[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4293":3,"related-4293":97},{"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":28,"primary_topic":34,"secondary_topics":40,"classification":41,"search_phrases":70,"slug":73,"view_count":74,"doi":75,"paper":76,"created_at":96},4293,"Deep Learning for Early Disease Identification in Leaves: A Pathway to Sustainable Mango Production","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23159807","Abstract: Today, the challenges in agriculture are so big and complicated that agricultural professionals can't just look at them and figure them out. This study looks at the newest deep learning and computer vision techniques for finding and sorting mango leaf diseases. Leaf diseases cut the quality and quantity of mango crops by 30–80%, which costs the worldwide mango industry billions of dollars. We meticulously examine numerous scholarly articles on deep neural networks and image processing. We categorize current methodologies into three technical generations: conventional image processing systems, first deep learning applications, and advanced hybrid architectures that incorporate transfer learning, attention mechanisms, and explainable AI. We systematically assess performance metrics, dataset characteristics, and implementation challenges across diverse geographical regions. Our comprehensive evaluation framework and prospective research trajectories underscore sustainable, scalable, and farmer-centric solutions. This review is a complete guide for researchers studying tropical fruit and people who make agricultural technologies. This study fills in the gaps in research on dataset standardization, model interpretability, real-time deployment, and the integration of precision agriculture systems. Keywords: Smart Farming, Deep Learning, Mango Diseases, Computer Vision, Precision Agriculture, Transfer Learning. Title: Deep Learning for Early Disease Identification in Leaves: A Pathway to Sustainable Mango Production Author: Shivam Saini, Rohit Goyal, Rakesh Arya International Journal of Computer Science and Information Technology Research ISSN 2348-1196 (print), ISSN 2348-120X (online) Vol. 14, Issue 4, October 2026 - December 2026 Page No: 8-13 Research Publish Journals Website: www.researchpublish.com Published Date: 05-October-2026 DOI: https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23159808 Paper Download Link (Source) https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fdeep-learning-for-early-disease-identification-in-leaves-a-pathway-to-sustainable-mango-production","摘要：如今，农业面临的挑战如此巨大而复杂，农业专业人员仅凭观察已无法应对。本研究探讨了用于发现和分类芒果叶片病害的最新深度学习与计算机视觉技术。叶片病害使芒果作物的质量和产量下降30%–80%，给全球芒果产业造成数十亿美元的损失。我们细致梳理了大量关于深度神经网络和图像处理的学术论文。我们将当前方法划分为三个技术世代：传统图像处理系统、第一代深度学习应用，以及融合迁移学习、注意力机制和可解释人工智能的先进混合架构。我们系统评估了不同地理区域的性能指标、数据集特征和实施挑战。我们的综合评估框架和前瞻性研究路径强调了可持续、可扩展且以农户为中心的解决方案。本综述为研究热带水果的研究人员以及农业技术开发者提供了完整指南。本研究填补了数据集标准化、模型可解释性、实时部署以及精准农业系统集成方面的研究空白。关键词：智慧农业、深度学习、芒果病害、计算机视觉、精准农业、迁移学习。标题：深度学习用于叶片早期病害识别：通往可持续芒果生产的路径。作者：Shivam Saini，Rohit Goyal，Rakesh Arya。《国际计算机科学与信息技术研究杂志》，ISSN 2348-1196（印刷版），ISSN 2348-120X（在线版），第14卷，第4期，2026年10月–2026年12月，页码：8-13。Research Publish Journals网站：www.researchpublish.com。发布日期：2026年10月5日。DOI：https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23159808。