[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1878":3,"related-1878":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":37,"classification":44,"search_phrases":68,"slug":71,"view_count":72,"doi":73,"paper":74,"created_at":100},1878,"Decoding Electro-Priming responses in cotton using an integrated taguchi-machine learning framework for optimizing seed performance","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112362","Decoding Electro-Priming responses in cotton using an integrated taguchi-machine learning framework for optimizing seed performance。Computers and Electronics in Agriculture","利用集成田口-机器学习框架解析棉花电引发响应以优化种子性能。《农业中的计算机与电子》",null,"Computers and Electronics in Agriculture","2026-09-07T00:00:00Z","论文",10,false,62,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,18,16,14,2,1,"研究结合田口法与机器学习优化棉花电引发种子处理，方法新颖，但发表于2026年9月7日，时效性较低，影响范围限于特定作物领域。",[25],{"name":10,"url":6},[27,28,29,30],"智慧农业","农业人工智能","棉花","种子处理",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,57,63],{"code":32,"score":51,"supported":52,"title":53,"abstract":55,"tags":56},15,true,[54],"cotton",[29,54],[29],{"code":39,"score":51,"supported":52,"title":58,"abstract":60,"tags":62},[59],"machine learning",[61,59],"机器学习",[28],{"code":64,"score":22,"supported":14,"title":65,"abstract":66,"tags":67},"I1",[],[],[27],[69,70],"农业人工智能 智慧农业 种子处理 棉花","农业人工智能 智慧农业","农业人工智能智慧农业种子处理棉花-1878",3,"10.1016\u002Fj.compag.2026.112362",{"doi":73,"openalex_id":75,"authors":76,"venue":10,"cited_by_count":92,"oa_url":9,"card":93,"direction":97,"ingested_from":99},"W7211870713",[77,80,83,85,87,90],{"name":78,"orcid":79},"Muhammad Aasım","https:\u002F\u002Forcid.org\u002F0000-0002-8524-9029",{"name":81,"orcid":82},"Ramazan Katırcı","https:\u002F\u002Forcid.org\u002F0000-0003-2448-011X",{"name":84,"orcid":9},"Salma Naimatullah Soomro",{"name":86,"orcid":9},"Sabeen Rehman Soomro",{"name":88,"orcid":89},"Ahmet Say","https:\u002F\u002Forcid.org\u002F0000-0001-5259-7580",{"name":91,"orcid":9},"Seyid Amjad Ali",0,{"tldr":94,"method":95,"finding":96,"direction":97,"opportunity":98},"用田口-机器学习框架优化棉花种子电引发处理，提升种子性能。","田口实验设计与机器学习集成框架。","电引发参数可优化，显著提升棉花种子性能。","农业人工智能与决策模型","可扩展至其他作物或种子处理方式，探索机器学习在农业实验优化中的应用。","openalex","2026-09-08T23:30:01.361561Z",{"total":102,"page":22,"page_size":102,"items":103},6,[104,158,243,365,420,496],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":9,"content":9,"source_name":109,"source_url":9,"published_at":9,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":114,"tags":116,"primary_topic":119,"secondary_topics":120,"classification":122,"search_phrases":145,"slug":148,"view_count":92,"doi":9,"paper":149,"created_at":157},4966,"基于改进YOLO 11n模型的棉花田间复杂环境障碍物检测方法","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455619.html","韩科立、王振坤等(中国农业机械化科学研究院集团有限公司;现代农装科技股份有限公司;农业装备技术全国重点实验室)针对棉花田间复杂环境障碍物被遮挡致准确检测难、边缘设备算力有限的问题,提出一种基于改进YOLO 11n模型的田间障碍物检测方法。采用StarNet作为主要特征提取网络并引入DBA模块增强多尺度特征交互能力;使用KAGNConv替换C3k2瓶颈结构增强灵活性与可解释性;集成分离与增强注意力模块SEAM至检测头增强遮挡场景能力。试验结果表明,改进模型YOLO 11n-SKS精确率、召回率、mAP50、mAP50-95分别提升2.3、2.1、1.3、1.4个百分点,达到91.7%、88.3%、91.9%、62.3%。","《农业机械学报》",71,{"impact":19,"substance":112,"depth":18,"authority":20,"freshness":21,"relevant":22,"comment":113},21,"改进YOLO 11n实现棉花田间遮挡障碍物检测，方法新颖、指标提升明确，属农业人工智能细分领域实质进展，但发布日期未知、时效性偏弱。",[115],{"name":109,"url":107},[27,28,29,117,118],"障碍物检测","采棉机",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[121],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":123},{"candidates":124,"agricultural_evidence":52},[125,129,134,141],{"code":32,"score":17,"supported":52,"title":126,"abstract":127,"tags":128},[29],[29],[29],{"code":39,"score":17,"supported":52,"title":130,"abstract":132,"tags":133},[131],"YOLO",[131],[28],{"code":135,"score":102,"supported":52,"title":136,"abstract":137,"tags":140},"F5",[],[138,139],"农业机械","机械化",[],{"code":64,"score":22,"supported":14,"title":142,"abstract":143,"tags":144},[],[],[27],[146,147],"中国农业机械化科学研究院 