[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4804":3,"related-4804":94},{"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":32,"secondary_topics":38,"classification":39,"search_phrases":66,"slug":69,"view_count":22,"doi":70,"paper":71,"created_at":93},4804,"Comparative Deep Learning and RISE-Based Explainable AI Framework for Orange Fruit Disease Detection","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1850038","Orange diseases significantly threaten fruit quality and agricultural productivity, resulting in substantial economic losses. Traditional diagnostic methods are limited by their labor-intensive nature, high costs, and reliance on subjective expert evaluation, increasing the demand for automated solutions. This study systematically compared three state-of the-art deep learning architectures-EfficientNet-B0, ConvNeXt-Tiny, and Vision Transformer (ViT-B\u002F16)-on the Orange Fruit dataset, which comprises healthy, citrus canker, and melanose samples. To enhance generalization and mitigate overfitting, transfer learning with ImageNet pretraining was combined with advanced data augmentation strategies like Mixup and Cutout. Experimental results demonstrated that the ConvNeXt-Tiny architecture, supported by these techniques, achieved superior performance, reaching 98.76% Accuracy, 99% F1-Score, and 99.95% ROC-AUC. Beyond numerical metrics, model transparency was investigated using Explainable Artificial Intelligence (XAI). The study evaluated the widely used Gradient-weighted Class Activation Mapping (Grad-CAM) method alongside Randomized Input Sampling for Explanation (RISE), which, to the best of our knowledge, represents one of the first applications of RISE in plant disease image analysis. RISE provided more comprehensive visualizations of the fruit surface regions influencing decisions, thereby strengthening interpretability. These findings confirm the high potential of modern deep learning for early disease diagnosis and highlight that XAI integration significantly enhances the reliability of agricultural decision support systems. Five fold cross-validation experiments and paired t-test analysis further confirmed the robustness and statistical significance of these findings.","橙病严重威胁果实品质和农业生产力，造成重大经济损失。传统诊断方法受限于劳动强度大、成本高以及依赖专家主观评估，增加了对自动化解决方案的需求。本研究在包含健康、柑橘溃疡病和黑斑病样本的橙果数据集上，系统比较了三种先进的深度学习架构——EfficientNet-B0、ConvNeXt-Tiny和Vision Transformer（ViT-B\u002F16）。为增强泛化能力并缓解过拟合，将基于ImageNet预训练的迁移学习与Mixup和Cutout等先进数据增强策略相结合。实验结果表明，在这些技术的支持下，ConvNeXt-Tiny架构取得了最优性能，达到98.76%的准确率、99%的F1分数和99.95%的ROC-AUC。除数值指标外，本研究还利用可解释人工智能（XAI）探讨了模型透明度。研究评估了广泛使用的梯度加权类激活映射（Grad-CAM）方法以及随机输入采样解释方法（RISE），据我们所知，这是RISE在植物病害图像分析中的首批应用之一。RISE提供了更全面的果实表面区域可视化，展示了影响决策的区域，从而增强了可解释性。这些发现证实了现代深度学习在早期病害诊断中的巨大潜力，并表明XAI的整合显著提升了农业决策支持系统的可靠性。五折交叉验证实验和配对t检验分析进一步证实了这些发现的稳健性和统计显著性。",null,"Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z","论文",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,18,13,9,1,"系统比较三种深度学习架构并首次将RISE用于植物病害图像分析，方法新颖、数据可靠，对智慧农业病害诊断有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","可解释AI","柑橘","病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,54,61],{"code":33,"score":18,"supported":46,"title":47,"abstract":49,"tags":53},true,[48],"deep learning",[50,48,51,52],"深度学习","artificial intelligence","decision support",[28,29,31],{"code":55,"score":56,"supported":46,"title":57,"abstract":58,"tags":60},"B2",7,[],[30,59],"citrus",[30],{"code":62,"score":22,"supported":14,"title":63,"abstract":64,"tags":65},"I1",[],[],[27],[67,68],"ConvNeXt 柑橘病害检测","RISE 可解释AI 植物病害","ConvNeXt柑橘病害检测-4804","10.15832\u002Fankutbd.1850038",{"doi":70,"openalex_id":72,"authors":73,"venue":10,"cited_by_count":83,"oa_url":84,"card":85,"direction":91,"ingested_from":92},"W7221532433",[74,77,80],{"name":75,"orcid":76},"Kürşad Buğrahan Yapar","https:\u002F\u002Forcid.org\u002F0009-0006-7666-6177",{"name":78,"orcid":79},"Nurettin Doğan","https:\u002F\u002Forcid.org\u002F0000-0002-8267-8469",{"name":81,"orcid":82},"Özgür