[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5130":3,"related-5130":80},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":65,"slug":68,"view_count":69,"doi":8,"paper":70,"created_at":79},5130,"DefoliationCAM:面向葡萄藤食叶严重度实时评估的边缘AI系统 [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20879","Fuchen Li等提出DefoliationCAM(D-CAM),一种太阳能供电的边缘AI系统,用于估算葡萄藤树冠食叶程度并通过LoRa将结果传输至Web仪表盘。流水线使用YOLOX-Nano在4K图像中定位葡萄藤主干,并使用基于MobileNet的轻量级通道注意力分类器对320×320像素的斑块进行分类。29,674个田间采集斑块被标注为背景或四种损伤等级之一;合并中度和重度类别将类别不平衡比从约40:1降至8.8:1。合成增强使macro-F1从0.768提升至0.838。分类器以更少的参数量(1.08M vs 23.52M)在macro-F1上优于ResNet-50。利用TensorRT FP16在NVIDIA Jetson Orin Nano上每张4K图像处理时间约1.5秒,完整运行周期57-60秒。两台设备为期五周的田间部署验证了自主太阳能运行、LoRa通信和远程食叶监测的可行性。",null,"arXiv 2610.20879 2026 年 10 月 14 日","2026-10-14T00:00:00Z","论文",10,false,75,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,22,18,11,8,1,"预印本提出太阳能边缘AI系统，实现葡萄藤食叶严重度实时评估与LoRa远程监测，方法新颖、数据规模大、田间验证充分，具智慧农业应用价值。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","边缘计算","葡萄藤","病害评估",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":39,"locked":13,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,50,55,60],{"code":32,"score":19,"supported":45,"title":46,"abstract":48,"tags":49},true,[47],"葡萄",[47],[],{"code":51,"score":21,"supported":13,"title":52,"abstract":53,"tags":54},"I1",[],[],[26],{"code":56,"score":21,"supported":13,"title":57,"abstract":58,"tags":59},"I2",[],[],[27],{"code":61,"score":21,"supported":13,"title":62,"abstract":63,"tags":64},"I5",[],[],[28],[66,67],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",0,{"doi":8,"openalex_id":8,"authors":71,"venue":8,"cited_by_count":69,"oa_url":8,"card":72,"direction":76,"ingested_from":78},[],{"tldr":73,"method":74,"finding":75,"direction":76,"opportunity":77},"提出太阳能边缘AI系统DefoliationCAM，实时评估葡萄藤食叶严重度并远程传输。","YOLOX-Nano定位主干，MobileNet通道注意力分类，TensorRT","轻量分类器macro-F1达0.838，优于ResNet-50，田间部署验证可行。","智慧农业 \u002F 农业物联网","可探索多作物迁移、损伤等级细化及边缘模型自适应更新以提升泛化性。","agent","2026-10-17T00:13:44.932340Z",{"total":81,"page":21,"page_size":81,"items":82},6,[83,159,233,289,395,463],{"id":84,"title":85,"url":86,"summary":87,"summary_zh":88,"content":8,"source_name":89,"source_url":86,"published_at":90,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":91,"score_detail":92,"sources":97,"tags":99,"primary_topic":102,"secondary_topics":103,"classification":104,"search_phrases":131,"slug":134,"view_count":69,"doi":135,"paper":136,"created_at":158},5401,"A HIERARCHICAL DISTRIBUTED EDGE AI FRAMEWORK FOR REAL-TIME APPLE LEAF DISEASE CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr260506002g","The application of artificial intelligence (AI) in agriculture has transformed crop management, particularly in the detection of plant diseases. Apple trees, a key agricultural commodity, are vulnerable to various diseases, which can severely impact crop yields. Traditional disease detection methods, often reliant on manual inspections, are time-consuming and prone to error. In response, this study proposes a novel two-stage edge AI framework for apple leaf disease classification that integrates RGB imagery with distributed edge computing. The first stage performs binary classification to distinguish between healthy and diseased leaves, achieving an F1 score of 95.50%. This optimization is achieved by