[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3137":3,"related-3137":130},{"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":82,"slug":85,"view_count":86,"doi":87,"paper":88,"created_at":129},3137,"From patterns to prediction: detecting crop sequence and interpreting crop selection with explainable AI at field level in Denmark","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104982","CONTEXT Crop sequences are important for sustainable agriculture, yet we know relatively little about how they recur across individual fields or which information best predicts the crop grown each year. Denmark's national field records allow both questions to be examined over time. OBJECTIVE We identified recurrent crop sequences across Denmark and tested how well annual crop-family selection could be predicted from crop history, farm characteristics, management, prices, soil and climate. METHODS Using 10 years (2011−2020) of national field-level crop data (∼600,000 fields yr −1 ), we developed a heuristic algorithm to detect recurring crop sequence patterns. We then trained machine learning (LightGBM) and deep learning (TabNet) models to predict annual crop choices based on preceding crops and lagged management and farm structure predictors, and pedoclimatic conditions. Models were evaluated through forward-chaining validation and temporal holdout tests, and SHAP values were used to examine how LightGBM used each predictor. RESULTS AND DISCUSSION Crop sequences were largely dominated by cereals, with little diversification even in longer sequences. Crop selection patterns were strongly associated with the previous crops and farm typology, but pedoclimatic conditions and previous management played a minor role. The DL model achieved a slightly higher overall accuracy, particularly for dominant crops, while the ML model provided a more balanced performance across different crops and enabled interpretation through SHAP. SIGNIFICANCE The analysis separates two distinct tasks: identifying multi-year crop sequences and predicting the crop family grown each year. The sequence analysis shows why diversification cannot be assessed from sequence length or crop counts alone. The predictive models could help generate locally plausible sequences for agri-environmental simulations, reducing reliance on standard rotations that poorly reflect observed field histories.","背景 作物序列对可持续农业至关重要，但我们对它们在单个田块中如何重复出现，以及哪些信息最能预测每年种植的作物知之甚少。丹麦的国家田块记录使这两个问题得以在长时间尺度上加以考察。 目标 我们识别了丹麦全国范围内重复出现的作物序列，并检验了年度作物科选择能在多大程度上由作物历史、农场特征、管理、价格、土壤和气候来预测。 方法 利用10年（2011−2020年）的国家田块级作物数据（每年约60万块田），我们开发了一种启发式算法来检测重复出现的作物序列模式。随后，我们训练了机器学习（LightGBM）和深度学习（TabNet）模型，基于前茬作物以及滞后的管理和农场结构预测因子及土壤气候条件来预测年度作物选择。模型通过前向链式验证和时间留出测试进行评估，并使用SHAP值考察LightGBM如何利用每个预测因子。 结果与讨论 作物序列在很大程度上以谷类作物为主，即使在较长的序列中也几乎没有多样化。作物选择模式与前茬作物和农场类型密切相关，而土壤气候条件和先前管理的作用较小。深度学习模型取得了略高的总体准确率，尤其是在优势作物上，而机器学习模型在不同作物之间提供了更均衡的表现，并可通过SHAP进行解释。 意义 该分析区分了两个不同的任务：识别多年作物序列和预测每年种植的作物科。序列分析表明，为什么不能仅凭序列长度或作物计数来评估多样化。