论文下载链接（来源）：https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fdeep-learning-for-early-disease-identification-in-leaves-a-pathway-to-sustainable-mango-production",null,"Zenodo (CERN European Organization for Nuclear Research)","2026-10-05T00:00:00Z","论文",25,false,60,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,18,15,6,9,1,"综述性论文，系统梳理芒果叶病深度学习识别技术代际与瓶颈，对热带果树智慧植保有参考价值，但期刊层级与影响范围有限。",[25,26],{"name":10,"url":6},{"name":10,"url":27},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23159808",[29,30,31,32,33],"智慧农业","农业人工智能","计算机视觉","精准农业","芒果病害",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":42,"locked":14,"version":43,"method":44,"evidence":45},"classified","2026-10-22.2","rules",{"candidates":46,"agricultural_evidence":49},[47,56,63],{"code":35,"score":48,"supported":49,"title":50,"abstract":52,"tags":55},19,true,[51],"deep learning",[53,31,51,54],"深度学习","computer vision",[30,31],{"code":57,"score":58,"supported":49,"title":59,"abstract":60,"tags":62},"I1",11,[],[29,32,61],"precision agriculture",[29,32],{"code":64,"score":65,"supported":49,"title":66,"abstract":67,"tags":69},"B2",3,[],[68],"芒果",[],[71,72],"芒果叶片病害 深度学习","芒果病害 计算机视觉","芒果叶片病害深度学习-4293",2,"10.5281\u002Fzenodo.23159807",{"doi":75,"openalex_id":77,"authors":78,"venue":10,"cited_by_count":87,"oa_url":6,"card":88,"direction":94,"ingested_from":95},"W7220380038",[79,82,84],{"name":80,"orcid":81},"Shivam Saini","https:\u002F\u002Forcid.org\u002F0009-0002-3981-2260",{"name":83,"orcid":9},"Rohit Goyal",{"name":85,"orcid":86},"Rakesh Arya","https:\u002F\u002Forcid.org\u002F0000-0003-2436-3060",0,{"tldr":89,"method":90,"finding":91,"direction":92,"opportunity":93},"综述深度学习与计算机视觉在芒果叶片病害早期识别中的应用，梳理三代技术并展望可持续种植。","系统综述深度神经网络与图像处理文献，按三代技术分类并评估性能、数据集与落地挑战。","叶片病害致芒果减产30–80%，需标准化数据集、可解释模型与实时部署。","农业人工智能与决策模型","芒果等热带果树病害数据集标准化与轻量化实时模型、可解释AI的田间落地研究仍空白。","智慧农业 \u002F 农业物联网","openalex","2026-10-06T23:30:07.644270Z",{"total":20,"page":22,"page_size":20,"items":98},[99,177,233,286,389,439],{"id":100,"title":101,"url":102,"summary":103,"summary_zh":104,"content":9,"source_name":105,"source_url":102,"published_at":106,"category":12,"cover_url":9,"hotness":107,"is_selected":14,"score":108,"score_detail":109,"sources":115,"tags":117,"primary_topic":119,"secondary_topics":120,"classification":121,"search_phrases":143,"slug":146,"view_count":87,"doi":147,"paper":148,"created_at":176},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",10,76,{"impact":110,"substance":111,"depth":112,"authority":113,"freshness":21,"relevant":22,"comment":114},16,21,17,13,"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。",[116],{"name":105,"url":102},[29,30,118,32,33],"可解释AI",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[],{"status":42,"locked":14,"version":43,"method":44,"evidence":122},{"candidates":123,"agricultural_evidence":49},[124,128,133,137],{"code":35,"score":110,"supported":49,"title":125,"abstract":126,"tags":127},[51],[53,51],[30,118],{"code":57,"score":58,"supported":49,"title":129,"abstract":130,"tags":132},[],[29,32,131],"smart agriculture",[29,32],{"code":64,"score":65,"supported":49,"title":134,"abstract":135,"tags":136},[],[68],[],{"code":138,"score":65,"supported":49,"title":139,"abstract":140,"tags":142},"H8",[],[141],"可持续农业",[],[144,145],"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":147,"openalex_id":149,"authors":150,"venue":105,"cited_by_count":87,"oa_url":9,"card":171,"direction":94,"ingested_from":95},"W7222328160",[151,154,157,159,162,165,168],{"name":152,"orcid":153},"Anay Ghosh","https:\u002F\u002Forcid.org\u002F0009-0006-6237-7905",{"name":155,"orcid":156},"Tawfikur