utilizing lightweight models on edge devices, thereby enhancing computational efficiency. The second stage employs a consensus-based multiclass classification approach, achieving a 96.44% F1 score in identifying specific diseases. This dual-stage system, supported by an edge AI architecture, ensures real-time disease detection while minimizing resource consumption and enhancing scalability in large-scale agricultural environments. The full system achieved a 95.50% accuracy and F1 score on the special dataset. The results demonstrate the system’s efficacy in controlled laboratory conditions, offering a promising solution for precise, real-time agricultural monitoring. This study underscores the potential of distributed edge AI systems for scalable and efficient disease detection in precision agriculture.","人工智能（AI）在农业中的应用已深刻改变了作物管理方式，尤其是在植物病害检测方面。苹果树作为重要的农业经济作物，易受多种病害侵袭，严重影响作物产量。传统的病害检测方法通常依赖人工检查，耗时且易出错。为此，本研究提出了一种新颖的两阶段边缘AI框架，用于苹果叶片病害分类，该框架将RGB图像与分布式边缘计算相结合。第一阶段执行二分类以区分健康叶片与患病叶片，F1分数达到95.50%。该优化通过在边缘设备上采用轻量级模型实现，从而提升了计算效率。第二阶段采用基于共识的多类分类方法，在识别具体病害方面F1分数达到96.44%。该双阶段系统在边缘AI架构的支持下，实现了实时病害检测，同时最大限度地降低了资源消耗，并增强了在大规模农业环境中的可扩展性。完整系统在专用数据集上达到了95.50%的准确率和F1分数。结果表明，该系统在受控实验室条件下具有有效性，为精准、实时的农业监测提供了一种有前景的解决方案。本研究凸显了分布式边缘AI系统在精准农业中实现可扩展且高效病害检测的潜力。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",76,{"impact":18,"substance":93,"depth":94,"authority":95,"freshness":20,"relevant":21,"comment":96},21,17,12,"该研究提出两级边缘AI框架，在苹果叶片病害识别上取得95%以上F1值，方法新颖、数据可靠，对精准农业实时监测有参考价值，但尚处实验室验证阶段，产业影响有限。",[98],{"name":89,"url":86},[26,27,28,100,101],"作物病害识别","苹果病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":105},{"candidates":106,"agricultural_evidence":45},[107,113,120,125],{"code":32,"score":18,"supported":45,"title":108,"abstract":110,"tags":112},[109],"apple",[34,111,109],"苹果",[101],{"code":51,"score":114,"supported":45,"title":115,"abstract":116,"tags":119},7,[],[117,118],"精准农业","precision agriculture",[26],{"code":61,"score":114,"supported":45,"title":121,"abstract":122,"tags":124},[],[28,123],"edge computing",[28],{"code":56,"score":126,"supported":45,"title":127,"abstract":128,"tags":130},5,[],[129],"artificial intelligence",[100,27],[132,133],"苹果叶片病害 边缘AI","分布式边缘计算 病害分类","苹果叶片病害边缘AI-5401","10.22190\u002Ffuacr260506002g",{"doi":135,"openalex_id":137,"authors":138,"venue":89,"cited_by_count":69,"oa_url":86,"card":151,"direction":156,"ingested_from":157},"W7222964752",[139,142,145,148],{"name":140,"orcid":141},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":143,"orcid":144},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":146,"orcid":147},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":149,"orcid":150},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":152,"method":153,"finding":154,"direction":76,"opportunity":155},"提出两级边缘AI框架，用RGB图像实时分类苹果叶片病害。","分布式边缘计算+轻量模型，先二分类再共识多分类。","两级系统准确率与F1均达95.50%，多分类F1为96.44%。","仅在受控实验室验证，可延伸至田间复杂光照与多作物泛化及边缘能耗优化。","农业人工智能与决策模型","openalex","2026-10-20T23:30:33.830748Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":8,"source_name":165,"source_url":162,"published_at":166,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":167,"score_detail":168,"sources":174,"tags":176,"primary_topic":179,"secondary_topics":180,"classification":181,"search_phrases":202,"slug":205,"view_count":206,"doi":207,"paper":208,"created_at":232},2499,"Real-time