[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3789":3,"related-3789":90},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":55,"slug":58,"view_count":59,"doi":60,"paper":61,"created_at":89},3789,"A Satellite-Based Framework for Flood Mapping: Enhancing Explainability Through Multispectral Indices and SHAP Analysis","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs41976-026-00311-1","While machine learning (ML) models have shown considerable promise for modelling complex environmental phenomena such as floods, their adoption in flood mapping is often constrained by limited interpretability. This study develops an integrated SHapley Additive exPlanations (SHAP)-enhanced framework for satellite-based flood extent mapping using multispectral and topographic variables. Spectral information derived from Landsat 7, including the Normalized Difference Water Index (NDWI), Automated Water Extraction Index (AWEI), Normalized Difference Vegetation Index (NDVI), and near- and shortwave-infrared reflectance, was combined with slope and elevation derived from SRTM. Historical flood extent labels were obtained from the Global Flood Database. Feature selection was performed in two stages by first reducing redundancy through correlation analysis and then applying SHAP-based attribution to quantify the contribution of the remaining variables. The final model retained four primary predictors: AWEI, Near-Infrared (NIR) reflectance, slope, and elevation. A supervised Light Gradient Boosting Machine (LightGBM) model achieved an accuracy of 92% and an AUC of 0.950, outperforming Logistic Regression and TabNet. SHAP analysis provided global and local explanations of the model output, while spatial comparison with the MODIS-derived flood extent showed broad agreement in the analysed event. The framework therefore focuses on event-based flood extent classification rather than long-term pre-event flood susceptibility prediction and demonstrates the value of combining predictive performance with model transparency for remote-sensing-based flood mapping.","尽管机器学习（ML）模型在洪水等复杂环境现象的建模中展现出相当大的潜力，但其在洪水制图中的采用往往受限于可解释性不足。本研究开发了一个集成的SHapley加法解释（SHAP）增强框架，用于基于多光谱和地形变量的卫星洪水范围制图。从Landsat 7获取的光谱信息，包括归一化差异水体指数（NDWI）、自动水体提取指数（AWEI）、归一化差异植被指数（NDVI）以及近红外和短波红外反射率，与从SRTM获取的坡度和高程相结合。历史洪水范围标签来自全球洪水数据库。特征选择分两个阶段进行：首先通过相关性分析减少冗余，然后应用基于SHAP的归因来量化剩余变量的贡献。最终模型保留了四个主要预测因子：AWEI、近红外（NIR）反射率、坡度和高程。监督式轻量梯度提升机（LightGBM）模型达到了92%的准确率和0.950的AUC，优于逻辑回归和TabNet。SHAP分析为模型输出提供了全局和局部解释，而与MODIS衍生洪水范围的空间比较显示，在分析事件中两者具有广泛一致性。因此，该框架侧重于基于事件的洪水范围分类，而非长期灾前洪水脆弱性预测，并展示了将预测性能与模型透明度相结合对于基于遥感的洪水制图的价值。",null,"Remote Sensing in Earth Systems Sciences","2026-09-28T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"将SHAP可解释性引入多光谱遥感洪水制图，方法新颖、精度可靠，对农业灾害监测信息化有参考价值，但属细分领域技术论文，影响面有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","可解释AI","遥感","洪水监测","多光谱指数",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":54},[39,47],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":46},"I3",15,true,[44],"multispectral",[29,44],[29],{"code":48,"score":21,"supported":42,"title":49,"abstract":50,"tags":53},"I2",[],[51,52],"机器学习","machine learning",[27,28],"农业相关性需要复核",[56,57],"Landsat 7 NDWI 洪水制图","SHAP LightGBM 洪水范围","Landsat7NDWI洪水制图-3789",3,"10.1007\u002Fs41976-026-00311-1",{"doi":60,"openalex_id":62,"authors":63,"venue":10,"cited_by_count":80,"oa_url":81,"card":82,"direction":86,"ingested_from":88},"W7214537961",[64,67,70,73,75,77],{"name":65,"orcid":66},"Nur Suhaili