[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4982":3,"related-4982":85},{"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":65,"slug":68,"view_count":21,"doi":69,"paper":70,"created_at":84},4982,"A Nightshade-SWIN Transformer-Based Framework for Enhanced Multi-Crop Plant Disease Classification","https:\u002F\u002Fdoi.org\u002F10.17148\u002Fijarcce.2026.151037","Nightshade crops (Solanaceae) face significant yield threats from phenotypically similar foliar diseases that can be difficult to distinguish during the early stages of infection.Accurate and timely disease identification is therefore essential for reducing crop losses, improving disease management, and supporting sustainable agricultural practices.While Convolutional Neural Networks (CNNs) have demonstrated strong performance in image-based plant disease classification due to their ability to extract spatial and local features, they may have limitations in capturing long-range dependencies and global contextual relationships within leaf images.These limitations become particularly important when disease symptoms exhibit subtle differences in texture, color, shape, and lesion distribution or when images are captured against complex field backgrounds.To address these challenges, we propose Nightshade-SWIN, an optimized deep learning framework based on the Swin Transformer architecture.The proposed framework utilizes a hierarchical shifted-window self-attention mechanism to effectively capture both minute lesion textures and global leaf morphology.By progressively learning multi-scale representations, Nightshade-SWIN can identify discriminative pathological characteristics while maintaining computational efficiency.The model was evaluated on a curated dataset of 5,000 multicrop images collected under variable field conditions, including differences in illumination, background complexity, leaf orientation, and disease severity.Experimental results demonstrate that Nightshade-SWIN achieves a peak classification accuracy of 94.6%, outperforming ResNet50 and EfficientNet-B0 by 4.9% and 3.4%, respectively.These results indicate the effectiveness of transformer-based feature learning for distinguishing visually similar foliar diseases.Furthermore, interpretability analysis using LIME and Grad-CAM confirms that the model primarily focuses on biologically relevant pathological regions, such as lesions, discoloration, spots, and infected leaf areas.This enhances the transparency and reliability of the proposed framework and supports its potential application in precision agriculture, automated crop monitoring, and early disease diagnosis.","茄科作物（Solanaceae）面临表型相似叶部病害的严重产量威胁，这些病害在感染早期难以区分。因此，准确及时地识别病害对于减少作物损失、改善病害管理以及支持可持续农业实践至关重要。尽管卷积神经网络（CNN）因其提取空间和局部特征的能力而在基于图像的植物病害分类中表现出色，但它们在捕捉叶片图像中的长距离依赖关系和全局上下文关联方面可能存在局限。当病害症状在纹理、颜色、形状和病斑分布上表现出细微差异，或图像在复杂田间背景下拍摄时，这些局限尤为突出。为应对这些挑战，我们提出了Nightshade-SWIN，一种基于Swin Transformer架构的优化深度学习框架。该框架利用分层移位窗口自注意力机制，有效捕捉微小的病斑纹理和全局叶片形态。通过逐步学习多尺度表征，Nightshade-SWIN能够在保持计算效率的同时识别具有判别力的病理特征。该模型在包含5,000张多作物图像的数据集上进行了评估，这些图像采集自多变田间条件，包括光照、背景复杂度、叶片朝向和病害严重程度的差异。实验结果表明，Nightshade-SWIN达到了94.6%的最高分类准确率，分别优于ResNet50和EfficientNet-B0达4.9%和3.4%。这些结果表明了基于Transformer的特征学习在区分视觉相似叶部病害方面的有效性。此外，使用LIME和Grad-CAM进行的可解释性分析证实，该模型主要关注生物学相关的病理区域，如病斑、变色、斑点及受感染叶片区域。这增强了所提框架的透明度和可靠性，并支持其在精准农业、自动化作物监测和早期病害诊断中的潜在应用。",null,"IJARCCE","2026-10-14T00:00:00Z","论文",10,false,68,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},12,20,17,9,1,"该论文提出基于Swin Transformer的茄科作物病害分类框架，在5000张多作物图像上达到94.6%准确率，方法新颖、数据规模可观，对智慧农业病害识别有参考价值，但属细分领域学术进展，公共影响有限。