on-tree Korla pear grading with a shared ordinal–anomaly descriptor field","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112371","On-tree grading of Korla fragrant pears couples two decisions of different nature: a gradual Grade-A\u002FGrade-B appearance transition and a Grade-C surface-defect judgement, both made under illumination change, occlusion and scale variation. Detectors that treat the fruit as a single class, and graders that place the three grades on one flat classification axis, optimise a small A\u002FB deviation and an A\u002FC defect error through the same geometry and leave no explicit account of what ordinal and defect information each spatial location should preserve. We address this by adding an explicit ordinal–anomaly descriptor field to the shared feature hierarchy. A shallow module generates three channels – ordinal tendency, defect tendency and foreground confidence – that condition four downstream detector stages, and a hierarchical head converts the two kinds of evidence into normalised grade probabilities. On the orchard-disjoint KPR-3 dataset (3826 images, 12,458 instances, three commercial orchards), the model reaches 94.0% mAP@50 and 92.6% matched-instance grade accuracy, and lowers the unsafe-pick rate from 4.8% to 2.1%. On a Jetson Orin Nano at 15 W, the INT8 engine runs at 93.1% mAP@50 and sustains 42 FPS of end-to-end pipelined throughput. Monocular sensing remains a key limitation under severe front–back fruit overlap.","库尔勒香梨的树上分级耦合了两个性质不同的决策：渐变的A级\u002FB级外观过渡，以及C级表面缺陷判定，二者均在光照变化、遮挡和尺度变化下做出。将果实视为单一类别的检测器，以及将三个等级置于同一扁平分类轴上的分级器，通过相同的几何结构优化较小的A\u002FB偏差和A\u002FC缺陷误差，却未明确说明每个空间位置应保留何种序数信息和缺陷信息。我们通过在共享特征层级中增加一个显式的序数–异常描述符场来解决这一问题。一个浅层模块生成三个通道——序数倾向、缺陷倾向和前景置信度——用以调节四个下游检测器阶段，一个层级式头部将两类证据转换为归一化等级概率。在果园不相交的KPR-3数据集（3826幅图像、12458个实例、三个商业果园）上，模型达到94.0% mAP@50和92.6%的匹配实例等级准确率，并将不安全采摘率从4.8%降至2.1%。在15 W的Jetson Orin Nano上，INT8引擎以93.1% mAP@50运行，并维持42 FPS的端到端流水线吞吐量。在严重前后果实重叠情况下，单目感知仍是主要局限。","Computers and Electronics in Agriculture","2026-09-14T00:00:00Z",83,{"impact":18,"substance":169,"depth":170,"authority":171,"freshness":172,"relevant":21,"comment":173},23,19,14,9,"提出序数-异常描述子场的树上香梨实时分级方法，在自建KPR-3数据集与Jetson边缘端验证，方法新颖、数据扎实，对果园采摘机器人有直接参考价值。",[175],{"name":165,"url":162},[26,27,28,177,178],"库尔勒香梨","水果分级",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":182},{"candidates":183,"agricultural_evidence":45},[184,190,194,198],{"code":32,"score":185,"supported":45,"title":186,"abstract":187,"tags":189},3,[],[188],"orchard",[],{"code":51,"score":21,"supported":13,"title":191,"abstract":192,"tags":193},[],[],[26],{"code":56,"score":21,"supported":13,"title":195,"abstract":196,"tags":197},[],[],[27],{"code":61,"score":21,"supported":13,"title":199,"abstract":200,"tags":201},[],[],[28],[203,204],"农业人工智能 库尔勒香梨 智慧农业 水果分级","农业人工智能 库尔勒香梨","农业人工智能库尔勒香梨智慧农业水果分级-2499",4,"10.1016\u002Fj.compag.2026.112371",{"doi":207,"openalex_id":209,"authors":210,"venue":165,"cited_by_count":69,"oa_url":162,"card":227,"direction":76,"ingested_from":157},"W7212908812",[211,213,216,218,220,222,224],{"name":212,"orcid":8},"Bingyu Cao",{"name":214,"orcid":215},"Peng Zhou","https:\u002F\u002Forcid.org\u002F0000-0002-6345-5307",{"name":217,"orcid":8},"Zhikai Yang",{"name":219,"orcid":8},"Wei