采棉机 障碍物检测","YOLO 11n 棉花 田间障碍物","中国农业机械化科学研究院采棉机障碍物检测-4966",{"doi":9,"openalex_id":9,"authors":150,"venue":9,"cited_by_count":92,"oa_url":9,"card":151,"direction":97,"ingested_from":156},[],{"tldr":152,"method":153,"finding":154,"direction":97,"opportunity":155},"提出改进YOLO 11n模型，实现棉花田间复杂遮挡环境下障碍物高精度检测。","以StarNet为骨干，引入DBA、KAGNConv与SEAM注意力模块，改进Y","改进模型精确率91.7%、召回率88.3%、mAP50达91.9%，各项指标均提升。","可探索轻量化模型在边缘设备实时部署，并扩展至多作物多类障碍物检测。","agent","2026-10-15T00:06:08.577388Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":163,"content":9,"source_name":164,"source_url":161,"published_at":165,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":166,"score_detail":167,"sources":171,"tags":173,"primary_topic":176,"secondary_topics":177,"classification":179,"search_phrases":208,"slug":210,"view_count":72,"doi":211,"paper":212,"created_at":242},2288,"Field-based deep learning classification of cotton and weeds for machine-vision-assisted intra-row weed management","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102567","Timely and precise weed management is essential for reducing crop-weed competition, labour requirements, and unnecessary weed-control inputs in cotton production. Reliable discrimination between cotton plants and weeds is a prerequisite for automated intra-row weed management. This study evaluated two pretrained convolutional neural network models, MobileNetV2 and DenseNet169, for binary classification of cotton and weeds using field-acquired RGB images. Images were collected from a farmer-managed cotton field in Haryana and an experimental cotton field at ICAR-Indian Agricultural Research Institute, New Delhi, during May-September 2025 under natural field conditions. The dataset comprised 2,195 weed images representing six predominant weed species and 1,211 cotton images. Images were classified into two operational classes, cotton and weed. Training images were augmented to address the original class imbalance, whereas validation and test images were retained without augmentation. Transfer learning was used to fine-tune both models, and performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and inference time. Both models achieved high classification performance. DenseNet169 attained a test accuracy of 99.47%, compared with 98.27% for MobileNetV2. The results indicate that pretrained CNNs can provide accurate image-level discrimination between cotton and weed vegetation under the investigated field conditions. DenseNet169 therefore shows promise as a visual-perception component for machine-vision-assisted intra-row weed management. However, the present study is limited to image-level classification and does not demonstrate plant localization, continuous machine operation, actuator coordination, or field-scale weed removal. Further validation under independent locations, varying weed densities, illumination conditions, machine travel speeds, and complete perception-decision-actuation pipelines is required.","及时、精准的杂草管理对于减少棉花生产中的棉草竞争、劳动力需求和不必要的除草投入至关重要。可靠地区分棉花植株与杂草是实现行内自动化杂草管理的前提。本研究评估了两种预训练卷积神经网络模型——MobileNetV2和DenseNet169，利用田间采集的RGB图像对棉花与杂草进行二分类。图像于2025年5月至9月期间，在自然田间条件下，采集自哈里亚纳邦一处农民管理的棉田以及新德里ICAR-印度农业研究所的实验棉田。数据集包含2，195幅杂草图像，涵盖六种主要杂草种类，以及1，211幅棉花图像。图像被分为棉花和杂草两个操作类别。训练图像经过增强处理以解决原始类别不平衡问题，而验证和测试图像则保留未增强状态。