[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1892":3,"related-1892":101},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":31,"secondary_topics":36,"classification":48,"search_phrases":80,"slug":83,"view_count":22,"doi":84,"paper":85,"created_at":100},1892,"Deep learning technique for rice leaf disease classification and severity level identification via Hybrid ResConvolutional Neural Network","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-68755-5","Rice leaf diseases significantly reduce agricultural yield and pose a major challenge for sustainable food production, particularly owing to the limitations associated with manual and visual inspection methods that are subjective and often ineffective in early-stage detection. This investigation proposes a new Hybrid ResConvolutional Neural Network (HyResCN-Net) for effective classification and severity identification of rice plant leaf diseases. The proposed framework integrates an Internet of Things (IoT) -based data acquisition and routing simulation using CrowWhale Energy Trust Routing (CrowWhale-ETR) for efficient data handling. Initially, preprocessing is done by an averaging filter to reduce noise. Then, plant leaves are segmented using the Eff-UNet++ method. Augmentation techniques like rotation, scaling, and color change are applied to expand the dataset. Features, like entropy with Gradient Directional Pattern (GDP), Complete Local Binary Pattern (CLBP), and histogram features, are extracted to enhance feature representation. These features are then used within the proposed HyResCN-Net model, which integrates Parallel Convolutional Neural Network (PCNN) and ResNeXt to improve discriminative learning for disease classification and severity estimation. Experimental evaluation is conducted on the Rice Leaf Bacterial and Fungal Disease Dataset. Considering a k-value of 8, the HyResCN-Net gains an accuracy of 94.258%, a True Positive Rate (TPR) of 96.479%, a True Negative Rate (TNR) of 92.898%, a precision of 91.312% and an F1-score of 93.824% compared to existing methods. The HyResCN-Net efficiently enhances rice leaf disease identification and severity analysis, supporting its applicability in precision agriculture applications.","水稻叶部病害显著降低农业产量，并对可持续粮食生产构成重大挑战，尤其是由于人工目视检查方法存在主观性，且在早期检测中往往效果不佳。本研究提出了一种新型混合残差卷积神经网络（HyResConvolutional Neural Network，HyResCN-Net），用于水稻叶片病害的有效分类和严重程度识别。所提出的框架集成了基于物联网（Internet of Things，IoT）的数据采集和路由模拟，采用CrowWhale能量信任路由（CrowWhale-ETR）以实现高效的数据处理。首先，通过平均滤波器进行预处理以降低噪声。然后，利用Eff-UNet++方法对植物叶片进行分割。应用旋转、缩放和颜色变化等增强技术来扩充数据集。提取熵结合梯度方向模式（Gradient Directional Pattern，GDP）、完整局部二值模式（Complete Local Binary Pattern，CLBP）及直方图特征等特征，以增强特征表示。这些特征随后被用于所提出的HyResCN-Net模型中，该模型集成了并行卷积神经网络（Parallel Convolutional Neural Network，PCNN）和ResNeXt，以提升疾病分类和严重程度评估的判别学习能力。实验评估在水稻叶片细菌性和真菌性病害数据集上进行。在k值为8的情况下，与现有方法相比，HyResCN-Net达到了94.258%的准确率、96.479%的真阳性率（True Positive Rate，TPR）、92.898%的真阴性率（True Negative Rate，TNR）、91.312%的精确率以及93.824%的F1分数。HyResCN-Net有效增强了水稻叶片病害识别和严重程度分析，支持其在精准农业应用中的适用性。",null,"Scientific Reports","2026-09-06T00:00:00Z","论文",10,false,68,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,18,12,3,1,"提出混合残差卷积网络用于水稻叶部病害分类与严重度识别，方法新颖且实验数据详实，对精准农业有参考价值。",[25],{"name":10,"url":6},[27,28,29,30],"智慧农业","农业人工智能","水稻","病虫害防治",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[37,43],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":49,"locked":14,"version":50,"method":51,"evidence":52},"classified","2026-10-22.2","rules",{"candidates":53,"agricultural_evidence":55},[54,59,65,72],{"code":32,"score":17,"supported":55,"title":56,"abstract":57,"tags":58},true,[33],[29,33],[29],{"code":38,"score":60,"supported":55,"title":61,"abstract":63,"tags":64},9,[62],"deep