Chen",{"name":221,"orcid":8},"Yingchao Wang",{"name":223,"orcid":8},"Mingqi Kan",{"name":225,"orcid":226},"Haiyong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-5262-4208",{"tldr":228,"method":229,"finding":230,"direction":76,"opportunity":231},"提出共享序数-异常描述子场，实现树上库尔勒香梨实时分级。","在共享特征层级加入序数、缺陷、前景三通道描述子，用KPR-3数据集训练。","mAP@50达94.0%，分级准确率92.6%，不安全采摘率从4.8%降至2.1%。","可探索多模态或深度传感融合，解决严重前后遮挡下的单目感知局限。","2026-09-15T23:30:01.440708Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":8,"content":8,"source_name":238,"source_url":8,"published_at":239,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":240,"score_detail":241,"sources":244,"tags":246,"primary_topic":249,"secondary_topics":250,"classification":251,"search_phrases":277,"slug":280,"view_count":185,"doi":8,"paper":281,"created_at":288},2490,"Lightweight Detection of Blueberries at Different Maturity Stages in Complex Orchard Environments(YOLOv12n+SHSA2C2f+知识蒸馏)","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F1949","云南农业大学大数据学院联合云南省农业大数据工程技术研究中心 2026 年 9 月 10 日在《Agriculture》发表。针对小果、密集、遮挡、色彩过渡细微等复杂田间条件下的蓝莓成熟期检测难题,构建 4680 图像 60573 标注框田间数据集,重新设计 YOLOv12n 的 P3\u002FP4\u002FP5 检测结构为 P2\u002FP3\u002FP4 架构,引入轻量化 SHSA2C2f 单头自注意力特征增强模块,DINOv3 (ViT-S\u002F16) 引导的非对称知识蒸馏。精度导向 M4 模型 mAP@0.5 达 92.68%±0.04%、mAP@0.5:0.95 86.38%±0.10%,参数量仅 0.79 M;经 TensorRT FP16 转换后保留 92.75% mAP@0.5,可在 Jetson Orin Nano 上以 15.9 FPS 运行。","MDPI Agriculture 2026-09-10","2026-09-09T16:00:00Z",80,{"impact":18,"substance":169,"depth":18,"authority":242,"freshness":20,"relevant":21,"comment":243},13,"面向复杂果园的蓝莓成熟期轻量化检测研究，方法新颖、数据规模扎实且给出边缘部署实测性能，具备较高专业参考价值。",[245],{"name":238,"url":236},[26,27,28,247,248],"目标检测","蓝莓",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":252},{"candidates":253,"agricultural_evidence":45},[254,258,264,269,273],{"code":32,"score":172,"supported":45,"title":255,"abstract":256,"tags":257},[188],[],[248],{"code":259,"score":185,"supported":45,"title":260,"abstract":261,"tags":263},"I6",[],[262],"农业大数据",[],{"code":56,"score":265,"supported":13,"title":266,"abstract":267,"tags":268},2,[],[],[27,247],{"code":51,"score":21,"supported":13,"title":270,"abstract":271,"tags":272},[],[],[26],{"code":61,"score":21,"supported":13,"title":274,"abstract":275,"tags":276},[],[],[28],[278,279],"农业人工智能 智慧农业 目标检测 边缘计算","农业人工智能 智慧农业","农业人工智能智慧农业目标检测边缘计算-2490",{"doi":8,"openalex_id":8,"authors":282,"venue":8,"cited_by_count":69,"oa_url":8,"card":283,"direction":156,"ingested_from":78},[],{"tldr":284,"method":285,"finding":286,"direction":156,"opportunity":287},"提出轻量YOLOv12n改进模型，实现复杂果园中多成熟期蓝莓的实时检测。","4680张田间图像数据集，P2\u002FP3\u002FP4结构、SHSA2C2f模块与DINOv","M4模型mAP@0.5达92.68%，仅0.79M参数，Jetson Orin Nano上15.9 ","可探索多作物通用轻量检测框架，或结合成熟度计数用于产量预测与采摘决策。","2026-09-15T00:04:27.061523Z",{"id":290,"title":291,"url":292,"summary":293,"summary_zh":294,"content":8,"source_name":295,"source_url":292,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":296,"score_detail":297,"sources":299,"tags":301,"primary_topic":305,"secondary_topics":310,"classification":317,"search_phrases":368,"slug":371,"view_count":21,"doi":372,"paper":373,"created_at":394},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science",81,{"impact":18,"substance":17,"depth":18,"authority":171,"freshness":172,"relevant":21,"comment":298},"