预测模型有助于为农业环境模拟生成局部合理的序列，减少对不能很好反映观测田块历史的标准轮作方式的依赖。",null,"Agricultural Systems","2026-09-21T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,9,1,"基于丹麦十年全国田块数据，用可解释AI预测作物选择，方法新颖、数据规模大，对农业信息化与轮作模拟有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","可解释AI","作物轮作","丹麦农业",{"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":47},[45,55,63,70,77],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":54},11,true,[],[50,51,52,53],"深度学习","机器学习","machine learning","deep learning",[28,29],{"code":56,"score":57,"supported":47,"title":58,"abstract":59,"tags":62},"H2",6,[],[60,61],"土壤","soil",[],{"code":64,"score":57,"supported":47,"title":65,"abstract":66,"tags":69},"H8",[],[67,68],"可持续农业","sustainable agriculture",[],{"code":71,"score":72,"supported":47,"title":73,"abstract":74,"tags":76},"A7",3,[],[75],"轮作",[],{"code":78,"score":22,"supported":14,"title":79,"abstract":80,"tags":81},"I1",[],[],[27],[83,84],"丹麦 作物序列 机器学习","LightGBM 作物选择 预测","丹麦作物序列机器学习-3137",5,"10.1016\u002Fj.agsy.2026.104982",{"doi":87,"openalex_id":89,"authors":90,"venue":10,"cited_by_count":121,"oa_url":6,"card":122,"direction":126,"ingested_from":128},"W7213919617",[91,93,96,99,101,103,105,107,110,112,115,118],{"name":92,"orcid":9},"João G. Serra",{"name":94,"orcid":95},"Edwin Haas","https:\u002F\u002Forcid.org\u002F0000-0003-0664-642X",{"name":97,"orcid":98},"Diego Ábalos","https:\u002F\u002Forcid.org\u002F0000-0002-4189-5563",{"name":100,"orcid":9},"Søren Kolind Hvid",{"name":102,"orcid":9},"Tommy Dalgaard",{"name":104,"orcid":9},"Lars Uldall-Jessen",{"name":106,"orcid":9},"Franca Giannini-Kurina",{"name":108,"orcid":109},"Meshach Ojo Aderele","https:\u002F\u002Forcid.org\u002F0009-0007-9381-6445",{"name":111,"orcid":9},"Bo Thiesson",{"name":113,"orcid":114},"Jørgen Eivind Olesen","https:\u002F\u002Forcid.org\u002F0000-0002-6639-1273",{"name":116,"orcid":117},"Klaus Butterbach‐Bahl","https:\u002F\u002Forcid.org\u002F0000-0001-9499-6598",{"name":119,"orcid":120},"Jaber Rahimi","https:\u002F\u002Forcid.org\u002F0000-0002-2754-2358",0,{"tldr":123,"method":124,"finding":125,"direction":126,"opportunity":127},"用丹麦十年田块数据识别轮作模式并预测年度作物选择。","60万田块年数据，启发式序列检测+LightGBM\u002FTabNet，SHAP解释。","作物序列以谷物为主、多样化低；作物选择主要由前茬和农场类型决定。","农业人工智能与决策模型","可结合可解释AI生成区域化可行轮作方案，替代脱离实际的标准化轮作假设。","openalex","2026-09-22T23:30:05.518307Z",{"total":57,"page":22,"page_size":57,"items":131},[132,210,283,360,411,486],{"id":133,"title":134,"url":135,"summary":136,"summary_zh":137,"content":9,"source_name":138,"source_url":135,"published_at":139,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":140,"score_detail":141,"sources":146,"tags":148,"primary_topic":151,"secondary_topics":152,"classification":153,"search_phrases":175,"slug":178,"view_count":121,"doi":179,"paper":180,"created_at":209},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":17,"substance":142,"depth":143,"authority":144,"freshness":21,"relevant":22,"comment":145},21,17,13,"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。",[147],{"name":138,"url":135},[27,28,29,149,150],"精准农业","芒果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":154},{"candidates":155,"agricultural_evidence":47},[156,160,165,171],{"code":33,"score":17,"supported":47,"title":157,"abstract":158,"tags":159},[53],[50,53],[28,29],{"code":78,"score":46,"supported":47,"title":161,"abstract":162,"tags":164},[],[27,149,163],"smart agriculture",[27,149],{"code":166,"score":72,"supported":47,"title":167,"abstract":168,"tags":170},"B2",[],[169],"芒果",[],{"code":64,"score":72,"supported":47,"title":172,"abstract":173,"tags":174},[],[67],[],[176,177],"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":179,"openalex_id":181,"authors":182,"venue":138,"cited_by_count":121,"oa_url":9,"card":203,"direction":208,"ingested_from":128},"W7222328160",[183,186,189,191,194,197,200],{"name":184,"orcid":185},"Anay