Rahman","https:\u002F\u002Forcid.org\u002F0000-0002-0456-5143",{"name":158,"orcid":9},"Md Moniruzzaman",{"name":160,"orcid":161},"Nibedita Deb","https:\u002F\u002Forcid.org\u002F0000-0002-1579-1138",{"name":163,"orcid":164},"Hanan Abdullah Mengash","https:\u002F\u002Forcid.org\u002F0000-0002-4103-2434",{"name":166,"orcid":167},"Noorlindawaty Md Jizat","https:\u002F\u002Forcid.org\u002F0000-0001-7618-2283",{"name":169,"orcid":170},"Samir Salem Al‐Bawri","https:\u002F\u002Forcid.org\u002F0000-0003-2852-575X",{"tldr":172,"method":173,"finding":174,"direction":92,"opportunity":175},"提出可解释深度学习框架，用AlexNet结合贝叶斯调参、微调和Grad-CAM实现芒果叶病十分类。","AlexNet+贝叶斯超参优化、两阶段微调、八视图TTA、Grad-CAM，约5","测试准确率达99.2%，ROC-AUC为1.00，Grad-CAM能定位病斑等生物相关症状。","可延伸至田间复杂背景验证、可解释性定量评估及轻量化边缘部署研究。","2026-10-16T23:30:08.303796Z",{"id":178,"title":179,"url":180,"summary":181,"summary_zh":182,"content":9,"source_name":10,"source_url":180,"published_at":183,"category":12,"cover_url":9,"hotness":107,"is_selected":14,"score":184,"score_detail":185,"sources":188,"tags":190,"primary_topic":193,"secondary_topics":194,"classification":195,"search_phrases":213,"slug":216,"view_count":87,"doi":217,"paper":218,"created_at":232},5587,"Calibration-Shift Inference for Computer Vision Agriculture Yield Models Under Retrofit Sensor Replacement: An Artificial Intelligence Post-Deployment Recalibration Guarantee","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544195","Computer vision yield models deployed in agricultural fields are routinely paired with retrofit sensor packages that replace or supplement the original imaging hardware, and the resulting calibration shift can silently invalidate the model's predictive guarantees. The analysis characterises the operating characteristics of the design under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, using 2000 replications per design cell across cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The design attains 80% power at a 5 percentage point effect with 54 clusters. The paper states a formal guarantee: under stated assumptions on the stability of the calibration map, the before-after-control-impact estimator yields a consistent and asymptotically normal estimate of the calibration shift, and the associated confidence interval covers the true shift at the nominal rate. The contribution is a design-theoretic account of how retrofit-induced calibration shift can be detected and bounded without observational data, together with the sample-size requirements that follow.","部署在农田中的计算机视觉产量模型通常与改装传感器组件配合使用，这些组件用于替换或补充原始成像硬件，由此产生的校准偏移可能悄然使模型的预测保证失效。该分析在声明的方差结构下刻画了设计的工作特性，其中组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64，每个设计单元采用2000次重复，聚类数分别为8、16、24和32，效应量为3、5和8个百分点。该设计在54个聚类、5个百分点效应下达到80%的检验力。论文给出了一项形式化保证：在关于校准映射稳定性的既定假设下，前后对照影响（before-after-control-impact）估计量给出校准偏移的一致且渐近正态的估计，且相关置信区间以名义覆盖率覆盖真实偏移。其贡献在于从设计理论角度说明了如何在没有观测数据的情况下检测并界定改装引起的校准偏移，以及随之而来的样本量要求。","2026-10-21T00:00:00Z",65,{"impact":186,"substance":18,"depth":112,"authority":17,"freshness":107,"relevant":22,"comment":187},8,"方法学扎实、统计设计严谨的预印本论文，但偏理论设计层面，缺乏田间实证数据，产业影响有限，适合作为技术参考而非每日精选头条。",[189],{"name":10,"url":180},[29,30,31,191,192],"产量预测","传感器校准",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[],{"status":42,"locked":14,"version":43,"method":44,"evidence":196},{"candidates":197,"agricultural_evidence":49},[198,204,208],{"code":35,"score":199,"supported":49,"title":200,"abstract":202,"tags":203},24,[201,54],"artificial