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","精准农业","植物病害识别","茄科作物",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":47},[44,52,58],{"code":45,"score":46,"supported":47,"title":48,"abstract":49,"tags":51},"I1",8,true,[],[28,50],"precision agriculture",[26,28],{"code":32,"score":46,"supported":47,"title":53,"abstract":54,"tags":57},[],[55,56],"深度学习","deep learning",[27,29],{"code":59,"score":60,"supported":47,"title":61,"abstract":62,"tags":64},"H8",3,[],[63],"可持续农业",[],[66,67],"Nightshade-SWIN 病害分类","Swin Transformer 植物病害","Nightshade-SWIN病害分类-4982","10.17148\u002Fijarcce.2026.151037",{"doi":69,"openalex_id":71,"authors":72,"venue":10,"cited_by_count":75,"oa_url":6,"card":76,"direction":82,"ingested_from":83},"W7221746668",[73],{"name":74,"orcid":9},"Dr. Barkha Joshi",0,{"tldr":77,"method":78,"finding":79,"direction":80,"opportunity":81},"提出Nightshade-SWIN框架，用Swin Transformer提升茄科多作物叶片病害分类","基于Swin Transformer的移位窗口自注意力，5000张田间多作物图像","分类准确率达94.6%，优于ResNet50和EfficientNet-B0，且模型关注病斑等生物相","农业人工智能与决策模型","可探索轻量化Transformer在移动端实时病害诊断及跨作物迁移学习，结合多模态数据提升田间泛化能力。","智慧农业 \u002F 农业物联网","openalex","2026-10-15T23:30:08.177373Z",{"total":86,"page":21,"page_size":86,"items":87},6,[88,149,212,268,328,428],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":9,"source_name":94,"source_url":91,"published_at":95,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":97,"sources":101,"tags":103,"primary_topic":105,"secondary_topics":106,"classification":107,"search_phrases":119,"slug":122,"view_count":21,"doi":123,"paper":124,"created_at":148},4425,"Fuzzy-guided hyperparameter optimization for efficient CNN-based plant disease classification","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-64880-3","Abstract Deep Convolutional Neural Networks (DCNNs) have exhibited outstanding performance in plant disease classification. Nevertheless, their usefulness is very susceptible to hyperparameter selection. Efficient Hyper-Parameter Optimization (HPO) remains a fundamental challenge in deploying deep learning models for plant disease classification, as implementing extensive search techniques such as grid search, Bayesian Optimization (BO), and evolutionary algorithms requires considerable computational cost. Such conventional HPO approaches frequently rely on single-objective fitness criteria and demand substantial computational resources. Moreover, these approaches often lack interpretability in decision making. In this study, we propose an HPO based on a Fuzzy Inference System (FIS) approach that integrates a Mamdani FIS into the hyperparameter selection process of a DCNN. It maintains classification accuracy, while speeding up the hyperparameter selection process. The candidate configurations are assessed based on several factors, including validation accuracy, validation loss, and training time, rather than being assessed based on just one factor. These factors are combined into a single, crisp fitness score using fuzzy linguistic rules, providing transparent, interpretable, and multi-objective decision making. In order to minimize computational cost, candidate hyperparameters are first assessed using a quick partial training method that makes use of frozen convolutional layers and warm-started weights. A Mamdani FIS is then used to aggregate performance metrics including accuracy, loss, and training time, producing a crisp score for candidate ranking. After that, training of the chosen hyperparameters is exposed to fully end-to-end training, resulting in superior classification performance with respect to the state-of-the-art exhaustive search techniques. Experiments have been executed on four public plant disease datasets, using an AlexNet-based architecture, where the first experiments have been performed on a baseline model with a randomly-chosen hyperparameter configuration before the fuzzy-guided optimization process is initiated. Then, the model is performed with the best optimized hyperparameter configuration selected by the fuzzy-guided optimization process, demonstrating up to 29% improvement in accuracy, precision, recall and F1-score, along with