Computers and Electronics in Agriculture最新文献

{"title":"Retraction notice to “Shrimp larvae detection and counting in aquaculture using multiscale feature fusion networks” [Comput. Electron. Agric., 233 (2025) 109850]","authors":"Thai-Ha Dang, Ngoc-Hai Dang, Viet-Thang Tran","doi":"10.1016/j.compag.2026.112189","DOIUrl":"10.1016/j.compag.2026.112189","url":null,"abstract":"","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"253 ","pages":"Article 112189"},"PeriodicalIF":10.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149159429","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":"Corrigendum to “A multisource weakly supervised high-resolution crop mapping framework based on low-resolution noise labels” [Comput. Electron. Agric. 251 (2026) 112003]","authors":"Hongyan Che, Jun Ma, Yaozhong Pan, Xiufang Zhu, Xingsheng Xia, Yinda Wang, Lingang Wang, Yongsheng Huang","doi":"10.1016/j.compag.2026.112243","DOIUrl":"10.1016/j.compag.2026.112243","url":null,"abstract":"","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"253 ","pages":"Article 112243"},"PeriodicalIF":10.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149159428","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":"Corrigendum to “Physics-guided GAN and ANN hybrid framework for small-sample performance prediction of seed-maize harvester conveying device” [Comput. Electron. Agric. 253 (2026) 112064]","authors":"Xiaojing Ren, Leilei Chang, Wuyun Zhao, Fei Dai, Ruijie Shi, Delong Yang, Wenlong Cao","doi":"10.1016/j.compag.2026.112241","DOIUrl":"10.1016/j.compag.2026.112241","url":null,"abstract":"","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"253 ","pages":"Article 112241"},"PeriodicalIF":10.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149159038","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":"Damage mechanism and evolution of Korla fragrant pear under quasi-static compressive loading","authors":"Chen Ding,&nbsp;Peiyu Chen,&nbsp;Yurong Tang,&nbsp;Lin Liao,&nbsp;Wen Li,&nbsp;Xirui Yang,&nbsp;Haipeng Lan,&nbsp;Hong Zhang","doi":"10.1016/j.compag.2026.112002","DOIUrl":"10.1016/j.compag.2026.112002","url":null,"abstract":"<div><div>Korla fragrant pear is prone to compression injury during mechanized harvesting because of its thin peel and delicate flesh. To quantify ripeness-dependent failure mechanisms and provide design bounds for end-effectors, we developed an experimentally validated finite element–discrete element (FDEM) model with embedded cohesive elements to simulate quasi-static uniaxial compression. The model reproduced the measured force–displacement responses across six ripeness levels (R² &gt; 0.96). Simulations show that stress/strain localize at the platen–fruit contact interfaces, where cracks initiate and then propagate preferentially along the fruit major axis before lateral spreading triggers global instability. Energy tracking indicates that external work is stored mainly as elastic strain energy at early loading, whereas damage dissipation and fracture-related energy rise before the peak load and shift earlier as ripening progresses. The dominant failure mode transitions from shear-dominated to tension-dominated behavior: the shear contribution decreases from ∼ 75% to ∼ 38%, while the tensile contribution increases from ∼ 25% to ∼ 62%. These results link field variables and energy partitioning to cohesive fracture evolution, enabling ripeness-aware parameter selection for low-damage gripping. These findings provide practical references for setting ripeness-specific gripping force, displacement limits, and compliant contact parameters in low-damage mechanized harvesting.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"253 ","pages":"Article 112002"},"PeriodicalIF":10.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149159036","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":"Corrigendum to “Accurate localization of fruit targets and picking points with multi-dimensional attention and dynamic upsampling”, [Comput. Electr. Agr. 240 (2026) 111211 doi: 10.1016/j.compag.2025.111211]","authors":"Yikun Huang,&nbsp;Gang Li,&nbsp;Jinghu Li,&nbsp;Hao Chen,&nbsp;Hefei Lin,&nbsp;Changcai Yang,&nbsp;Riqing Chen","doi":"10.1016/j.compag.2026.112162","DOIUrl":"10.1016/j.compag.2026.112162","url":null,"abstract":"","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"253 ","pages":"Article 112162"},"PeriodicalIF":10.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149159037","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":"PheMuT: A phenology-informed, multi-modal time-series model for strawberry yield forecasting","authors":"Zijing Huang ,&nbsp;Won Suk Lee ,&nbsp;Yiannis Ampatzidis ,&nbsp;Shinsuke Agehara ,&nbsp;Natalia A Peres","doi":"10.1016/j.compag.2026.111526","DOIUrl":"10.1016/j.compag.2026.111526","url":null,"abstract":"<div><div><em>Accurate yield forecasting is crucial in optimizing resource management and decision-making processes in agriculture, particularly in crops such as strawberries, which require precise predictions due to their rapid and continuous ripening cycles. This study introduces PheMuT, a novel phenology-informed, multi-modal time-series model that integrates visual and meteorological data streams to enhance strawberry yield forecasting. The proposed method employs advanced computer vision techniques, including two YOLOv11 detectors, an optimized ByteTrack tracker, Segment Anything (SAM), and Depth Anything v2 (DAv2), for precise fruit detection, canopy, and volume estimation. Concurrently, high-frequency weather data are processed using a self-supervised autoregressive Temporal Convolutional Network (TCN), resulting in concise and informative weather embeddings. These visual and weather features are fused within an LSTM-based model to produce weekly yield forecasts. PheMuT was validated using two strawberry cultivars at a Florida research facility over two consecutive seasons. Results indicated that PheMuT improved forecasting accuracy, reducing mean absolute error (MAE) by 10.7%, root mean squared error (RMSE) by 12.5%, and mean absolute percentage error (MAPE) by 18.6% compared to baseline manual methods. Additionally, the model exhibited a notable improvement of 17.2% in the coefficient of determination (R²). PheMuT offers an efficient, automated framework for yield forecasting. Code and data are available at</em> <span><span><em>https://github.com/Sycamorers/PheMuT</em></span><svg><path></path></svg></span><em>.