","doi":"10.1016/j.compag.2025.110291","DOIUrl":"10.1016/j.compag.2025.110291","url":null,"abstract":"<div><div>Intramuscular fat (IMF) content plays an essential role in the evaluation of meat quality. To select pig breeds with different IMF content, developing a method to predict the IMF content in live pigs was greatly significant to reduce the cost and time of breeding. In the current study, real-time ultrasound images 5 cm off-midline across the third and fourth last thoracic ribs of 336 live pigs were collected using the B-model technique, and image feature parameters were extracted by computer image processing techniques. Furthermore, multiple linear regression (MLR) and two machine learning algorithms, support vector machine (SVM) and back-propagation artificial neural network (BPANN), were used to develop the prediction models of IMF content. The experimental pigs were divided into a training dataset (n = 266) for developing the prediction models and a validation dataset (n = 70) for estimating the accuracy of the models, and a test set (n = 67) for additional model performance evaluation. The results reveal that the coefficient of determination (<em>R</em>²) of models ranges from 0.65 to 0.80 with a root-mean-square error (RMSE) range of 0.50 %–0.65 % in the training dataset. By contrast, the correlation coefficients (<em>R</em>) between the predicted IMF (PIMF) and the chemically measured IMF (CIMF) range from 0.72 to 0.82 with an RMSE ≤ 0.69 % for all the models in the validation and test dataset. Moreover, the results indicate that the individual ratio of absolute difference (ADIF) within 1 % between PIMF and CIMF is &gt; 86.57 % for all the models. In addition, classification accuracy shows that the BPANN1 model has superior classification ability in both low and high IMF content groups compared to the other two types of models in the validation dataset, but not in the test dataset. The MLR models are superior to other models in the medium IMF content group. Overall, our research demonstrates that it is feasible to predict IMF content based on ultrasound images in live pigs and provides several alternative models for accurate determination of IMF content, which could accelerate the genetic improvement of IMF content, thereby improving the pork quality in pig breeding programs.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110291"},"PeriodicalIF":7.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving the estimation accuracy of alfalfa quality based on UAV hyperspectral imagery by using data enhancement and synergistic band selection strategies","authors":"Shuai Fu ,&nbsp;Jie Liu ,&nbsp;Jinlong Gao ,&nbsp;Qisheng Feng ,&nbsp;Senyao Feng ,&nbsp;Chunli Miao ,&nbsp;Yunhao Li ,&nbsp;Caixia Wu ,&nbsp;Tiangang Liang","doi":"10.1016/j.compag.2025.110305","DOIUrl":"10.1016/j.compag.2025.110305","url":null,"abstract":"<div><div>Accurate and timely assessment of alfalfa nutritional parameters is crucial for optimizing harvest management, maximizing yield, and ensuring high-quality forage in China’s Hexi Corridor, a key alfalfa-growing region. UAV-based hyperspectral remote sensing offers a nondestructive and efficient method for monitoring these parameters, providing high-resolution data and covering large areas efficiently. Previous studies have faced challenges related to the scarcity and imbalance of hyperspectral samples and the effective selection of spectral bands for evaluating crop nutrients. Additionally, the simultaneous evaluation of multiple nutrient parameters using a common set of spectral bands has rarely been reported. Least Absolute Shrinkage and Selection Operator (LASSO) is an important method for hyperspectral band selection, but its linear fitting process is challenged by the complex relationship between spectral reflectance and plant properties. In this study, we propose a new band selection strategy that identifies the most informative spectral bands and improves model performance by combining the strengths of both LASSO selection of bands and machine learning’s ability to fit complex relationships. To address the issue of imbalanced field samples, we generated high-quality synthetic data using the synthetic minority oversampling technique for regression with Gaussian noise (SMOGN) algorithm. Three machine learning models (ANN, RF, and SVM) were then employed to predict alfalfa nutritional parameters. Our findings show that the proposed synergistic band