[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3626":3,"related-3626":118},{"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":95,"slug":98,"view_count":99,"doi":100,"paper":101,"created_at":117},3626,"A Hybrid Model for Crop Yield Prediction Using Recurrent Neural Networks and Explainable Artificial Intelligence","https:\u002F\u002Fdoi.org\u002F10.22194\u002Fjgias\u002F27.2061","Accurate maize yield prediction is essential for ensuring food security and supporting agricultural planning in Kenya. However, the changes in climate and severe weather are posing more challenges to the stability of yield and food security. While advanced machine learning models, such as Long Short–Term Memory (LSTM) networks, offer strong predictive performance, their inherent \"black–box\" nature limits their practical adoption by farmers and policymakers who require interpretable and trustworthy insights. This study developed a transparent predictive model by integrating LSTM with Explainable Artificial Intelligence (XAI). Using county–level maize yield data (2012–2023), the hybrid model was compared against Random Forest and Gradient Boosting baselines. The LSTM model achieved superior performance (R² = 0.8551, RMSE = 0.3715, MAE = 0.2705), compared to Random Forest (R2 = 0.8441, RMSE= 0.3851 and MAE= 0.2856) and Gradient Boosting (R2 = 0.7925, RMSE = 0.4443 and MAE = 0.3234) baselines. XAI analysis, using SHapley Additive explanations (SHAP) and Local Interpretable Model–agnostic Explanations (LIME), identified longitude, latitude, and annual rainfall as key predictors. The model maintained high accuracy while improving interpretability, increasing transparency and trust. This provides actionable insights for farmers and policymakers, supporting evidence–based planning and enhancing resilience in smallholder systems. Keywords: Crop yield prediction, long short–term memory (LSTM), explainable artificial intelligence, precision agriculture, machine learning.","准确的玉米产量预测对于保障肯尼亚粮食安全和支持农业规划至关重要。然而，气候变化和极端天气对产量稳定性和粮食安全构成了更多挑战。尽管长短期记忆（LSTM）网络等先进机器学习模型具有强大的预测性能，但其固有的“黑箱”特性限制了农民和政策制定者的实际采用，因为他们需要可解释且可信的洞见。本研究通过将LSTM与可解释人工智能（XAI）相结合，开发了一个透明的预测模型。利用县级玉米产量数据（2012—2023年），将该混合模型与随机森林和梯度提升基线模型进行了比较。LSTM模型取得了更优的性能（R² = 0.8551，RMSE = 0.3715，MAE = 0.2705），优于随机森林（R2 = 0.8441，RMSE= 0.3851，MAE= 0.2856）和梯度提升（R2 = 0.7925，RMSE = 0.4443，MAE = 0.3234）基线模型。使用SHapley加法解释（SHAP）和局部可解释模型无关解释（LIME）进行的XAI分析，确定了经度、纬度和年降雨量是关键预测因子。该模型在保持高精度的同时提高了可解释性，增强了透明度和信任。这为农民和政策制定者提供了可操作的洞见，支持基于证据的规划，并增强小农系统的韧性。关键词：作物产量预测，长短期记忆（LSTM），可解释人工智能，精准农业，机器学习。",null,"Journal of Global Innovations in Agricultural Sciences","2026-09-25T00:00:00Z","论文",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,21,17,13,8,1,"将LSTM与可解释AI结合用于肯尼亚县级玉米产量预测，方法新颖、指标详实，对智慧农业有参考价值，但属境外区域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","机器学习","可解释AI","玉米产量预测",{"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},[45,53,61,69,76,83,89],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":52},20,true,[49],"artificial intelligence",[29,51,49],"machine learning",[28,30,29],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":60},"I1",7,[],[58,59],"精准农业","precision agriculture",[27],{"code":62,"score":63,"supported":47,"title":64,"abstract":65,"tags":68},"A3",6,[],[66,67],"玉米","maize",[],{"code":70,"score":63,"supported":47,"title":71,"abstract":72,"tags":75},"A8",[],[73,74],"粮食安全","food security",[],{"code":77,"score":78,"supported":47,"title":79,"abstract":80,"tags":82},"G2",3,[],[81],"smallholder",[],{"code":84,"score":78,"supported":47,"title":85,"abstract":86,"tags":88},"H7",[],[87],"气候变化",[],{"code":90,"score":78,"supported":47,"title":91,"abstract":92,"tags":94},"J1",[],[93],"农业规划",[],[96,97],"LSTM 玉米产量预测","SHAP LIME 