learning",[],[28],{"code":44,"score":60,"supported":55,"title":66,"abstract":67,"tags":71},[],[68,69,70],"物联网","internet of things","IoT",[],{"code":73,"score":74,"supported":55,"title":75,"abstract":76,"tags":79},"I1",7,[],[77,78],"精准农业","precision agriculture",[27],[81,82],"农业人工智能 病虫害防治 智慧农业 水稻","农业人工智能 病虫害防治","农业人工智能病虫害防治智慧农业水稻-1892","10.1038\u002Fs41598-026-68755-5",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":92,"oa_url":6,"card":93,"direction":97,"ingested_from":99},"W7210271395",[88,90],{"name":89,"orcid":9},"R. Creesy",{"name":91,"orcid":9},"K. Michael Mahesh",0,{"tldr":94,"method":95,"finding":96,"direction":97,"opportunity":98},"提出混合Res卷积神经网络用于水稻叶部病害分类与严重度识别，结合物联网数据采集。","HyResCN-Net结合PCNN和ResNeXt，使用Eff-UNet++分割","在数据集上准确率达94.258%，优于现有方法，支持精准农业应用。","智慧农业 \u002F 农业物联网","可探索模型在多种作物病害上的泛化能力，或结合边缘计算实现田间实时诊断。","openalex","2026-09-08T23:30:11.816325Z",{"total":102,"page":22,"page_size":102,"items":103},6,[104,176,235,317,375,462],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":109,"content":9,"source_name":110,"source_url":107,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":113,"sources":117,"tags":119,"primary_topic":122,"secondary_topics":123,"classification":126,"search_phrases":148,"slug":151,"view_count":152,"doi":153,"paper":154,"created_at":175},2646,"IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0356383","Early and real-time detection of rice leaf diseases (RLD) poses a significant challenge for farmers, especially in rural regions with limited access to advanced technology. Conventional deep learning models often require substantial computational resources, rendering them impractical for deployment on mobile or edge devices commonly used in agricultural environments. Although models such as ResNet50, VGG16, and InceptionV3 can achieve high accuracy, they are computationally expensive and may be less suitable for real-time deployment in smart agricultural systems. Furthermore, many existing studies rely on limited datasets, which can restrict model generalizability under diverse real-world conditions. Although transfer learning can improve classification performance, developing lightweight models suitable for real-time IoT deployment remains challenging. To address these limitations, we curated a hybrid dataset of 7,092 rice leaf images by combining self-collected and Kaggle samples and proposed IoT-RiceMobileNet, a lightweight improved MobileNetV2-based model that can be effectively integrated into our developed IoT system. The proposed model outperformed transfer learning and deep learning baseline models, achieving 99.19% test accuracy and 99.20% precision while maintaining low computational complexity. We further confirmed model stability using stratified 5-fold and 10-fold cross-validation on both the constructed RLD and multi-source datasets, achieving mean accuracies of 98.04% and 98.13% on the constructed RLD dataset and 98.11% and 98.58% on the multi-source dataset, respectively. Moreover, our models compact size and 85.17 FPS inference speed support real-time deployment. Finally, the model was integrated into an IoT-enabled mobile, web, and cloud-based inference framework, demonstrating its practical potential for scalable rice disease detection in smart agriculture.","水稻叶片病害（RLD）的早期和实时检测对农民而言是一项重大挑战，尤其是在难以获取先进技术的农村地区。传统的深度学习模型通常需要大量计算资源，使其难以在实际农业环境中常用的移动或边缘设备上部署。尽管ResNet50、VGG16和InceptionV3等模型可以达到较高精度，但其计算成本高昂，可能不太适合在智慧农业系统中实时部署。此外，许多现有研究依赖有限的数据集，这可能限制模型在多样化真实条件下的泛化能力。尽管迁移学习可以提升分类性能，但开发适合实时物联网部署的轻量级模型仍具有挑战性。为解决这些局限，我们通过整合自采集样本和Kaggle样本，构建了一个包含7092张水稻叶片图像的混合数据集，并提出了IoT-RiceMobileNet，这是一种基于MobileNetV2改进的轻量级模型，可有效集成到我们开发的物联网系统中。