Öksüz","https:\u002F\u002Forcid.org\u002F0000-0001-5568-6116",0,"https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5543457",{"tldr":86,"method":87,"finding":88,"direction":89,"opportunity":90},"比较三种深度学习模型检测橙子病害，并用RISE提升可解释性。","EfficientNet-B0、ConvNeXt-Tiny、ViT-B\u002F16，迁","ConvNeXt-Tiny达98.76%准确率，RISE比Grad-CAM提供更全面可解释可视化。","农业人工智能与决策模型","RISE在植物病害分析中应用尚少，可探索更多XAI方法提升农业决策系统可信度。","智慧农业 \u002F 农业物联网","openalex","2026-10-13T23:30:08.943247Z",{"total":95,"page":22,"page_size":95,"items":96},6,[97,151,212,299,363,435],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":104,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":106,"sources":109,"tags":111,"primary_topic":113,"secondary_topics":114,"classification":115,"search_phrases":129,"slug":132,"view_count":133,"doi":134,"paper":135,"created_at":150},3860,"Multi-Scale Texture-Attention Network for Automated Arecanut Disease Classification Using Explainable Deep Learning","https:\u002F\u002Fdoi.org\u002F10.20944\u002Fpreprints202609.2530.v1","Arecanut cultivation is affected by several diseases and disorders that can reduce crop health and productivity. Automated disease identification from field images is challenging because of visually similar symptoms, illumination variations, complex backgrounds, and disease-specific texture patterns. This paper proposes a Multi-Scale Texture-Attention Network (MSTANet) for automated nine-class arecanut health and disease classification. MSTANet integrates multi-scale convolutional feature extraction, a texture-aware branch based on depthwise-separable convolutions, coordinate attention, and feature fusion to capture complementary spatial and textural characteristics. The proposed model contains 1.397 million trainable parameters and processes images resized to 150 × 150 pixels. Experiments were conducted using 5,628 images for model development and an independent test set containing 1,757 images. The model achieved 100.00% validation accuracy with a validation loss of 0.0012. On the independent test set, MSTANet achieved 88.84% accuracy, 90.55% weighted precision, 88.84% weighted recall, and 88.97% weighted F1-score. It further achieved 86.97% balanced accuracy, an MCC of 0.8669, Cohen’s kappa of 0.8643, weighted ROC-AUC of 0.9909, and weighted PR-AUC of 0.9558. The highest class-wise F1-scores were obtained for Healthy Nut (98.72%) and Mahali Koleroga (95.48%). Grad-CAM analysis was employed to provide qualitative visual explanations of model predictions and to examine the disease-relevant regions used by the network. A literature-based comparison with previously reported models addressing the same nine-class arecanut classification problem further demonstrates the competitive performance of MSTANet. The results indicate that MSTANet provides a compact, multi-scale, texture-cale feature learning, texture-aware learning, coordinate attention, explainable artificial intelligence (XAI), Grad-CAM, convolutional neural networks, precision agriculture.","槟榔种植受到多种病害和生理失调的影响，这些因素会降低作物健康水平和产量。从田间图像中进行自动化病害识别面临诸多挑战，原因包括症状视觉相似、光照变化、复杂背景以及病害特异性纹理模式。本文提出了一种多尺度纹理注意力网络（MSTANet），用于九类槟榔健康与病害的自动化分类。MSTANet 集成了多尺度卷积特征提取、基于深度可分离卷积的纹理感知分支、坐标注意力以及特征融合，以捕获互补的空间与纹理特征。所提模型包含 139.7 万个可训练参数，处理调整为 150 × 150 像素的图像。实验使用 5,628 张图像进行模型开发，并使用包含 1,757 张图像的独立测试集进行评估。模型取得了 100.00% 的验证准确率，验证损失为 0.0012。在独立测试集上，MSTANet 取得了 88.84% 的准确率、90.55% 的加权精确率、88.84% 的加权召回率和 88.97% 的加权 F1 分数。此外，它还取得了 86.97% 的平衡准确率、0.8669 的 MCC、0.8643 的 Cohen's kappa、0.9909 的加权 ROC-AUC 和 0.9558 的加权 PR-AUC。类别 F1 分数最高的是健康坚果（98.72%）和 Mahali Koleroga（95.48%）。采用 Grad-CAM 分析为模型预测提供定性可视化解释，并检查网络所使用的病害相关区域。基于文献与先前报道的解决同一九类槟榔分类问题的模型进行比较，进一步证明了 MSTANet 的竞争性性能。