采用迁移学习对两种模型进行微调，并使用准确率、精确率、召回率、F1分数、混淆矩阵和推理时间评估性能。两种模型均取得了较高的分类性能。DenseNet169的测试准确率达到99.47%，而MobileNetV2为98.27%。结果表明，预训练卷积神经网络能够在所研究的田间条件下实现棉花与杂草植被在图像层面的准确区分。因此，DenseNet169有望作为机器视觉辅助行内杂草管理的视觉感知组件。然而，本研究仅限于图像层面的分类，并未展示植株定位、机器连续作业、执行器协调或田间规模除草。仍需在独立地点、不同杂草密度、光照条件、机器行进速度以及完整的感知-决策-执行流程下进行进一步验证。","Smart Agricultural Technology","2026-09-11T00:00:00Z",67,{"impact":17,"substance":18,"depth":19,"authority":168,"freshness":169,"relevant":22,"comment":170},13,8,"基于田间RGB图像的棉花与杂草深度学习分类研究，DenseNet169测试准确率达99.47%，方法扎实但仅限图像级分类，尚缺定位与执行环节验证，属细分领域技术进展。",[172],{"name":164,"url":161},[27,28,29,174,175],"杂草识别","机器视觉",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[178],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":180},{"candidates":181,"agricultural_evidence":52},[182,186,191,198,204],{"code":32,"score":51,"supported":52,"title":183,"abstract":184,"tags":185},[54],[29,54],[29],{"code":39,"score":13,"supported":52,"title":187,"abstract":189,"tags":190},[188],"deep learning",[],[28,175],{"code":192,"score":193,"supported":52,"title":194,"abstract":195,"tags":197},"F4",4,[],[196],"除草",[174],{"code":199,"score":72,"supported":52,"title":200,"abstract":201,"tags":203},"A4",[],[202],"花生",[],{"code":64,"score":22,"supported":14,"title":205,"abstract":206,"tags":207},[],[],[27],[209,70],"农业人工智能 智慧农业 机器视觉 杂草识别","农业人工智能智慧农业机器视觉杂草识别-2288","10.1016\u002Fj.atech.2026.102567",{"doi":211,"openalex_id":213,"authors":214,"venue":164,"cited_by_count":92,"oa_url":161,"card":237,"direction":97,"ingested_from":99},"W7212315230",[215,217,220,223,226,228,231,233,235],{"name":216,"orcid":9},"Shaik Nasreen",{"name":218,"orcid":219},"Roaf Ahmad Parray","https:\u002F\u002Forcid.org\u002F0000-0002-8303-1990",{"name":221,"orcid":222},"Parveen Dhanger","https:\u002F\u002Forcid.org\u002F0000-0001-5250-0275",{"name":224,"orcid":225},"Rishi Raj","https:\u002F\u002Forcid.org\u002F0009-0002-7918-1141",{"name":227,"orcid":9},"Tapan Kumar Khura",{"name":229,"orcid":230},"P. Sahoo","https:\u002F\u002Forcid.org\u002F0000-0002-3888-8506",{"name":232,"orcid":9},"Tushar Dhar",{"name":234,"orcid":9},"Prajwal R",{"name":236,"orcid":9},"Sripriyanka S. Nalla",{"tldr":238,"method":239,"finding":240,"direction":97,"opportunity":241},"用MobileNetV2和DenseNet169对田间棉花与杂草图像做二分类，验证机器视觉除草可行性","迁移学习微调两种预训练CNN，使用2025年田间RGB图像共3406张。","DenseNet169测试准确率达99.47%，优于MobileNetV2的98.27%。","可延伸至植株定位、多光照与密度条件下的感知-决策-执行全流程田间验证。","2026-09-13T23:30:04.183782Z",{"id":244,"title":245,"url":246,"summary":247,"summary_zh":248,"content":9,"source_name":249,"source_url":246,"published_at":250,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":251,"score_detail":252,"sources":255,"tags":257,"primary_topic":260,"secondary_topics":261,"classification":268,"search_phrases":320,"slug":323,"view_count":72,"doi":324,"paper":325,"created_at":364},1325,"Changing pest dynamics and pesticide use in cotton: Challenges and sustainable management","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.16195","Cotton (Gossypium spp.) is one of the world’s most important fibre crops, yet its sustainability is increasingly challenged by evolving pest complexes, intensified pesticide use, climate change and climate variability. The evidence indicates current knowledge on pest dynamics, pesticide dependence and ecological interactions in cotton agroecosystems, highlighting the shift from bollworm-dominated pest complexes to the increasing prevalence of secondary pests following the widespread adoption of Bacillus thuringiensis (Bt) cotton. Although Bt (Cry toxin)-based transgenic cotton technology initially reduced insecticide use against the bollworm