所提出的模型优于迁移学习和深度学习基线模型，在保持低计算复杂度的同时，实现了99.19%的测试准确率和99.20%的精确率。我们进一步通过在构建的RLD数据集和多源数据集上采用分层5折和10折交叉验证确认了模型稳定性，在构建的RLD数据集上分别达到98.04%和98.13%的平均准确率，在多源数据集上分别达到98.11%和98.58%的平均准确率。此外，该模型紧凑的规模和85.17 FPS的推理速度支持实时部署。最后，该模型被集成到一个支持物联网的移动端、网页端和云端推理框架中，展示了其在智慧农业中可扩展水稻病害检测的实际潜力。","PLoS ONE","2026-09-15T00:00:00Z",80,{"impact":19,"substance":114,"depth":19,"authority":115,"freshness":60,"relevant":22,"comment":116},22,13,"提出轻量级MobileNetV2水稻病害检测模型并集成物联网推理框架，实测精度与推理速度俱佳，方法新颖、数据规模可观，对边缘端智慧农业落地有参考价值。",[118],{"name":110,"url":107},[27,28,68,120,121],"水稻病害","轻量化模型",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[124,125],{"code":44,"slug":45,"name":46,"path":47,"parent_code":42},{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":127},{"candidates":128,"agricultural_evidence":55},[129,133,137,143],{"code":32,"score":17,"supported":55,"title":130,"abstract":131,"tags":132},[33],[29,33],[120],{"code":44,"score":17,"supported":55,"title":134,"abstract":135,"tags":136},[70],[68,70],[68],{"code":38,"score":138,"supported":55,"title":139,"abstract":140,"tags":142},8,[],[141,62],"深度学习",[28,121],{"code":73,"score":74,"supported":55,"title":144,"abstract":145,"tags":147},[],[27,146],"smart agriculture",[27],[149,150],"农业人工智能 轻量化模型 智慧农业 水稻病害","农业人工智能 轻量化模型","农业人工智能轻量化模型智慧农业水稻病害-2646",2,"10.1371\u002Fjournal.pone.0356383",{"doi":153,"openalex_id":155,"authors":156,"venue":110,"cited_by_count":92,"oa_url":107,"card":170,"direction":97,"ingested_from":99},"W7213328321",[157,159,161,163,165,167],{"name":158,"orcid":9},"Khawja Imran Masud",{"name":160,"orcid":9},"Md Yasin Zihad",{"name":162,"orcid":9},"Mehedi Hasan Shuvo",{"name":164,"orcid":9},"Mst Raonik Jannat",{"name":166,"orcid":9},"Jia Uddin",{"name":168,"orcid":169},"Sahara Ali","https:\u002F\u002Forcid.org\u002F0000-0002-8578-948X",{"tldr":171,"method":172,"finding":173,"direction":97,"opportunity":174},"提出轻量级IoT-RiceMobileNet模型，实现水稻病害实时多类检测。","改进MobileNetV2，融合自采与Kaggle共7092张图像，IoT端部署","测试准确率99.19%，推理速度85.17 FPS，适合边缘设备实时检测。","可探索多作物病害泛化、田间复杂光照下轻量模型鲁棒性及边缘联邦学习。","2026-09-16T23:30:12.197386Z",{"id":177,"title":178,"url":179,"summary":180,"summary_zh":181,"content":9,"source_name":182,"source_url":179,"published_at":183,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":184,"sources":186,"tags":188,"primary_topic":191,"secondary_topics":192,"classification":194,"search_phrases":213,"slug":216,"view_count":92,"doi":217,"paper":218,"created_at":234},4802,"A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1837705","The correct and prompt detection of leaf diseases in paddy crops remains essential for protecting agricultural output and yield stability and reducing major losses that occur during severe disease outbreaks. The widespread use of conventional centralized machine learning techniques becomes impractical for real-world agricultural applications, as their effectiveness diminishes under three main conditions: data privacy limitations, delayed transmission of information, along with reduced performance accuracy from non-independent and identically distributed (non-IID) data properties across different agro-climatic regions. This research develops a decentralized diagnostic system which combines Federated Learning with an Enhanced Pretrained Novel EfficientNet-Lite4 model designed for paddy leaf disease classification. The Paddy Doctor dataset served as training material for the system which contained 16,225 RGB images that classified 12 disease types alongside healthy categories. The proposed model reached 98.7% classification accuracy and 98.5% precision and 98.6% F1-score while maintaining a final loss of 0.21 after 100 communication rounds. The system underwent field testing which demonstrated its ability to generate accurate diagnostic results in real time in various working conditions. The study demonstrates how privacy preserving AI-based paddy disease management works in practice and recommends local agricultural institutions to build decentralized learning systems. The suggested system will give farmers direct access to field level decision support and facilitate the creation of sustainable digital pest management systems required to ensure food supply.","正确且及时地检测水稻作物叶片病害，对于保护农业产出和产量稳定、减少病害严重暴发期间发生的重大损失仍然至关重要。