intelligence",[31,54],[30,31],{"code":57,"score":22,"supported":14,"title":205,"abstract":206,"tags":207},[],[],[29],{"code":209,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},"I3",[],[],[191],[214,215],"计算机视觉 产量预测 传感器校准","农业人工智能 传感器校准 计算机视觉 产量预测","计算机视觉产量预测传感器校准-5587","10.5281\u002Fzenodo.23544195",{"doi":217,"openalex_id":219,"authors":220,"venue":10,"cited_by_count":87,"oa_url":180,"card":227,"direction":92,"ingested_from":95},"W7223104380",[221,223,225],{"name":222,"orcid":9},"Tigist Alemu Gebremariam",{"name":224,"orcid":9},"Hawi Tesfaye Desta",{"name":226,"orcid":9},"Mulugeta Bekele Wolde",{"tldr":228,"method":229,"finding":230,"direction":92,"opportunity":231},"提出改造传感器替换后视觉产量模型校准漂移的检测与置信区间保证方法。","用前后对照影响估计量，基于方差结构做2000次重复的模拟设计分析。","5个百分点效应下54个集群可达80%检验力，估计量一致且渐近正态。","可将该设计理论扩展到多传感器异构替换与在线校准监测，填补真实田间验证空白。","2026-10-22T11:21:01.554995Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":238,"content":9,"source_name":10,"source_url":236,"published_at":183,"category":12,"cover_url":9,"hotness":107,"is_selected":14,"score":239,"score_detail":240,"sources":243,"tags":245,"primary_topic":248,"secondary_topics":249,"classification":250,"search_phrases":266,"slug":269,"view_count":87,"doi":270,"paper":271,"created_at":285},5584,"Distributionally-Robust Evaluation of Computer Vision Agriculture Disease Classifiers Under Climate-Driven Pathogen Range Shifts: An Artificial Intelligence Worst-Case Generalization Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544150","Computer vision classifiers for crop disease are evaluated almost exclusively on held-out samples drawn from the same distribution as their training data, yet climate-driven pathogen range shifts mean that deployment environments are systematically out of distribution. The framework treats the deployment distribution as an adversarial perturbation of the training distribution within a Wasserstein ball whose radius is calibrated to observed climate displacement. Using NASA POWER monthly reanalysis for Harare, Zimbabwe (2000-2023, 312 monthly observations), the analysis estimates a mean air temperature of 18.914 C, a standard deviation of 3.107 C, and a warming trend of 0.2001 C per decade. These estimates anchor the radius of the ambiguity set and the resulting bound. The bound decomposes worst-case risk into an empirical risk term, a Wasserstein radius term scaled by the Lipschitz constant of the classifier, and a concentration term. Under plausible Lipschitz constants for convolutional backbones, the radius term dominates the empirical risk term once the climate displacement exceeds a threshold that the Harare record already approaches. The contribution is a formal evaluation criterion that replaces the i. i. d. assumption with a climate-calibrated ambiguity set, together with the analytical machinery needed to compute it.","作物病害的计算机视觉分类器几乎完全在与训练数据同分布的留出样本上进行评估，然而气候驱动的病原体分布范围变化意味着部署环境系统性地处于分布之外。该框架将部署分布视为训练分布在Wasserstein球内的对抗性扰动，球的半径根据观测到的气候位移进行校准。利用NASA POWER对津巴布韦哈拉雷的月度再分析数据（2000—2023年，312个月度观测值），分析估计平均气温为18.914°C，标准差为3.107°C，每十年升温趋势为0.2001°C。这些估计值锚定了模糊集的半径及由此得到的界。该界将最坏情况风险分解为经验风险项、由分类器Lipschitz常数缩放后的Wasserstein半径项以及集中项。在卷积骨干网络合理的Lipschitz常数下，一旦气候位移超过哈拉雷记录已接近的阈值，半径项便主导经验风险项。本文的贡献在于提出了一种形式化评估准则，以气候校准的模糊集替代独立同分布（i.i.d.）