complex, primarily lepidopteran species, the emergence of resistance among bollworms and the upsurge of certain sucking pests in recent decades have reinstated insecticide dependence for pest management. This has led to ecological imbalance, non-target toxicity, the decline of pollinator populations and natural enemy communities, biodiversity loss, environmental contamination, accumulation of residues in products and yield challenges, in addition to increased production costs. The review emphasises the critical role of integrated pest management (IPM) strategies that integrate biological control, habitat diversification, resistant cultivars and threshold-based pesticide applications to restore ecological stability. Alternative approaches such as botanical pesticides, nanoformulations and plant volatile-mediated pest regulation are highlighted as promising tools for sustainable pest control. Advances in precision agriculture, including artificial intelligence (AI), machine learning and unmanned aerial vehicle (UAV)-based pesticide delivery systems, have the potential to improve pest surveillance and reduce chemical inputs. Supply-chain procurement, certification, traceability and consumer demand can encourage lower-pesticide production, although these mechanisms require fair price incentives to avoid transferring compliance costs to smallholders. Sustainable cotton therefore requires region-specific, climate-resilient, evidence-based IPM supported by extension, market incentives, resistance monitoring and coordinated policy.","棉花（Gossypium spp.）是全球最重要的纤维作物之一，然而其可持续性正日益受到害虫群落演变、农药使用强度增加、气候变化及气候变率等因素的挑战。现有证据表明，当前对棉花农业生态系统中害虫动态、农药依赖及生态互作的认识，凸显了自苏云金芽孢杆菌（Bacillus thuringiensis, Bt）棉花广泛推广以来，害虫群落从以棉铃虫为主向次生害虫日益增多的转变。尽管基于Bt（Cry毒素）的转基因棉花技术最初减少了对棉铃虫复合体（主要为鳞翅目害虫）的杀虫剂使用，但近几十年来棉铃虫抗药性的出现及某些刺吸式害虫的激增，重新导致害虫管理对杀虫剂的依赖。这引发了生态失衡、非靶标毒性、传粉昆虫种群及天敌群落减少、生物多样性丧失、环境污染、产品中残留物积累及产量挑战，同时增加了生产成本。本综述强调了综合害虫管理（IPM）策略的关键作用，该策略整合生物防治、生境多样化、抗性品种及基于阈值的农药施用，以恢复生态稳定性。植物源农药、纳米制剂及植物挥发物介导的害虫调控等替代方法，被强调为可持续害虫防治的有前景工具。精准农业的进展，包括人工智能（AI）、机器学习及基于无人机（UAV）的农药施用系统，有望改善害虫监测并减少化学投入。供应链采购、认证、可追溯性及消费者需求可促进低农药生产，但这些机制需辅以公平价格激励，以避免将合规成本转嫁给小农户。因此，可持续棉花生产需要区域特异性、气候韧性、基于证据的IPM，并辅以推广服务、市场激励、抗性监测及协调政策支持。","Plant Science Today","2026-08-31T00:00:00Z",72,{"impact":18,"substance":253,"depth":18,"authority":17,"freshness":21,"relevant":22,"comment":254},22,"综述性论文，系统分析棉花害虫动态与农药依赖问题，提出IPM与精准农业等可持续路径，对农业绿色发展有参考价值。",[256],{"name":249,"url":246},[27,28,29,258,259],"农药减量","病虫害防治",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[262,267],{"code":192,"slug":263,"name":264,"path":265,"parent_code":266},"crop-protection","农药与绿色防控","\u002Ftopic\u002Finputs-equipment\u002Fcrop-protection","F",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":269},{"candidates":270,"agricultural_evidence":52},[271,278,282,287,296,303,310,314],{"code":192,"score":18,"supported":52,"title":272,"abstract":274,"tags":277},[273],"pesticide",[275,276,273],"农药","生物防治",[258],{"code":32,"score":51,"supported":52,"title":279,"abstract":280,"tags":281},[54],[29,54],[29],{"code":39,"score":13,"supported":52,"title":283,"abstract":284,"tags":286},[],[61,59,285],"artificial intelligence",[28],{"code":288,"score":289,"supported":52,"title":290,"abstract":291,"tags":295},"H6",9,[],[292,293,294],"生物多样性","农业生态","biodiversity",[],{"code":64,"score":297,"supported":52,"title":298,"abstract":299,"tags":302},7,[],[300,301],"精准农业","precision agriculture",[27],{"code":304,"score":102,"supported":52,"title":305,"abstract":306,"tags":309},"H7",[],[307,308],"气候变化","climate