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[300],{"name":295,"url":292},[26,27,302,303,304],"产量预测","多模态融合","遥感",{"code":56,"slug":306,"name":307,"path":308,"parent_code":309},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[311,312],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":313,"slug":314,"name":315,"path":316,"parent_code":309},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":39,"locked":13,"version":40,"method":41,"evidence":318},{"candidates":319,"agricultural_evidence":45},[320,328,333,339,343,350,356,362],{"code":56,"score":19,"supported":45,"title":321,"abstract":322,"tags":327},[],[323,324,325,326],"深度学习","机器学习","machine learning","deep learning",[27,303],{"code":32,"score":172,"supported":45,"title":329,"abstract":330,"tags":332},[],[111,331,188,109],"芒果",[],{"code":313,"score":20,"supported":45,"title":334,"abstract":335,"tags":338},[],[336,337],"无人机多光谱","multispectral",[302,304],{"code":51,"score":114,"supported":45,"title":340,"abstract":341,"tags":342},[],[117,118],[26],{"code":344,"score":81,"supported":45,"title":345,"abstract":346,"tags":349},"H2",[],[347,348],"土壤","soil",[],{"code":61,"score":81,"supported":45,"title":351,"abstract":352,"tags":355},[],[353,354],"物联网","IoT",[],{"code":357,"score":185,"supported":45,"title":358,"abstract":359,"tags":361},"H6",[],[360],"农业生态",[],{"code":363,"score":185,"supported":45,"title":364,"abstract":365,"tags":367},"H7",[],[366],"气候适应",[],[369,370],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":372,"openalex_id":374,"authors":375,"venue":295,"cited_by_count":69,"oa_url":292,"card":389,"direction":76,"ingested_from":157},"W7221795850",[376,379,381,383,385,387],{"name":377,"orcid":378},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":380,"orcid":8},"Umarfarooque Momin",{"name":382,"orcid":8},"Sudeep Kumar E",{"name":384,"orcid":8},"Itfaq Ahmad Mir",{"name":386,"orcid":8},"Ab Rouf Khan",{"name":388,"orcid":8},"Ghulam Mohammad Mir",{"tldr":390,"method":391,"finding":392,"direction":156,"opportunity":393},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","2026-10-15T23:30:08.750140Z",{"id":396,"title":397,"url":398,"summary":399,"summary_zh":400,"content":8,"source_name":401,"source_url":398,"published_at":402,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":403,"score_detail":404,"sources":406,"tags":408,"primary_topic":412,"secondary_topics":413,"classification":416,"search_phrases":436,"slug":439,"view_count":21,"doi":440,"paper":441,"created_at":462},4808,"Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1898342","Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.","农业病害是种植者面临的重大问题，会对果实和叶片造成严重损害，导致产量损失。因此，开发植物病害早期检测系统是一个至关重要的问题。本研究提出了一种基于深度学习的新型混合模型，用于植物病害的检测与分割，具体针对苹果园中的苹果黑星病和葡萄园中的霜霉病。该早期病害检测系统的开发使用了2023年5月至2024年12月期间通过无人机在土耳其泰基尔达省农业区域采集的多光谱影像数据。数据集包含3625幅苹果园图像和5625幅葡萄园图像。所用DJI Phantom 4多光谱无人机配备五个光谱波段（蓝、绿、红、红边和近红外），用于捕捉光谱丰富度和时间变化过程。本研究提出了一种专门开发的深度学习架构，用于基于时间序列的多光谱无人机影像病害检测与分割。植物随时间的变化提供了关于植物病害发生的重要信息。因此，本研究使用时间序列从植物随时间的变化中提取特征。所提出的模型架构专门设计以利用时间序列信息，从而能够稳健地跟踪作物健康状况随时间的变化。使用苹果病害数据集训练的模型达到了82.05%的平均交并比（IoU）值，而使用葡萄园病害数据集训练的模型达到了79.67%的IoU值。研究结果凸显了将无人机获取的多光谱时间序列数据与先进深度学习模型相结合，在精准农业中实现可扩展、准确且及时的植物病害检测方面的有效性。