结果表明，MSTANet 提供了一种紧凑的、多尺度的、纹理感知的特征学习、坐标注意力、可解释人工智能（XAI）、Grad-CAM、卷积神经网络、精准农业。","Preprints.org","2026-09-29T00:00:00Z",64,{"impact":17,"substance":18,"depth":107,"authority":95,"freshness":21,"relevant":22,"comment":108},17,"预印本提出轻量多尺度纹理注意力网络实现槟榔九类病害识别，方法新颖、数据规模可观，但尚未经同行评审，属细分领域技术进展。",[110],{"name":103,"url":100},[27,28,29,31,112],"槟榔",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":116},{"candidates":117,"agricultural_evidence":46},[118,123],{"code":33,"score":119,"supported":46,"title":120,"abstract":121,"tags":122},14,[48],[51],[28,29,31],{"code":62,"score":56,"supported":46,"title":124,"abstract":125,"tags":128},[],[126,127],"精准农业","precision agriculture",[27],[130,131],"槟榔 病害 识别 深度学习","MSTANet 槟榔 病害 分类","槟榔病害识别深度学习-3860",3,"10.20944\u002Fpreprints202609.2530.v1",{"doi":134,"openalex_id":136,"authors":137,"venue":103,"cited_by_count":83,"oa_url":100,"card":145,"direction":89,"ingested_from":92},"W7214735506",[138,140,142],{"name":139,"orcid":9},"Sumalatha U",{"name":141,"orcid":9},"Krishna Prakasha",{"name":143,"orcid":144},"T. Shreekumar","https:\u002F\u002Forcid.org\u002F0000-0002-5632-9767",{"tldr":146,"method":147,"finding":148,"direction":89,"opportunity":149},"提出MSTANet多尺度纹理注意力网络，实现槟榔九类病害自动分类。","多尺度卷积、深度可分离纹理分支、坐标注意力、特征融合与Grad-CAM，5628","独立测试准确率88.84%，健康果与Mahali Koleroga的F1最高，验证集达100%。","可探索轻量模型在田间复杂背景下的泛化与跨作物迁移，并结合多模态数据提升可解释性。","2026-09-30T23:30:50.264385Z",{"id":152,"title":153,"url":154,"summary":155,"summary_zh":156,"content":9,"source_name":157,"source_url":154,"published_at":158,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":159,"score_detail":160,"sources":164,"tags":166,"primary_topic":168,"secondary_topics":169,"classification":170,"search_phrases":187,"slug":190,"view_count":133,"doi":191,"paper":192,"created_at":211},3368,"A PCA-based deep feature optimization framework for explainable orange fruit disease classification","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs12870-026-09984-8","Accurate classification of orange fruit diseases is important for precision agriculture and yield protection. This study develops and rigorously benchmarks a hybrid deep-feature framework for classifying Black Spot, Canker, Fresh, and Greening oranges (1,090 images), combining deep feature extraction, PCA-based dimensionality reduction, and classical machine-learning classification. Eight backbones (seven CNNs and a Vision Transformer, ViT) and four classifiers (32 configurations in total) were evaluated under 5 × 5 repeated stratified cross-validation, with PCA fitted exclusively on training-fold features in every iteration to eliminate data leakage. The proposed ViT + PCA+SVM configuration achieved the highest mean accuracy, 99.12%±0.71%, significantly outperforming every CNN-based backbone, including DenseNet201 + PCA + SVM (98.48%±0.81%, p \u003C 0.001). A dedicated variance-retention sensitivity analysis justifies the 98% threshold used throughout, and ablation experiments confirm that PCA substantially reduces feature dimensionality (by ~ 55.7% for ViT and ~ 76.6% for DenseNet201) without a significant loss of accuracy for either backbone. Explainability analysis — occlusion sensitivity and SHAP for the proposed ViT model, and Grad-CAM and SHAP for the DenseNet201 comparison model — shows that both configurations base predictions on biologically relevant, disease-affected regions of the fruit rather than spurious cues. These results identify ViT + PCA+SVM as the most accurate configuration evaluated, with DenseNet201 + PCA + SVM as a closely competitive, more compact convolutional alternative for intelligent orchard disease-monitoring systems.","橙类果实病害的准确分类对精准农业和产量保护具有重要意义。本研究开发并严格基准测试了一种混合深度特征框架，用于对黑斑病、溃疡病、新鲜和黄龙病橙类（1，090张图像）进行分类，该框架结合了深度特征提取、基于PCA的降维和经典机器学习分类。在5×5重复分层交叉验证下评估了八种骨干网络（七种CNN和一种视觉Transformer，ViT）和四种分类器（共32种配置），每次迭代中PCA仅在训练折特征上拟合以消除数据泄漏。所提出的ViT + PCA+SVM配置取得了最高平均准确率，为99.12%±0.71%，显著优于所有基于CNN的骨干网络，包括DenseNet201 + PCA + SVM（98.48%±0.81%，p \u003C 0.001）。专门的方差保留敏感性分析证明了全程使用的98%阈值是合理的，消融实验证实PCA大幅降低了特征维度（ViT约降低55.7%，DenseNet201约降低76.6%），且两种骨干网络均无显著准确率损失。可解释性分析——对所提出的ViT模型采用遮挡敏感性和SHAP，对DenseNet201对比模型采用Grad-CAM和SHAP——表明两种配置均基于果实中生物学相关的病害影响区域而非虚假线索进行预测。