Ghosh","https:\u002F\u002Forcid.org\u002F0009-0006-6237-7905",{"name":187,"orcid":188},"Tawfikur Rahman","https:\u002F\u002Forcid.org\u002F0000-0002-0456-5143",{"name":190,"orcid":9},"Md Moniruzzaman",{"name":192,"orcid":193},"Nibedita Deb","https:\u002F\u002Forcid.org\u002F0000-0002-1579-1138",{"name":195,"orcid":196},"Hanan Abdullah Mengash","https:\u002F\u002Forcid.org\u002F0000-0002-4103-2434",{"name":198,"orcid":199},"Noorlindawaty Md Jizat","https:\u002F\u002Forcid.org\u002F0000-0001-7618-2283",{"name":201,"orcid":202},"Samir Salem Al‐Bawri","https:\u002F\u002Forcid.org\u002F0000-0003-2852-575X",{"tldr":204,"method":205,"finding":206,"direction":126,"opportunity":207},"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。","智慧农业 \u002F 农业物联网","2026-10-16T23:30:08.303796Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":215,"content":9,"source_name":216,"source_url":213,"published_at":139,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":217,"score_detail":218,"sources":222,"tags":224,"primary_topic":227,"secondary_topics":228,"classification":229,"search_phrases":262,"slug":265,"view_count":22,"doi":266,"paper":267,"created_at":282},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。","Preprints.org",64,{"impact":219,"substance":220,"depth":143,"authority":57,"freshness":21,"relevant":22,"comment":221},12,20,"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。",[223],{"name":216,"url":213},[27,28,29,225,226],"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":230},{"candidates":231,"agricultural_evidence":47},[232,238,243,250,256],{"code":78,"score":233,"supported":47,"title":234,"abstract":235,"tags":237},15,[163],[149,236],"precision agriculture",[27],{"code":33,"score":239,"supported":47,"title":240,"abstract":241,"tags":242},8,[],[51,52],[28,29],{"code":244,"score":57,"supported":47,"title":245,"abstract":246,"tags":249},"I5",[],[247,248],"物联网","IoT",[],{"code":251,"score":72,"supported":47,"title":252,"abstract":253,"tags":255},"B1",[],[254],"生菜",[],{"code":257,"score":72,"supported":47,"title":258,"abstract":259,"tags":261},"B7",[],[260],"hydroponic",[],[263,264],"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":266,"openalex_id":268,"authors":269,"venue":216,"cited_by_count":121,"oa_url":213,"card":277,"direction":208,"ingested_from":128},"W7222080602",[270,272,275],{"name":271,"orcid":9},"Muhammad Majid",{"name":273,"orcid":274},"Attia Ghafoor","https:\u002F\u002Forcid.org\u002F0009-0000-3828-6479",{"name":276,"orcid":9},"Amna Munir",{"tldr":278,"method":279,"finding":280,"direction":208,"opportunity":281},"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",{"id":284,"title":285,"url":286,"summary":287,"summary_zh":288,"content":9,"source_name":289,"source_url":286,"published_at":290,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":291,"score_detail":292,"sources":294,"tags":296,"primary_topic":299,"secondary_topics":305,"classification":307,"search_phrases":329,"slug":332,"view_count":22,"doi":333,"paper":334,"created_at":359},4993,"Effects of within-season temporal aggregation of weather variables on performance and