传统集中式机器学习技术的广泛使用在现实农业应用中变得不切实际，因为在三种主要条件下其有效性会下降：数据隐私限制、信息传输延迟，以及不同农业气候区域间非独立同分布（non-IID）数据特性导致的性能准确率降低。本研究开发了一种去中心化诊断系统，将联邦学习与一种增强的预训练新型高效网络模型EfficientNet-Lite4相结合，用于水稻叶片病害分类。Paddy Doctor数据集作为该系统的训练材料，包含16,225张RGB图像，涵盖12种病害类型以及健康类别。所提出的模型在100轮通信后达到了98.7%的分类准确率、98.5%的精确率和98.6%的F1分数，同时最终损失保持在0.21。该系统经过实地测试，证明其能够在各种工作条件下实时生成准确的诊断结果。该研究展示了基于隐私保护人工智能的水稻病害管理如何在实践中运作，并建议地方农业机构构建去中心化学习系统。所建议的系统将为农民提供直接的田间决策支持，并促进建立确保粮食供应所需的可持续数字病虫害管理系统。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",{"impact":19,"substance":114,"depth":19,"authority":115,"freshness":60,"relevant":22,"comment":185},"将联邦学习与轻量级EfficientNet-Lite4结合用于水稻叶病识别，兼顾隐私保护与98.7%高精度，对智慧农业落地有参考价值。",[187],{"name":182,"url":179},[27,28,29,189,190],"病虫害识别","联邦学习",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[193],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":195},{"candidates":196,"agricultural_evidence":55},[197,202,209],{"code":32,"score":17,"supported":55,"title":198,"abstract":200,"tags":201},[199],"paddy",[29,199],[29],{"code":38,"score":20,"supported":55,"title":203,"abstract":204,"tags":208},[],[205,206,207],"机器学习","machine learning","decision support",[28,189,190],{"code":73,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},[],[],[27],[214,215],"Paddy Doctor 数据集 水稻病害","EfficientNet-Lite4 水稻叶片病害","PaddyDoctor数据集水稻病害-4802","10.15832\u002Fankutbd.1837705",{"doi":217,"openalex_id":219,"authors":220,"venue":182,"cited_by_count":92,"oa_url":227,"card":228,"direction":97,"ingested_from":99},"W7221522859",[221,224],{"name":222,"orcid":223},"B Johnson","https:\u002F\u002Forcid.org\u002F0009-0009-8281-4051",{"name":225,"orcid":226},"Chandrakumar Thangavel","https:\u002F\u002Forcid.org\u002F0000-0002-1186-5988","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5486058",{"tldr":229,"method":230,"finding":231,"direction":232,"opportunity":233},"提出联邦学习结合改进EfficientNet-Lite4的水稻叶片病害检测框架，兼顾隐私与精度。","联邦学习+预训练EfficientNet-Lite4，用Paddy Doctor","12类病害分类准确率达98.7%，100轮通信后损失0.21，支持实时诊断。","农业人工智能与决策模型","可探索非IID数据下联邦聚合优化与轻量化模型在边缘设备的部署研究。","2026-10-13T23:30:08.809781Z",{"id":236,"title":237,"url":238,"summary":239,"summary_zh":9,"content":9,"source_name":240,"source_url":238,"published_at":241,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":242,"score_detail":243,"sources":245,"tags":247,"primary_topic":250,"secondary_topics":251,"classification":258,"search_phrases":278,"slug":281,"view_count":22,"doi":282,"paper":283,"created_at":316},4500,"Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11163942\u002Fv1","Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice。Research Square","Research Square","2026-10-08T00:00:00Z",74,{"impact":19,"substance":18,"depth":19,"authority":13,"freshness":138,"relevant":22,"comment":244},"将无人机遥感与深度学习结合用于水稻白叶枯病早期检测，方法有创新、结论具应用价值，但属预印本且为细分技术进展，适合进入主题聚合而非头条精选。",[246],{"name":240,"url":238},[27,28,29,248,249],"遥感","病害检测",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[252,253],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":254,"slug":255,"name":256,"path":257,"parent_code":42},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":49,"locked":14,"version":50,"method":51,"evidence":259},{"candidates":260,"agricultural_evidence":55},[261,265,269,274],{"code":32,"score":20,"supported":55,"title":262,"abstract":263,"tags":264},[33],[33],[29],{"code":38,"score":20,"supported":55,"title":266,"abstract":267,"tags":268},[62],[62],[28],{"code":254,"score":20,"supported":55,"title":270,"abstract":272,"tags":273},[271],"remote