假设，并提供了计算该准则所需的分析工具。",75,{"impact":17,"substance":241,"depth":18,"authority":113,"freshness":107,"relevant":22,"comment":242},22,"方法新颖、数据具体，但属方法论预印论文，产业影响有限，适合作为专业精选而非头条。",[244],{"name":10,"url":236},[29,30,31,246,247],"作物病害","气候变化",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[],{"status":42,"locked":14,"version":43,"method":44,"evidence":251},{"candidates":252,"agricultural_evidence":49},[253,257,262],{"code":35,"score":199,"supported":49,"title":254,"abstract":255,"tags":256},[201,54],[31,54],[30,31],{"code":258,"score":22,"supported":14,"title":259,"abstract":260,"tags":261},"H7",[],[],[247],{"code":57,"score":22,"supported":14,"title":263,"abstract":264,"tags":265},[],[],[29],[267,268],"NASA POWER 哈拉雷 气温","Wasserstein 分布鲁棒 病害分类","NASAPOWER哈拉雷气温-5584","10.5281\u002Fzenodo.23544150",{"doi":270,"openalex_id":272,"authors":273,"venue":10,"cited_by_count":87,"oa_url":236,"card":280,"direction":92,"ingested_from":95},"W7223087892",[274,276,278],{"name":275,"orcid":9},"Kossi Afeli",{"name":277,"orcid":9},"Akouvi Amegashie",{"name":279,"orcid":9},"Komlan Sélom Dossou",{"tldr":281,"method":282,"finding":283,"direction":92,"opportunity":284},"提出气候校准的分布鲁棒评估准则，替代i.i.d.假设评价作物病害视觉分类器。","用Wasserstein球建模部署分布偏移，以NASA POWER哈拉雷气温数据","气候位移超阈值后，半径项主导经验风险，现有评估会高估模型泛化能力。","可将气候校准的鲁棒评估扩展到多作物多区域，并研究适应分布偏移的鲁棒训练方法。","2026-10-22T11:21:00.036937Z",{"id":287,"title":288,"url":289,"summary":290,"summary_zh":291,"content":9,"source_name":292,"source_url":289,"published_at":183,"category":12,"cover_url":9,"hotness":107,"is_selected":14,"score":293,"score_detail":294,"sources":296,"tags":298,"primary_topic":301,"secondary_topics":302,"classification":314,"search_phrases":365,"slug":368,"view_count":87,"doi":369,"paper":370,"created_at":388},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":18,"substance":241,"depth":18,"authority":113,"freshness":21,"relevant":22,"comment":295},"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。",[297],{"name":292,"url":289},[29,30,299,32,300],"物联网","气候韧性",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[303,308],{"code":304,"slug":305,"name":306,"path":307,"parent_code":39},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":309,"slug":310,"name":311,"path":312,"parent_code":313},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"status":42,"locked":14,"version":43,"method":44,"evidence":315},{"candidates":316,"agricultural_evidence":49},[317,323,327,334,340,346,353,359],{"code":35,"score":18,"supported":49,"title":318,"abstract":319,"tags":322},[201],[53,320,31,321,51,54],"机器学习","machine learning",[30],{"code":57,"score":110,"supported":49,"title":324,"abstract":325,"tags":326},[61],[32,61],[29,32],{"code":304,"score":107,"supported":49,"title":328,"abstract":329,"tags":333},[],[299,330,331,332],"边缘计算","IoT","edge computing",[299],{"code":309,"score":21,"supported":49,"title":335,"abstract":336,"tags":339},[],[337,338,310],"灌溉","水资源",[],{"code":258,"score":341,"supported":49,"title":342,"abstract":343,"tags":345},7,[],[247,344],"climate change",[300],{"code":347,"score":20,"supported":49,"title":348,"abstract":349,"tags":352},"H2",[],[350,351],"土壤","soil",[],{"code":354,"score":65,"supported":49,"title":355,"abstract":356,"tags":358},"A7",[],[357],"间作",[],{"code":360,"score":65,"supported":49,"title":361,"abstract":362,"tags":364},"F3",[],[363],"养分管理",[],[366,367],"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":369,"openalex_id":371,"authors":372,"venue":292,"cited_by_count":87,"oa_url":289,"card":383,"direction":94,"ingested_from":95},"W7223121456",[373,376,378,380],{"name":374,"orcid":375},"Olumayowa J. Iyanda","https:\u002F\u002Forcid.org\u002F0000-0002-5340-9884",{"name":377,"orcid":9},"Oluwadare OYEBODE",{"name":379,"orcid":9},"Iretiayo