interpretability in rice yield machine learning models","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-75646-2","While crop responses are inherently stage-dependent, machine learning yield models often rely on weather variables aggregated over the entire growing season. This study evaluates how within-season temporal aggregation of weather variables affects both predictive performance and interpretability in machine learning-based rice yield modeling. Using CYGMA (Crop Yield Growth Model with Assumptions on Climate and Socioeconomics)-simulated potential yield as a synthetic response variable, we minimized confounding effects from observational noise and management variability, enabling a clearer evaluation of the role of within-season weather aggregation. Daily weather variables were averaged over the rice growing period after dividing each season into multiple equal-length segments, and several machine learning algorithms were trained and evaluated using temporally independent validation. Increasing within-season temporal resolution improved model performance up to a moderate level, after which gains diminished. Interpretation using SHAP (SHapley Additive exPlanations) and response diagnostics consistently indicated that yield sensitivity concentrates in specific windows of the season, with temperature-related effects emerging most strongly early in the season and humidity-related effects later. Finer temporal aggregation sharpened the identification of window-specific nonlinear and threshold-like responses that were obscured under coarse seasonal averages. Overall, moderate within-season aggregation provides a practical balance between predictive skill and mechanistic interpretability, supporting more reliable identification of phenology-relevant meteorological risks for climate-impact assessment and decision support.","尽管作物响应本质上具有阶段依赖性，但机器学习产量模型往往依赖于整个生长季聚合的天气变量。本研究评估了天气变量的季节内时间聚合如何影响基于机器学习的水稻产量建模的预测性能与可解释性。以CYGMA（Crop Yield Growth Model with Assumptions on Climate and Socioeconomics，气候与社会经济假设下的作物产量生长模型）模拟的潜在产量作为合成响应变量，我们最大限度地减少了观测噪声和管理变异性带来的混杂效应，从而能够更清晰地评估季节内天气聚合的作用。将每个生长季划分为多个等长时段后，对水稻生长期内的逐日天气变量进行平均，并采用时间独立验证对多种机器学习算法进行训练和评估。提高季节内时间分辨率可提升模型性能，直至达到中等水平，此后增益递减。利用SHAP（SHapley Additive exPlanations，沙普利加性解释）和响应诊断进行的解释一致表明，产量敏感性集中在季节的特定窗口，温度相关效应在季节早期最为显著，湿度相关效应则在后期出现。更精细的时间聚合增强了对窗口特异性非线性和阈值型响应的识别，而这些响应在粗粒度季节平均下被掩盖。总体而言，中等程度的季节内聚合在预测能力与机制可解释性之间提供了实用平衡，有助于更可靠地识别与物候相关的气象风险，以支持气候影响评估和决策支持。","Scientific Reports","2026-10-13T00:00:00Z",72,{"impact":219,"substance":220,"depth":19,"authority":20,"freshness":239,"relevant":22,"comment":293},"该研究通过CYGMA模拟数据系统评估了生长季内气象变量时间聚合对水稻产量机器学习模型性能与可解释性的影响，方法新颖、结论可靠，对农业气象风险识别与决策支持有参考价值，但属学术论文，公共影响范围有限。",[295],{"name":289,"url":286},[27,28,29,297,298],"农业气象","水稻产量预测",{"code":300,"slug":301,"name":302,"path":303,"parent_code":304},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[306],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":308},{"candidates":309,"agricultural_evidence":47},[310,316,320,325],{"code":33,"score":311,"supported":47,"title":312,"abstract":313,"tags":315},19,[52],[51,52,314],"decision support",[28,29],{"code":300,"score":20,"supported":47,"title":317,"abstract":318,"tags":319},[301],[302,301],[],{"code":321,"score":22,"supported":14,"title":322,"abstract":323,"tags":324},"H7",[],[],[297],{"code":78,"score":22,"supported":14,"title":326,"abstract":327,"tags":328},[],[],[27],[330,331],"水稻产量 