[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1299":3,"related-1299":160},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":49,"search_phrases":135,"slug":138,"view_count":139,"doi":140,"paper":141,"created_at":159},1299,"Remote Sensing and Machine Learning for Futuristic Horticulture: A Comprehensive Review","https:\u002F\u002Fdoi.org\u002F10.25125\u002Fijoear-aug-2026-26","Horticultural crops—fruits, vegetables, plantation crops, flowers, spices and medicinal plants—form the nutritional and economic backbone of India's agricultural sector. However, they face persistent challenges of yield variability, water and nutrient inefficiency, pest and disease pressure and post-harvest losses. This review synthesises the transformative role of Remote Sensing (RS) and Machine Learning (ML) in enabling futuristic, sustainable and precision horticulture. The evolution of agricultural production systems from Agriculture 1.0 to Agriculture 5.0 is traced, followed by a comprehensive discussion of RS principles, elements, four fundamental resolutions (spatial, spectral, temporal, radiometric), and multi-platform architectures (satellite, aerial, UAV, ground-based). A parallel taxonomy of ML—supervised, semi-supervised, unsupervised, reinforcement and deep-learning frameworks—is presented, with emphasis on Random Forest, Support Vector Machine, XGBoost, and Convolutional Neural Network algorithms most widely applied to horticultural datasets. Five representative case studies are analysed in depth: (i) UAV multispectral + ensemble learning for leaf nitrogen monitoring in custard apple; (ii) hyperspectral + ANN \u002F RF \u002F DT models for mango and strawberry fruit-quality parameters; (iii) UAV-hyperspectral detection of citrus canker; (iv) machine-learning-based crop recommendation under NPK, pH and climatic variables; and (v) RS + GIS soil-site suitability for six major fruit crops in the Ganjigatti sub-watershed, Karnataka. National platforms such as CHAMAN, Bhoonidhi, Bhuvan and PMFBY are reviewed as operational demonstrations of the RS + ML value chain. Finally, technical, economic and ethical challenges—ground-truth scarcity, sensor cost, model interpretability, digital divide and data privacy—are discussed, and a way forward for Indian horticulture in the Agriculture 5.0 era is proposed.","园艺作物——包括水果、蔬菜、种植园作物、花卉、香料及药用植物——构成了印度农业部门营养与经济的基础。然而，它们持续面临产量波动、水资源与养分利用效率低下、病虫害压力以及采后损失等挑战。本综述综合探讨了遥感（Remote Sensing, RS）与机器学习（Machine Learning, ML）在推动未来化、可持续及精准园艺中的变革性作用。文章追溯了农业生产系统从农业1.0到农业5.0的演进历程，随后全面讨论了遥感的基本原理、要素、四种基本分辨率（空间、光谱、时间、辐射）以及多平台架构（卫星、航空、无人机、地面）。同时，提出了机器学习的并行分类体系——监督学习、半监督学习、无监督学习、强化学习及深度学习框架，并重点介绍了最广泛应用于园艺数据集的随机森林、支持向量机、XGBoost和卷积神经网络算法。文章深入分析了五个代表性案例研究：（i）基于无人机多光谱与集成学习对番荔枝叶片氮素监测；（ii）基于高光谱与人工神经网络\u002F随机森林\u002F决策树模型对芒果和草莓果实品质参数的评估；（iii）基于无人机高光谱的柑橘溃疡病检测；（iv）基于NPK、pH及气候变量的机器学习作物推荐系统；以及（v）基于遥感和地理信息系统（GIS）的卡纳塔克邦甘吉加蒂子流域六种主要果树土壤-立地适宜性评价。文章还回顾了CHAMAN、Bhoonidhi、Bhuvan和PMFBY等国家平台，作为遥感与机器学习价值链的运营示范。最后，讨论了技术、经济和伦理方面的挑战——包括地面真值稀缺、传感器成本、模型可解释性、数字鸿沟和数据隐私问题，并提出了印度园艺业在农业5.0时代的发展路径。",null,"International Journal of Environmental and Agriculture Research","2026-08-31T00:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,12,4,1,"综述全面，案例详实，对印度园艺精准农业有参考价值，但时效性一般。