change",[],{"code":199,"score":72,"supported":52,"title":311,"abstract":312,"tags":313},[],[202],[],{"code":315,"score":72,"supported":52,"title":316,"abstract":317,"tags":319},"G2",[],[318],"小农户",[],[321,322],"农业人工智能 病虫害防治 农药减量 智慧农业","农业人工智能 病虫害防治","农业人工智能病虫害防治农药减量智慧农业-1325","10.14719\u002Fpst.16195",{"doi":324,"openalex_id":326,"authors":327,"venue":249,"cited_by_count":92,"oa_url":246,"card":358,"direction":97,"ingested_from":99},"W7204806269",[328,331,334,337,340,343,346,349,352,355],{"name":329,"orcid":330},"V Veeragowtham","https:\u002F\u002Forcid.org\u002F0009-0002-9822-4901",{"name":332,"orcid":333},"A. Suganthi","https:\u002F\u002Forcid.org\u002F0000-0001-7013-4459",{"name":335,"orcid":336},"M. Murugan","https:\u002F\u002Forcid.org\u002F0000-0002-7485-1153",{"name":338,"orcid":339},"P. Renukadevi","https:\u002F\u002Forcid.org\u002F0000-0001-9665-1681",{"name":341,"orcid":342},"S. Vellaikumar","https:\u002F\u002Forcid.org\u002F0000-0001-9277-457X",{"name":344,"orcid":345},"Ali Iqra","https:\u002F\u002Forcid.org\u002F0009-0008-6095-9471",{"name":347,"orcid":348},"J Kousika","https:\u002F\u002Forcid.org\u002F0000-0002-2455-5268",{"name":350,"orcid":351},"Sheela Venugopal","https:\u002F\u002Forcid.org\u002F0000-0002-4689-4105",{"name":353,"orcid":354},"Prakash Kolanchi","https:\u002F\u002Forcid.org\u002F0000-0003-1244-199X",{"name":356,"orcid":357},"Murugesh Dharani","https:\u002F\u002Forcid.org\u002F0009-0004-6705-1344",{"tldr":359,"method":360,"finding":361,"direction":362,"opportunity":363},"综述棉花害虫动态与农药使用变化，提出可持续管理策略。","综述文献，分析Bt棉影响、害虫抗性及IPM、精准农业等技术。","Bt棉导致次生害虫上升和抗性，需综合IPM与精准农业减少农药。","农业绿色发展与碳","可研究AI与无人机在棉花害虫监测与精准施药中的实际应用效果及小农采纳机制。","2026-09-01T23:30:34.470501Z",{"id":366,"title":367,"url":368,"summary":369,"summary_zh":9,"content":9,"source_name":370,"source_url":9,"published_at":371,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":372,"score_detail":373,"sources":376,"tags":378,"primary_topic":382,"secondary_topics":383,"classification":385,"search_phrases":407,"slug":410,"view_count":92,"doi":9,"paper":411,"created_at":419},5532,"精准棉花病害管理：融合无人机影像与定制YOLO深度学习框架","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.24182","研究提出单阶段全卷积检测器Cotton-Vision，融合幽灵瓶颈通道注意力与跨阶段部分融合三项轻量化设计，参数减少20%。在巴基斯坦旁遮普省7个棉田采集的2700余幅高分辨率无人机影像上测试，精确率97.7%、召回率77.7%、mAP@50为85.6%，较主流基线提升10至20个百分点。预印本，仅在巴基斯坦单一区域验证。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",69,{"impact":19,"substance":112,"depth":374,"authority":289,"freshness":102,"relevant":22,"comment":375},17,"方法轻量化与实测数据有增量，但仅单区域预印本验证，属细分技术进展，可入精选备选。",[377],{"name":370,"url":368},[27,28,379,380,381],"目标检测","无人机遥感","棉花病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[384],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":386},{"candidates":387,"agricultural_evidence":52},[388,393,398,402],{"code":39,"score":18,"supported":52,"title":389,"abstract":391,"tags":392},[390,131],"深度学习",[],[28,379],{"code":32,"score":394,"supported":52,"title":395,"abstract":396,"tags":397},11,[29],[54],[],{"code":64,"score":22,"supported":14,"title":399,"abstract":400,"tags":401},[],[],[27],{"code":403,"score":22,"supported":14,"title":404,"abstract":405,"tags":406},"I3",[],[],[380],[408,409],"Cotton-Vision 棉花病害","无人机影像 棉花 检测","Cotton-Vision棉花病害-5532",{"doi":9,"openalex_id":9,"authors":412,"venue":9,"cited_by_count":92,"oa_url":9,"card":413,"direction":417,"ingested_from":156},[],{"tldr":414,"method":415,"finding":416,"direction":417,"opportunity":418},"提出轻量化检测器Cotton-Vision，用无人机影像精准识别棉花病害。","基于YOLO改进，融合幽灵瓶颈通道注意力与跨阶段部分融合，用2700余幅无人机影","精确率97.7%、mAP@50达85.6%，较主流基线提升10至20个百分点。","农业遥感与作物表型","仅在巴基斯坦单一区域验证，可扩展至多区域多品种，并探索边缘设备实时部署。","2026-10-22T00:07:09.816790Z",{"id":421,"title":422,"url":423,"summary":424,"summary_zh":425,"content":9,"source_name":426,"source_url":423,"published_at":371,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":427,"score_detail":428,"sources":430,"tags":432,"primary_topic":435,"secondary_topics":436,"classification":438,"search_phrases":455,"slug":458,"view_count":22,"doi":459,"paper":460,"created_at":495},5150,"MSFANet: a multi-scale feature aggregation network for tobacco pest recognition","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1871587","Introduction Tobacco is a globally significant economic crop, and pest infestation represents one of the primary factors contributing to declines in both yield and quality. However, tobacco pests encompass a wide variety of species that differ substantially in morphology and scale. Field-captured images are frequently subject to complex background interference and class imbalance, presenting considerable challenges for automated recognition. Existing deep learning approaches remain limited in their capacity for multi-scale feature extraction and discriminative feature representation under such conditions. To address these challenges, this study proposes a Multi-Scale Feature Aggregation Network (MSFANet) for tobacco pest recognition, formulated here as a single-label image classification task. Methods To address scale variation and complex field backgrounds, two task-oriented modules were developed. The Multi-Scale Pyramid Pooling (MSPP) module aggregates contextual information across multiple receptive fields through parallel feature extraction and adaptive cross-branch fusion. The Hierarchical Feature Fusion Block (HFFB) subsequently refines the feature representations through spatial gating and partial convolution. An auxiliary classification head and Focal Loss were incorporated during training to provide intermediate supervision and address class imbalance, respectively. Results The effectiveness of MSFANet was evaluated on a dataset comprising 13 tobacco-associated pest and natural-enemy categories. The model achieved accuracy, precision, recall, and F1-score of 97.63%, 97.89%, 97.59%, and 97.71%, respectively, with a parameter count of 1.21 M. Among the models trained from random initialization, MSFANet shared the highest accuracy while using the fewest parameters. Discussion By combining multi-scale contextual aggregation with hierarchical feature refinement, MSFANet achieved accurate classification across the 13 tobacco-associated categories under complex field conditions. The proposed method provides effective technical support for automated and precision-oriented pest monitoring in tobacco fields, offering practical value for advancing precise pest management and the broader development of smart agriculture.","引言 烟草是全球重要的经济作物，虫害侵染是导致其产量和品质下降的主要因素之一。然而，烟草害虫种类繁多，形态和尺度差异显著。田间采集的图像常受到复杂背景干扰和类别不平衡的影响，给自动化识别带来了相当大的挑战。现有深度学习方法在此类条件下进行多尺度特征提取和判别性特征表示的能力仍然有限。为应对这些挑战，本研究提出了一种用于烟草害虫识别的多尺度特征聚合网络（Multi-Scale Feature Aggregation Network，MSFANet），并将其形式化为单标签图像分类任务。方法 针对尺度变化和复杂田间背景，开发了两个面向任务的模块。多尺度金字塔池化（Multi-Scale Pyramid Pooling，MSPP）模块通过并行特征提取和自适应跨分支融合，聚合多个感受野的上下文信息。分层特征融合模块（Hierarchical Feature Fusion Block，HFFB）随后通过空间门控和部分卷积对特征表示进行细化。训练过程中引入辅助分类头和Focal Loss，分别提供中间监督和处理类别不平衡。结果 在包含13个烟草相关害虫及天敌类别的数据集上评估了MSFANet的有效性。模型的准确率、精确率、召回率和F1分数分别为97.63%、97.89%、97.59%和97.71%，参数量为1.21 M。在随机初始化训练的模型中，MSFANet以最少的参数量取得了最高准确率。讨论 通过结合多尺度上下文聚合与分层特征细化，MSFANet在复杂田间条件下实现了对13个烟草相关类别的准确分类。