reliable and comprehensible hyperparameter ranking and optimization. The achieved results show that while keeping an acceptable computing cost, the introduced fuzzy-guided technique consistently outperforms baseline model configurations with respect to all evaluation metrics, yielding greater classification accuracy and enhanced generalization. Hence, our suggested approach provides a lightweight, comprehensible, and efficient solution for hyperparameter tuning in the plant disease classification domain when compared to conventional HPO techniques, offering a practical direction for resource-efficient model optimization in precision agriculture that enables quick deployment of deep learning systems.","深度卷积神经网络（DCNN）在植物病害分类中表现出卓越的性能。然而，其有效性极易受到超参数选择的影响。高效超参数优化（HPO）仍然是将深度学习模型部署于植物病害分类中的一个基本挑战，因为实施网格搜索、贝叶斯优化（BO）和进化算法等大规模搜索技术需要相当大的计算成本。这类传统HPO方法通常依赖单目标适应度标准，并且需要大量计算资源。此外，这些方法在决策过程中往往缺乏可解释性。在本研究中，我们提出了一种基于模糊推理系统（FIS）的HPO方法，将Mamdani FIS集成到DCNN的超参数选择过程中。该方法在保持分类精度的同时，加快了超参数选择过程。候选配置基于多个因素进行评估，包括验证准确率、验证损失和训练时间，而不是仅基于单一因素进行评估。这些因素通过模糊语言规则组合为一个单一的清晰适应度分数，从而提供透明、可解释且多目标的决策。为了最小化计算成本，候选超参数首先通过一种快速部分训练方法进行评估，该方法利用冻结的卷积层和热启动权重。随后，使用Mamdani FIS聚合包括准确率、损失和训练时间在内的性能指标，生成用于候选排序的清晰分数。之后，对所选超参数进行完全端到端训练，从而相对于最先进的穷举搜索技术取得更优的分类性能。实验在四个公开植物病害数据集上执行，采用基于AlexNet的架构，其中在启动模糊引导优化过程之前，首先在随机选择超参数配置的基线模型上进行实验。然后，使用由模糊引导优化过程选出的最佳优化超参数配置运行模型，在准确率、精确率、召回率和F1分数上最高提升29%，同时实现可靠且可理解的超参数排序与优化。所获得的结果表明","Scientific Reports","2026-10-06T00:00:00Z",74,{"impact":98,"substance":18,"depth":19,"authority":99,"freshness":46,"relevant":21,"comment":100},15,14,"提出模糊推理系统驱动的多目标超参数优化方法，在四个公开植物病害数据集上显著提升CNN分类性能，兼具方法新颖性与农业落地价值。",[102],{"name":94,"url":91},[26,27,28,29,104],"超参数优化",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":108},{"candidates":109,"agricultural_evidence":47},[110,114],{"code":32,"score":46,"supported":47,"title":111,"abstract":112,"tags":113},[],[55,56],[27,29],{"code":45,"score":115,"supported":47,"title":116,"abstract":117,"tags":118},5,[],[50],[26,28],[120,121],"CNN 植物病害分类","模糊推理 超参数优化","CNN植物病害分类-4425","10.1038\u002Fs41598-026-64880-3",{"doi":123,"openalex_id":125,"authors":126,"venue":94,"cited_by_count":75,"oa_url":142,"card":143,"direction":82,"ingested_from":83},"W7220695608",[127,129,131,134,137,139],{"name":128,"orcid":9},"Medhat Hamdy",{"name":130,"orcid":9},"Heba M. Elhoseny",{"name":132,"orcid":133},"Fathi E. Abd El‐Samie","https:\u002F\u002Forcid.org\u002F0000-0001-8749-9518",{"name":135,"orcid":136},"Adel S. El‐Fishawy","https:\u002F\u002Forcid.org\u002F0000-0003-1567-457X",{"name":138,"orcid":9},"Sami A. El‐Dolil",{"name":140,"orcid":141},"Elhossiny Ibrahim","https:\u002F\u002Forcid.org\u002F0000-0001-5421-2170","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-64880-3_reference.pdf",{"tldr":144,"method":145,"finding":146,"direction":80,"opportunity":147},"提出模糊推理系统引导的CNN超参数优化方法，用于植物病害分类，兼顾精度与效率。","Mamdani模糊推理系统结合部分训练与热启动权重，在四个公开病害数据集上优化A","相比传统穷举搜索，精度等指标最高提升29%，且超参数排序可解释、计算成本更低。","可将模糊多目标HPO迁移到轻量边缘设备或跨作物迁移学习场景，探索动态超参数自适应机制。","2026-10-08T23:30:12.271848Z",{"id":150,"title":151,"url":152,"summary":153,"summary_zh":154,"content":9,"source_name":155,"source_url":152,"published_at":156,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":157,"score_detail":158,"sources":163,"tags":165,"primary_topic":167,"secondary_topics":172,"classification":174,"search_phrases":191,"slug":194,"view_count":21,"doi":195,"paper":196,"created_at":211},3885,"InResKolArno_SCO: An Efficient Plant Disease Classification Framework for IoT-Enabled Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.1142\u002Fs0218001426500503","This study proposes a hybrid approach for plant disease classification, integrating Swarm Cray Optimization (SCO) with the InResKolArno, a deep learning model, to address challenges like environmental sensitivity, high computational demands, and limited resources in IoT