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","机器学习","遥感","园艺",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[38,44],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":50,"locked":14,"version":51,"method":52,"evidence":53},"classified","2026-10-22.2","rules",{"candidates":54,"agricultural_evidence":57},[55,63,71,78,89,97,104,111,118,124,130],{"code":32,"score":56,"supported":57,"title":58,"abstract":60,"tags":62},19,true,[59],"machine learning",[61,28,59],"深度学习",[27,28],{"code":45,"score":17,"supported":57,"title":64,"abstract":66,"tags":70},[65],"remote sensing",[29,67,65,68,69],"无人机多光谱","multispectral","hyperspectral",[29],{"code":39,"score":72,"supported":57,"title":73,"abstract":74,"tags":77},9,[],[41,75,76],"草莓","strawberry",[],{"code":79,"score":72,"supported":57,"title":80,"abstract":81,"tags":88},"B2",[],[82,83,84,85,86,87],"果树","柑橘","芒果","荔枝","apple","citrus",[],{"code":90,"score":91,"supported":57,"title":92,"abstract":93,"tags":96},"H2",6,[],[94,95],"土壤","soil",[],{"code":98,"score":91,"supported":57,"title":99,"abstract":100,"tags":103},"I4",[],[101,102],"地理信息","GIS",[],{"code":105,"score":91,"supported":57,"title":106,"abstract":107,"tags":110},"I6",[],[108,109],"数字鸿沟","digital divide",[],{"code":112,"score":113,"supported":57,"title":114,"abstract":115,"tags":117},"B4",3,[],[116],"花卉",[],{"code":119,"score":113,"supported":57,"title":120,"abstract":121,"tags":123},"B6",[],[122],"药用植物",[],{"code":125,"score":113,"supported":57,"title":126,"abstract":127,"tags":129},"H3",[],[128],"水资源",[],{"code":131,"score":21,"supported":14,"title":132,"abstract":133,"tags":134},"I1",[],[],[26],[136,137],"农业人工智能 智慧农业 机器学习 园艺","农业人工智能 智慧农业","农业人工智能智慧农业机器学习园艺-1299",2,"10.25125\u002Fijoear-aug-2026-26",{"doi":140,"openalex_id":142,"authors":143,"venue":10,"cited_by_count":149,"oa_url":150,"card":151,"direction":157,"ingested_from":158},"W7204829467",[144,147],{"name":145,"orcid":146},"Jadala Shankaraswamy","https:\u002F\u002Forcid.org\u002F0000-0002-5623-6384",{"name":148,"orcid":9},"Md Abdul Gaffor",0,"https:\u002F\u002Fijoear.com\u002Fassets\u002Farticles_menuscripts\u002Ffile\u002FIJOEAR-AUG-2026-26.pdf",{"tldr":152,"method":153,"finding":154,"direction":155,"opportunity":156},"综述遥感与机器学习在印度园艺作物精准管理中的应用，涵盖原理、方法、案例与挑战。","系统综述遥感平台与机器学习算法，分析五个典型案例及国家平台。","遥感与机器学习结合可提升园艺作物养分、病虫害、适种性等管理精度，但面临成本与数据挑战。","农业遥感与作物表型","可探索低成本、可解释的遥感-机器学习模型，并集成多源数据以解决小农园艺场景的适用性问题。","智慧农业 \u002F 农业物联网","openalex","2026-09-01T23:30:09.105185Z",{"total":91,"page":21,"page_size":91,"items":161},[162,245,336,389,442,515],{"id":163,"title":164,"url":165,"summary":166,"summary_zh":167,"content":9,"source_name":168,"source_url":165,"published_at":169,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":170,"score_detail":171,"sources":177,"tags":179,"primary_topic":183,"secondary_topics":184,"classification":187,"search_phrases":218,"slug":221,"view_count":139,"doi":222,"paper":223,"created_at":244},2805,"Synergistic effects of spectral preprocessing and machine learning algorithms for nitrogen estimation in tomato using hyperspectral spectral data","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71908-1","Abstract Accurate estimation of leaf nitrogen content is essential for optimizing fertilization management and improving crop productivity. This study proposes a nondestructive hyperspectral imaging framework combined with advanced machine learning algorithms to classify nitrogen levels in tomato leaves (Solanum lycopersicum L., Royal variety). A total of 300 hyperspectral samples were collected from plants subjected to three nitrogen treatments (N-30%, N-60%, and N-90%) under controlled conditions. Reflectance data (400–1000 nm) were calibrated and preprocessed using Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Savitzky–Golay (SG) filtering. Both unsupervised and supervised algorithms were systematically evaluated. Clustering results demonstrated that preprocessing substantially influenced class separability. The MSC + GMM combination yielded the best unsupervised results, with the lowest Davies–Bouldin index (0.443) and the highest silhouette coefficient (0.975), indicating improved cluster compactness and separation. In supervised learning, Neural Networks (NN) consistently