机器学习 气象","SHAP 水稻 产量预测","水稻产量机器学习气象-4993","10.1038\u002Fs41598-026-75646-2",{"doi":333,"openalex_id":335,"authors":336,"venue":289,"cited_by_count":121,"oa_url":353,"card":354,"direction":208,"ingested_from":128},"W7221657053",[337,339,341,343,345,347,350],{"name":338,"orcid":9},"Noh-Hyun Lee",{"name":340,"orcid":9},"Wonjae Jeong",{"name":342,"orcid":9},"Hyeon-Ji Yang",{"name":344,"orcid":9},"Hana Cho",{"name":346,"orcid":9},"Hyeon-Yeong Ju",{"name":348,"orcid":349},"Toshichika Iizumi","https:\u002F\u002Forcid.org\u002F0000-0002-0611-4637",{"name":351,"orcid":352},"Ki‐Tae Kim","https:\u002F\u002Forcid.org\u002F0000-0002-8249-5283","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75646-2_reference.pdf",{"tldr":355,"method":356,"finding":357,"direction":126,"opportunity":358},"评估生长季内天气变量时间聚合粒度对水稻产量机器学习模型预测与可解释性的影响。","用CYGMA模拟潜在产量作响应变量，按等长时段聚合逐日天气，训练多种机器学习模型","适度提高季内时间分辨率可提升性能，产量敏感性集中在特定窗口，温度效应偏早、湿度效应偏晚。","可探索不同作物与气候区下最优聚合粒度，并将窗口特异性气象风险嵌入气候影响评估与决策支持系统。","2026-10-15T23:30:10.483881Z",{"id":361,"title":362,"url":363,"summary":364,"summary_zh":365,"content":9,"source_name":366,"source_url":363,"published_at":290,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":217,"score_detail":367,"sources":369,"tags":371,"primary_topic":374,"secondary_topics":375,"classification":376,"search_phrases":394,"slug":397,"view_count":72,"doi":398,"paper":399,"created_at":410},4907,"PEAS-DeiT: Multi-Scale Spatial Attention Enhanced DeiT for Pea Leaf Disease Classification","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fapp162010113","Early and accurate detection of pea diseases is essential for reducing crop losses and supporting precision agriculture. Although deep learning methods have shown good performance in plant disease classification, CNN-based models may have limitations in learning long-range relationships and detailed disease features. In this study, an explainable transformer-based framework, named PEAS-DeiT, is proposed for automated pea leaf disease classification. The proposed approach integrates a multi-scale spatial attention mechanism into the Data-efficient Image Transformer (DeiT) architecture to enhance the representation of disease-related visual features. A unified pea leaf disease dataset (UPLDD) was constructed by combining multiple publicly available datasets, covering six classes, including five disease categories and healthy samples. The proposed model was evaluated against CNN-based and transformer-based architectures using five-fold cross-validation. Furthermore, explainable artificial intelligence (XAI) analysis was performed to investigate the regions contributing to model predictions. Experimental results demonstrate that PEAS-DeiT achieved an accuracy of 93.11%, showing competitive performance compared with the evaluated CNN and transformer-based models. The gradient-based saliency analysis also revealed localized response patterns in several evaluated samples, providing qualitative insight into the image regions contributing to model predictions. Statistical analyses were conducted to evaluate the performance differences among the compared models. These findings indicate that PEAS-DeiT provides a competitive approach for pea leaf disease classification within the evaluated experimental setting.","豌豆病害的早期准确检测对于减少作物损失和支持精准农业至关重要。