这些结果确定ViT + PCA+SVM为所评估的最准确配置，而DenseNet201 + PCA + SVM则是一种竞争力接近且更紧凑的卷积替代方案，可用于智能果园病害监测系统。","BMC Plant Biology","2026-09-23T00:00:00Z",79,{"impact":161,"substance":162,"depth":19,"authority":119,"freshness":21,"relevant":22,"comment":163},16,22,"方法严谨、数据与消融实验充分，对果园智能病害监测有实用参考价值，但属细分技术论文，产业影响有限。",[165],{"name":157,"url":154},[27,28,29,31,167],"柑橘种植",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":171},{"candidates":172,"agricultural_evidence":46},[173,177,182],{"code":62,"score":56,"supported":46,"title":174,"abstract":175,"tags":176},[],[126,127],[27],{"code":33,"score":95,"supported":46,"title":178,"abstract":179,"tags":181},[],[180],"机器学习",[28,29,31],{"code":55,"score":133,"supported":46,"title":183,"abstract":184,"tags":186},[],[185],"orchard",[],[188,189],"柑橘病害 深度学习 分类","ViT PCA SVM 病害识别","柑橘病害深度学习分类-3368","10.1186\u002Fs12870-026-09984-8",{"doi":191,"openalex_id":193,"authors":194,"venue":157,"cited_by_count":83,"oa_url":154,"card":206,"direction":89,"ingested_from":92},"W7214068709",[195,197,199,201,204],{"name":196,"orcid":9},"Amruta Hingmire",{"name":198,"orcid":9},"Avinash Golande",{"name":200,"orcid":9},"Vinodkumar Bhutnal",{"name":202,"orcid":203},"Sagar Dhanraj Pande","https:\u002F\u002Forcid.org\u002F0000-0003-4506-6997",{"name":205,"orcid":9},"Tanuja Pande",{"tldr":207,"method":208,"finding":209,"direction":89,"opportunity":210},"提出PCA深度特征优化框架，用ViT+SVM分类橙子病害，准确率达99.12%。","8种骨干网络提取特征，PCA降维，4种分类器，5×5交叉验证。","ViT+PCA+SVM最优，PCA降维超55%且精度不降，可解释性验证有效。","可探索轻量化模型在移动端或边缘设备的实时病害检测与多作物泛化。","2026-09-24T23:30:34.116938Z",{"id":213,"title":214,"url":215,"summary":216,"summary_zh":217,"content":9,"source_name":218,"source_url":215,"published_at":219,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":220,"score_detail":221,"sources":224,"tags":226,"primary_topic":228,"secondary_topics":234,"classification":236,"search_phrases":267,"slug":270,"view_count":22,"doi":271,"paper":272,"created_at":298},3153,"Explainable optimized deep learning and generative AI based framework for finger millet disease detection in smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02222-y","Abstract Eleusine coracana, locally known as finger millet (ragi), is a wholesome, climate-resilient crop. It is a staple food in semi-dry and dry areas of Asia and Africa. The productivity of this crop can be severely reduced by diseases such as downy, mottle, seedling, smut, and wilt. Conventional diagnosis methods are often time-consuming and unsuitable for large-scale farming. Therefore,Deep Learning (DL) offers an alternative for smart commercial farming that can streamline disease screening and improve productivity. This work offers an AI-integrated framework for early disease intervention combining DL, Explainable AI (XAI), and an image-based decision-support interface. The finger millet (ragi) dataset from Kaggle was used to train and evaluate custom CNN, VGG16, and ResNet50 models. To reduce feature redundancy and improve generalization, Grey Wolf Optimizer (GWO) based feature selection was applied to the penultimate-layer features of each model. Custom CNN, VGG16, and ResNet50 achieved accuracies of 89.40%, 83.11%, and 91.83%, respectively. Further, the use of GWO improved the accuracies to 97.71%, 90.84%, and 98.36%, respectively. ResNet50 achieved the highest accuracy 98.36% and was selected as the final backbone. The final ResNet50 model is integrated with the Gemini API to provide disease-specific recommendations based on the predicted class and user queries. To increase prediction transparency, Grad-CAM was used to highlight image regions that influenced the model output. The integration of DL, XAI, and generative AI provides a scalable approach for detecting and managing finger millet diseases. The proposed work boosts precision agriculture by providing AI-based and XAI-supported decision-making, while fostering sustainable agricultural practices.","摘要 穇子（Eleusine coracana），当地称为指黍（ragi），是一种有益健康且气候适应性强的作物。它是亚洲和非洲半干旱及干旱地区的主食。霜霉病、斑驳病、苗枯病、黑穗病和枯萎病等病害可严重降低该作物的产量。传统诊断方法往往耗时且不适合大规模种植。因此，深度学习（DL）为智能商业农业提供了一种替代方案，可简化病害筛查并提高生产力。本研究提出了一种人工智能集成框架，用于早期病害干预，结合了深度学习、可解释人工智能（XAI）和基于图像的决策支持界面。使用来自Kaggle的指黍（ragi）数据集训练和评估了自定义CNN、VGG16和ResNet50模型。为减少特征冗余并提高泛化能力，将灰狼优化器（GWO）基于特征选择应用于每个模型的倒数第二层特征。自定义CNN、VGG16和ResNet50分别达到了89.40%、83.11%和91.83%的准确率。此外，使用GWO将准确率分别提高到97.71%、90.84%和98.36%。ResNet50达到了最高准确率98.36%，并被选为最终骨干网络。最终的ResNet50模型与Gemini API集成，根据预测类别和用户查询提供针对特定病害的建议。为提高预测透明度，使用Grad-CAM突出显示影响模型输出的图像区域。深度学习、可解释人工智能和生成式人工智能的集成提供了一种可扩展的方法，用于检测和管理指黍病害。