outperformed the other models, achieving 100% accuracy and an ROC–AUC of 1.00 under SNV, MSC, and SG preprocessing. Gradient Boosting (GB) and Support Vector Machine (SVM) also demonstrated strong predictive capability, whereas conventional models, including LDA, LR, KNN, and NB, showed moderate improvements following preprocessing. Statistical analysis confirmed the significant effect of spectral preprocessing on both clustering and classification outcomes ( p \u003C 0.05). Overall, integrating hyperspectral imaging with appropriate preprocessing and nonlinear machine learning models provided strong classification performance under the controlled experimental conditions. However, the exceptionally high performance observed for some models should be interpreted cautiously because of the relatively small dataset and experimentally controlled nitrogen treatments. Moreover, the absence of an independent external validation dataset limits the assessment of generalizability across growing conditions, cultivars, and field environments. Therefore, independent validation using larger and more diverse datasets is required before broader application of the proposed framework in practical precision agriculture.","摘要 准确估算叶片氮含量对于优化施肥管理和提高作物生产力至关重要。本研究提出了一种无损高光谱成像框架，结合先进的机器学习算法对番茄叶片（Solanum lycopersicum L.，Royal品种）的氮水平进行分类。在受控条件下，从接受三种氮处理（N-30%、N-60%和N-90%）的植株中共采集了300个高光谱样本。反射率数据（400–1000 nm）经标准正态变量变换（SNV）、多元散射校正（MSC）和Savitzky–Golay（SG）滤波进行校准和预处理。系统评估了无监督和有监督算法。聚类结果表明，预处理对类别可分性产生了显著影响。MSC + GMM组合取得了最佳无监督结果，具有最低的Davies–Bouldin指数（0.443）和最高的轮廓系数（0.975），表明聚类紧密度和分离度得到改善。在有监督学习中，神经网络（NN）始终优于其他模型，在SNV、MSC和SG预处理下均达到100%的准确率和1.00的ROC–AUC。梯度提升（GB）和支持向量机（SVM）也表现出较强的预测能力，而传统模型（包括LDA、LR、KNN和NB）在预处理后表现出中等程度的改善。统计分析证实了光谱预处理对聚类和分类结果均有显著影响（p \u003C 0.05）。总体而言，将高光谱成像与适当的预处理及非线性机器学习模型相结合，在受控实验条件下提供了较强的分类性能。然而，由于数据集相对较小且氮处理为实验受控条件，某些模型所表现出的极高性能应谨慎解读。此外，缺乏独立的外部验证数据集限制了对跨生长条件、品种和田间环境泛化能力的评估。因此，在将该框架广泛应用于实际精准农业之前，需要使用更大规模、更多样化的数据集进行独立验证。","Scientific Reports","2026-09-17T00:00:00Z",77,{"impact":172,"substance":173,"depth":174,"authority":175,"freshness":13,"relevant":21,"comment":176},15,21,17,14,"高光谱结合机器学习实现番茄叶片氮素无损估测，方法系统、结论明确，但样本量小且缺乏外部验证，属细分领域方法学进展。",[178],{"name":168,"url":165},[26,27,180,181,182],"精准施肥","番茄种植","高光谱遥感",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},[185,186],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":188},{"candidates":189,"agricultural_evidence":57},[190,196,200,204,212],{"code":39,"score":172,"supported":57,"title":191,"abstract":193,"tags":195},[192],"tomato",[194,192],"番茄",[181],{"code":32,"score":172,"supported":57,"title":197,"abstract":198,"tags":199},[59],[28,59],[27],{"code":45,"score":19,"supported":57,"title":201,"abstract":202,"tags":203},[69],[69],[182],{"code":205,"score":206,"supported":57,"title":207,"abstract":208,"tags":211},"F3",7,[],[209,210],"施肥","fertilization",[180],{"code":131,"score":206,"supported":57,"title":213,"abstract":214,"tags":217},[],[215,216],"精准农业","precision agriculture",[26],[219,220],"农业人工智能 高光谱遥感 智慧农业 番茄种植","农业人工智能 高光谱遥感","农业人工智能高光谱遥感智慧农业番茄种植-2805","10.1038\u002Fs41598-026-71908-1",{"doi":222,"openalex_id":224,"authors":225,"venue":168,"cited_by_count":149,"oa_url":165,"card":238,"direction":243,"ingested_from":158},"W7213472002",[226,229,232,235],{"name":227,"orcid":228},"Mohammad Vahedi Torshizi","https:\u002F\u002Forcid.org\u002F0000-0003-3648-1515",{"name":230,"orcid":231},"Sajad Sabzi","https:\u002F\u002Forcid.org\u002F0000-0003-2439-5329",{"name":233,"orcid":234},"Mohsen Azadbakht","https:\u002F\u002Forcid.org\u002F0000-0002-5726-9321",{"name":236,"orcid":237},"Razieh