[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5234":3,"related-5234":87},{"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":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":63,"slug":66,"view_count":21,"doi":67,"paper":68,"created_at":86},5234,"A smart agriculture-oriented cross-attention multiscale CNN for sugarcane disease diagnosis","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23080477.2026.2749739","Sugarcane leaf diseases can adversely affect crop health and yield, making timely disease identification important for smart agriculture. Manual inspection of leaf diseases is time-consuming and requires expert knowledge, particularly when large cultivation areas need to be monitored. To tackle this problem, this study proposes a Cross-Attention Multiscale Parallel Convolutional Neural Network for automatic classification of sugarcane leaf diseases. This framework comprises a Parallel Feature Extraction Stem, cross-attention mechanism, Dense Connection Blocks, and Inception Blocks to learn disease features at various spatial scales. The PFES extracts fine and broad disease patterns using parallel convolutional branches, while the cross-attention mechanism refines the extracted features by emphasizing disease-related information. The DCB supports feature propagation and reuse, and the IB further captures multi-scale feature representations. The proposed model was tested on two benchmark datasets of leaf diseases for sugarcane plants. The proposed framework obtained an accuracy (98.79%), precision (98.31%), recall (97.81%), specificity (98.60%), and F1-Score (98.05%). For assessing the classification accuracy and consistency of the framework, the comparative study, ablation studies, and five-fold cross-validation are carried out. The results show that CA-MPCNN provides accurate sugarcane leaf disease classification and can support automated disease diagnosis in smart agriculture applications.","甘蔗叶片病害会对作物健康与产量造成不利影响，因此及时识别病害对智慧农业具有重要意义。人工检查叶片病害耗时且需要专业知识，尤其是在需要监测大面积种植区域时。为解决该问题，本研究提出一种用于甘蔗叶片病害自动分类的交叉注意力多尺度并行卷积神经网络（Cross-Attention Multiscale Parallel Convolutional Neural Network）。该框架由并行特征提取主干（Parallel Feature Extraction Stem）、交叉注意力机制、密集连接块（Dense Connection Blocks）和Inception块组成，用于学习不同空间尺度上的病害特征。PFES通过并行卷积分支提取细粒度与广域病害模式，而交叉注意力机制通过强调病害相关信息对提取的特征进行细化。DCB支持特征传播与复用，IB进一步捕获多尺度特征表示。所提出的模型在两个甘蔗植株叶片病害基准数据集上进行了测试。该框架取得了准确率（98.79%）、精确率（98.31%）、召回率（97.81%）、特异性（98.60%）和F1分数（98.05%）。为评估该框架的分类准确性和一致性，开展了对比研究、消融研究和五折交叉验证。结果表明，CA-MPCNN能够实现准确的甘蔗叶片病害分类，并可支持智慧农业应用中的自动化病害诊断。",null,"Smart Science","2026-10-17T00:00:00Z","论文",10,false,69,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,20,16,9,1,"该研究提出一种面向甘蔗叶部病害自动分类的交叉注意力多尺度CNN，在两个基准数据集上准确率达98.79%，方法新颖、实验充分，但属于细分作物应用研究，产业影响有限，时效性强，值得进入每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","甘蔗","深度学习","病害诊断",{"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",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51,57],{"code":32,"score":45,"supported":46,"title":47,"abstract":49,"tags":50},15,true,[48],"sugarcane",[28,48],[28],{"code":52,"score":45,"supported":46,"title":53,"abstract":55,"tags":56},"I1",[54],"smart agriculture",[26,54],[26],{"code":58,"score":59,"supported":14,"title":60,"abstract":61,"tags":62},"I2",2,[],[],[27,29],[64,65],"甘蔗 叶部病害 智能诊断","CA-MPCNN 甘蔗 病害","甘蔗叶部病害智能诊断-5234","10.1080\u002F23080477.2026.2749739",{"doi":67,"openalex_id":69,"authors":70,"venue":10,"cited_by_count":77,"oa_url":9,"card":78,"direction":84,"ingested_from":85},"W7222832245",[71,73,75],{"name":72,"orcid":9},"Bala Subramanian Chokkalingam",{"name":74,"orcid":9},"Uvarani Meenrajan",{"name":76,"orcid":9},"Shanmugapriya Sankaran",0,{"tldr":79,"method":80,"finding":81,"direction":82,"opportunity":83},"提出交叉注意力多尺度并行CNN，实现甘蔗叶病自动分类。","并行卷积分支、交叉注意力、密集连接与Inception块，两个基准数据集验证。","模型准确率达98.79%，消融与五折交叉验证证明其有效稳定。","农业人工智能与决策模型","可探索田间复杂背景与轻量化部署，并扩展到多作物病害实时诊断。","智慧农业 \u002F 农业物联网","openalex","2026-10-18T23:30:07.777036Z",{"total":88,"page":21,"page_size":88,"items":89},6,[90,174,219,285,360,411],{"id":91,"title":92,"url":93,"summary":94,"summary_zh":95,"content":9,"source_name":96,"source_url":93,"published_at":97,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":98,"score_detail":99,"sources":104,"tags":106,"primary_topic":109,"secondary_topics":110,"classification":116,"search_phrases":134,"slug":137,"view_count":21,"doi":138,"paper":139,"created_at":173},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","2026-10-16T00:00:00Z",76,{"impact":19,"substance":100,"depth":101,"authority":102,"freshness":20,"relevant":21,"comment":103},21,17,13,"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。",[105],{"name":96,"url":93},[26,27,29,107,108],"病虫害识别","烟草",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[111],{"code":58,"slug":112,"name":113,"path":114,"parent_code":115},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":117},{"candidates":118,"agricultural_evidence":46},[119,124,129],{"code":32,"score":45,"supported":46,"title":120,"abstract":122,"tags":123},[121],"tobacco",[108,121],[108],{"code":58,"score":20,"supported":46,"title":125,"abstract":126,"tags":128},[],[29,127],"deep learning",[27,29,107],{"code":52,"score":130,"supported":46,"title":131,"abstract":132,"tags":133},7,[],[26,54],[26],[135,136],"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":138,"openalex_id":140,"authors":141,"venue":96,"cited_by_count":77,"oa_url":167,"card":168,"direction":84,"ingested_from":85},"W7222603139",[142,144,146,148,150,152,154,156,159,162,165],{"name":143,"orcid":9},"Shun He",{"name":145,"orcid":9},"Sifan Li",{"name":147,"orcid":9},"Xinjian Li",{"name":149,"orcid":9},"Qianqian Luo",{"name":151,"orcid":9},"Dong Sufen",{"name":153,"orcid":9},"Lu Lei",{"name":155,"orcid":9},"Xingjiang Chen",{"name":157,"orcid":158},"Liuti Cai","https:\u002F\u002Forcid.org\u002F0000-0002-9151-8002",{"name":160,"orcid":161},"Jian‐Yu Meng","https:\u002F\u002Forcid.org\u002F0000-0002-5796-1086",{"name":163,"orcid":164},"Ning Lu","https:\u002F\u002Forcid.org\u002F0000-0003-0214-5038",{"name":166,"orcid":9},"Hancheng Wang","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1871587\u002Fpdf",{"tldr":169,"method":170,"finding":171,"direction":82,"opportunity":172},"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。","2026-10-17T23:30:08.695455Z",{"id":175,"title":176,"url":177,"summary":178,"summary_zh":9,"content":9,"source_name":179,"source_url":9,"published_at":180,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":181,"sources":184,"tags":186,"primary_topic":189,"secondary_topics":190,"classification":191,"search_phrases":206,"slug":209,"view_count":21,"doi":9,"paper":210,"created_at":218},4965,"Uncertainty-Aware Semi-Supervised Framework with Supervised Contrastive Learning for Sugarcane Leaf Disease Detection [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.17996","Shalini Dangi等提出基于Mean-Teacher半监督学习的不确定性感知病害检测网络U-SSDNet,用于甘蔗叶病检测。论文针对(i)同一病害在不同生育期表现差异大,(ii)病健组织类间相似,(iii)标签噪声等问题,先以离散小波变换增强病斑并降低类内差异,再用KL散度优化伪标签减轻确认偏差,同时引入监督对比学习提升类间区分度。甘蔗叶病数据集上的实验显示,U-SSDNet仅需少量标注即可接近全监督模型精度,显著优于当前主流监督与半监督方法。","arXiv 2610.17996 2026 年 10 月 13 日","2026-10-13T00:00:00Z",{"impact":17,"substance":18,"depth":101,"authority":182,"freshness":20,"relevant":21,"comment":183},11,"预印本提出不确定性感知半监督框架，方法新颖且少标注下接近全监督精度，对作物病害智能识别有参考价值，但尚属实验室阶段成果。",[185],{"name":179,"url":177},[26,27,28,187,188],"病害检测","半监督学习",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":192},{"candidates":193,"agricultural_evidence":46},[194,198,202],{"code":32,"score":17,"supported":46,"title":195,"abstract":196,"tags":197},[48],[28],[28],{"code":52,"score":21,"supported":14,"title":199,"abstract":200,"tags":201},[],[],[26],{"code":58,"score":21,"supported":14,"title":203,"abstract":204,"tags":205},[],[],[27],[207,208],"甘蔗叶病 