所提出的工作通过提供基于人工智能和可解释人工智能支持的决策，促进了精准农业，同时推动了可持续农业实践。","Discover Artificial Intelligence","2026-09-22T00:00:00Z",75,{"impact":222,"substance":18,"depth":19,"authority":17,"freshness":13,"relevant":22,"comment":223},15,"将深度学习、可解释AI与生成式AI结合用于指状粟病害识别，方法新颖、数据充分，对智慧农业有参考价值。",[225],{"name":218,"url":215},[27,28,29,31,227],"小米作物",{"code":229,"slug":230,"name":231,"path":232,"parent_code":233},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[235],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":237},{"candidates":238,"agricultural_evidence":46},[239,243,248,254,261],{"code":33,"score":107,"supported":46,"title":240,"abstract":241,"tags":242},[48],[50,48],[28,29,31],{"code":62,"score":222,"supported":46,"title":244,"abstract":246,"tags":247},[245],"smart agriculture",[126,127],[27],{"code":229,"score":249,"supported":46,"title":250,"abstract":252,"tags":253},11,[251],"millet",[251],[],{"code":255,"score":95,"supported":46,"title":256,"abstract":257,"tags":260},"H7",[],[258,259],"气候适应","干旱",[],{"code":262,"score":133,"supported":46,"title":263,"abstract":264,"tags":266},"H8",[],[265],"可持续农业",[],[268,269],"ResNet50 GWO 病害识别","农业人工智能 小米作物 智慧农业 病害识别","ResNet50GWO病害识别-3153","10.1007\u002Fs44163-026-02222-y",{"doi":271,"openalex_id":273,"authors":274,"venue":218,"cited_by_count":83,"oa_url":215,"card":293,"direction":91,"ingested_from":92},"W7213978567",[275,278,280,282,284,287,290],{"name":276,"orcid":277},"Sunil Kumar Mohapatra","https:\u002F\u002Forcid.org\u002F0000-0002-5865-095X",{"name":279,"orcid":9},"A. Sanjib Kumar Patro",{"name":281,"orcid":9},"Lulen Kumar Sahu",{"name":283,"orcid":9},"Chinmaye Dora",{"name":285,"orcid":286},"Sujata Chakravarty","https:\u002F\u002Forcid.org\u002F0000-0002-1293-5378",{"name":288,"orcid":289},"Kshira Sagar Sahoo","https:\u002F\u002Forcid.org\u002F0000-0002-6435-5738",{"name":291,"orcid":292},"Byomakesh Mahapatra","https:\u002F\u002Forcid.org\u002F0000-0002-9126-1729",{"tldr":294,"method":295,"finding":296,"direction":89,"opportunity":297},"提出融合深度学习、可解释AI与生成式AI的指状粟病害检测框架，实现高精度识别与决策支持。","用Kaggle指状粟图像训练CNN、VGG16、ResNet50，并用灰狼优化做","GWO特征选择显著提升精度，ResNet50达98.36%，结合Grad-CAM与Gemini AP","可探索轻量化模型与多作物泛化，并将XAI与生成式建议在田间移动端实时验证。","2026-09-22T23:30:10.255790Z",{"id":300,"title":301,"url":302,"summary":303,"summary_zh":304,"content":9,"source_name":305,"source_url":302,"published_at":306,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":307,"score_detail":308,"sources":311,"tags":313,"primary_topic":316,"secondary_topics":317,"classification":318,"search_phrases":349,"slug":352,"view_count":83,"doi":353,"paper":354,"created_at":362},5311,"AI SMART AGRO SYSTEM: A WEB-BASED AI-ASSISTED DECISION SUPPORT PLATFORM FOR FARMERS","https:\u002F\u002Fdoi.org\u002F10.56726\u002Firjmets103514","Farmers often have to decide on disease control, crop selection, soil management and irrigation without timely expert advice, which leads to yield loss and wastage of water and fertiliser.This paper presents AI Smart Agro System, a web-based decision-support platform that brings five services into one dashboard: leaf disease detection from an uploaded photograph, crop recommendation, soil health analysis, irrigation advisory and weather-based farming advice.The system is built with PHP, MySQL and JavaScript, while disease detection and crop recommendation are handled by an external Python Flask AI service that is called through a secured REST API.Soil, irrigation and weather advice are generated by transparent rule-based logic using soil pH, N-P-K values, soil moisture, rainfall, temperature and humidity.Every result is stored in the user's history, and notifications and an administrator panel support monitoring.The prototype is designed to return the disease name, confidence, treatment and prevention tips for an uploaded leaf image, to recommend the three most suitable crops, and to give clear advice for soil and water management.Quantitative evaluation of the AI models is left for future work.","农民常常需要在没有及时专家建议的情况下决定病害防治、作物选择、土壤管理和灌溉，这会导致产量损失以及水和肥料的浪费。本文提出AI Smart Agro System，这是一个基于Web的决策支持平台，将五项服务整合到一个仪表板中：根据上传照片进行叶片病害检测、作物推荐、土壤健康分析、灌溉建议以及基于天气的农事建议。