尽管深度学习方法在植物病害分类中表现出良好性能，但基于卷积神经网络（CNN）的模型在学习长程关系和病害细节特征方面可能存在局限。本研究提出了一种基于Transformer的可解释框架PEAS-DeiT，用于豌豆叶片病害的自动化分类。该方法将多尺度空间注意力机制集成到数据高效图像Transformer（DeiT）架构中，以增强病害相关视觉特征的表征能力。通过整合多个公开数据集，构建了统一的豌豆叶片病害数据集（UPLDD），涵盖六个类别，包括五类病害和健康样本。采用五折交叉验证，将所提模型与基于CNN和基于Transformer的架构进行了评估比较。此外，进行了可解释人工智能（XAI）分析，以探究对模型预测有贡献的区域。实验结果表明，PEAS-DeiT达到了93.11%的准确率，与所评估的基于CNN和基于Transformer的模型相比展现出有竞争力的性能。基于梯度的显著性分析还揭示了若干评估样本中的局部响应模式，为理解对模型预测有贡献的图像区域提供了定性见解。通过统计分析评估了所比较模型之间的性能差异。这些发现表明，在所评估的实验设置下，PEAS-DeiT为豌豆叶片病害分类提供了一种有竞争力的方法。","Applied Sciences",{"impact":239,"substance":19,"depth":17,"authority":144,"freshness":21,"relevant":22,"comment":368},"提出多尺度空间注意力增强的DeiT模型用于豌豆叶病害分类，构建六类统一数据集并达93.11%准确率，方法有创新但属实验室验证阶段，产业影响有限。",[370],{"name":366,"url":363},[27,28,29,372,373],"植物病害识别","豌豆",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":377},{"candidates":378,"agricultural_evidence":47},[379,384,389],{"code":33,"score":219,"supported":47,"title":380,"abstract":381,"tags":383},[],[50,53,382],"artificial intelligence",[28,29,372],{"code":78,"score":385,"supported":47,"title":386,"abstract":387,"tags":388},7,[],[149,236],[27],{"code":390,"score":22,"supported":14,"title":391,"abstract":392,"tags":393},"A5",[],[],[373],[395,396],"PEAS-DeiT 豌豆叶病害","DeiT 植物病害分类","PEAS-DeiT豌豆叶病害-4907","10.3390\u002Fapp162010113",{"doi":398,"openalex_id":400,"authors":401,"venue":366,"cited_by_count":121,"oa_url":363,"card":405,"direction":126,"ingested_from":128},"W7221612639",[402],{"name":403,"orcid":404},"Fatma Ozge Ozkok","https:\u002F\u002Forcid.org\u002F0000-0002-1421-4670",{"tldr":406,"method":407,"finding":408,"direction":126,"opportunity":409},"提出PEAS-DeiT模型，将多尺度空间注意力融入DeiT，实现豌豆叶片病害分类。","多尺度空间注意力增强DeiT，构建UPLDD数据集，五折交叉验证与XAI分析。","PEAS-DeiT达到93.11%准确率，优于对比的CNN和Transformer模型。","可探索轻量化Transformer在移动端病害识别中的部署，并扩展多作物跨域泛化能力。","2026-10-14T23:30:46.091813Z",{"id":412,"title":413,"url":414,"summary":415,"summary_zh":416,"content":9,"source_name":417,"source_url":414,"published_at":418,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":419,"score_detail":420,"sources":422,"tags":424,"primary_topic":426,"secondary_topics":427,"classification":428,"search_phrases":456,"slug":459,"view_count":121,"doi":460,"paper":461,"created_at":485},4811,"Explainable deep learning framework for real-time insect pest detection in smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02109-y","Abstract Global losses of crop production due to insect pest infestations are estimated to be around 20–40% annually, which represents one of the highest threats to agricultural productivity, farmer livelihoods and food security. Current manual scouting is labor intensive, subjective and non-scalable, and many automated scouting methods suffer when they come to deal with different field conditions and offer little insight into decision making. To tackle these challenges, this study proposes Crop Protection in Smart Agriculture—Real-time Insect Pest Detection using Continual Spatio-Temporal Graph Convolutional Network (CPSA-RIPD-CSTGCN), a unified and interpretable deep learning framework that combines the four synergistic components: (i) the Ensemble Transform Schmidt–Kalman Filter (ETSKF) for image preprocessing, including