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",77,{"impact":16,"substance":93,"depth":18,"authority":242,"freshness":172,"relevant":21,"comment":405},"该研究提出基于多光谱时序影像的新型深度学习模型，实现果园与葡萄园病害早期检测，数据规模大、方法新颖，对精准农业病害预警具有参考价值。",[407],{"name":401,"url":398},[26,409,27,410,411],"无人机","遥感监测","病害预警",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[414,415],{"code":56,"slug":306,"name":307,"path":308,"parent_code":309},{"code":313,"slug":314,"name":315,"path":316,"parent_code":309},{"status":39,"locked":13,"version":40,"method":41,"evidence":417},{"candidates":418,"agricultural_evidence":45},[419,423,428,432],{"code":32,"score":94,"supported":45,"title":420,"abstract":421,"tags":422},[109],[111,47,109],[],{"code":56,"score":424,"supported":45,"title":425,"abstract":426,"tags":427},15,[326],[323,326],[27],{"code":313,"score":95,"supported":45,"title":429,"abstract":430,"tags":431},[337],[337],[410],{"code":51,"score":114,"supported":45,"title":433,"abstract":434,"tags":435},[],[117,118],[26],[437,438],"苹果黑星病 无人机 多光谱","葡萄园 霜霉病 深度学习","苹果黑星病无人机多光谱-4808","10.15832\u002Fankutbd.1898342",{"doi":440,"openalex_id":442,"authors":443,"venue":401,"cited_by_count":69,"oa_url":455,"card":456,"direction":76,"ingested_from":157},"W7221558726",[444,447,450,452],{"name":445,"orcid":446},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":448,"orcid":449},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":451,"orcid":8},"Fatih Sinan Bir",{"name":453,"orcid":454},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":457,"method":458,"finding":459,"direction":460,"opportunity":461},"提出一种基于无人机多光谱时序影像的深度学习混合模型，实现苹果黑星病和葡萄霉病的早期检测与分割。","DJI Phantom 4多光谱无人机采集时序影像，构建时序深度学习分割模型。","苹果病IoU达82.05%，葡萄病达79.67%，验证多光谱时序数据有效性。","农业遥感与作物表型","可探索多作物、多病害的时序多光谱通用模型，并融合气象与地面数据提升早期预警能力。","2026-10-13T23:30:10.242467Z",{"id":464,"title":465,"url":466,"summary":467,"summary_zh":468,"content":8,"source_name":469,"source_url":466,"published_at":470,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":471,"score_detail":472,"sources":475,"tags":477,"primary_topic":480,"secondary_topics":481,"classification":483,"search_phrases":499,"slug":502,"view_count":69,"doi":503,"paper":504,"created_at":528},4744,"An empirical performance comparison of deep learning models for apple leaf disease recognition","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10573-4","Currently, Biotic and abiotic factors, in agriculture, are estimated to be responsible for around 22% of the total losses in crop production. It is therefore very important, but at the same time very difficult for farmers to identify these constraints at the earliest possible stage. The most recent developments in computer vision have made it possible to identify as well as classify plant lesions at a primary level. Various deep learning techniques have made it possible to detect biotic stress in apple plant leaves with a very high degree of accuracy. Hence, automated segmentation of images of diseased leaves has become a leading research theme all over the world. In this paper, a dataset from FGVC7, which is an open, source dataset and contains four different classes of leaf diseases of the apple crop is used to measure the performance of the proposed model. A three, step image preprocessing procedure is conducted, which involves image enhancement, removal of background noise, and object identification through a variety of approaches. Using UNet, PSPNet, and