Pourdarbani","https:\u002F\u002Forcid.org\u002F0000-0003-0766-8305",{"tldr":239,"method":240,"finding":241,"direction":155,"opportunity":242},"用高光谱成像结合预处理与机器学习，对番茄叶片氮素水平进行分类。","300个高光谱样本，SNV、MSC、SG预处理，聚类与多种监督分类算法对比。","MSC+GMM聚类最优，神经网络在三种预处理下均达100%准确率。","样本少且无外部验证，可扩展多品种、多环境田间数据并做独立验证以提升泛化性。","农业人工智能与决策模型","2026-09-17T23:30:59.361085Z",{"id":246,"title":247,"url":248,"summary":249,"summary_zh":250,"content":9,"source_name":251,"source_url":248,"published_at":252,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":170,"score_detail":253,"sources":257,"tags":259,"primary_topic":261,"secondary_topics":262,"classification":270,"search_phrases":310,"slug":313,"view_count":20,"doi":314,"paper":315,"created_at":335},2659,"Application of Remote Sensing and Machine Learning in Sustainable Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu18189472","Global agriculture is undergoing a period of profound transformation, driven by the need to increase food production in a context characterized by climate change, the degradation of natural resources and increasing pressure on agricultural ecosystems [...]","全球农业正经历一场深刻变革，其驱动力是在气候变化、自然资源退化以及农业生态系统压力日益增大的背景下提高粮食产量的需求。[...]","Sustainability","2026-09-16T00:00:00Z",{"impact":17,"substance":254,"depth":174,"authority":255,"freshness":72,"relevant":21,"comment":256},20,13,"发表于核心期刊的遥感与机器学习综述，方法视角新颖、时效性强，对智慧农业技术路线有参考价值，值得进入每日精选。",[258],{"name":251,"url":248},[26,27,28,260,29],"可持续农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[263,269],{"code":264,"slug":265,"name":266,"path":267,"parent_code":268},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture","H",{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":271},{"candidates":272,"agricultural_evidence":57},[273,277,282,286,293,300,306],{"code":32,"score":13,"supported":57,"title":274,"abstract":275,"tags":276},[59],[],[27,28],{"code":264,"score":72,"supported":57,"title":278,"abstract":280,"tags":281},[279],"sustainable agriculture",[],[260],{"code":45,"score":72,"supported":57,"title":283,"abstract":284,"tags":285},[65],[],[29],{"code":287,"score":91,"supported":57,"title":288,"abstract":289,"tags":292},"H7",[],[290,291],"气候变化","climate change",[],{"code":294,"score":91,"supported":57,"title":295,"abstract":296,"tags":299},"J3",[],[297,298],"全球农业","global agriculture",[],{"code":301,"score":113,"supported":57,"title":302,"abstract":303,"tags":305},"H6",[],[304],"农业生态",[],{"code":131,"score":21,"supported":14,"title":307,"abstract":308,"tags":309},[],[],[26],[311,312],"农业人工智能 可持续农业 智慧农业 机器学习","农业人工智能 可持续农业","农业人工智能可持续农业智慧农业机器学习-2659","10.3390\u002Fsu18189472",{"doi":314,"openalex_id":316,"authors":317,"venue":251,"cited_by_count":149,"oa_url":248,"card":330,"direction":155,"ingested_from":158},"W7213301703",[318,321,324,327],{"name":319,"orcid":320},"Mihai Valentin Herbei","https:\u002F\u002Forcid.org\u002F0000-0002-3884-3658",{"name":322,"orcid":323},"Ana-Cornelia Badea","https:\u002F\u002Forcid.org\u002F0000-0003-4521-5403",{"name":325,"orcid":326},"Aleksandar Ristić","https:\u002F\u002Forcid.org\u002F0000-0003-0979-3345",{"name":328,"orcid":329},"Paul Sestraș","https:\u002F\u002Forcid.org\u002F0000-0002-8554-0924",{"tldr":331,"method":332,"finding":333,"direction":155,"opportunity":334},"综述遥感与机器学习在可持续农业中的应用现状与前景。","综述遥感数据与机器学习方法在农业中的应用。","遥感结合机器学习可提升农业监测与可持续管理能力。","可探索多源遥感与可解释机器学习融合，用于小农户精准决策与碳核算。","2026-09-16T23:30:28.640661Z",{"id":337,"title":338,"url":339,"summary":340,"summary_zh":9,"content":9,"source_name":341,"source_url":9,"published_at":342,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":343,"score_detail":344,"sources":346,"tags":348,"primary_topic":350,"secondary_topics":351,"classification":353,"search_phrases":375,"slug":378,"view_count":21,"doi":379,"paper":380,"created_at":388},2212,"《基于遥感的农作物产量估算综述:机器学习技术及环境、算法和硬件限制》","https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffpls.2026.1742689\u002Ffull","Muhammad等系统综述遥感技术在农作物和植物产量估算中的应用进展,提出将遥感方法学系统分类为:传感器方法、平台方法、分析与建模方法、机器学习方法。