resizing, normalization, and noise suppression; (ii) data augmentation using rotation, flipping, scaling, shearing, and contrast adjustment, which enhances generalization and reduces overfitting; (iii) the Continual Spatio-Temporal Graph Convolutional Network (CSTGCN) that jointly models the spatial dependency across crop regions and temporal evolution of pest dynamics to achieve robust feature extraction and classification; and (iv) the Revolution Optimization Algorithm (ROA) for hyperparameter optimization of CSTGCN weights to adaptively adjust the network. Further, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization is introduced to give post-hoc explainability as it shows regions that are relevant to the biological process and areas that are affected by pests. This framework was tested on IP102 benchmark dataset with 60%-40%-split train-test with 10 economically important classes of pests with 97% accuracy, 98% precision, 98% recall and 98% F1 score, mean ± 0.32% accuracy, across 5-fold cross validation. Among other baseline models, these results consistently outperform VGG16 (82%), InceptionV3 (85%), MobileNetV2 (87%), DenseNet121 (88%), EfficientNetB0 (89%) and task-specific models like EDCP-DIA-RNN(Early Disease and Crop Pest—Diagnosis\u002FDetection using Image Analysis RNN) (94%), EPCY-TPA-ANN (Efficient Prediction of Crop Yield—Through Parameter Analysis ANN) (91%) and ICPM-ESA-CNN (Interactive Crop and Pest Management Enhanced Soil Analysis CNN) (90%). The results of ablation studies showed the solitary effects of each module of the Ensemble Transform Schmidt–Kalman Filter pre-processing and Revolution Optimization Algorithm optimization, and the confusion matrix analysis demonstrated high per-class reliability and only a small amount of misclassification, implying that the proposed method could be applied to real-time, large-scale smart agriculture deployments.","摘要 由于害虫侵扰导致的全球作物产量损失估计每年约为20–40%，这是对农业生产力、农民生计和粮食安全的最大威胁之一。当前的人工田间巡查劳动强度大、主观性强且难以规模化，而许多自动化巡查方法在面对不同田间条件时表现不佳，且对决策制定提供的洞见有限。为应对这些挑战，本研究提出了智慧农业中的作物保护——基于持续时空图卷积网络的实时害虫检测（CPSA-RIPD-CSTGCN），这是一个统一且可解释的深度学习框架，融合了四个协同组件：（i）集成变换施密特-卡尔曼滤波器（ETSKF），用于图像预处理，包括调整尺寸、归一化和噪声抑制；（ii）使用旋转、翻转、缩放、剪切和对比度调整进行数据增强，以增强泛化能力并减少过拟合；（iii）持续时空图卷积网络（CSTGCN），联合建模作物区域间的空间依赖性和害虫动态的时间演化，以实现鲁棒的特征提取和分类；（iv）革命优化算法（ROA），用于CSTGCN权重的超参数优化，以自适应调整网络。此外，引入梯度加权类激活映射（Grad-CAM）可视化以提供事后可解释性，因为它显示了与生物过程相关的区域以及受害虫影响的区域。该框架在IP102基准数据集上进行了测试，采用60%-40%的训练-测试划分，涵盖10个具有经济重要性的害虫类别，在5折交叉验证中达到了97%的准确率、98%的精确率、98%的召回率和98%的F1分数，准确率均值±0.32%。在其他基线模型中，这些结果持续优于VGG16（82%）、InceptionV3（85%）、MobileNetV2（87%）、DenseNet121（88%）、EfficientNetB0（89%）以及特定任务模型，如EDCP-DIA-RNN（基于图像分析的早期病害和作物害虫诊断\u002F检测RNN）（94%）、EPCY-TPA-ANN（通过参数分析人工神经网络高效预测作物产量）（91%）和ICPM-ESA-CNN（交互式作物和害虫管理增强土壤分析CNN）（90%）。消融研究的结果显示了集成变换施密特-卡尔曼滤波器预处理和革命优化算法各模块的单独效果。","Discover Artificial Intelligence","2026-10-12T00:00:00Z",80,{"impact":19,"substance":18,"depth":19,"authority":144,"freshness":21,"relevant":22,"comment":421},"提出可解释时空图卷积虫害实时检测框架，在IP102基准上达97%准确率并优于多种主流模型，方法新颖、数据扎实，对智慧农业植保具有参考价值。",[423],{"name":417,"url":414},[27,28,29,50,425],"病虫害检测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":429},{"candidates":430,"agricultural_evidence":47},[431,435,439,446,450],{"code":33,"score":143,"supported":47,"title":432,"abstract":433,"tags":434},[53],[50,53],[28,29,50,425],{"code":78,"score":233,"supported":47,"title":436,"abstract":437,"tags":438},[163],[27,163],[27],{"code":440,"score":57,"supported":47,"title":441,"abstract":442,"tags":445},"A8",[],[443,444],"粮食安全","food