农业模型","LSTM玉米产量预测-3626",5,"10.22194\u002Fjgias\u002F27.2061",{"doi":100,"openalex_id":102,"authors":103,"venue":10,"cited_by_count":109,"oa_url":6,"card":110,"direction":114,"ingested_from":116},"W7214446524",[104,106],{"name":105,"orcid":9},"Stephen Gitau Ndung’u",{"name":107,"orcid":108},"Consolata Gakii","https:\u002F\u002Forcid.org\u002F0000-0003-2783-9992",0,{"tldr":111,"method":112,"finding":113,"direction":114,"opportunity":115},"用LSTM结合可解释AI预测肯尼亚玉米产量，兼顾精度与透明度。","基于2012-2023县级玉米产量数据，LSTM融合SHAP与LIME，对比随机","LSTM精度最高（R²=0.8551），经度、纬度和年降雨量是主要预测因子。","农业人工智能与决策模型","可探索将可解释AI与遥感、气象多源数据融合，提升小农户区域产量预测的可信度与推广性。","openalex","2026-09-27T23:31:22.771605Z",{"total":63,"page":22,"page_size":63,"items":119},[120,211,291,369,437,512],{"id":121,"title":122,"url":123,"summary":124,"summary_zh":125,"content":9,"source_name":126,"source_url":123,"published_at":127,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":128,"score_detail":129,"sources":134,"tags":136,"primary_topic":139,"secondary_topics":140,"classification":147,"search_phrases":184,"slug":187,"view_count":109,"doi":188,"paper":189,"created_at":210},5400,"Artificial intelligence in food safety: a bibliometric and empirical synthesis of emerging technologies and research frontiers","https:\u002F\u002Fdoi.org\u002F10.1108\u002Fbfj-06-2025-0819","Purpose This study aimed to identify recent research trends in the integration of artificial intelligence (AI) with food safety and security through a comprehensive bibliometric analysis. Design\u002Fmethodology\u002Fapproach A total of 2,782 documents published between 2021 and 2025 were retrieved from the Web of Science Core Collection. The dataset was refined by removing duplicates, filtering document types and excluding irrelevant records. VOSviewer was then used to conduct co-authorship, keyword co-occurrence, citation, co-citation and bibliographic coupling analyses. Findings Machine learning and deep learning emerged as core technologies associated with food security, contamination detection and quality prediction. Keyword clustering demonstrated interdisciplinary connections with agriculture, climate change and public health. Citation and co-citation analyses identified three major intellectual foundations: traditional machine learning, computer vision-based deep learning and time-series modeling. China, India and the United States were the most influential contributors in terms of research output and technological development. Bibliographic coupling and source co-citation analyses further indicated increasing convergence between food science and computational science. Originality\u002Fvalue This study provides a comprehensive overview of the intellectual structure, collaborative networks and thematic evolution of AI-driven food safety research. Unlike previous studies focusing on specific technologies or applications, it maps global research patterns and interdisciplinary linkages. The findings provide strategic insights for researchers, policymakers and industry stakeholders. Future studies should prioritize explainable AI integration into regulatory frameworks and the development of larger, more diverse datasets to improve model generalizability across food systems.","目的 本研究旨在通过全面的文献计量分析，识别人工智能（AI）与食品安全及保障融合领域的最新研究趋势。设计与方法 从Web of Science核心合集中检索了2021年至2025年间发表的2，782篇文献。通过去除重复记录、筛选文献类型并排除不相关记录对数据集进行精炼。随后使用VOSviewer进行合著、关键词共现、引文、共被引及文献耦合分析。研究发现 机器学习和深度学习成为与食品安全、污染检测和质量预测相关的核心技术。关键词聚类显示了与农业、气候变化和公共卫生的跨学科联系。引文和共被引分析识别出三大主要知识基础：传统机器学习、基于计算机视觉的深度学习和时间序列建模。中国、印度和美国在研究产出和技术发展方面是最具影响力的贡献者。文献耦合和来源共被引分析进一步表明食品科学与计算科学之间的融合日益加深。原创性\u002F价值 本研究全面概述了AI驱动的食品安全研究的知识结构、合作网络和主题演变。与以往聚焦特定技术或应用的研究不同，本研究绘制了全球研究模式和跨学科联系。研究结果为研究人员、政策制定者和行业利益相关者提供了战略性见解。