sensing",[271],[248],{"code":73,"score":22,"supported":14,"title":275,"abstract":276,"tags":277},[],[],[27],[279,280],"无人机遥感 水稻 白叶枯病","深度学习 水稻病害 早期检测","无人机遥感水稻白叶枯病-4500","10.21203\u002Frs.3.rs-11163942\u002Fv1",{"doi":282,"openalex_id":284,"authors":285,"venue":240,"cited_by_count":92,"oa_url":238,"card":9,"direction":315,"ingested_from":99},"W7221055917",[286,289,292,294,296,299,301,303,306,308,310,312],{"name":287,"orcid":288},"Carlito B. Balingbing","https:\u002F\u002Forcid.org\u002F0000-0002-3672-9253",{"name":290,"orcid":291},"Dmytro Chebotarov","https:\u002F\u002Forcid.org\u002F0000-0003-1351-9453",{"name":293,"orcid":9},"Ian  Carlo Perilla",{"name":295,"orcid":9},"Stephen Klassen",{"name":297,"orcid":298},"Nancy Castilla","https:\u002F\u002Forcid.org\u002F0000-0002-9143-4933",{"name":300,"orcid":9},"Raphael  Gabriel Carvajal",{"name":302,"orcid":9},"Kendrix Ortega",{"name":304,"orcid":305},"Joseph M. Sandro","https:\u002F\u002Forcid.org\u002F0000-0002-8311-2299",{"name":307,"orcid":9},"Nurmi Pangesti",{"name":309,"orcid":9},"Caesar Arloo R. Centeno",{"name":311,"orcid":9},"Arnel Rala",{"name":313,"orcid":314},"Li-Yu  Daisy Liu","https:\u002F\u002Forcid.org\u002F0000-0001-6997-8101","农业遥感与作物表型","2026-10-09T23:30:18.390549Z",{"id":318,"title":319,"url":320,"summary":321,"summary_zh":322,"content":9,"source_name":10,"source_url":320,"published_at":323,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":324,"score_detail":325,"sources":328,"tags":330,"primary_topic":333,"secondary_topics":334,"classification":336,"search_phrases":356,"slug":359,"view_count":152,"doi":360,"paper":361,"created_at":374},4431,"A multimodal deep learning for rice crop health monitoring using vegetation index feature selection","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-74895-5","Crop health monitoring is essential for sustaining agricultural productivity and ensuring stable production, particularly in major crop-producing regions that face challenges due to climate variability, resource constraints, and spatial heterogeneity. Traditional methods struggle to effectively integrate spatial heterogeneity and environmental variability from multi-source remote sensing (RS) data. To address this problem, the proposed work explores the role of satellite imagery in monitoring rice crop health with the help of Vegetation Indices (VIs) under the impact of changing weather conditions. Multi-temporal Sentinel-1 and Sentinel-2 satellite data were acquired from a rice cultivation field in Gorakhpur, Uttar Pradesh, India, during three Kharif growing seasons (2023-2025). In this work, we propose a supervised MI-based feature selection framework employing Otsu’s adaptive thresholding for selection of VIs that strongly determine the health of rice crop. To ensure data integrity, cloud-contaminated observations were systematically excluded through a two-stage cleaning process. Further, we propose a multimodal deep learning (DL) framework that fuses a Swin Transformer (Swin-T) backbone for spatial feature extraction from vegetation index imagery with a Multi-Layer Perceptron (MLP) for structured numerical modeling of meteorological variables. The proposed framework achieved 94.05% accuracy on an independent held-out test set and a mean accuracy of \\(92.12 \\pm 5.28\\) % under 10-fold cross-validation, consistently outperforming competing hybrid deep learning baselines. These results highlight that integrating transformer-based spatial representations with environmental information provides an efficient approach for rice crop health classification. The proposed framework can be extended to multi-region crop monitoring by incorporating additional vegetation index modalities and diverse climatic conditions.","作物健康监测对于维持农业生产力、保障稳定生产至关重要，尤其是在面临气候变异性、资源约束和空间异质性挑战的主要作物产区。