该系统使用PHP、MySQL和JavaScript构建，而病害检测和作物推荐由外部Python Flask AI服务处理，并通过安全的REST API调用。土壤、灌溉和天气建议由透明的基于规则的逻辑生成，使用土壤pH、N-P-K值、土壤湿度、降雨量、温度和湿度。每个结果都存储在用户历史记录中，通知和管理员面板支持监控。该原型旨在为上传的叶片图像返回病害名称、置信度、治疗和预防提示，推荐三种最合适的作物，并为土壤和水管理提供明确建议。AI模型的定量评估留待未来工作。","International Research Journal of Modernization in Engineering Technology and Science","2026-10-17T00:00:00Z",49,{"impact":309,"substance":119,"depth":17,"authority":95,"freshness":21,"relevant":22,"comment":310},8,"原型系统整合病害识别、作物推荐与灌溉建议，思路清晰但缺乏定量评估，属细分技术进展，公共影响有限。",[312],{"name":305,"url":302},[27,28,314,31,315],"决策支持系统","灌溉管理",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":319},{"candidates":320,"agricultural_evidence":46},[321,325,332,339,345],{"code":33,"score":249,"supported":46,"title":322,"abstract":323,"tags":324},[52],[],[28,314,31],{"code":326,"score":56,"supported":46,"title":327,"abstract":328,"tags":331},"H3",[],[329,330],"灌溉","irrigation",[315],{"code":333,"score":95,"supported":46,"title":334,"abstract":335,"tags":338},"H2",[],[336,337],"土壤","soil",[],{"code":340,"score":133,"supported":46,"title":341,"abstract":342,"tags":344},"F3",[],[343],"肥料",[],{"code":62,"score":22,"supported":14,"title":346,"abstract":347,"tags":348},[],[],[27],[350,351],"Web 农业决策支持平台","农业人工智能 决策支持系统 智慧农业 灌溉管理","Web农业决策支持平台-5311","10.56726\u002Firjmets103514",{"doi":353,"openalex_id":355,"authors":356,"venue":305,"cited_by_count":83,"oa_url":302,"card":357,"direction":91,"ingested_from":92},"W7222785888",[],{"tldr":358,"method":359,"finding":360,"direction":89,"opportunity":361},"构建一个面向农民的网页版AI决策支持平台，集成病害识别、选种、土壤、灌溉与天气建议。","PHP\u002FMySQL\u002FJS前端，Python Flask提供病害与选种AI服务，规","原型可输出病害名称、置信度与防治建议，推荐三种适宜作物并给出水土管理建议。","AI模型尚未定量评估，可补充精度验证与田间实测，并扩展多语言、离线与本地化作物模型。","2026-10-19T23:30:08.043132Z",{"id":364,"title":365,"url":366,"summary":367,"summary_zh":368,"content":9,"source_name":369,"source_url":366,"published_at":370,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":371,"score_detail":372,"sources":375,"tags":377,"primary_topic":379,"secondary_topics":380,"classification":381,"search_phrases":401,"slug":404,"view_count":83,"doi":405,"paper":406,"created_at":434},5080,"Explainable deep learning for Mango leaf disease recognition using AlexNet and grad-CAM","https:\u002F\u002Fdoi.org\u002F10.1177\u002F1088467x261495708","Early and accurate detection of plant diseases is essential for improving crop productivity and supporting sustainable agricultural practices. Mango (Mangifera indica), one of the most economically important tropical fruit crops worldwide, is highly susceptible to several leaf diseases that can significantly reduce yield and fruit quality. This study presents an explainable deep learning framework for automated ten-class mango leaf disease classification using a publicly available dataset containing approximately 5000 images distributed across Anthracnose, Bacterial Canker, Cutting Weevil, Dag Disease, Die Back, Galls, Healthy, Powdery Mildew, Red Rust, and Sooty Mould classes. Unlike conventional AlexNet-based approaches, the proposed framework integrates Bayesian hyperparameter optimization, two-stage fine-tuning, test-time augmentation (TTA), and Grad-CAM-based explainability to improve both predictive performance and interpretability. Experimental results demonstrate that the proposed framework achieves a final test accuracy of 99.2% using eight-view test-time augmentation (TTA), with corresponding precision, recall, and F1-score of approximately 99.1%. The model also achieves micro-average and macro-average ROC–AUC scores of 1.00 on the curated test set, indicating strong discriminative capability across the considered disease categories. Comparative evaluations against MobileNetV2, DenseNet201, ConvNeXt, and LeafNet demonstrate competitive or superior classification performance while maintaining moderate computational complexity and architectural simplicity. Furthermore, Grad-CAM visualizations qualitatively highlight biologically relevant disease symptoms, including lesions, necrotic regions, rust spots, fungal growth, and tissue discoloration, thereby enhancing model interpretability. Although field-scale validation and quantitative explainability assessment remain subjects for future investigation, the proposed framework provides an accurate, computationally efficient, and interpretable approach for automated mango leaf disease diagnosis with strong potential for smart agriculture and precision farming applications.","植物病害的早期准确检测对于提高作物生产力和支持可持续农业实践至关重要。