selection strategy significantly improves model performance, yielding a 14–25 % reduction in RMSE while requiring only 37–59 % of the original spectral bands. By integrating this band selection strategy with the SMOGN method, our optimal model for estimating alfalfa nutrient parameters achieved R² values of 0.92–0.95 and PRMSE values of 5.1–7.1 %. We observed the importance of the spectral regions around 730 nm and 960 nm for predicting alfalfa quality parameters. This finding suggests that existing satellite platforms such as Sentinel-2 and Landsat could improve the accuracy and efficiency of alfalfa quality monitoring by incorporating these specific spectral bands. Overall, our approach provides a robust and transferable framework for improving the accuracy and reliability of remote sensing-based crop quality monitoring, which is important for optimizing the spectral band configurations of future satellite sensors for precision agriculture.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110305"},"PeriodicalIF":7.7,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing different statistical models for predicting greenhouse gas emissions, energy-, and nitrogen intensity","authors":"Kristian Nikolai Jæger Hansen ,&nbsp;Håvard Steinshamn ,&nbsp;Sissel Hansen ,&nbsp;Matthias Koesling ,&nbsp;Tommy Dalgaard ,&nbsp;Bjørn Gunnar Hansen","doi":"10.1016/j.compag.2025.110209","DOIUrl":"10.1016/j.compag.2025.110209","url":null,"abstract":"<div><div>To evaluate the environmental impact across multiple dairy farms cost-effectively, the methodological framework for environmental assessments may be redefined. This article aims to assess the ability of various statistical tools to predict impact assessment made from a Life Cyle Assessment (LCA). The different models predicted estimates of Greenhouse Gas (GHG) emissions, Energy (E) and Nitrogen (N) intensity. The functional unit in the study was defined as 2.78 MJ_MM human-edible energy from milk and meat. This amount is equivalent to the edible energy in one kg of energy-corrected milk but includes energy from milk and meat. The GHG emissions (GWP₁₀₀) were calculated as kg CO₂-eq per number of FU delivered, E intensity as fossil and renewable energy used divided by number of FU delivered, and N intensity as kg N imported and produced divided by kg N delivered in milk or meat (kg N/kg N). These predictions were based on 24 independent variables describing farm characteristics, management, use of external inputs, and dairy herd characteristics.</div><div>All models were able to moderately estimate the results from the LCA calculations. However, their precision was low. Artificial Neural Network (ANN) was best for predicting GHG emissions on the test dataset, (RMSE = 0.50, R² = 0.86), followed by Multiple Linear Regression (MLR) (RMSE = 0.68, R² = 0.74). For E intensity, the Supported Vector Machine (SVM) model was performing best, (RMSE = 0.68, R² = 0.73), followed by ANN (RMSE = 0.55, R² = 0.71,) and Gradient Boosting Machine (GBM) (RMSE = 0.55, R² = 0.71). For N intensity predictions the Multiple Linear Regression (MLR) (RMSE = 0.36, R² = 0.89) and Lasso regression (RMSE = 0.36, R² = 0.88), followed by the ANN (RMSE = 0.41, R² = 0.86,). In this study, machine learning provided some benefits in prediction of GHG emission, over simpler models like Multiple Linear Regressions with backward selection. This benefit was limited for N and E intensity. The precision of predictions improved most when including the variables “fertiliser import nitrogen” (kg N/ha) and “proportion of milking cows” (number of dairy cows/number of all cattle) for predicting GHG emission across the different models. The inclusion of “fertiliser import nitrogen” was also important across the different models and prediction of E and N intensity.