未来研究应优先关注可解释AI融入监管框架以及开发更大、更多样化的数据集，以提高模型在食品系统中的泛化能力。","British Food Journal","2026-10-19T00:00:00Z",80,{"impact":130,"substance":131,"depth":130,"authority":132,"freshness":21,"relevant":22,"comment":133},18,22,14,"基于2782篇文献的AI食品安全计量分析，方法规范、结论有参考价值，但属综述性研究，产业落地影响有限。",[135],{"name":126,"url":123},[27,28,29,137,138],"食品安全","文献计量",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[141],{"code":142,"slug":143,"name":144,"path":145,"parent_code":146},"E4","food-safety","质量安全与溯源","\u002Ftopic\u002Ffood-supply\u002Ffood-safety","E",{"status":40,"locked":14,"version":41,"method":42,"evidence":148},{"candidates":149,"agricultural_evidence":47},[150,159,165,171,176,180],{"code":33,"score":151,"supported":47,"title":152,"abstract":153,"tags":158},19,[49],[154,29,155,51,156,49,157],"深度学习","计算机视觉","deep learning","computer vision",[28,29],{"code":142,"score":160,"supported":47,"title":161,"abstract":163,"tags":164},15,[162],"food safety",[137,162],[137],{"code":166,"score":160,"supported":47,"title":167,"abstract":169,"tags":170},"I7",[168],"bibliometric",[138,168],[138],{"code":84,"score":63,"supported":47,"title":172,"abstract":173,"tags":175},[],[87,174],"climate change",[],{"code":70,"score":78,"supported":47,"title":177,"abstract":178,"tags":179},[],[74],[],{"code":54,"score":22,"supported":14,"title":181,"abstract":182,"tags":183},[],[],[27],[185,186],"AI 食品安全 文献计量","机器学习 食品质量预测","AI食品安全文献计量-5400","10.1108\u002Fbfj-06-2025-0819",{"doi":188,"openalex_id":190,"authors":191,"venue":126,"cited_by_count":109,"oa_url":9,"card":205,"direction":114,"ingested_from":116},"W7222920742",[192,194,196,199,202],{"name":193,"orcid":9},"Harang Lee",{"name":195,"orcid":9},"지은서",{"name":197,"orcid":198},"Yoonbin Kim","https:\u002F\u002Forcid.org\u002F0000-0002-5625-2560",{"name":200,"orcid":201},"Joon-Goo Lee","https:\u002F\u002Forcid.org\u002F0000-0003-3617-5518",{"name":203,"orcid":204},"Woo‐Ju Kim","https:\u002F\u002Forcid.org\u002F0000-0002-6954-1580",{"tldr":206,"method":207,"finding":208,"direction":114,"opportunity":209},"对2021-2025年2782篇文献做文献计量，梳理AI与食品安全交叉研究趋势。","Web of Science文献计量，VOSviewer共被引、关键词共现与耦合","机器学习与深度学习是核心，形成传统ML、计算机视觉、时序建模三大知识基础。","可解释AI嵌入监管框架、构建更大更多样数据集以提升跨食物系统泛化能力。","2026-10-20T23:30:31.567802Z",{"id":212,"title":213,"url":214,"summary":215,"summary_zh":216,"content":9,"source_name":217,"source_url":214,"published_at":218,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":219,"score_detail":220,"sources":222,"tags":224,"primary_topic":226,"secondary_topics":227,"classification":228,"search_phrases":248,"slug":251,"view_count":109,"doi":252,"paper":253,"created_at":290},5306,"A growing challenge: stakeholder perceptions of AI and ML applications in U.S. agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10459-x","Abstract Context The global population is expected to exceed ten billion by 2050 and food demand is projected to increase by up to 100% in the same timeframe. Agricultural management must adapt to meet the increasing global demands. Artificial intelligence (AI) and machine learning (ML) technologies can help the agricultural community respond to these needs. Aims An online survey and follow-up interviews were conducted to examine patterns of use, perceptions, and barriers among early adopting stakeholders regarding AI and ML. Methods The online survey with agricultural stakeholders (n=129) included questions regarding the participants’ views on incorporating AI and ML techniques into farming practices and individual follow-up interviews with agricultural stakeholders (n=10) were conducted to better understand their concerns toward technology use and adoption of AI-enabled tools and technologies. Key results Using a mixed-methods approach, four challenges to establishing AI-\u002FML-enabled technology in agriculture were identified. Namely, challenges related to (1) systems of systems (SoS), (2) sub-seasonal to seasonal weather (S2S) forecasts, (3) precision