environments. The process begins with collecting a plant disease recognition dataset, followed by image preprocessing steps such as nearest neighbor interpolation and normalization to improve quality. Disease regions are isolated using color-based thresholding for segmentation. Feature extraction is carried out using deep convolutional neural networks (DCNN), specifically VGG16 and GoogLeNet, to extract high-level leaf features. The InResKolArno classifier, enhanced by SCO (a combination of Particle Swarm Optimization and Crayfish Optimization), is employed to categorize the leaves into three classes: healthy, rust, and powdery mildew. This method improves classification accuracy and reduces data transmission costs in IoT-based precision farming systems. The proposed model achieves high performance with an accuracy of 99.41% and a Positive Predictive Value (PPV) of 99.69%, identifying plant diseases in just 28 seconds. This hybrid model provides superior computational efficiency, making it suitable for real-time deployment in smart farming applications, effectively identifying plant diseases for early intervention and better crop management.","本研究提出了一种植物病害分类的混合方法，将群虾优化算法（Swarm Cray Optimization，SCO）与深度学习模型InResKolArno相结合，以应对物联网环境中的环境敏感性、高计算需求和资源受限等挑战。该流程首先收集植物病害识别数据集，随后进行图像预处理步骤，如最近邻插值和归一化，以提高图像质量。利用基于颜色的阈值分割方法分离病害区域。采用深度卷积神经网络（DCNN），具体为VGG16和GoogLeNet，进行特征提取，以获取叶片的高层特征。经SCO（粒子群优化与螯虾优化的结合）增强的InResKolArno分类器用于将叶片分为三类：健康、锈病和白粉病。该方法提高了分类准确率，并降低了基于物联网的精准农业系统中的数据传输成本。所提出的模型实现了高性能，准确率达99.41%，阳性预测值（PPV）达99.69%，仅需28秒即可识别植物病害。该混合模型具有优越的计算效率，适用于智能农业应用中的实时部署，能够有效识别植物病害，从而实现早期干预和更好的作物管理。","International Journal of Pattern Recognition and Artificial Intelligence","2026-09-30T00:00:00Z",76,{"impact":159,"substance":160,"depth":19,"authority":161,"freshness":20,"relevant":21,"comment":162},16,21,13,"提出SCO优化InResKolArno的植物病害分类框架，准确率99.41%、28秒识别，面向IoT智慧农业实时部署，方法新颖且数据可靠，值得入选。",[164],{"name":155,"url":152},[26,27,166,28,29],"物联网",{"code":168,"slug":169,"name":170,"path":171,"parent_code":36},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[173],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":175},{"candidates":176,"agricultural_evidence":47},[177,182,187],{"code":168,"score":98,"supported":47,"title":178,"abstract":180,"tags":181},[179],"IoT",[166,179],[166],{"code":45,"score":161,"supported":47,"title":183,"abstract":185,"tags":186},[184],"smart agriculture",[28],[26,28],{"code":32,"score":46,"supported":47,"title":188,"abstract":189,"tags":190},[],[55,56],[27,29],[192,193],"InResKolArno SCO 植物病害分类","VGG16 GoogLeNet 病害识别","InResKolArnoSCO植物病害分类-3885","10.1142\u002Fs0218001426500503",{"doi":195,"openalex_id":197,"authors":198,"venue":155,"cited_by_count":75,"oa_url":9,"card":206,"direction":82,"ingested_from":83},"W7214976120",[199,202,204],{"name":200,"orcid":201},"Chitoor Venkat Rao Ajay Kumar","https:\u002F\u002Forcid.org\u002F0009-0001-4082-5416",{"name":203,"orcid":9},"C. Anbuananth",{"name":205,"orcid":9},"Pandi Chiranjeevi",{"tldr":207,"method":208,"finding":209,"direction":82,"opportunity":210},"提出InResKolArno_SCO混合框架，用于物联网智慧农业中的植物病害分类。","VGG16与GoogLeNet提取特征，结合粒子群与螯虾优化算法优化分类器。","在健康、锈病、白粉病三分类上准确率达99.41%，仅需28秒。","可探索轻量化模型在边缘设备上的部署，并扩展至更多病害与田间复杂环境验证。","2026-10-01T23:30:09.723646Z",{"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":225,"tags":227,"primary_topic":229,"secondary_topics":230,"classification":231,"search_phrases":250,"slug":253,"view_count":75,"doi":254,"paper":255,"created_at":267},2178,"Hybrid explainable DeiT-based framework for plant disease classification and severity estimation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02191-2","The detection of plant diseases is essential for preserving agricultural productivity and food security; however, existing approaches often suffer from limited interpretability and generalization capability. This study