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110209"},"PeriodicalIF":7.7,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143644332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel architecture for automated delineation of the agricultural fields using partial training data in remote sensing images","authors":"Sumesh KC ,&nbsp;Jagannath Aryal ,&nbsp;Dongryeol Ryu","doi":"10.1016/j.compag.2025.110265","DOIUrl":"10.1016/j.compag.2025.110265","url":null,"abstract":"<div><div>Digital agricultural services (DAS) rely on timely and accurate spatial information of agricultural fields. Initiatives, including deep learning (DL), have been used to extract accurate spatial information using remote sensing images. However, DL approaches require a large amount of fully segmented and labelled field boundary data for training that is not readily available. Obtaining high-quality training data is often costly and time-consuming. To address this challenge, we develop a multi-scale, multi-task DL-based novel architecture with two modules, an edge enhancement block (EEB) and a spatial attention block (SAB), using partial training data (i.e., weak supervision). This architecture is capable of delineating narrow and weak boundaries of agricultural fields. The model simultaneously learns three tasks: boundary prediction, extent prediction and distance estimation, and enhances the generalisability of the network. The EEB module extracts semantic edge features at multiple levels. The SAB module integrates the features from the encoder and decoder to improve the geometric accuracy of field boundary delineation. We conduct an experiment in Ille-et-Vilaine, France, using time-series monthly composite images from Sentinel-2 to capture key phenological stages of crops. The segmentation output from different months is combined and post-processed to generate individual field instances using hierarchical watershed segmentation. The performance of our method is superior in both pixel-based (86.42% Matthew’s correlation coefficient (MCC)) and object-based accuracy measures (76% shape similarity and 60% intersection over union (IoU)) to existing multi-task models. The ablation study shows that the EEB and SAB modules enhance the efficiency of feature extraction relevant to field extent and boundaries and improve accuracy. We conclude that the developed model and method can be used to improve the extraction of agricultural fields under weak supervision and different settings (satellite sensors and agricultural landscape).</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110265"},"PeriodicalIF":7.7,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An automatic landmarking algorithm for leaf morphology based on conformal mapping","authors":"Peige Zhong ,&nbsp;Xiaojun Liu ,&nbsp;Yulu Ye ,&nbsp;Rui Zhang ,&nbsp;Hu Zhou ,&nbsp;Yan Guo ,&nbsp;Baoguo Li ,&nbsp;Jinyu Zhu ,&nbsp;Yuntao Ma","doi":"10.1016/j.compag.2025.110274","DOIUrl":"10.1016/j.compag.2025.110274","url":null,"abstract":"<div><div>Leaf shape is of great significance in plant phenotype research. Landmarks method is a widely used morphometric approach, which can comprehensively describe the morphological differences among leaves. However, the selection of landmarks is time-consuming and laborious. An automatic landmarking algorithm is proposed here. Based on conformal mapping, the leaf outline can be transformed into a monotonically increasing function curve, referred to as the ’fingerprint function’. The Dynamic Time Warping (DTW) algorithm was introduced to match landmarks between different leaves. Two leaf datasets were used to validate the algorithm separately in different species and developmental stages. Dataset1 is a public dataset which covers 26 different types of leaves. The average positional difference between automatic and manual landmarks for dataset1 was only 2.95%. Dataset2 consists of cotton leaves collected in the field at various growth stages, and the positional difference for this dataset was all below 5%. These results validate that our algorithm is applicable to a wide range of leaf types and capable of identifying and locating novel features that emerge during leaf growth. The automatic landmarking algorithm can simulate manual landmarking to a great extent. It provides a new approach for automated acquisition of plant leaf shape homology tailored to the research needs of botanists.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110274"},"PeriodicalIF":7.