传统方法难以有效整合多源遥感（RS）数据中的空间异质性和环境变异性。为解决这一问题，本研究探索了卫星影像在天气条件变化影响下借助植被指数（VIs）监测水稻作物健康的作用。研究在印度北方邦戈勒克布尔的稻田中，于三个水稻生长季（2023—2025年）获取了多时相Sentinel-1和Sentinel-2卫星数据。在本研究中，我们提出了一种基于互信息（MI）的监督式特征选择框架，采用Otsu自适应阈值法筛选对水稻作物健康具有强判别能力的植被指数。为确保数据完整性，通过两阶段清洗流程系统性地剔除了受云污染的观测数据。此外，我们提出了一种多模态深度学习（DL）框架，该框架融合了Swin Transformer（Swin-T）主干网络用于从植被指数影像中提取空间特征，以及多层感知机（MLP）用于气象变量的结构化数值建模。所提框架在独立留出测试集上达到了94.05%的准确率，在10折交叉验证下平均准确率为\\(92.12 \\pm 5.28\\)%，持续优于竞争的混合深度学习基线模型。这些结果表明，将基于Transformer的空间表征与环境信息相结合，为水稻作物健康分类提供了一种高效方法。所提框架可通过纳入更多植被指数模态和多样化气候条件，扩展至多区域作物监测。","2026-10-07T00:00:00Z",81,{"impact":19,"substance":114,"depth":19,"authority":326,"freshness":60,"relevant":22,"comment":327},14,"方法新颖、数据跨三个生长季且精度可靠，属农业遥感与AI交叉的细分领域进展，值得进入每日精选。",[329],{"name":10,"url":320},[27,28,29,331,332],"遥感监测","作物长势",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[335],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":337},{"candidates":338,"agricultural_evidence":55},[339,344,348,352],{"code":32,"score":19,"supported":55,"title":340,"abstract":341,"tags":343},[33],[29,342,33],"稻田",[29],{"code":38,"score":17,"supported":55,"title":345,"abstract":346,"tags":347},[62],[141,62],[28],{"code":254,"score":74,"supported":55,"title":349,"abstract":350,"tags":351},[],[248,271],[331],{"code":73,"score":22,"supported":14,"title":353,"abstract":354,"tags":355},[],[],[27],[357,358],"Sentinel-2 水稻 遥感监测","Swin Transformer 作物健康","Sentinel-2水稻遥感监测-4431","10.1038\u002Fs41598-026-74895-5",{"doi":360,"openalex_id":362,"authors":363,"venue":10,"cited_by_count":92,"oa_url":320,"card":369,"direction":315,"ingested_from":99},"W7220838898",[364,367],{"name":365,"orcid":366},"Shashank Gupta","https:\u002F\u002Forcid.org\u002F0000-0003-1291-7951",{"name":368,"orcid":9},"Shefali Arora Chouhan",{"tldr":370,"method":371,"finding":372,"direction":315,"opportunity":373},"融合Sentinel-1\u002F2植被指数与气象数据，用多模态深度学习监测水稻健康。","Sentinel-1\u002F2多时相数据、MI特征选择、Otsu阈值、Swin-T+M","独立测试准确率94.05%，10折交叉验证92.12%，优于混合基线。","可扩展至多区域多作物，探索更多植被指数模态与极端气候下的泛化能力。","2026-10-08T23:30:29.254071Z",{"id":376,"title":377,"url":378,"summary":379,"summary_zh":380,"content":9,"source_name":381,"source_url":378,"published_at":382,"category":12,"cover_url":9,"hotness":383,"is_selected":14,"score":384,"score_detail":385,"sources":389,"tags":393,"primary_topic":395,"secondary_topics":396,"classification":399,"search_phrases":446,"slug":449,"view_count":92,"doi":450,"paper":451,"created_at":461},4310,"Comprehensive remote sensing and machine learning framework for multi-regional rice yield forecasting under hydroclimatic variability in Sahelian Niger","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149579","It is crucial to forecast rice yields effectively in order to improve agricultural planning and resilience to climate change in the Sahel, where production is greatly affected by hydroclimatic variability. This research has developed an integrated framework combining remote sensing analysis and machine learning to assess the variability in rice production in Niamey, Dosso, Tillaberi and Diffa, in Niger, over the period 2010–2025. They combined Landsat-derived NDVI and EVI with parameters such as evapotranspiration, precipitation, temperature, humidity, solar radiation, soil moisture, cultivated