Adelaiye",{"name":381,"orcid":382},"Ayomide Afolabi","https:\u002F\u002Forcid.org\u002F0000-0002-5171-886X",{"tldr":384,"method":385,"finding":386,"direction":92,"opportunity":387},"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":390,"title":391,"url":392,"summary":393,"summary_zh":394,"content":9,"source_name":395,"source_url":392,"published_at":396,"category":12,"cover_url":9,"hotness":107,"is_selected":14,"score":397,"score_detail":398,"sources":400,"tags":402,"primary_topic":404,"secondary_topics":405,"classification":406,"search_phrases":424,"slug":427,"view_count":87,"doi":428,"paper":429,"created_at":438},5385,"A Comprehensive Review of Deep Learning and Computer Vision Techniques for Fruit Quality Assessment and Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.75s.151","Fruit image analysis has become an essential research area in precision agriculture, enabling automated fruit classification, quality grading, maturity estimation, disease diagnosis, yield prediction, and intelligent harvesting through advances in computer vision and artificial intelligence (AI).Recent progress in imaging technologies, large-scale benchmark datasets, and deep learning has substantially improved the accuracy, robustness, and scalability of automated fruit analysis systems.This survey presents a comprehensive and systematic review of image processing and AI techniques for fruit image analysis.It covers the complete image analysis pipeline, including image acquisition, preprocessing, enhancement, color space transformation, segmentation, feature extraction, and handcrafted texture descriptors.Furthermore, conventional machine learning algorithms are reviewed alongside state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba models, for applications such as fruit recognition, quality assessment, disease detection, ripeness estimation, and object detection.Publicly available benchmark datasets, evaluation metrics, and performance comparison strategies are also summarized to facilitate objective assessment of existing approaches.In addition, the survey discusses key research challenges, including illumination variations, occlusion, complex orchard environments, limited annotated datasets, computational complexity, and domain adaptation, while highlighting emerging research trends such as self-supervised learning, multimodal learning, explainable AI, lightweight deep networks, foundation models, and edge intelligence for real-time deployment.By providing a unified review of methodologies, datasets, evaluation protocols, challenges, and future research directions, this survey offers a comprehensive reference for researchers and practitioners developing intelligent and scalable fruit image analysis systems for precision agriculture.","水果图像分析已成为精准农业中的一个重要研究领域，借助计算机视觉和人工智能（AI）的进步，实现了果实自动分类、品质分级、成熟度估计、病害诊断、产量预测和智能采收。成像技术、大规模基准数据集和深度学习的最新进展显著提升了自动化水果分析系统的准确性、鲁棒性和可扩展性。本综述对用于水果图像分析的图像处理和AI技术进行了全面而系统的回顾。内容涵盖完整的图像分析流程，包括图像采集、预处理、增强、颜色空间变换、分割、特征提取和手工纹理描述符。此外，综述了传统机器学习算法以及最先进的深度学习架构，包括卷积神经网络（CNN）、视觉Transformer（ViT）和视觉Mamba模型，用于果实识别、品质评估、病害检测、成熟度估计和目标检测等应用。同时总结了公开可用的基准数据集、评价指标和性能比较策略，以便对现有方法进行客观评估。此外，本综述讨论了关键研究挑战，包括光照变化、遮挡、复杂果园环境、标注数据集有限、计算复杂度和域适应，并重点介绍了新兴研究趋势，如自监督学习、多模态学习、可解释AI、轻量级深度网络、基础模型和面向实时部署的边缘智能。