基于多项研究结果发现,基于深度学习的架构在精度、查准率、查全率和F1分数等关键评估指标上一致实现优越性能,这种性能优势源于其学习分层表示、捕捉复杂非线性关系、高效扩展大规模数据集的能力。论文还将局限性系统归纳为环境、算法、硬件操作和无线传感器网络四大类别。","Frontiers in Plant Science 2026年9月","2026-09-07T00:00:00Z",78,{"impact":17,"substance":18,"depth":17,"authority":175,"freshness":91,"relevant":21,"comment":345},"系统综述遥感产量估算方法学并归纳环境、算法与硬件限制，方法分类清晰、结论可靠，对农业遥感与AI应用有较高参考价值。",[347],{"name":341,"url":339},[26,27,28,29,349],"产量估算",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[352],{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":354},{"candidates":355,"agricultural_evidence":57},[356,361,365,371],{"code":32,"score":357,"supported":57,"title":358,"abstract":359,"tags":360},16,[28],[61,28],[27,28],{"code":45,"score":255,"supported":57,"title":362,"abstract":363,"tags":364},[29],[29],[349,29],{"code":366,"score":113,"supported":57,"title":367,"abstract":368,"tags":370},"I5",[],[369],"无线传感",[],{"code":131,"score":21,"supported":14,"title":372,"abstract":373,"tags":374},[],[],[26],[376,377],"农业人工智能 产量估算 智慧农业 机器学习","农业人工智能 产量估算","农业人工智能产量估算智慧农业机器学习-2212","10.3389\u002Ffpls.2026.1742689\u002Ffull",{"doi":379,"openalex_id":9,"authors":381,"venue":9,"cited_by_count":149,"oa_url":9,"card":382,"direction":155,"ingested_from":387},[],{"tldr":383,"method":384,"finding":385,"direction":155,"opportunity":386},"系统综述遥感估产方法，分类传感器、平台、建模与机器学习，指出深度学习性能最优。","文献综述，按传感器、平台、分析建模、机器学习四类归纳遥感估产方法。","深度学习在精度、查准率、召回率和F1上一致优于其他方法，局限归为环境、算法、硬件与无线传感器网络四类","可针对综述指出的环境与硬件限制，研究轻量化深度学习模型在边缘设备上的实时估产。","agent","2026-09-12T00:06:40.290409Z",{"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":13,"is_selected":14,"score":397,"score_detail":398,"sources":401,"tags":403,"primary_topic":406,"secondary_topics":407,"classification":409,"search_phrases":426,"slug":429,"view_count":149,"doi":430,"paper":431,"created_at":441},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",67,{"impact":399,"substance":254,"depth":174,"authority":19,"freshness":13,"relevant":21,"comment":400},8,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[402],{"name":395,"url":392},[26,27,404,29,405],"产量预测","可解释性",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[408],{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":410},{"candidates":411,"agricultural_evidence":57},[412,418,422],{"code":32,"score":19,"supported":57,"title":413,"abstract":415,"tags":417},[414],"computer vision",[416],"计算机视觉",[27],{"code":45,"score":399,"supported":57,"title":419,"abstract":420,"tags":421},[],[29,65],[404,29],{"code":131,"score":21,"supported":14,"title":423,"abstract":424,"tags":425},[],[],[26],[427,428],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":430,"openalex_id":432,"authors":433,"venue":395,"cited_by_count":149,"oa_url":392,"card":436,"direction":155,"ingested_from":158},"W7223114002",[434],{"name":435,"orcid":9},"Kadiatou Barry",{"tldr":437,"method":438,"finding":439,"direction":155,"opportunity":440},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":9,"source_name":448,"source_url":445,"published_at":449,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":450,"score_detail":451,"sources":453,"tags":455,"primary_topic":458,"secondary_topics":459,"classification":464,"search_phrases":489,"slug":492,"view_count":149,"doi":493,"paper":494,"created_at":514},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":19,"substance":173,"depth":174,"authority":255,"freshness":72,"relevant":21,"comment":452},"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[454],{"name":448,"url":445},[26,27,29,456,457],"土壤盐渍化","新疆农业",{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},[460,463],{"code":90,"slug":95,"name":461,"path":462,"parent_code":268},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":465},{"candidates":466,"agricultural_evidence":57},[467,471,475,480,485],{"code":45,"score":172,"supported":57,"title":468,"abstract":469,"tags":470},[65],[29,65],[29],{"code":90,"score":175,"supported":57,"title":472,"abstract":473,"tags":474},[95],[94,95],[],{"code":32,"score":72,"supported":57,"title":476,"abstract":478,"tags":479},[477],"deep