芒果（Mangifera indica）是全球最具经济重要性的热带水果作物之一，极易感染多种叶部病害，这些病害可显著降低产量和果实品质。本研究提出了一种可解释的深度学习框架，用于自动化十类芒果叶部病害分类，所使用的公开数据集包含约5000张图像，分布于炭疽病（Anthracnose）、细菌性溃疡病（Bacterial Canker）、切叶象甲（Cutting Weevil）、枯枝病（Dag Disease）、回枯病（Die Back）、虫瘿（Galls）、健康（Healthy）、白粉病（Powdery Mildew）、红锈病（Red Rust）和煤烟病（Sooty Mould）十个类别。与传统的基于AlexNet的方法不同，所提出的框架集成了贝叶斯超参数优化、两阶段微调、测试时增强（TTA）以及基于Grad-CAM的可解释性，以同时提升预测性能和可解释性。实验结果表明，所提出的框架在使用八视图测试时增强（TTA）时达到了99.2%的最终测试准确率，相应的精确率、召回率和F1分数约为99.1%。该模型在精选测试集上还取得了1.00的微平均和宏平均ROC–AUC分数，表明在所考虑的病害类别间具有较强的判别能力。与MobileNetV2、DenseNet201、ConvNeXt和LeafNet的对比评估表明，该框架在保持适中计算复杂度和架构简洁性的同时，具有竞争性或更优的分类性能。此外，Grad-CAM可视化定性地突出了具有生物学相关性的病害症状，包括病斑、坏死区域、锈斑、真菌生长和组织变色，从而增强了模型的可解释性。尽管田间规模验证和定量可解释性评估仍有待未来研究，但所提出的框架为自动化芒果叶部病害诊断提供了一种准确、计算高效且可解释的方法，在智慧农业和精准农业应用中具有强大潜力。","Intelligent Data Analysis","2026-10-15T00:00:00Z",76,{"impact":161,"substance":373,"depth":107,"authority":20,"freshness":21,"relevant":22,"comment":374},21,"将贝叶斯调参、两阶段微调与Grad-CAM结合用于十类芒果叶病识别，准确率99.2%，方法新颖且可解释性强，对智慧农业植保应用有参考价值。",[376],{"name":369,"url":366},[27,28,29,126,378],"芒果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":382},{"candidates":383,"agricultural_evidence":46},[384,388,392,397],{"code":33,"score":161,"supported":46,"title":385,"abstract":386,"tags":387},[48],[50,48],[28,29],{"code":62,"score":249,"supported":46,"title":389,"abstract":390,"tags":391},[],[27,126,245],[27,126],{"code":55,"score":133,"supported":46,"title":393,"abstract":394,"tags":396},[],[395],"芒果",[],{"code":262,"score":133,"supported":46,"title":398,"abstract":399,"tags":400},[],[265],[],[402,403],"芒果叶片病害 AlexNet","Grad-CAM 芒果病害识别","芒果叶片病害AlexNet-5080","10.1177\u002F1088467x261495708",{"doi":405,"openalex_id":407,"authors":408,"venue":369,"cited_by_count":83,"oa_url":9,"card":429,"direction":91,"ingested_from":92},"W7222328160",[409,412,415,417,420,423,426],{"name":410,"orcid":411},"Anay Ghosh","https:\u002F\u002Forcid.org\u002F0009-0006-6237-7905",{"name":413,"orcid":414},"Tawfikur Rahman","https:\u002F\u002Forcid.org\u002F0000-0002-0456-5143",{"name":416,"orcid":9},"Md Moniruzzaman",{"name":418,"orcid":419},"Nibedita Deb","https:\u002F\u002Forcid.org\u002F0000-0002-1579-1138",{"name":421,"orcid":422},"Hanan Abdullah Mengash","https:\u002F\u002Forcid.org\u002F0000-0002-4103-2434",{"name":424,"orcid":425},"Noorlindawaty Md Jizat","https:\u002F\u002Forcid.org\u002F0000-0001-7618-2283",{"name":427,"orcid":428},"Samir Salem Al‐Bawri","https:\u002F\u002Forcid.org\u002F0000-0003-2852-575X",{"tldr":430,"method":431,"finding":432,"direction":89,"opportunity":433},"提出可解释深度学习框架，用AlexNet结合贝叶斯调参、微调和Grad-CAM实现芒果叶病十分类。","AlexNet+贝叶斯超参优化、两阶段微调、八视图TTA、Grad-CAM，约5","测试准确率达99.2%，ROC-AUC为1.00，Grad-CAM能定位病斑等生物相关症状。","可延伸至田间复杂背景验证、可解释性定量评估及轻量化边缘部署研究。","2026-10-16T23:30:08.303796Z",{"id":436,"title":437,"url":438,"summary":439,"summary_zh":440,"content":9,"source_name":103,"source_url":438,"published_at":370,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":441,"sources":443,"tags":445,"primary_topic":448,"secondary_topics":449,"classification":450,"search_phrases":481,"slug":484,"view_count":22,"doi":485,"paper":486,"created_at":501},5076,"Trustworthy Explainable AI for Lettuce Growth Stage Prediction Using Sensor Data in Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.20944\u002Fpreprints202610.1452.v1","Background In precision agriculture, especially in hydroponic systems where environmental management affects both production and resource efficiency, interpretable modeling of crop phenological stages is crucial. Typical visualization-based approaches are generally expensive and ecologically dependent. To classify and visualize lettuce growth stages (Seedling, Vegetative