检测 半监督学习","U-SSDNet 甘蔗","甘蔗叶病检测半监督学习-4965",{"doi":9,"openalex_id":9,"authors":211,"venue":9,"cited_by_count":77,"oa_url":9,"card":212,"direction":82,"ingested_from":217},[],{"tldr":213,"method":214,"finding":215,"direction":82,"opportunity":216},"提出半监督不确定性感知网络U-SSDNet，用少量标注实现甘蔗叶病高精度检测。","Mean-Teacher半监督、离散小波变换、KL散度伪标签优化、监督对比学习。","仅需少量标注即接近全监督精度，显著优于主流监督与半监督方法。","可将该不确定性半监督框架迁移至其他作物病害，并探索田间复杂光照与多生育期泛化。","agent","2026-10-15T00:06:08.498104Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":9,"content":9,"source_name":224,"source_url":222,"published_at":225,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":226,"score_detail":227,"sources":229,"tags":231,"primary_topic":233,"secondary_topics":234,"classification":236,"search_phrases":259,"slug":262,"view_count":88,"doi":263,"paper":264,"created_at":284},3463,"Cotton leaf disease classification using deep learning models for smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs40066-026-00610-2","Cotton leaf disease classification using deep learning models for smart agriculture。Agriculture & Food Security","Agriculture & Food Security","2026-09-25T00:00:00Z",66,{"impact":17,"substance":19,"depth":45,"authority":102,"freshness":13,"relevant":21,"comment":228},"核心期刊论文，方法有一定参考价值，但属细分技术研究，产业影响有限。",[230],{"name":224,"url":222},[26,27,29,232],"棉花病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[235],{"code":58,"slug":112,"name":113,"path":114,"parent_code":115},{"status":39,"locked":14,"version":40,"method":41,"evidence":237},{"candidates":238,"agricultural_evidence":46},[239,243,247,252],{"code":58,"score":102,"supported":46,"title":240,"abstract":241,"tags":242},[127],[127],[27,29],{"code":52,"score":17,"supported":46,"title":244,"abstract":245,"tags":246},[54],[54],[26],{"code":32,"score":182,"supported":46,"title":248,"abstract":250,"tags":251},[249],"cotton",[249],[],{"code":253,"score":254,"supported":46,"title":255,"abstract":256,"tags":258},"A8",3,[],[257],"food security",[],[260,261],"棉花叶部病害 深度学习 分类","农业人工智能 智慧农业 棉花病害 深度学习","棉花叶部病害深度学习分类-3463","10.1186\u002Fs40066-026-00610-2",{"doi":263,"openalex_id":265,"authors":266,"venue":224,"cited_by_count":77,"oa_url":222,"card":9,"direction":84,"ingested_from":85},"W7214238516",[267,269,272,275,278,281],{"name":268,"orcid":9},"Hina Kiran Abbas",{"name":270,"orcid":271},"Muhammad Farrukh Shahid","https:\u002F\u002Forcid.org\u002F0009-0004-8787-1868",{"name":273,"orcid":274},"Rehab Bahaaddin Ashari","https:\u002F\u002Forcid.org\u002F0000-0003-1225-7535",{"name":276,"orcid":277},"Arwa Mashat","https:\u002F\u002Forcid.org\u002F0000-0002-0612-6005",{"name":279,"orcid":280},"Tariq Jamil Saifullah Khanzada","https:\u002F\u002Forcid.org\u002F0000-0003-1617-4403",{"name":282,"orcid":283},"M. Hassan Tanveer","https:\u002F\u002Forcid.org\u002F0000-0001-9266-6368","2026-09-25T23:30:09.012501Z",{"id":286,"title":287,"url":288,"summary":289,"summary_zh":290,"content":9,"source_name":291,"source_url":288,"published_at":292,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":293,"sources":296,"tags":298,"primary_topic":301,"secondary_topics":302,"classification":304,"search_phrases":343,"slug":346,"view_count":347,"doi":348,"paper":349,"created_at":359},2940,"A Hybrid CNN–Transformer–LSTM Deep Learning Framework for Automated Cotton Disease Detection","https:\u002F\u002Fdoi.org\u002F10.53365\u002Fnrfhh.1816","Cotton production is frequently affected by leaf diseases that can reduce plant productivity, deteriorate crop quality, and cause considerable financial losses for farmers. Consequently, rapid and reliable disease identification is an important requirement for precision agriculture and effective crop protection. Conventional image-based approaches predominantly employ CNN architectures for visual classification; however, such methods may have limited capability