proposes a hybrid deep learning framework based on Data-efficient Image Transformers (DeiT) for plant disease classification and severity estimation. The framework employs DeiT-Base, DeiT-Small, and DeiT-Tiny models to capture global contextual dependencies in plant leaf images. To improve interpretability, a hybrid Explainable Artificial Intelligence (XAI) module is introduced by combining Gradient-weighted Class Activation Mapping (Grad-CAM) for local feature attribution with Attention Rollout for global dependency visualization. In addition, HSV-based segmentation is applied after classification to isolate disease-relevant regions for damage ratio computation, severity estimation, and explanation refinement. The damage ratio is further integrated with Hybrid XAI attention maps to estimate disease severity. Experiments were conducted on the New Plant Diseases Dataset (Augmented), comprising 70,295 training images and 17,572 validation images across 38 disease classes and 14 plant species. The proposed DeiT-Base model achieved a maximum classification accuracy of 99.13%, outperforming several CNN architectures, including ResNet50, DenseNet121, MobileNetV3, EfficientNet-B4, and InceptionV3. Furthermore, the proposed Hybrid XAI framework demonstrated superior interpretability performance in terms of Focus Score, Background Noise, Signal-to-Noise Ratio (SNR), and Entropy compared with individual explanation methods. Overall, the proposed framework improves classification accuracy, enhances model transparency, and provides meaningful disease severity estimation, making it a promising solution for intelligent precision agriculture.","植物病害检测对于保障农业生产力和粮食安全至关重要，然而现有方法往往存在可解释性有限和泛化能力不足的问题。本研究提出了一种基于数据高效图像Transformer（Data-efficient Image Transformers，DeiT）的混合深度学习框架，用于植物病害分类和严重程度估计。该框架采用DeiT-Base、DeiT-Small和DeiT-Tiny模型来捕获植物叶片图像中的全局上下文依赖关系。为提高可解释性，引入了一种混合可解释人工智能（Explainable Artificial Intelligence，XAI）模块，将用于局部特征归因的梯度加权类激活映射（Gradient-weighted Class Activation Mapping，Grad-CAM）与用于全局依赖可视化的注意力展开（Attention Rollout）相结合。此外，在分类之后应用基于HSV的分割来分离病害相关区域，以进行损伤比率计算、严重程度估计和解释优化。损伤比率进一步与混合XAI注意力图相结合以估计病害严重程度。实验在新植物病害数据集（增强版）（New Plant Diseases Dataset (Augmented)）上进行，该数据集包含70,295张训练图像和17,572张验证图像，涵盖38个病害类别和14种植物物种。所提出的DeiT-Base模型达到了99.13%的最高分类准确率，优于多种CNN架构，包括ResNet50、DenseNet121、MobileNetV3、EfficientNet-B4和InceptionV3。此外，所提出的混合XAI框架在聚焦分数（Focus Score）、背景噪声（Background Noise）、信噪比（Signal-to-Noise Ratio，SNR）和熵（Entropy）方面表现出优于单一解释方法的可解释性性能。总体而言，所提出的框架提高了分类准确率，增强了模型透明度，并提供了有意义的病害严重程度估计，使其成为智能精准农业的一种有前景的解决方案。","Discover Artificial Intelligence","2026-09-10T00:00:00Z",78,{"impact":222,"substance":223,"depth":222,"authority":17,"freshness":46,"relevant":21,"comment":224},18,22,"基于DeiT与混合可解释AI的植物病害分类与严重度估计研究，在7万张图像、38类病害上取得99.13%准确率，方法新颖、数据扎实，对智慧农业病害智能诊断有参考价值。",[226],{"name":218,"url":215},[26,27,228,28,29],"可解释AI",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":232},{"candidates":233,"agricultural_evidence":47},[234,239,243],{"code":32,"score":17,"supported":47,"title":235,"abstract":236,"tags":238},[],[55,56,237],"artificial intelligence",[27,228,29],{"code":45,"score":46,"supported":47,"title":240,"abstract":241,"tags":242},[],[28,50],[26,28],{"code":244,"score":86,"supported":47,"title":245,"abstract":246,"tags":249},"A8",[],[247,248],"粮食安全","food security",[],[251,252],"农业人工智能 植物病害识别 智慧农业 精准农业","农业人工智能 植物病害识别","农业人工智能植物病害识别智慧农业精准农业-2178","10.1007\u002Fs44163-026-02191-2",{"doi":254,"openalex_id":256,"authors":257,"venue":218,"cited_by_count":75,"oa_url":215,"card":262,"direction":80,"ingested_from":83},"W7212179384",[258,260],{"name":259,"orcid":9},"Muskan Batra",{"name":261,"orcid":9},"Pooja