</em> The full datasets used in this study are available from the authors upon request.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"244 ","pages":"Article 111526"},"PeriodicalIF":8.9,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173937","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":"Comparison of soil property predictions in Lithuanian croplands using UAV, satellite, EMI data and machine learning","authors":"R. Žydelis ,&nbsp;L. Weihermüller ,&nbsp;L.C. Gomes ,&nbsp;A.B. Møller ,&nbsp;F. Castaldi ,&nbsp;J. Volungevičius ,&nbsp;A. Kavaliauskas ,&nbsp;T. Koganti ,&nbsp;J. Wetterlind ,&nbsp;İ. Cinkaya ,&nbsp;L. Borůvka ,&nbsp;F. van Egmond ,&nbsp;S. Higgins ,&nbsp;F. Liebisch ,&nbsp;V. Povilaitis ,&nbsp;A. Kazlauskaitė-Jadzevičė ,&nbsp;K. Amalevičiūtė-Volungė ,&nbsp;S. Pranaitienė ,&nbsp;E. Vaudour","doi":"10.1016/j.compag.2026.111543","DOIUrl":"10.1016/j.compag.2026.111543","url":null,"abstract":"<div><div>Combining remote and proximal sensing provides a cost-effective solution for mapping soil properties in croplands. This study assessed the potential of remote sensing based on high resolution multispectral UAV imagery (2.6 cm), satellite (Sentinel-2), and in-field measured electromagnetic induction (EMI) data for predicting six soil properties − soil organic carbon content (SOC), clay, sand, silt contents, pH, and soil water content (SWC) − across five Lithuanian agroclimatic zones. Seven modelling scenarios, using individual and combined sources of sensor data, employing a random forest model, were evaluated. To assess real-world applicability, sampling-reduction simulation were additionally performed. SOC and clay predictions achieved the highest accuracy, while silt, sand, and SWC showed acceptable accuracy only in a few sites or specific modelling scenarios. Soil pH predictions were poor across all scenarios. Prediction accuracy varied across study sites, likely influenced by climate, soil parent material, topography, and agricultural management. Sensor data resolutions (2.6 cm, 1.6 m, 10 m per pixel) significantly affected prediction accuracy. For SOC predictions, UAV and Sentinel-2 data performed best, while EMI alone was less effective. In contrast, for clay predictions, EMI data yielded the highest accuracy, emphasizing its role for soil texture assessment. Multi-sensor fusion improved model performance during training but did not consistently enhance validation accuracy across sites, highlighting important cost–accuracy trade-offs and the need for realistic performance evaluation. Overall, the results demonstrate that the benefits of multi-sensor soil mapping are property-specific and site-dependent, providing guidance for scalable and economically viable field-scale soil mapping strategies.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"244 ","pages":"Article 111543"},"PeriodicalIF":8.9,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173949","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":"In-situ decomposition sensor output correlates with soil health indicators","authors":"Taylor J. Sharpe ,&nbsp;Madhur Atreya ,&nbsp;Shangshi Liu ,&nbsp;Mengyi Gong ,&nbsp;Nicole Luna ,&nbsp;Noah Smock ,&nbsp;Jessica Davies ,&nbsp;John N. Quinton ,&nbsp;Richard D. Bardgett ,&nbsp;Jason C. Neff ,&nbsp;Rebecca Killick ,&nbsp;Gregory L. Whiting","doi":"10.1016/j.compag.2026.111427","DOIUrl":"10.1016/j.compag.2026.111427","url":null,"abstract":"<div><div>Monitoring of soil microbiological processes can inform strategies to improve soil health and agricultural productivity. Biological soil health measurements are currently difficult to make in-situ and in real time, usually involving manual sampling and laboratory analysis. This is costly, time consuming, resource intensive, and cannot measure changes at high temporal and spatial resolution, limiting the ability to make prompt informed land management decisions. Low-cost soil sensors manufactured using printing techniques offer a potential scalable solution to these issues. Here, we tested the use of novel sensors for the proxy evaluation of soil microbial processes, hypothesizing that sensor decomposition rates may be related to manual soil sampling measurements. This is the first multi-plot field deployment of sensors which use a biodegradable composite conductor to transduce microbial decomposition of substrates to a change in electrical resistance, providing time-series decomposition rate data. Sensors were installed for 50 days across 44 experimental plots of a long-term grassland experiment with varying historical treatments and significant differences in soil microbial activity. Early failures and unresponsive substrates reduced the included sensor count to 31. Measurements commonly used as soil health indicators, including microbial biomass and enzymatic activities related to nutrient cycling, were determined using standard laboratory methods and compared to sensor responses. Three statistical approaches found positive correlations between the sensor signal and laboratory measurements of microbial biomass carbon and soil organic carbon, and some approaches found weaker correlations with enzymatic measurements. Although this experiment is limited in scope to a single experimental field and season, these initial findings show promise for enabling the proxy measurement of soil microbial processes in-situ using low-cost, scalable printed sensors.