UNet++, disease areas are identified. UNet + + delivering the most precise object segmentation. The segmented patch data are then fed into a fusion, based classification model as input. Patch segmentation makes it possible to separate the various disease areas, thus increasing the classification accuracy. The proposed framework combines several CNN architectures, namely, VGG16, InceptionV3, AlexNet, and GoogleNet, in order to take advantage of their complementary strengths, then a Vision Transformer (ViT) is used to identify distinct local features via early feature fusion. After this, the efficiency of the proposed model is check in comparison with the pre-trained CNN models individually. Comparing with all other models the proposed model has shown the accuracy of highest order i.e. 98.85%, clearly out performing individual CNN models.","目前，农业中的生物和非生物因素估计约占作物生产总损失的22%。因此，农民尽早识别这些限制因素非常重要，但同时也非常困难。计算机视觉的最新发展使得在初级水平上识别和分类植物病变成为可能。各种深度学习技术使得以极高准确度检测苹果植株叶片的生物胁迫成为可能。因此，患病叶片图像的自动分割已成为世界范围内的前沿研究主题。本文使用来自FGVC7的数据集来衡量所提出模型的性能，该数据集是一个开放源数据集，包含苹果作物的四类不同叶片病害。进行了三步图像预处理，包括图像增强、背景噪声去除以及通过多种方法进行目标识别。使用UNet、PSPNet和UNet++识别病害区域，其中UNet++提供了最精确的目标分割。然后将分割后的图像块数据作为输入馈入基于融合的分类模型。图像块分割使得能够分离不同的病害区域，从而提高分类准确率。所提出的框架结合了多种CNN架构，即VGG16、InceptionV3、AlexNet和GoogleNet，以利用它们互补的优势，然后使用视觉Transformer（ViT）通过早期特征融合来识别不同的局部特征。此后，将所提出模型的效率与各个预训练CNN模型进行比较。与所有其他模型相比，所提出的模型显示出最高阶的准确率，即98.85%，明显优于各个单独的CNN模型。","Discover Computing","2026-10-10T00:00:00Z",69,{"impact":95,"substance":473,"depth":16,"authority":242,"freshness":20,"relevant":21,"comment":474},20,"方法组合（UNet++分割+CNN与ViT融合）与98.85%准确率有参考价值，但属实验室数据集验证，产业落地影响有限，可作为技术前沿资讯收录。",[476],{"name":469,"url":466},[26,27,478,323,479],"计算机视觉","苹果病害识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[482],{"code":56,"slug":306,"name":307,"path":308,"parent_code":309},{"status":39,"locked":13,"version":40,"method":41,"evidence":484},{"candidates":485,"agricultural_evidence":45},[486,491,495],{"code":56,"score":473,"supported":45,"title":487,"abstract":488,"tags":490},[326],[323,478,326,489],"computer vision",[27,323,478],{"code":32,"score":171,"supported":45,"title":492,"abstract":493,"tags":494},[109],[111,109],[],{"code":51,"score":21,"supported":13,"title":496,"abstract":497,"tags":498},[],[],[26],[500,501],"苹果叶片病害 深度学习","FGVC7 苹果病害 数据集","苹果叶片病害深度学习-4744","10.1007\u002Fs10791-026-10573-4",{"doi":503,"openalex_id":505,"authors":506,"venue":469,"cited_by_count":69,"oa_url":522,"card":523,"direction":76,"ingested_from":157},"W7221353656",[507,509,512,514,516,519],{"name":508,"orcid":8},"Apoorva Arora",{"name":510,"orcid":511},"Vinay Gautam","https:\u002F\u002Forcid.org\u002F0000-0002-0258-5132",{"name":513,"orcid":8},"Anand Muni Mishra",{"name":515,"orcid":8},"Santar Pal Singh",{"name":517,"orcid":518},"Yadvendra Pratap Singh","https:\u002F\u002Forcid.org\u002F0000-0001-6396-3355",{"name":520,"orcid":521},"Mukund Pratap Singh","https:\u002F\u002Forcid.org\u002F0000-0001-5877-9510","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs10791-026-10573-4.pdf",{"tldr":524,"method":525,"finding":526,"direction":156,"opportunity":527},"用UNet++分割苹果病叶并融合多种CNN与ViT分类，实现98.85%识别准确率。","FGVC7数据集，UNet\u002FPSPNet\u002FUNet++分割，VGG16等CNN与","UNet++分割最准，融合模型准确率达98.85%，优于单个CNN模型。","可探索轻量化分割-分类联合模型在田间移动端的实时部署与多作物泛化。","2026-10-12T23:30:09.091475Z"]