soil management, and (4) policy and economics. Each challenge was discussed in the context of recent literature. Conclusion Concerns were voiced clustered around four broad research themes. This brief communication brings the perspective of agricultural stakeholders to the discussion of the potential of AI\u002FML-enabled technology and the direction of their development in the agricultural sector. Implications Data collected in 2021, establish an important baseline for the early phase of AI\u002FML use in U.S. agriculture, enabling comparison of future perceptions and developments in the sector. Impact This brief communication describes a survey and follow-up interviews conducted with agricultural stakeholders on factors influencing their willingness and reluctance to incorporate AI and ML techniques into farming practices. The findings, summarized and discussed as four key challenges for AI and ML in the agricultural sector, have the potential to streamline research activities.","摘要\n\n背景 预计到2050年全球人口将超过100亿，同期粮食需求预计将增加多达100%。农业管理必须作出调整以满足不断增长的全球需求。人工智能（AI）和机器学习（ML）技术可帮助农业界应对这些需求。\n\n目的 通过开展在线调查和后续访谈，考察早期采用相关技术的利益相关者在AI和ML方面的使用模式、认知及障碍。\n\n方法 针对农业利益相关者（n=129）的在线调查包含有关参与者对将AI和ML技术纳入农业实践看法的问题，并对农业利益相关者（n=10）进行个体后续访谈，以更好地了解他们对技术使用及采用AI赋能工具和技术的顾虑。\n\n主要结果 采用混合方法，识别出在农业中建立AI\u002FML赋能技术面临的四项挑战，即与以下方面相关的挑战：（1）系统之系统（SoS），（2）次季节至季节天气（S2S）预报，（3）精准土壤管理，以及（4）政策与经济。每项挑战均结合近期文献进行了讨论。\n\n结论 所表达的顾虑集中于四个广泛的研究主题。本简报将农业利益相关者的视角引入关于AI\u002FML赋能技术潜力及其在农业部门发展方向讨论中。\n\n意义 2021年收集的数据为美国农业中AI\u002FML应用的早期阶段建立了重要基线，有助于比较该部门未来的认知和发展。\n\n影响 本简报描述了针对农业利益相关者开展的一项调查和后续访谈，内容涉及影响其愿意和不愿将AI和ML技术纳入农业实践的因素。研究结果总结并讨论为农业部门AI和ML的四项关键挑战，有望优化研究活动。","Precision Agriculture","2026-10-18T00:00:00Z",77,{"impact":130,"substance":46,"depth":19,"authority":132,"freshness":21,"relevant":22,"comment":221},"基于129份问卷与10次访谈的混合方法研究，系统梳理美国农业AI\u002FML应用的四大挑战，为早期采用者认知提供基线数据，对智慧农业研究有参考价值。",[223],{"name":217,"url":214},[27,28,29,58,225],"农户认知",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":229},{"candidates":230,"agricultural_evidence":47},[231,236,243],{"code":33,"score":232,"supported":47,"title":233,"abstract":234,"tags":235},11,[],[29,51,49],[28,29],{"code":237,"score":63,"supported":47,"title":238,"abstract":239,"tags":242},"H2",[],[240,241],"土壤","soil",[],{"code":54,"score":244,"supported":14,"title":245,"abstract":246,"tags":247},2,[],[],[27,58],[249,250],"美国农业 AI ML 调查","农业人工智能 应用障碍","美国农业AIML调查-5306","10.1007\u002Fs11119-026-10459-x",{"doi":252,"openalex_id":254,"authors":255,"venue":217,"cited_by_count":109,"oa_url":214,"card":285,"direction":114,"ingested_from":116},"W7222866367",[256,259,262,265,268,271,274,277,279,282],{"name":257,"orcid":258},"Jennifer Koch","https:\u002F\u002Forcid.org\u002F0000-0002-7067-2705",{"name":260,"orcid":261},"Andrew Fox","https:\u002F\u002Forcid.org\u002F0000-0001-6719-8902",{"name":263,"orcid":264},"Richa Bhattarai","https:\u002F\u002Forcid.org\u002F0000-0003-3827-7761",{"name":266,"orcid":267},"Hank C. Jenkins‐Smith","https:\u002F\u002Forcid.org\u002F0000-0002-5204-2726",{"name":269,"orcid":270},"Jonathan McFadden","https:\u002F\u002Forcid.org\u002F0000-0003-3762-1428",{"name":272,"orcid":273},"Audrey Reinert","https:\u002F\u002Forcid.org\u002F0000-0001-8951-702X",{"name":275,"orcid":276},"Juan Sesmero","https:\u002F\u002Forcid.org\u002F0000-0002-2669-4536",{"name":278,"orcid":9},"M. Z. Walkup",{"name":280,"orcid":281},"Wolfgang Jentner","https:\u002F\u002Forcid.org\u002F0000-0003-1045-6020",{"name":283,"orcid":284},"David