Growth, Heading, Bolting and Senescence) using temperature, humidity, total dissolved solids (TDS) and pH, this study proposed XGB-StageVision, a sensor-powered machine learning setup combining supervised and unsupervised learning techniques. Using XG Boost, LightGBM, CatBoost, ExtraTrees, Random Forest and LSTM under an 80\u002F20 train-test split, a dataset of 3,169 unique observations from 70 hydroponically grown lettuce plants was evaluated. Methods and Results XGB-StageVision achieved 99.86% test accuracy, a ROC AUC of 1.00, an MCC of 0.9982 and perfect precision, recall, F1 scores and specificity across all classes, performing competitively with the best baseline models, including LightGBM, which achieved statistically comparable cross validation performance. The unsupervised t-SNE visualization showed clearly distinct structural clusters across growth stages, while SHAP revealed temperature as the strongest predictor (≈75% contribution), followed by TDS. Novel Contributions SHAP, LIME and t-SNE provided global, local and structural interpretability and transparent perspectives on environmental influences regarding plant development. Statistical analysis and 10-fold cross-validation were used to further test the model’s robustness, reliability and generalizability. Conclusion XGB-StageVision provides an IoT-ready, interpretable and imaging-free system for monitoring lettuce growth stages in real time. The framework combines supervised predictive modeling with unsupervised structural visualization to ensure transparency, sustainability and high performance, supporting resource-efficient, data-driven strategic planning in contemporary hydroponic agriculture to lower monitoring costs, optimize inputs and improve yield consistency.","背景 在精准农业中，尤其是在环境管理同时影响产量和资源效率的水培系统中，作物物候阶段的可解释建模至关重要。典型的基于可视化的方法通常成本高昂且依赖生态条件。为了利用温度、湿度、总溶解固体（TDS）和pH对生菜生长阶段（幼苗期、营养生长期、结球期、抽薹期和衰老期）进行分类和可视化，本研究提出了XGB-StageVision，一种由传感器驱动的机器学习方案，结合了监督学习和无监督学习技术。在80\u002F20的训练-测试划分下，使用XGBoost、LightGBM、CatBoost、ExtraTrees、随机森林和LSTM，对来自70株水培生菜的3，169个独特观测值数据集进行了评估。方法与结果 XGB-StageVision达到了99.86%的测试准确率、1.00的ROC AUC、0.9982的MCC，并在所有类别上实现了完美的精确率、召回率、F1分数和特异性，与最佳基线模型表现相当，包括LightGBM，其交叉验证性能在统计上具有可比性。无监督t-SNE可视化显示了各生长阶段之间明显不同的结构聚类，而SHAP揭示温度是最强的预测因子（约75%贡献），其次是TDS。新颖贡献 SHAP、LIME和t-SNE提供了全局、局部和结构可解释性，以及关于环境对植物发育影响的可透明视角。使用统计分析和10折交叉验证进一步检验了模型的稳健性、可靠性和泛化性。结论 XGB-StageVision提供了一种物联网就绪、可解释且无需成像的系统，用于实时监测生菜生长阶段。该框架将监督预测建模与无监督结构可视化相结合，以确保透明度、可持续性和高性能，支持当代水培农业中资源高效、数据驱动的战略规划，以降低监测成本、优化投入并提高产量一致性。",{"impact":17,"substance":18,"depth":107,"authority":95,"freshness":21,"relevant":22,"comment":442},"预印本论文，方法新颖、数据规模可观且强调可解释性，但尚未经同行评审，属细分领域技术进展。",[444],{"name":103,"url":438},[27,28,29,446,447],"水培生菜","传感器监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":451},{"candidates":452,"agricultural_evidence":46},[453,457,462,469,475],{"code":62,"score":222,"supported":46,"title":454,"abstract":455,"tags":456},[245],[126,127],[27],{"code":33,"score":309,"supported":46,"title":458,"abstract":459,"tags":461},[],[180,460],"machine learning",[28,29],{"code":463,"score":95,"supported":46,"title":464,"abstract":465,"tags":468},"I5",[],[466,467],"物联网","IoT",[],{"code":470,"score":133,"supported":46,"title":471,"abstract":472,"tags":474},"B1",[],[473],"生菜",[],{"code":476,"score":133,"supported":46,"title":477,"abstract":478,"tags":480},"B7",[],[479],"hydroponic",[],[482,483],"XGB-StageVision 生菜 生长阶段","水培生菜 传感器 生长预测","XGB-StageVision生菜生长阶段-5076","10.20944\u002Fpreprints202610.1452.v1",{"doi":485,"openalex_id":487,"authors":488,"venue":103,"cited_by_count":83,"oa_url":438,"card":496,"direction":91,"ingested_from":92},"W7222080602",[489,491,494],{"name":490,"orcid":9},"Muhammad Majid",{"name":492,"orcid":493},"Attia Ghafoor","https:\u002F\u002Forcid.org\u002F0009-0000-3828-6479",{"name":495,"orcid":9},"Amna Munir",{"tldr":497,"method":498,"finding":499,"direction":91,"opportunity":500},"提出XGB-StageVision，用传感器数据与可解释AI预测水培生菜生长阶段。","XGBoost等模型结合SHAP、LIME、t-SNE，基于3169条温湿度TD","测试准确率99.86%，温度贡献约75%，t-SNE显示各生长阶段聚类清晰。","可探索多作物、多环境迁移与低成本传感器部署下的可解释模型泛化能力。","2026-10-16T23:30:08.020788Z"]