所提方法为烟草田间害虫的自动化和精准监测提供了有效的技术支持，对推进精准害虫管理和智慧农业的更广泛发展具有实用价值。","Frontiers in Plant Science",76,{"impact":19,"substance":112,"depth":374,"authority":168,"freshness":289,"relevant":22,"comment":429},"该论文提出轻量化多尺度特征聚合网络，在烟草害虫识别上取得97%以上精度且参数量仅1.21M，方法新颖、数据扎实，对智慧农业虫情监测有实用价值，值得进入每日精选。",[431],{"name":426,"url":423},[27,28,390,433,434],"病虫害识别","烟草",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[437],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":439},{"candidates":440,"agricultural_evidence":52},[441,446,450],{"code":32,"score":51,"supported":52,"title":442,"abstract":444,"tags":445},[443],"tobacco",[434,443],[434],{"code":39,"score":289,"supported":52,"title":447,"abstract":448,"tags":449},[],[390,188],[28,390,433],{"code":64,"score":297,"supported":52,"title":451,"abstract":452,"tags":454},[],[27,453],"smart agriculture",[27],[456,457],"MSFANet 烟草害虫识别","多尺度特征聚合 害虫识别","MSFANet烟草害虫识别-5150","10.3389\u002Ffpls.2026.1871587",{"doi":459,"openalex_id":461,"authors":462,"venue":426,"cited_by_count":92,"oa_url":488,"card":489,"direction":494,"ingested_from":99},"W7222603139",[463,465,467,469,471,473,475,477,480,483,486],{"name":464,"orcid":9},"Shun He",{"name":466,"orcid":9},"Sifan Li",{"name":468,"orcid":9},"Xinjian Li",{"name":470,"orcid":9},"Qianqian Luo",{"name":472,"orcid":9},"Dong Sufen",{"name":474,"orcid":9},"Lu Lei",{"name":476,"orcid":9},"Xingjiang Chen",{"name":478,"orcid":479},"Liuti Cai","https:\u002F\u002Forcid.org\u002F0000-0002-9151-8002",{"name":481,"orcid":482},"Jian‐Yu Meng","https:\u002F\u002Forcid.org\u002F0000-0002-5796-1086",{"name":484,"orcid":485},"Ning Lu","https:\u002F\u002Forcid.org\u002F0000-0003-0214-5038",{"name":487,"orcid":9},"Hancheng Wang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1871587\u002Fpdf",{"tldr":490,"method":491,"finding":492,"direction":97,"opportunity":493},"提出MSFANet多尺度特征聚合网络，实现复杂田间背景下烟草害虫的自动识别。","多尺度金字塔池化MSPP、分层特征融合HFFB、辅助分类头与Focal Loss","模型准确率97.63%、参数量仅1.21M，在随机初始化模型中精度最高且参数最少。","可探索轻量多尺度网络在边缘设备部署及跨作物害虫迁移识别，结合类不平衡与复杂背景的鲁棒性研究。","智慧农业 \u002F 农业物联网","2026-10-17T23:30:08.695455Z",{"id":497,"title":498,"url":499,"summary":500,"summary_zh":501,"content":9,"source_name":502,"source_url":499,"published_at":503,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":504,"score_detail":505,"sources":508,"tags":510,"primary_topic":512,"secondary_topics":513,"classification":520,"search_phrases":553,"slug":556,"view_count":22,"doi":557,"paper":558,"created_at":571},4660,"IoT-Based Automatic Cotton Leaf Disease Detection, Infection Percentage Estimation, and Treatment Recommendation Using Raspberry PI","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23280692","Cotton is one of the most important commercial crops worldwide, and its productivity is significantly affected by various leaf diseases such as bacterial blight, alter aria leaf spot, Cercospora leaf spot, powdery mildew, and leaf curl disease. Early and accurate identification of these diseases is essential to minimize crop losses and improve yield. Traditional disease diagnosis relies on manual field inspection by experts, which is time-consuming, labour-intensive, and often impractical for large agricultural fields. The proposed system integrates a Raspberry Pi5, a high-resolution camera module, environmental sensors, and wireless communication technologies to create an intelligent crop monitoring platform. Images of cotton leaves are captured using the Raspberry Pi camera and processed through computer vision techniques for leaf segmentation and feature extraction. A lightweight deep learning model based on MobileNetV2 is employed to automatically identify different cotton leaf diseases. In addition to disease classification, image segmentation techniques are used to calculate the percentage of infected leaf area, enabling the system