area, year and season. We processed and harmonised the datasets using Google Earth Engine and Python. We then evaluated four regression algorithms separately, Random Forest (RF), k-nearest neighbours (KNN), support vector regression (SVR) and XGBoost (XGB), for each region. The correlation analysis revealed modest positive links between rice yield and the NDVI (r = 0.27) and the EVI (r = 0.14), while a strong correlation was observed between the NDVI and the EVI (r = 0.80). The vegetation indices showed marked seasonal and interannual variability, generally exhibiting higher values during the wet season. Model performance varied considerably from one region to another","在萨赫勒地区，有效预测水稻产量对于改善农业规划和增强气候变化适应能力至关重要，因为该地区的生产在很大程度上受到水文气候变率的制约。本研究开发了一个集成框架，将遥感分析与机器学习相结合，以评估尼日尔尼亚美、多索、蒂拉贝里和迪法在2010—2025年期间水稻产量的变异性。研究将基于Landsat的归一化植被指数（NDVI）和增强型植被指数（EVI）与蒸散发、降水、温度、湿度、太阳辐射、土壤水分、耕地面积、年份和季节等参数相结合。利用Google Earth Engine和Python对数据集进行了处理和协调。随后，针对每个地区分别评估了四种回归算法：随机森林（RF）、k近邻（KNN）、支持向量回归（SVR）和XGBoost（XGB）。相关分析显示，水稻产量与NDVI（r = 0.27）和EVI（r = 0.14）之间存在弱正相关，而NDVI与EVI之间则观察到强相关（r = 0.80）。植被指数表现出明显的季节性和年际变异性，通常在湿季呈现较高值。模型性能在不同地区之间差异显著。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-05T00:00:00Z",25,72,{"impact":20,"substance":386,"depth":387,"authority":115,"freshness":60,"relevant":22,"comment":388},21,17,"基于Landsat植被指数与四种机器学习模型的多区域水稻产量预测研究，方法扎实、数据跨度长，但属区域性学术成果，对国内农业信息化有方法借鉴价值。",[390,391],{"name":381,"url":378},{"name":381,"url":392},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[27,28,29,394,248],"产量预测",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[397,398],{"code":254,"slug":255,"name":256,"path":257,"parent_code":42},{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":400},{"candidates":401,"agricultural_evidence":55},[402,407,411,415,422,429,436,442],{"code":254,"score":403,"supported":55,"title":404,"abstract":405,"tags":406},16,[271],[248,271],[394,248],{"code":32,"score":17,"supported":55,"title":408,"abstract":409,"tags":410},[33],[29,33],[29],{"code":38,"score":17,"supported":55,"title":412,"abstract":413,"tags":414},[206],[205,206],[28],{"code":416,"score":102,"supported":55,"title":417,"abstract":418,"tags":421},"H2",[],[419,420],"土壤","soil",[],{"code":423,"score":102,"supported":55,"title":424,"abstract":425,"tags":428},"H3",[],[426,427],"蒸散发","evapotranspiration",[],{"code":430,"score":102,"supported":55,"title":431,"abstract":432,"tags":435},"H7",[],[433,434],"气候变化","climate change",[],{"code":437,"score":21,"supported":55,"title":438,"abstract":439,"tags":441},"J1",[],[440],"农业规划",[],{"code":73,"score":22,"supported":14,"title":443,"abstract":444,"tags":445},[],[],[27],[447,448],"尼日尔 水稻 遥感 产量预测","Landsat NDVI 水稻 机器学习","尼日尔水稻遥感产量预测-4310","10.5281\u002Fzenodo.23149579",{"doi":450,"openalex_id":452,"authors":453,"venue":381,"cited_by_count":92,"oa_url":378,"card":456,"direction":315,"ingested_from":99},"W7220391503",[454],{"name":455,"orcid":9},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":457,"method":458,"finding":459,"direction":315,"opportunity":460},"结合遥感植被指数与机器学习，预测尼日尔萨赫勒四地区2010–2025年水稻产量。","Landsat NDVI\u002FEVI 加气象土壤变量，GEE与Python处理，比较","NDVI\u002FEVI与产量仅弱相关，模型精度区域差异大，植被指数呈明显季节与年际波动。","可引入时序深度学习与迁移学习，解决跨区域泛化差及植被指数解释力弱的问题。","2026-10-06T23:30:20.077977Z",{"id":463,"title":464,"url":465,"summary":466,"summary_zh":467,"content":9,"source_name":468,"source_url":465,"published_at":469,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":470,"sources":472,"tags":474,"primary_topic":476,"secondary_topics":477,"classification":480,"search_phrases":500,"slug":503,"view_count":152,"doi":504,"paper":505,"created_at":521},3164,"Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16182034","Accurate plant