Sharma",{"tldr":263,"method":264,"finding":265,"direction":80,"opportunity":266},"提出基于DeiT的混合可解释框架，实现植物病害分类与严重度估计。","DeiT-Base\u002FSmall\u002FTiny结合Grad-CAM与Attention","DeiT-Base分类准确率达99.13%，混合XAI可解释性指标优于单一方法。","可探索轻量化DeiT在边缘设备部署及多模态数据融合的病害严重度实时估计。","2026-09-11T23:30:47.756846Z",{"id":269,"title":270,"url":271,"summary":272,"summary_zh":273,"content":9,"source_name":274,"source_url":271,"published_at":275,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":279,"tags":281,"primary_topic":284,"secondary_topics":290,"classification":292,"search_phrases":309,"slug":311,"view_count":75,"doi":312,"paper":313,"created_at":327},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",69,{"impact":46,"substance":160,"depth":222,"authority":17,"freshness":13,"relevant":21,"comment":278},"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[280],{"name":274,"url":271},[26,27,282,29,283],"小农户","可解释性",{"code":285,"slug":286,"name":287,"path":288,"parent_code":289},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[291],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":293},{"candidates":294,"agricultural_evidence":47},[295,300,305],{"code":285,"score":17,"supported":47,"title":296,"abstract":298,"tags":299},[297],"smallholder",[297],[282],{"code":32,"score":13,"supported":47,"title":301,"abstract":303,"tags":304},[302],"computer vision",[],[27,29],{"code":45,"score":21,"supported":14,"title":306,"abstract":307,"tags":308},[],[],[26],[310,252],"农业人工智能 植物病害识别 可解释性 智慧农业","农业人工智能植物病害识别可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":312,"openalex_id":314,"authors":315,"venue":274,"cited_by_count":75,"oa_url":271,"card":322,"direction":80,"ingested_from":83},"W7223137323",[316,318,320],{"name":317,"orcid":9},"Akshay Ramgoolam",{"name":319,"orcid":9},"Priya Bundhoo Appadoo",{"name":321,"orcid":9},"Jean-Noël LEspérance",{"tldr":323,"method":324,"finding":325,"direction":80,"opportunity":326},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z",{"id":329,"title":330,"url":331,"summary":332,"summary_zh":333,"content":9,"source_name":334,"source_url":331,"published_at":275,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":335,"score_detail":336,"sources":338,"tags":340,"primary_topic":342,"secondary_topics":343,"classification":351,"search_phrases":404,"slug":407,"view_count":75,"doi":408,"paper":409,"created_at":427},5553,"Artificial Intelligence–Driven Precision Agriculture Systems: Engineering Frameworks for Climate-Resilient Food Production","https:\u002F\u002Fdoi.org\u002F10.53982\u002Fajerd.2026.01.14-j","Climate change, soil issues, water scarcity, and the increasing need for food worldwide mean we need smart farming systems that can manage resources flexibly. Old farming methods used the same inputs and simple rules for decisions. AI can help us manage resources better by adapting and optimizing them as we deal with complex environmental factors. This paper looks closely at AI-powered precision agriculture systems designed to make food production more resilient to changing weather. The authors reviewed research from 2021 to 2026 in agricultural engineering, computer engineering, and environmental systems. The authors examined how machine learning, deep learning, reinforcement learning, computer vision, robotics, and IoT sensors are used for predicting crop yields, spotting diseases, improving irrigation, managing nutrients, and automating field tasks. Our analysis shows that hybrid deep learning models (CNN-LSTM) are better than single models for predicting crop yields over space and time. Reinforcement learning algorithms are also better at adjusting irrigation cycles when weather is unpredictable. Using edge computing for system design reduces delays and improves real-time decision-making compared to traditional cloud-based systems. However, there are still big challenges with understanding how AI models work, having enough diverse data, ensuring cybersecurity, setting common standards, and making these systems affordable, especially in developing countries. To tackle these problems, we suggest a framework that combines AI analysis, distributed sensor networks, adaptive controls, and climate risk assessments. The authors provided critical insights into essential research gaps and outline a technological roadmap towards achieving sustainable, resilient and intelligent agricultural systems.","气候变化、土壤问题、水资源短缺以及全球日益增长的粮食需求，意味着我们需要能够灵活管理资源的智能农业系统。