通过提供方法、数据集、评价协议、挑战和未来研究方向的统一综述，本综述为开发面向精准农业的智能且可扩展的水果图像分析系统的研究人员和实践者提供了全面的参考。","International Journal of Drug Delivery Technology","2026-10-18T00:00:00Z",56,{"impact":186,"substance":18,"depth":110,"authority":20,"freshness":186,"relevant":22,"comment":399},"系统性综述覆盖CNN、ViT、Vision Mamba等前沿方法，信息量足，但期刊权威性一般且偏学术综述，公共价值有限，适合主题聚合而非每日精选头条。",[401],{"name":395,"url":392},[29,30,31,53,403],"水果品质检测",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[],{"status":42,"locked":14,"version":43,"method":44,"evidence":407},{"candidates":408,"agricultural_evidence":49},[409,415,419],{"code":35,"score":410,"supported":49,"title":411,"abstract":412,"tags":414},28,[51,54],[413,53,320,31,321,51,201,54],"目标检测",[30,53,31],{"code":57,"score":341,"supported":49,"title":416,"abstract":417,"tags":418},[],[32,61],[29],{"code":64,"score":65,"supported":49,"title":420,"abstract":421,"tags":423},[],[422],"orchard",[],[425,426],"水果品质 计算机视觉 深度学习","农业人工智能 水果品质检测 计算机视觉 智慧农业","水果品质计算机视觉深度学习-5385","10.25258\u002Fijddt.16.75s.151",{"doi":428,"openalex_id":430,"authors":431,"venue":395,"cited_by_count":87,"oa_url":392,"card":432,"direction":94,"ingested_from":95},"W7222892831",[],{"tldr":433,"method":434,"finding":435,"direction":436,"opportunity":437},"系统综述深度学习与计算机视觉在水果品质评估与分级中的全流程方法。","综述图像采集到分割、特征提取及CNN、ViT、Vision Mamba等模型与公","深度学习显著提升水果分析精度与鲁棒性，但光照、遮挡和小样本仍是主要瓶颈。","农业遥感与作物表型","可探索自监督与轻量化模型在复杂果园遮挡、小样本场景下的边缘实时部署。","2026-10-20T23:30:10.066042Z",{"id":440,"title":441,"url":442,"summary":443,"summary_zh":444,"content":9,"source_name":445,"source_url":442,"published_at":446,"category":12,"cover_url":9,"hotness":107,"is_selected":49,"score":447,"score_detail":448,"sources":451,"tags":453,"primary_topic":456,"secondary_topics":457,"classification":458,"search_phrases":484,"slug":487,"view_count":474,"doi":488,"paper":489,"created_at":515},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":449,"substance":199,"depth":48,"authority":19,"freshness":21,"relevant":22,"comment":450},26,"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。",[452],{"name":445,"url":442},[29,30,32,454,455],"遥感","全球评估",{"code":35,"slug":36,"name":37,"path":38,"parent_code":39},[],{"status":42,"locked":14,"version":43,"method":44,"evidence":459},{"candidates":460,"agricultural_evidence":49},[461,465,469,473,478],{"code":57,"score":58,"supported":49,"title":462,"abstract":463,"tags":464},[],[29,32,61],[29,32],{"code":35,"score":341,"supported":49,"title":466,"abstract":467,"tags":468},[],[320,321],[30],{"code":309,"score":20,"supported":49,"title":470,"abstract":471,"tags":472},[],[337,310],[],{"code":209,"score":474,"supported":49,"title":475,"abstract":476,"tags":477},4,[],[454],[454],{"code":479,"score":65,"supported":49,"title":480,"abstract":481,"tags":483},"F4",[],[482],"除草",[],[485,486],"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":488,"openalex_id":490,"authors":491,"venue":445,"cited_by_count":87,"oa_url":442,"card":510,"direction":94,"ingested_from":95},"W7222974188",[492,495,498,501,504,507],{"name":493,"orcid":494},"Shahrear Roman","https:\u002F\u002Forcid.org\u002F0009-0006-5659-4292",{"name":496,"orcid":497},"Hadi Hadi","https:\u002F\u002Forcid.org\u002F0000-0002-2410-9751",{"name":499,"orcid":500},"Wyclife Agumba Oluoch","https:\u002F\u002Forcid.org\u002F0000-0003-0803-9279",{"name":502,"orcid":503},"David Zilberman","https:\u002F\u002Forcid.org\u002F0000-0001-5743-5134",{"name":505,"orcid":506},"Robert Finger","https:\u002F\u002Forcid.org\u002F0000-0002-0634-5742",{"name":508,"orcid":509},"David Wuepper","https:\u002F\u002Forcid.org\u002F0000-0002-1344-6023",{"tldr":511,"method":512,"finding":513,"direction":94,"opportunity":514},"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"]