height estimation is important for monitoring crop growth and supporting precision agricultural management. Manual measurements are labor-intensive, while LiDAR-based methods are expensive and require complex processing. UAV photogrammetry provides a lower-cost alternative but remains challenging in flooded rice paddies because of canopy deformation and difficulties in terrain extraction. This study proposes Rice-STNet, a spatiotemporal deep learning framework for end-to-end rice plant height estimation using multi-temporal UAV RGB imagery. Rice-STNet integrates a convolutional neural network for spatial feature extraction, Time2Vec for temporal encoding, and a gated recurrent unit network for modeling temporal dependencies across observation dates. The framework was evaluated using field data collected from rice paddies over two growing seasons. Rice-STNet achieved an R2 of 0.97, a root mean squared error of 1.97 cm, and a mean absolute error of 1.14 cm. It outperformed random forest, support vector regression, a CNN-only baseline, and a UAV photogrammetry-based point-cloud approach. In addition, the framework generated high-resolution plant height maps for field-scale analysis of spatial growth variability. These results underscore the importance of jointly modeling spatial and temporal characteristics for continuously evolving crop traits. The proposed framework offers an accurate, scalable, and non-destructive solution for large-scale crop phenotyping and precision agriculture.","准确的株高估算对于监测作物生长和支持精准农业管理具有重要意义。人工测量劳动强度大，而基于激光雷达（LiDAR）的方法成本高昂且需要复杂的处理。无人机摄影测量提供了一种成本较低的替代方案，但在淹水稻田中仍面临挑战，原因在于冠层变形和地形提取困难。本研究提出了Rice-STNet，一种时空深度学习框架，用于利用多时相无人机RGB影像进行端到端水稻株高估算。Rice-STNet集成了用于空间特征提取的卷积神经网络、用于时间编码的Time2Vec，以及用于建模观测日期之间时间依赖关系的门控循环单元网络。该框架利用两个生长季从稻田采集的田间数据进行了评估。Rice-STNet取得了R²为0.97、均方根误差为1.97 cm、平均绝对误差为1.14 cm的结果。其性能优于随机森林、支持向量回归、仅使用CNN的基线方法以及基于无人机摄影测量的点云方法。此外，该框架生成了高分辨率株高图，用于田块尺度空间生长变异性分析。这些结果凸显了联合建模空间与时间特征对于持续变化的作物性状的重要性。所提出的框架为大规模作物表型分析和精准农业提供了一种准确、可扩展且非破坏性的解决方案。","Agriculture","2026-09-21T00:00:00Z",{"impact":19,"substance":114,"depth":19,"authority":115,"freshness":60,"relevant":22,"comment":471},"提出时空深度学习框架Rice-STNet，用多时相无人机RGB影像实现水稻株高高精度估算，方法新颖、数据跨两个生长季，对作物表型与精准农业有实用价值。",[473],{"name":468,"url":465},[27,28,29,248,475],"作物表型",{"code":32,"slug":33,"name":29,"path":34,"parent_code":35},[478,479],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":254,"slug":255,"name":256,"path":257,"parent_code":42},{"status":49,"locked":14,"version":50,"method":51,"evidence":481},{"candidates":482,"agricultural_evidence":55},[483,487,491,496],{"code":32,"score":19,"supported":55,"title":484,"abstract":485,"tags":486},[33],[29,342,33],[29],{"code":38,"score":17,"supported":55,"title":488,"abstract":489,"tags":490},[62],[141,62],[28],{"code":254,"score":138,"supported":55,"title":492,"abstract":493,"tags":495},[],[475,494],"crop phenotyping",[475,248],{"code":73,"score":74,"supported":55,"title":497,"abstract":498,"tags":499},[],[77,78],[27],[501,502],"无人机 RGB 水稻株高","Rice-STNet 水稻表型","无人机RGB水稻株高-3164","10.3390\u002Fagriculture16182034",{"doi":504,"openalex_id":506,"authors":507,"venue":468,"cited_by_count":92,"oa_url":465,"card":516,"direction":315,"ingested_from":99},"W7213887432",[508,511,513],{"name":509,"orcid":510},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":512,"orcid":9},"Noboru Noguchi",{"name":514,"orcid":515},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":517,"method":518,"finding":519,"direction":315,"opportunity":520},"提出Rice-STNet时空深度学习框架，用多时相无人机RGB影像估算水稻株高。","CNN提取空间特征，Time2Vec编码时间，GRU建模时序依赖，两季稻田数据验","R²达0.97、RMSE 1.97cm，优于随机森林、SVR、纯CNN及点云方法。","可迁移至其他作物与多源遥感融合，探索轻量化模型及实时田间部署。","2026-09-22T23:30:18.545958Z"]