S. Ebert","https:\u002F\u002Forcid.org\u002F0000-0001-6177-1296",{"tldr":286,"method":287,"finding":288,"direction":114,"opportunity":289},"通过问卷与访谈调查美国农业利益相关者对AI\u002FML应用的认知与障碍。","在线问卷129人加10人深度访谈的混合方法。","识别出系统之系统、次季节天气预报、精准土壤管理和政策经济四大挑战。","可针对四类障碍开展分区域、分作物类型的采纳意愿追踪与干预研究。","2026-10-19T23:30:02.345893Z",{"id":292,"title":293,"url":294,"summary":295,"summary_zh":296,"content":9,"source_name":297,"source_url":294,"published_at":298,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":299,"score_detail":300,"sources":304,"tags":306,"primary_topic":308,"secondary_topics":309,"classification":310,"search_phrases":334,"slug":337,"view_count":109,"doi":338,"paper":339,"created_at":368},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":301,"substance":18,"depth":19,"authority":20,"freshness":302,"relevant":22,"comment":303},16,9,"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。",[305],{"name":297,"url":294},[27,28,30,58,307],"芒果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":311},{"candidates":312,"agricultural_evidence":47},[313,317,322,328],{"code":33,"score":301,"supported":47,"title":314,"abstract":315,"tags":316},[156],[154,156],[28,30],{"code":54,"score":232,"supported":47,"title":318,"abstract":319,"tags":321},[],[27,58,320],"smart agriculture",[27,58],{"code":323,"score":78,"supported":47,"title":324,"abstract":325,"tags":327},"B2",[],[326],"芒果",[],{"code":329,"score":78,"supported":47,"title":330,"abstract":331,"tags":333},"H8",[],[332],"可持续农业",[],[335,336],"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":338,"openalex_id":340,"authors":341,"venue":297,"cited_by_count":109,"oa_url":9,"card":362,"direction":367,"ingested_from":116},"W7222328160",[342,345,348,350,353,356,359],{"name":343,"orcid":344},"Anay Ghosh","https:\u002F\u002Forcid.org\u002F0009-0006-6237-7905",{"name":346,"orcid":347},"Tawfikur Rahman","https:\u002F\u002Forcid.org\u002F0000-0002-0456-5143",{"name":349,"orcid":9},"Md Moniruzzaman",{"name":351,"orcid":352},"Nibedita Deb","https:\u002F\u002Forcid.org\u002F0000-0002-1579-1138",{"name":354,"orcid":355},"Hanan Abdullah Mengash","https:\u002F\u002Forcid.org\u002F0000-0002-4103-2434",{"name":357,"orcid":358},"Noorlindawaty Md Jizat","https:\u002F\u002Forcid.org\u002F0000-0001-7618-2283",{"name":360,"orcid":361},"Samir Salem Al‐Bawri","https:\u002F\u002Forcid.org\u002F0000-0003-2852-575X",{"tldr":363,"method":364,"finding":365,"direction":114,"opportunity":366},"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":370,"title":371,"url":372,"summary":373,"summary_zh":374,"content":9,"source_name":375,"source_url":372,"published_at":298,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":376,"score_detail":377,"sources":379,"tags":381,"primary_topic":384,"secondary_topics":385,"classification":386,"search_phrases":416,"slug":419,"view_count":22,"doi":420,"paper":421,"created_at":436},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":17,"substance":46,"depth":19,"authority":63,"freshness":302,"relevant":22,"comment":378},"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。",[380],{"name":375,"url":372},[27,28,30,382,383],"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":387},{"candidates":388,"agricultural_evidence":47},[389,393,397,404,410],{"code":54,"score":160,"supported":47,"title":390,"abstract":391,"tags":392},[320],[58,59],[27],{"code":33,"score":21,"supported":47,"title":394,"abstract":395,"tags":396},[],[29,51],[28,30],{"code":398,"score":63,"supported":47,"title":399,"abstract":400,"tags":403},"I5",[],[401,402],"物联网","IoT",[],{"code":405,"score":78,"supported":47,"title":406,"abstract":407,"tags":409},"B1",[],[408],"生菜",[],{"code":411,"score":78,"supported":47,"title":412,"abstract":413,"tags":415},"B7",[],[414],"hydroponic",[],[417,418],"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":420,"openalex_id":422,"authors":423,"venue":375,"cited_by_count":109,"oa_url":372,"card":431,"direction":367,"ingested_from":116},"W7222080602",[424,426,429],{"name":425,"orcid":9},"Muhammad Majid",{"name":427,"orcid":428},"Attia