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143631972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unveiling the infectious morphological behaviour of banana crop pathogenic nematodes inhabited from soil medium to pseudostem using an artificial intelligence approach","authors":"S.S. Jayakrishna,&nbsp;S. Sankar Ganesh","doi":"10.1016/j.compag.2025.110277","DOIUrl":"10.1016/j.compag.2025.110277","url":null,"abstract":"<div><div>Soil-borne microorganisms target the rhizosphere by invading from soil to plants through pseudostem. <em>Fusarium oxysporum</em> f.sp. <em>cubense</em>, an infectious agent’s host, interacts with nematodes present in the single point regional area (SPRA), causing tissue necrosis, and physical disordering of banana plants poses high yield loss. Diagnosing the source of pathogenic microbes on a crop significantly prevents its transmission to other regions. Disease characteristics cannot be accurately assessed through physical observation alone. We proposed Nematode Detection and Morphological Analysis (NDMA-YOLO), a deep learning-based futuristic algorithm, and Tracking Live Parasites (TLP) to tackle this issue. Experiments demonstrated in Fusarium-affected fields with similar soil properties. The chemical composition of soils is characterized by FTIR spectroscopic analysis, pH, moisture, SEM, and fluorescence spectrophotometer content characteristics. Physically identifying the source of infection using the (x, y) Grid Ring Axis Pseudo Stem Holistic (GRAPH) method, obtained plant tissue samples, and generated large image datasets through phase contrast microscopic. Recorded structure of nematodes to understand physiological, behavioral, and biotic stress patterns. We utilized AI-based computer vision for live event monitoring and morphological analysis, employing an enhanced YOLO-v8 model trained on a custom dataset to detect nematodes with 86.66 % accuracy and an overall performance of 98.93%. Our model surpasses previous versions like YOLO-v3, YOLO-v5, and YOLO-v7, showcasing significant advancements in dataset preparation for accurate predictions in plant pathology.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110277"},"PeriodicalIF":7.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143631973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accurate water level monitoring in Alternate Wetting and Drying rice cultivation using attention-based ConvNeXt architecture","authors":"Ahmed Rafi Hasan ,&nbsp;Niloy Kumar Kundu ,&nbsp;Saad Hasan ,&nbsp;Mohammad Rashedul Hoque ,&nbsp;Swakkhar Shatabda","doi":"10.1016/j.compag.2025.110216","DOIUrl":"10.1016/j.compag.2025.110216","url":null,"abstract":"<div><div>The Alternate Wetting and Drying (AWD) method is a rice-growing water management technique promoted as a sustainable alternative to Continuous Flooding (CF). Climate change has placed the agricultural sector in a challenging position, particularly as global water resources become increasingly scarce, affecting rice production on irrigated lowlands. Rice, a staple food for over half of the world’s population, demands significantly more water than other major crops. In Bangladesh, the cultivation of dry season, irrigated <em>Boro</em> rice demands substantial water inputs. Traditional manual water level measurement methods are time-consuming and error-prone, while ultrasonic sensors offer more precise readings but may be affected by environmental factors such as temperature fluctuations, changes in humidity levels, varying light conditions, and accumulation of dust or debris To overcome these limitations, we propose an innovative approach leveraging computer vision, specifically an attention-based ConvNeXt architecture, to automate water height measurement. Our method achieves state-of-the-art performance with an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> score of 0.989, a Root Mean Squared Error (RMSE) of 0.523 cm, and a Mean Squared Error (MSE) of 0.277 <span><math><mrow><mi>c</mi><msup><mrow><mi>m</mi></mrow><mrow><mn>2</mn></mrow></msup></mrow></math></span>, demonstrating superior accuracy and efficiency in managing AWD systems. This advancement represents a significant contribution to sustainable agriculture, enabling precise and automated water management in rice cultivation.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110216"},"PeriodicalIF":7.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating ecological niche and epidemiological models to predict wheat fusarium head blight using remote sensing and meteorological data","authors":"Shangzhou Li,&nbsp;Ping Dong,&nbsp;Hui Zhang,&nbsp;Xin Xu,&nbsp;Lei Shi,&nbsp;Tong Sun,&nbsp;Hongbo Qiao,&nbsp;Jibo Yue,&nbsp;Wei Guo","doi":"10.1016/j.compag.2025.110255","DOIUrl":"10.1016/j.compag.2025.110255","url":null,"abstract":"<div><div>Fusarium head blight (FHB) is a major wheat disease worldwide, significantly affecting yield and quality. Disease risk assessment and spatiotemporal dynamic prediction are crucial for effective FHB management and control. Although ecological niche