to determine the severity level of infection. The system also collects environmental parameters such as temperature, humidity, soil moisture, and light intensity using IoT sensors. These parameters, along with disease diagnosis results, are transmitted to a cloud-based dashboard for real-time monitoring and analysis. Automated alerts can be sent to farmers through SMS or mobile notifications when severe infections are detected. Experimental evaluation is expected to achieve disease classification accuracy above 93%, infection area estimation error below 5%, and real-time inference within one second per image on the Raspberry Pi platform. The proposed solution offers a cost-effective, portable, and scalable approach for precision agriculture by combining artificial intelligence, image processing, and IoT technologies. The system enables early disease detection, accurate infection assessment, timely treatment recommendations, reduced pesticide usage, and improved cotton crop productivity, making it a valuable tool for smart farming applications.","棉花是全球最重要的经济作物之一，其产量受到多种叶部病害的显著影响，如细菌性枯萎病（bacterial blight）、链格孢叶斑病（alternaria leaf spot）、尾孢叶斑病（Cercospora leaf spot）、白粉病（powdery mildew）和卷叶病（leaf curl disease）。早期准确识别这些病害对于减少作物损失和提高产量至关重要。传统的病害诊断依赖专家进行人工田间巡检，这种方式耗时、费力，且对于大面积农田往往不切实际。所提出的系统集成了Raspberry Pi5、高分辨率摄像头模块、环境传感器和无线通信技术，构建了一个智能作物监测平台。利用Raspberry Pi摄像头采集棉花叶片图像，并通过计算机视觉技术进行叶片分割和特征提取。采用基于MobileNetV2的轻量级深度学习模型自动识别不同的棉花叶部病害。除病害分类外，还利用图像分割技术计算受感染叶面积百分比，使系统能够确定感染的严重程度。该系统还通过物联网传感器采集温度、湿度、土壤水分和光照强度等环境参数。这些参数连同病害诊断结果一起传输至基于云端的仪表板，用于实时监测和分析。当检测到严重感染时，可通过短信或移动通知向农民发送自动警报。实验评估预期在Raspberry Pi平台上实现高于93%的病害分类准确率、低于5%的感染面积估计误差，以及每张图像一秒以内的实时推理。所提出的解决方案结合了人工智能、图像处理和物联网技术，为精准农业提供了一种经济高效、便携且可扩展的方法。该系统能够实现病害早期检测、准确感染评估、及时治疗建议、减少农药使用并提高棉花作物产量，使其成为智慧农业应用中的一种有价值的工具。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-10T00:00:00Z",74,{"impact":19,"substance":506,"depth":374,"authority":17,"freshness":289,"relevant":22,"comment":507},20,"基于树莓派与轻量深度学习的棉花叶病检测与物联网监测方案，方法具体、指标明确，对智慧植保有参考价值。",[509],{"name":502,"url":499},[27,28,511,300,381],"物联网",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[514,519],{"code":515,"slug":516,"name":517,"path":518,"parent_code":43},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":521},{"candidates":522,"agricultural_evidence":52},[523,528,532,536,542,546],{"code":515,"score":51,"supported":52,"title":524,"abstract":526,"tags":527},[525],"IoT",[511,525],[511],{"code":32,"score":20,"supported":52,"title":529,"abstract":530,"tags":531},[54],[29,54],[],{"code":64,"score":394,"supported":52,"title":533,"abstract":534,"tags":535},[],[27,300,301],[27,300],{"code":39,"score":13,"supported":52,"title":537,"abstract":538,"tags":541},[],[390,539,188,285,540],"计算机视觉","computer vision",[28],{"code":192,"score":102,"supported":52,"title":543,"abstract":544,"tags":545},[],[275,273],[],{"code":547,"score":102,"supported":52,"title":548,"abstract":549,"tags":552},"H2",[],[550,551],"土壤","soil",[],[554,555],"Raspberry Pi 棉花病害检测","MobileNetV2 棉花叶病识别","RaspberryPi棉花病害检测-4660","10.5281\u002Fzenodo.23280692",{"doi":557,"openalex_id":559,"authors":560,"venue":502,"cited_by_count":92,"oa_url":499,"card":566,"direction":494,"ingested_from":99},"W7221340722",[561,563],{"name":562,"orcid":9},"Deepak R Khadse",{"name":564,"orcid":565},"Pankaj Hiraman Zope","https:\u002F\u002Forcid.org\u002F0000-0003-3669-1440",{"tldr":567,"method":568,"finding":569,"direction":494,"opportunity":570},"基于树莓派与物联网，实现棉花叶病自动检测、感染率估算与防治推荐。","树莓派5+摄像头+环境传感器，MobileNetV2分类与图像分割，云端看板。","预期分类准确率超93%，感染面积误差低于5%，单图推理1秒内。","可探索边缘端轻量模型与多病害严重度分级、精准施药决策的闭环验证。","2026-10-11T23:30:07.876353Z"]