Mansor","https:\u002F\u002Forcid.org\u002F0000-0002-7780-3691",{"name":68,"orcid":69},"Sergio Molina-Palacios","https:\u002F\u002Forcid.org\u002F0000-0002-8909-6285",{"name":71,"orcid":72},"Hapini Awang","https:\u002F\u002Forcid.org\u002F0000-0001-6748-3893",{"name":74,"orcid":9},"Saw Wei Heng",{"name":76,"orcid":9},"Mou Leong Tan",{"name":78,"orcid":79},"George Hloupis","https:\u002F\u002Forcid.org\u002F0000-0001-7722-3112",0,"https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs41976-026-00311-1.pdf",{"tldr":83,"method":84,"finding":85,"direction":86,"opportunity":87},"构建SHAP增强的卫星洪水制图框架，用多光谱与地形变量训练LightGBM实现高精度分类。","Landsat 7多光谱指数与SRTM地形，两阶段特征选择，LightGBM建模","AWEI、NIR、坡度、高程为关键预测因子，LightGBM精度92%、AUC 0.950，优于对比","农业遥感与作物表型","可迁移至农田洪涝监测，探索多时相与作物物候耦合的可解释洪水风险制图。","openalex","2026-09-29T23:30:28.337497Z",{"total":91,"page":22,"page_size":91,"items":92},6,[93,168,233,286,398,461],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":101,"score_detail":102,"sources":106,"tags":108,"primary_topic":111,"secondary_topics":116,"classification":123,"search_phrases":144,"slug":147,"view_count":80,"doi":148,"paper":149,"created_at":167},5320,"Machine Learning for Drought Analysis and Forecasting: A Critical Review of Data Fusion, Extreme-Event Sensitivity, Explainability and Generalization","https:\u002F\u002Fdoi.org\u002F10.17485\u002Fijst\u002Fv19i36.1263","Background: Machine learning is increasingly applied to drought monitoring and forecasting, but studies differ widely in how drought is defined, what data are used, and how models are validated, which makes reported performance difficult to compare directly. Objectives: To explain why reported machine-learning drought-model performance varies across definitions, data sources and validation schemes, and to assess whether recent studies adequately address rare severe events and cross-domain transferability. Method: Journal articles published January 2018 to August 2026 were reviewed, starting from a 70-record high-relevance subset of a 359-record discovery export and extended through citation chaining. Publisher and DOI verification produced a final evidence base of 55 articles: 48 primary studies and 7 reviews. Target definition, input data, model family, validation design, metrics, class-imbalance treatment, explainability and external testing were compared across studies. Findings: Reported performance varied with the modelling task rather than with any single algorithm: Random Forest reached 97.7% AUC-ROC for agricultural-drought mapping in Queensland, SVM reached average R²=0.90 for hydrological drought in Algeria, and a CatBoost stacking model reached R²=0.9065 for remote-sensing-based drought monitoring. These scores are not directly comparable because targets, data and validation protocols differ. Recent studies increasingly test cross-product and cross-region transfer, use SHAP\u002FLIME explainability, and adopt extreme-aware losses, yet class-wise reporting of severe and extreme drought, ordinal-aware evaluation, and leakage-resistant temporal validation remain inconsistently applied across the 48 primary studies. Novelty: The review jointly evaluates predictive accuracy alongside rare-event sensitivity, ordinal drought severity, leakage-resistant validation, explainability, uncertainty and cross-domain generalization, criteria largely absent from earlier machine-learning drought reviews. Keywords: Drought Forecasting, Machine Learning, Remote Sensing, Explainable AI, Extreme Drought","背景：机器学习正日益应用于干旱监测与预报，但各研究在干旱定义、所用数据和模型验证方式上差异很大，导致所报告的模型性能难以直接比较。