传统农业方法对相同的投入采用固定模式，并依赖简单规则进行决策。人工智能可以帮助我们更好地管理资源，通过适应和优化资源利用来应对复杂的环境因素。本文深入探讨了人工智能驱动的精准农业系统，旨在使粮食生产对不断变化的天气更具韧性。作者综述了2021年至2026年间农业工程、计算机工程和环境系统领域的研究。作者考察了机器学习、深度学习、强化学习、计算机视觉、机器人技术及物联网传感器如何被用于作物产量预测、病害识别、灌溉优化、养分管理和田间作业自动化。我们的分析表明，混合深度学习模型（CNN-LSTM）在时空作物产量预测方面优于单一模型。在天气不可预测的情况下，强化学习算法在调整灌溉周期方面也表现更优。与传统基于云的系统相比，采用边缘计算进行系统设计可降低延迟并改善实时决策能力。然而，在理解人工智能模型的工作原理、获取足够多样化的数据、确保网络安全、制定通用标准以及使这些系统具备可负担性方面，仍存在重大挑战，尤其是在发展中国家。为应对这些问题，我们提出了一个融合人工智能分析、分布式传感器网络、自适应控制和气候风险评估的框架。作者对关键研究空白提供了重要见解，并勾勒了实现可持续、韧性和智能农业系统的技术路线图。","ABUAD Journal of Engineering Research and Development (AJERD)",80,{"impact":222,"substance":223,"depth":222,"authority":161,"freshness":20,"relevant":21,"comment":337},"系统综述AI驱动精准农业的工程框架与技术路线，方法梳理扎实、结论有参考价值，但属综述类论文，产业落地影响有限。",[339],{"name":334,"url":331},[26,27,166,28,341],"气候韧性",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[344,345],{"code":168,"slug":169,"name":170,"path":171,"parent_code":36},{"code":346,"slug":347,"name":348,"path":349,"parent_code":350},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"status":39,"locked":14,"version":40,"method":41,"evidence":352},{"candidates":353,"agricultural_evidence":47},[354,361,365,371,377,385,392,398],{"code":32,"score":222,"supported":47,"title":355,"abstract":356,"tags":360},[237],[55,357,358,359,56,302],"机器学习","计算机视觉","machine learning",[27],{"code":45,"score":159,"supported":47,"title":362,"abstract":363,"tags":364},[50],[28,50],[26,28],{"code":168,"score":13,"supported":47,"title":366,"abstract":367,"tags":370},[],[166,368,179,369],"边缘计算","edge computing",[166],{"code":346,"score":20,"supported":47,"title":372,"abstract":373,"tags":376},[],[374,375,347],"灌溉","水资源",[],{"code":378,"score":379,"supported":47,"title":380,"abstract":381,"tags":384},"H7",7,[],[382,383],"气候变化","climate change",[341],{"code":386,"score":86,"supported":47,"title":387,"abstract":388,"tags":391},"H2",[],[389,390],"土壤","soil",[],{"code":393,"score":60,"supported":47,"title":394,"abstract":395,"tags":397},"A7",[],[396],"间作",[],{"code":399,"score":60,"supported":47,"title":400,"abstract":401,"tags":403},"F3",[],[402],"养分管理",[],[405,406],"AI 精准农业 气候韧性","CNN-LSTM 作物产量预测","AI精准农业气候韧性-5553","10.53982\u002Fajerd.2026.01.14-j",{"doi":408,"openalex_id":410,"authors":411,"venue":334,"cited_by_count":75,"oa_url":331,"card":422,"direction":82,"ingested_from":83},"W7223121456",[412,415,417,419],{"name":413,"orcid":414},"Olumayowa J. Iyanda","https:\u002F\u002Forcid.org\u002F0000-0002-5340-9884",{"name":416,"orcid":9},"Oluwadare OYEBODE",{"name":418,"orcid":9},"Iretiayo Adelaiye",{"name":420,"orcid":421},"Ayomide Afolabi","https:\u002F\u002Forcid.org\u002F0000-0002-5171-886X",{"tldr":423,"method":424,"finding":425,"direction":80,"opportunity":426},"综述2021-2026年AI驱动精准农业系统，提出气候韧性粮食生产工程框架。","综述机器学习、深度学习、强化学习、计算机视觉、机器人与物联网在精准农业中的应用。","CNN-LSTM混合模型和强化学习在产量预测与灌溉调度上优于单一方法，边缘计算提升实时性。","可研究边缘计算与强化学习结合的轻量级灌溉决策系统，并探索发展中国家低成本部署与标准化路径。","2026-10-22T11:20:18.151376Z",{"id":429,"title":430,"url":431,"summary":432,"summary_zh":433,"content":9,"source_name":434,"source_url":431,"published_at":435,"category":12,"cover_url":9,"hotness":13,"is_selected":47,"score":436,"score_detail":437,"sources":442,"tags":444,"primary_topic":447,"secondary_topics":448,"classification":449,"search_phrases":477,"slug":480,"view_count":467,"doi":481,"paper":482,"created_at":508},5382,"Modeling the global potential of smart farming innovations","https:\u002F\u002Fdoi.org\u002F10.1073\u002Fpnas.2530081123","Smart