learning",[],[27],{"code":287,"score":113,"supported":57,"title":481,"abstract":482,"tags":484},[],[483],"干旱",[],{"code":131,"score":21,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[26],[490,491],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":493,"openalex_id":495,"authors":496,"venue":448,"cited_by_count":149,"oa_url":445,"card":509,"direction":155,"ingested_from":158},"W7221816183",[497,499,502,504,506],{"name":498,"orcid":9},"Mingjie Qian",{"name":500,"orcid":501},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":503,"orcid":9},"Peng Wang",{"name":505,"orcid":9},"Hangyuan Liu",{"name":507,"orcid":508},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":510,"method":511,"finding":512,"direction":155,"opportunity":513},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z",{"id":516,"title":517,"url":518,"summary":519,"summary_zh":520,"content":9,"source_name":521,"source_url":518,"published_at":449,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":522,"score_detail":523,"sources":525,"tags":527,"primary_topic":529,"secondary_topics":530,"classification":535,"search_phrases":576,"slug":579,"view_count":21,"doi":580,"paper":581,"created_at":602},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science",81,{"impact":17,"substance":18,"depth":17,"authority":175,"freshness":72,"relevant":21,"comment":524},"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[526],{"name":521,"url":518},[26,27,404,528,29],"多模态融合",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[531,534],{"code":79,"slug":532,"name":82,"path":533,"parent_code":43},"fruit","\u002Ftopic\u002Fhorticulture\u002Ffruit",{"code":45,"slug":46,"name":47,"path":48,"parent_code":36},{"status":50,"locked":14,"version":51,"method":52,"evidence":536},{"candidates":537,"agricultural_evidence":57},[538,543,549,553,557,561,567,571],{"code":32,"score":539,"supported":57,"title":540,"abstract":541,"tags":542},11,[],[61,28,59,477],[27,528],{"code":79,"score":72,"supported":57,"title":544,"abstract":545,"tags":548},[],[546,84,547,86],"苹果","orchard",[],{"code":45,"score":399,"supported":57,"title":550,"abstract":551,"tags":552},[],[67,68],[404,29],{"code":131,"score":206,"supported":57,"title":554,"abstract":555,"tags":556},[],[215,216],[26],{"code":90,"score":91,"supported":57,"title":558,"abstract":559,"tags":560},[],[94,95],[],{"code":366,"score":91,"supported":57,"title":562,"abstract":563,"tags":566},[],[564,565],"物联网","IoT",[],{"code":301,"score":113,"supported":57,"title":568,"abstract":569,"tags":570},[],[304],[],{"code":287,"score":113,"supported":57,"title":572,"abstract":573,"tags":575},[],[574],"气候适应",[],[577,578],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":580,"openalex_id":582,"authors":583,"venue":521,"cited_by_count":149,"oa_url":518,"card":597,"direction":157,"ingested_from":158},"W7221795850",[584,587,589,591,593,595],{"name":585,"orcid":586},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":588,"orcid":9},"Umarfarooque Momin",{"name":590,"orcid":9},"Sudeep Kumar E",{"name":592,"orcid":9},"Itfaq Ahmad Mir",{"name":594,"orcid":9},"Ab Rouf Khan",{"name":596,"orcid":9},"Ghulam Mohammad Mir",{"tldr":598,"method":599,"finding":600,"direction":243,"opportunity":601},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","2026-10-15T23:30:08.750140Z"]