security",[],{"code":56,"score":57,"supported":47,"title":447,"abstract":448,"tags":449},[],[60,61],[],{"code":451,"score":72,"supported":47,"title":452,"abstract":453,"tags":455},"F4",[],[454],"crop protection",[],[457,458],"IP102 害虫检测","CSTGCN 虫害识别","IP102害虫检测-4811","10.1007\u002Fs44163-026-02109-y",{"doi":460,"openalex_id":462,"authors":463,"venue":417,"cited_by_count":121,"oa_url":414,"card":480,"direction":208,"ingested_from":128},"W7221565168",[464,467,470,473,476,478],{"name":465,"orcid":466},"J. Briskilal","https:\u002F\u002Forcid.org\u002F0000-0003-4849-3249",{"name":468,"orcid":469},"M. K. Vidhyalakshmi","https:\u002F\u002Forcid.org\u002F0000-0002-6879-9897",{"name":471,"orcid":472},"Aswathy K Cherian","https:\u002F\u002Forcid.org\u002F0009-0002-3679-2583",{"name":474,"orcid":475},"S. Neduncheliyan","https:\u002F\u002Forcid.org\u002F0009-0002-0904-8695",{"name":477,"orcid":9},"Ajay Kumar",{"name":479,"orcid":9},"Rakesh Kumar",{"tldr":481,"method":482,"finding":483,"direction":126,"opportunity":484},"提出可解释深度学习框架CPSA-RIPD-CSTGCN，实现智慧农业中害虫实时检测。","用CSTGCN时空图卷积、ROA超参优化、ETSKF预处理与Grad-CAM，在","10类害虫检测准确率97%，优于VGG16、EfficientNetB0及多种任务专用模型。","可探索轻量化模型在边缘设备部署，并融合多模态田间数据提升跨域泛化能力。","2026-10-13T23:30:10.529316Z",{"id":487,"title":488,"url":489,"summary":490,"summary_zh":491,"content":9,"source_name":492,"source_url":489,"published_at":418,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":291,"score_detail":493,"sources":495,"tags":497,"primary_topic":500,"secondary_topics":501,"classification":502,"search_phrases":518,"slug":521,"view_count":22,"doi":522,"paper":523,"created_at":541},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。","Tarım Bilimleri Dergisi",{"impact":219,"substance":220,"depth":19,"authority":144,"freshness":21,"relevant":22,"comment":494},"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。",[496],{"name":492,"url":489},[27,28,29,498,499],"柑橘","病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":503},{"candidates":504,"agricultural_evidence":47},[505,509,514],{"code":33,"score":220,"supported":47,"title":506,"abstract":507,"tags":508},[53],[50,53,382,314],[28,29,499],{"code":166,"score":385,"supported":47,"title":510,"abstract":511,"tags":513},[],[498,512],"citrus",[498],{"code":78,"score":22,"supported":14,"title":515,"abstract":516,"tags":517},[],[],[27],[519,520],"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":522,"openalex_id":524,"authors":525,"venue":492,"cited_by_count":121,"oa_url":535,"card":536,"direction":208,"ingested_from":128},"W7221532433",[526,529,532],{"name":527,"orcid":528},"Kürşad Buğrahan Yapar","https:\u002F\u002Forcid.org\u002F0009-0006-7666-6177",{"name":530,"orcid":531},"Nurettin Doğan","https:\u002F\u002Forcid.org\u002F0000-0002-8267-8469",{"name":533,"orcid":534},"Özgür Öksüz","https:\u002F\u002Forcid.org\u002F0000-0001-5568-6116","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5543457",{"tldr":537,"method":538,"finding":539,"direction":126,"opportunity":540},"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。","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。","2026-10-13T23:30:08.943247Z"]