in learning long-range spatial dependencies and modeling changes associated with disease development over time. To overcome these limitations, this research introduces an integrated hybrid deep learning framework that combines Convolutional Neural Networks (CNNs), Transformer-based self-attention, and Long Short-Term Memory (LSTM) networks for intelligent cotton leaf disease recognition. The proposed framework utilizes a pre-trained EfficientNet network to extract discriminative spatial characteristics from cotton leaf images. The extracted representations are subsequently processed through a multi-head self-attention Transformer module, which enables the network to identify relationships between distant and relevant regions of the leaf. An LSTM component is then incorporated to learn sequential dependencies and provide a foundation for analyzing disease evolution and progression. To improve model reliability and generalization, the network is trained using an appropriately organized cotton leaf image dataset together with image augmentation, transfer learning, and fine-tuning techniques. The experimental evaluation indicates that the proposed CNN–Transformer–LSTM architecture provides improved disease classification performance and more effective feature learning compared with conventional CNN-based models. Performance assessment using classification metrics, confusion matrices, and ROC curves demonstrates strong discrimination among the considered cotton disease categories. The combined learning of local visual characteristics, global contextual information, and sequential dependencies provides a comprehensive framework for automated cotton disease assessment. The proposed approach can serve as a scalable artificial intelligence solution for precision agriculture applications. Its architecture also provides opportunities for future integration with IoT-based crop monitoring systems, environmental data acquisition, and disease progression prediction, supporting early warning systems and intelligent crop health management in smart farming environments.","棉花生产常受叶片病害影响，这些病害会降低植株生产力、恶化作物品质，并给农民造成相当大的经济损失。因此，快速可靠的病害识别是精准农业和有效作物保护的重要需求。传统的基于图像的方法主要采用CNN架构进行视觉分类；然而，此类方法在学习长程空间依赖关系以及建模与病害随时间发展相关的变化方面能力有限。为克服这些局限，本研究提出了一种集成混合深度学习框架，将卷积神经网络（CNN）、基于Transformer的自注意力机制和长短期记忆（LSTM）网络相结合，用于智能棉花叶片病害识别。所提出的框架利用预训练的EfficientNet网络从棉花叶片图像中提取具有判别力的空间特征。提取到的表示随后通过多头自注意力Transformer模块进行处理，使网络能够识别叶片中相距较远且相关区域之间的关系。随后引入LSTM组件以学习序列依赖关系，并为分析病害演变和进展提供基础。为提高模型可靠性和泛化能力，网络使用组织良好的棉花叶片图像数据集进行训练，并结合图像增强、迁移学习和微调技术。实验评估表明，与传统的基于CNN的模型相比，所提出的CNN–Transformer–LSTM架构提供了更好的病害分类性能和更有效的特征学习。使用分类指标、混淆矩阵和ROC曲线进行的性能评估表明，该方法在所考虑的棉花病害类别之间具有较强的判别能力。局部视觉特征、全局上下文信息和序列依赖关系的联合学习为自动化棉花病害评估提供了一个全面的框架。所提出的方法可作为精准农业应用中可扩展的人工智能解决方案。其架构也为未来与基于物联网的作物监测系统、环境数据采集和病害进展预测的集成提供了机会，从而支持预警系统和智能","Natural Resources for Human Health","2026-09-16T00:00:00Z",{"impact":17,"substance":18,"depth":101,"authority":17,"freshness":294,"relevant":21,"comment":295},8,"提出CNN-Transformer-LSTM混合框架用于棉花叶病识别，方法有创新但属实验室验证阶段，产业影响有限。",[297],{"name":291,"url":288},[26,27,29,299,300],"精准农业","棉花病害识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[303],{"code":58,"slug":112,"name":113,"path":114,"parent_code":115},{"status":39,"locked":14,"version":40,"method":41,"evidence":305},{"candidates":306,"agricultural_evidence":46},[307,313,319,324,331,337],{"code":58,"score":308,"supported":46,"title":309,"abstract":310,"tags":312},19,[127],[29,127,311],"artificial intelligence",[27,29],{"code":32,"score":314,"supported":46,"title":315,"abstract":316,"tags":318},14,[249],[317,249],"棉花",[],{"code":52,"score":294,"supported":46,"title":320,"abstract":321,"tags":323},[],[299,322],"precision agriculture",[26,299],{"code":325,"score":88,"supported":46,"title":326,"abstract":327,"tags":330},"I5",[],[328,329],"物联网","IoT",[],{"code":332,"score":254,"supported":46,"title":333,"abstract":334,"tags":336},"A4",[],[335],"花生",[],{"code":338,"score":254,"supported":46,"title":339,"abstract":340,"tags":342},"F4",[],[341],"crop