models (ENMs) and epidemiological models (EMs) have been widely applied to assess the potential distribution of diseases and simulate their progression, studies integrating these models with satellite remote sensing and meteorological data for crop disease prediction remain limited. To fill this gap, our study developed an integrated prediction framework based on susceptible-exposed-infected (SEI) model. First, remote sensing data extracted host factors, including wheat spatial distribution, key phenological (KPh) stages defined by Day of Year (DOY), and early physiological changes. This information, along with meteorological features, topographic factors, and sampling coordinates, was utilized to construct an ENM based on Maximum Entropy (MaxEnt) algorithm. MaxEnt evaluation results guided input adjustments, ensuring high AUC output to characterize initial infection levels for SEI model. Next, transition rates in SEI model were determined by the coupling of the parameterized response functions of daily temperature, relative humidity, and DOY for KPh stages to mechanize the EM. The mechanistic model (MM), with optimal parameter values derived from sensitivity analysis and optimization, provided a robust prediction of disease occurrence on the sampling day and enabled spatiotemporal dynamic simulation of wheat FHB. The final MM achieved a coefficient of determination of 0.83, mean absolute error of 0.06, root mean square error of 0.072, and classification F1-score of 0.88. The simulated disease progression curve was consistent with the epidemiological characteristics of FHB, exhibiting an S-shaped pattern. These results suggest that integrating remote sensing and meteorological data with MaxEnt and SEI models for FHB prediction holds significant application potential.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110255"},"PeriodicalIF":7.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating UAV and high-resolution satellite remote sensing for multi-scale rice disease monitoring","authors":"Lin Yuan ,&nbsp;Qimeng Yu ,&nbsp;Lirong Xiang ,&nbsp;Fanguo Zeng ,&nbsp;Jie Dong ,&nbsp;Ouguan Xu ,&nbsp;Jingcheng Zhang","doi":"10.1016/j.compag.2025.110287","DOIUrl":"10.1016/j.compag.2025.110287","url":null,"abstract":"<div><div>Rice Bacterial Blight (RBB), caused by <em>Xanthomonas oryzae pv. oryzae (Xoo)</em>, is a major rice disease that significantly threatens yield and quality. RBB spreads rapidly under favorable conditions, affects extensive areas, and requires timely, large-scale monitoring due to its narrow window for effective detection. Traditional satellite monitoring methods, which rely on specific remote sensing platforms and extensive ground surveys, often fail to meet the timely and efficient needs of large-scale disease monitoring. To address the limitations of these traditional methods, this study proposes a cross-scale crop disease monitoring approach that integrates unmanned aerial vehicle (UAV) and satellite remote sensing. With RBB disease monitoring in rice as a case study, the inconsistency between different scale remote sensing data is first introduced to align satellite imagery with UAV data. Next, a sensitivity analysis of the original reflectance and disease-related vegetation indices at both scales is conducted to identify features with consistent performance. The minimum redundancy maximum relevance (mRMR) feature selection algorithm is then employed to obtain sensitive feature sets for each scale. Three machine learning algorithms—Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)—were used to develop disease monitoring models at both UAV and satellite scales. The optimal UAV-scale RF model was then applied to the corrected satellite data for cross-scale monitoring. Results indicate that the proposed cross-scale monitoring method achieved an accuracy of 87.78%, a precision of 88.13%, a recall of 87.78%, and an F1-score of 0.88 for the three-class classification of healthy, mildly infected, and severely infected RBB. The method effectively overcomes the reliance on extensive ground survey data typical of traditional large-scale crop disease remote sensing monitoring methods. Furthermore, the developed approach enables the cross-scale transfer of small-scale monitoring models, ensuring timely disease monitoring during outbreaks.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110287"},"PeriodicalIF":7.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}