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"244 ","pages":"Article 111427"},"PeriodicalIF":8.9,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174057","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":"A new generation of embodied intelligent plant protection unmanned vehicle integrated with hydrostatic transmission and four-wheel drive technology: design, development and application","authors":"Zhigang Ren ,&nbsp;Jian Chen ,&nbsp;Mingjiang Sun ,&nbsp;Renzhong Fu","doi":"10.1016/j.compag.2026.111525","DOIUrl":"10.1016/j.compag.2026.111525","url":null,"abstract":"<div><div>Addressing the pain points of insufficient hardware performance, low adaptability to complex environments, and poor operational precision in domestic orchard spraying equipment, combined with the scene characteristics and agronomic requirements of domestic plain/hilly and mountainous orchards, this paper takes the core principle of Embodied Intelligence (real-time interaction and feedback between hardware and the environment) as the guiding framework. It designs a new-generation embodied intelligent plant protection unmanned vehicle, providing a standardized carrier for the implementation of embodied intelligent algorithms. The equipment integrates a customized hydrostatic transmission (HST) module, four-wheel drive (4WD) and synchronous steering technology, equipped with an electro-hydraulic steering system and a dual-core control architecture (dual CAN bus communication) consisting of an industrial computer and a programmable logic controller (PLC). It features smooth torque adjustment, a maximum speed of 11 km/h, and a pesticide carrying capacity of 600 L, enabling unmanned autonomous operations. Field tests under half-load conditions show that at a driving speed of 0.8 m/s, the maximum lateral deviations of path tracking under different working conditions are 0.076 m, 0.118 m, and 0.182 m respectively. Compared with the traditional algorithm, on rough terrain, the maximum lateral deviation, average deviation, and standard deviation are reduced by 10.3%, 10.4%, and 9.5% respectively. This study constructs a hardware scheme adapted to domestic orchards, filling the gap in embodied intelligent hardware for orchards and providing key technical support for the intelligent iteration of equipment hardware and the engineering application of embodied intelligent algorithms.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"244 ","pages":"Article 111525"},"PeriodicalIF":8.9,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174058","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":"Beyond Color: Advanced RGB-D data augmentation for robust semantic segmentation in crop farming scenes","authors":"Florian Kitzler ,&nbsp;Alexander Bauer ,&nbsp;Viktoria Kruder-Motsch","doi":"10.1016/j.compag.2026.111432","DOIUrl":"10.1016/j.compag.2026.111432","url":null,"abstract":"<div><div>The emergence of smart farming in recent years has substantially increased the importance of artificial vision systems in crop production. Data augmentation is essential for developing robust semantic segmentation models when dealing with small datasets, such as in selective weed control. Due to advances in multi-modal data fusion, RGB-D image datasets contribute substantially to improve model performance. However, most data augmentation techniques primarily modify the color channels, often neglecting the depth channel. Addressing this gap, we introduce three methods for augmenting RGB-D images: RGB-D-Aug, Recompose3D, and Compose3D. We conducted experiments utilizing a multi-modal fusion network tailored for semantic segmentation of different plant species, namely ESANet. RGB-D-Aug introduces artificial depth sensor noise in addition to commonly used geometric transformations and color variations. Recompose3D and Compose3D generate augmented RGB-D images and corresponding ground-truth labels by composing background images and a set of foreground plant snippets. Recompose3D rearranges plants from a given training image, while Compose3D employs all plant snippets available in the training dataset. In our experiments designed to evaluate generalization performance, we tested our three methods and compared them not only to the augmentation technique used in ESANet, which consists of geometric transformations and color channel variations, but also to an extended version of the Copy-Paste method, an image composition technique originally introduced for RGB images. All three of our proposed methods outperformed the ESANet augmentation. The image composition methods, Copy-Paste, Recompose3D, and Compose3D, performed significantly better, with Compose3D achieving the highest generalization performance of all methods tested. In addition to improving model robustness, Compose3D allows the creation of realistic agronomic image scenes. Our research is an important step towards developing robust and generalizable models for different applications in arable farming.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"244 ","pages":"Article 111432"},"PeriodicalIF":8.9,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025086","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}