Ghafoor","https:\u002F\u002Forcid.org\u002F0009-0000-3828-6479",{"name":430,"orcid":9},"Amna Munir",{"tldr":432,"method":433,"finding":434,"direction":367,"opportunity":435},"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":438,"title":439,"url":440,"summary":441,"summary_zh":442,"content":9,"source_name":443,"source_url":440,"published_at":444,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":445,"score_detail":446,"sources":448,"tags":450,"primary_topic":453,"secondary_topics":459,"classification":461,"search_phrases":481,"slug":484,"view_count":22,"doi":485,"paper":486,"created_at":511},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":17,"substance":46,"depth":130,"authority":132,"freshness":21,"relevant":22,"comment":447},"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。",[449],{"name":443,"url":440},[27,28,30,451,452],"农业气象","水稻产量预测",{"code":454,"slug":455,"name":456,"path":457,"parent_code":458},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[460],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":462},{"candidates":463,"agricultural_evidence":47},[464,469,473,477],{"code":33,"score":151,"supported":47,"title":465,"abstract":466,"tags":468},[51],[29,51,467],"decision support",[28,30],{"code":454,"score":132,"supported":47,"title":470,"abstract":471,"tags":472},[455],[456,455],[],{"code":84,"score":22,"supported":14,"title":474,"abstract":475,"tags":476},[],[],[451],{"code":54,"score":22,"supported":14,"title":478,"abstract":479,"tags":480},[],[],[27],[482,483],"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":485,"openalex_id":487,"authors":488,"venue":443,"cited_by_count":109,"oa_url":505,"card":506,"direction":367,"ingested_from":116},"W7221657053",[489,491,493,495,497,499,502],{"name":490,"orcid":9},"Noh-Hyun Lee",{"name":492,"orcid":9},"Wonjae Jeong",{"name":494,"orcid":9},"Hyeon-Ji Yang",{"name":496,"orcid":9},"Hana Cho",{"name":498,"orcid":9},"Hyeon-Yeong Ju",{"name":500,"orcid":501},"Toshichika Iizumi","https:\u002F\u002Forcid.org\u002F0000-0002-0611-4637",{"name":503,"orcid":504},"Ki‐Tae Kim","https:\u002F\u002Forcid.org\u002F0000-0002-8249-5283","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75646-2_reference.pdf",{"tldr":507,"method":508,"finding":509,"direction":114,"opportunity":510},"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":513,"title":514,"url":515,"summary":516,"summary_zh":517,"content":9,"source_name":518,"source_url":515,"published_at":444,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":376,"score_detail":519,"sources":521,"tags":523,"primary_topic":526,"secondary_topics":527,"classification":528,"search_phrases":544,"slug":547,"view_count":78,"doi":548,"paper":549,"created_at":560},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":21,"substance":130,"depth":301,"authority":20,"freshness":302,"relevant":22,"comment":520},"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。",[522],{"name":518,"url":515},[27,28,30,524,525],"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":529},{"candidates":530,"agricultural_evidence":47},[531,535,539],{"code":33,"score":17,"supported":47,"title":532,"abstract":533,"tags":534},[],[154,156,49],[28,30,524],{"code":54,"score":55,"supported":47,"title":536,"abstract":537,"tags":538},[],[58,59],[27],{"code":540,"score":22,"supported":14,"title":541,"abstract":542,"tags":543},"A5",[],[],[525],[545,546],"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":548,"openalex_id":550,"authors":551,"venue":518,"cited_by_count":109,"oa_url":515,"card":555,"direction":114,"ingested_from":116},"W7221612639",[552],{"name":553,"orcid":554},"Fatma Ozge Ozkok","https:\u002F\u002Forcid.org\u002F0000-0002-1421-4670",{"tldr":556,"method":557,"finding":558,"direction":114,"opportunity":559},"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"]