farming innovations can improve agricultural productivity, resilience, and environmental sustainability, yet their real-world impact hinges on their diffusion dynamics, which in turn depend on their economic viability. We present here a global assessment of the profitability of smart farming innovation across croplands at a spatial resolution of ~5 km from the farmers’ and the societal perspectives. We cover application mapping for precision agriculture, automated application of inputs, autonomous weeding machines, GPS steering assistance systems, and autonomous irrigation systems. For this, we compiled a globally comprehensive dataset of smart farming innovation adoption locations (N = 4,422) based on a combination of a survey (N = 2,677) and a meta-analysis (N = 1,745) and combined them with remotely sensed and statistical data to train an ensemble of five geospatial machine learning models (generalized linear models, random forests, support vector machines, maximum entropy, and boosted regression trees), which show the global distribution of the different innovations’ profitability and its overlap with major environmental issues the innovations can help to mitigate. Simulations of future socioeconomic pathways combined with assumptions about future agri-environmental policies reveal that, especially in middle-income countries, the potential of smart farming will grow over time.","智慧农业创新能够提升农业生产力、韧性和环境可持续性，然而其现实影响取决于扩散动态，而扩散动态又取决于其经济可行性。本文从农民和社会两个视角，以约5公里的空间分辨率对全球农田范围内智慧农业创新的盈利能力进行了评估。研究涵盖精准农业的应用测绘、投入品的自动化施用、自主除草机械、GPS转向辅助系统以及自主灌溉系统。为此，我们基于一项调查（N = 2,677）和一项元分析（N = 1,745）相结合，编制了全球范围内较为全面的智慧农业创新采用地点数据集（N = 4,422），并将其与遥感和统计数据相结合，用于训练由五种地理空间机器学习模型（广义线性模型、随机森林、支持向量机、最大熵和提升回归树）组成的集成模型，这些模型揭示了不同创新盈利能力的全球分布及其与这些创新有助于缓解的主要环境问题的重叠情况。对未来社会经济路径的模拟结合对未来农业环境政策的假设表明，智慧农业的潜力将随时间推移而增长，尤其是在中等收入国家。","Proceedings of the National Academy of Sciences","2026-10-19T00:00:00Z",93,{"impact":438,"substance":439,"depth":440,"authority":98,"freshness":20,"relevant":21,"comment":441},26,24,19,"PNAS 全球尺度智慧农业盈利性评估，数据规模与方法新颖，结论对智慧农业推广具政策参考价值，值得进入每日精选。",[443],{"name":434,"url":431},[26,27,28,445,446],"遥感","全球评估",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":450},{"candidates":451,"agricultural_evidence":47},[452,457,461,465,471],{"code":45,"score":453,"supported":47,"title":454,"abstract":455,"tags":456},11,[],[26,28,50],[26,28],{"code":32,"score":379,"supported":47,"title":458,"abstract":459,"tags":460},[],[357,359],[27],{"code":346,"score":86,"supported":47,"title":462,"abstract":463,"tags":464},[],[374,347],[],{"code":466,"score":467,"supported":47,"title":468,"abstract":469,"tags":470},"I3",4,[],[445],[445],{"code":472,"score":60,"supported":47,"title":473,"abstract":474,"tags":476},"F4",[],[475],"除草",[],[478,479],"农业人工智能 全球评估 智慧农业 精准农业","农业人工智能 全球评估","农业人工智能全球评估智慧农业精准农业-5382","10.1073\u002Fpnas.2530081123",{"doi":481,"openalex_id":483,"authors":484,"venue":434,"cited_by_count":75,"oa_url":431,"card":503,"direction":82,"ingested_from":83},"W7222974188",[485,488,491,494,497,500],{"name":486,"orcid":487},"Shahrear Roman","https:\u002F\u002Forcid.org\u002F0009-0006-5659-4292",{"name":489,"orcid":490},"Hadi Hadi","https:\u002F\u002Forcid.org\u002F0000-0002-2410-9751",{"name":492,"orcid":493},"Wyclife Agumba Oluoch","https:\u002F\u002Forcid.org\u002F0000-0003-0803-9279",{"name":495,"orcid":496},"David Zilberman","https:\u002F\u002Forcid.org\u002F0000-0001-5743-5134",{"name":498,"orcid":499},"Robert Finger","https:\u002F\u002Forcid.org\u002F0000-0002-0634-5742",{"name":501,"orcid":502},"David Wuepper","https:\u002F\u002Forcid.org\u002F0000-0002-1344-6023",{"tldr":504,"method":505,"finding":506,"direction":82,"opportunity":507},"全球5公里尺度评估五类智慧农业创新在农田的盈利性与扩散潜力。","整合4422个采用点调查与元分析数据，用五种地理空间机器学习集成建模。","智慧农业盈利性空间差异显著，中等收入国家未来潜力将随社会经济路径增长。","可结合区域政策与农户异质性，细化盈利性预测并评估环境协同效益。","2026-10-20T23:30:08.754594Z"]