protection",[],[344,345],"棉花叶病 CNN Transformer LSTM","EfficientNet 棉花病害检测","棉花叶病CNNTransformerLSTM-2940",5,"10.53365\u002Fnrfhh.1816",{"doi":348,"openalex_id":350,"authors":351,"venue":291,"cited_by_count":77,"oa_url":9,"card":354,"direction":84,"ingested_from":85},"W7213544712",[352],{"name":353,"orcid":9},"Prajakta Sunil Gupta",{"tldr":355,"method":356,"finding":357,"direction":82,"opportunity":358},"提出CNN-Transformer-LSTM混合框架，实现棉花叶片病害自动识别。","EfficientNet提取特征，Transformer自注意力与LSTM建模，","混合模型分类性能优于传统CNN，能同时学习局部特征、全局上下文和序列依赖。","可融合IoT环境数据与时间序列，开展病害进展预测和早期预警系统研究。","2026-09-19T23:30:19.558449Z",{"id":361,"title":362,"url":363,"summary":364,"summary_zh":9,"content":9,"source_name":365,"source_url":9,"published_at":97,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":366,"sources":368,"tags":370,"primary_topic":373,"secondary_topics":374,"classification":376,"search_phrases":398,"slug":401,"view_count":77,"doi":9,"paper":402,"created_at":410},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",{"impact":19,"substance":100,"depth":101,"authority":20,"freshness":88,"relevant":21,"comment":367},"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。",[369],{"name":365,"url":363},[26,27,371,372,232],"目标检测","无人机遥感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[375],{"code":58,"slug":112,"name":113,"path":114,"parent_code":115},{"status":39,"locked":14,"version":40,"method":41,"evidence":377},{"candidates":378,"agricultural_evidence":46},[379,385,389,393],{"code":58,"score":380,"supported":46,"title":381,"abstract":383,"tags":384},18,[29,382],"YOLO",[],[27,371],{"code":32,"score":182,"supported":46,"title":386,"abstract":387,"tags":388},[317],[249],[],{"code":52,"score":21,"supported":14,"title":390,"abstract":391,"tags":392},[],[],[26],{"code":394,"score":21,"supported":14,"title":395,"abstract":396,"tags":397},"I3",[],[],[372],[399,400],"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":403,"venue":9,"cited_by_count":77,"oa_url":9,"card":404,"direction":408,"ingested_from":217},[],{"tldr":405,"method":406,"finding":407,"direction":408,"opportunity":409},"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":412,"title":413,"url":414,"summary":415,"summary_zh":9,"content":9,"source_name":416,"source_url":9,"published_at":9,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":417,"score_detail":418,"sources":420,"tags":422,"primary_topic":425,"secondary_topics":426,"classification":428,"search_phrases":450,"slug":453,"view_count":77,"doi":9,"paper":454,"created_at":461},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":100,"depth":380,"authority":314,"freshness":59,"relevant":21,"comment":419},"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。",[421],{"name":416,"url":414},[26,27,317,423,424],"障碍物检测","采棉机",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[427],{"code":58,"slug":112,"name":113,"path":114,"parent_code":115},{"status":39,"locked":14,"version":40,"method":41,"evidence":429},{"candidates":430,"agricultural_evidence":46},[431,435,439,446],{"code":32,"score":17,"supported":46,"title":432,"abstract":433,"tags":434},[317],[317],[317],{"code":58,"score":17,"supported":46,"title":436,"abstract":437,"tags":438},[382],[382],[27],{"code":440,"score":88,"supported":46,"title":441,"abstract":442,"tags":445},"F5",[],[443,444],"农业机械","机械化",[],{"code":52,"score":21,"supported":14,"title":447,"abstract":448,"tags":449},[],[],[26],[451,452],"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":455,"venue":9,"cited_by_count":77,"oa_url":9,"card":456,"direction":82,"ingested_from":217},[],{"tldr":457,"method":458,"finding":459,"direction":82,"opportunity":460},"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。","2026-10-15T00:06:08.577388Z"]