目标：解释为何已报告的机器学习干旱模型性能会因定义、数据来源和验证方案的不同而变化，并评估近期研究是否充分处理了罕见的严重事件和跨域可迁移性问题。方法：综述了2018年1月至2026年8月发表的期刊论文，起始于359条发现导出记录中70条高相关性记录的子集，并通过引文追溯加以扩展。经出版商和DOI核验，最终证据基础为55篇文章：48篇原始研究和7篇综述。比较了各研究的目标定义、输入数据、模型族、验证设计、指标、类别不平衡处理、可解释性和外部测试。发现：所报告的性能随建模任务而非任何单一算法而变化：随机森林在昆士兰农业干旱制图中达到97.7%的AUC-ROC，SVM在阿尔及利亚水文干旱中达到平均R²=0.90，CatBoost堆叠模型在基于遥感的干旱监测中达到R²=0.9065。这些分数不能直接比较，因为目标、数据和验证方案不同。近期研究越来越多地测试跨产品和跨区域迁移，使用SHAP\u002FLIME可解释性，并采用极端事件感知损失函数，然而在48篇原始研究中，严重和极端干旱的分类别报告、序数感知评估以及防泄漏的时间验证仍应用不一致。新颖性：本综述将预测准确性与罕见事件敏感性、序数干旱严重程度、防泄漏验证、可解释性、不确定性和跨域泛化等标准共同评估，这些标准在以往的机器学习干旱综述中大多缺失。关键词：干旱预报，机器学习，遥感，可解释人工智能，极端干旱","Indian Journal of Science and Technology","2026-10-18T00:00:00Z",71,{"impact":17,"substance":103,"depth":19,"authority":17,"freshness":104,"relevant":22,"comment":105},21,9,"系统综述机器学习干旱分析与预测，指出评估口径不一、极端事件敏感性与可解释性不足，对农业旱情监测信息化有参考价值，但属学术综述、影响面偏细分领域。",[107],{"name":99,"url":96},[27,28,109,29,110],"极端天气","干旱监测",{"code":48,"slug":112,"name":113,"path":114,"parent_code":115},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[117],{"code":118,"slug":119,"name":120,"path":121,"parent_code":122},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":124,"locked":14,"version":35,"method":36,"evidence":125},"classified",{"candidates":126,"agricultural_evidence":42},[127,132,138],{"code":48,"score":128,"supported":42,"title":129,"abstract":130,"tags":131},16,[52],[51,52],[27,28],{"code":118,"score":41,"supported":42,"title":133,"abstract":135,"tags":137},[134],"drought",[136,134],"干旱",[110],{"code":40,"score":139,"supported":42,"title":140,"abstract":141,"tags":143},7,[],[29,142],"remote sensing",[29],[145,146],"机器学习 干旱预测","遥感 干旱监测","机器学习干旱预测-5320","10.17485\u002Fijst\u002Fv19i36.1263",{"doi":148,"openalex_id":150,"authors":151,"venue":99,"cited_by_count":80,"oa_url":96,"card":161,"direction":86,"ingested_from":88},"W7222882764",[152,155,158],{"name":153,"orcid":154},"Ritik Mallik","https:\u002F\u002Forcid.org\u002F0009-0000-2785-0265",{"name":156,"orcid":157},"Dayal Kumar Behera","https:\u002F\u002Forcid.org\u002F0000-0002-9740-8066",{"name":159,"orcid":160},"Satarupa Mohanty","https:\u002F\u002Forcid.org\u002F0000-0002-1434-7158",{"tldr":162,"method":163,"finding":164,"direction":165,"opportunity":166},"综述55篇文献，比较机器学习干旱监测预报在定义、数据与验证上的差异。","系统综述2018-2026年55篇文献，比较目标定义、数据、模型、验证与可解释性","模型性能差异主要源于任务与验证设计而非算法，极端事件与泄漏防护评估仍不足。","农业人工智能与决策模型","可构建面向极端干旱的序数感知评估与抗泄漏时序验证框架，提升跨区域泛化。","2026-10-19T23:30:22.840943Z",{"id":169,"title":170,"url":171,"summary":172,"summary_zh":173,"content":9,"source_name":174,"source_url":171,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":176,"score_detail":177,"sources":181,"tags":183,"primary_topic":187,"secondary_topics":188,"classification":189,"search_phrases":217,"slug":220,"view_count":80,"doi":221,"paper":222,"created_at":232},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",74,{"impact":17,"substance":178,"depth":179,"authority":17,"freshness":13,"relevant":22,"comment":180},22,18,"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[182],{"name":174,"url":171},[184,27,185,29,186],"智慧农业","粮食安全","气候分析",{"code":48,"slug":112,"name":113,"path":114,"parent_code":115},[],{"status":124,"locked":14,"version":35,"method":36,"evidence":190},{"candidates":191,"agricultural_evidence":42},[192,197,203,208,213],{"code":48,"score":104,"supported":42,"title":193,"abstract":195,"tags":196},[194],"artificial intelligence",[],[27],{"code":198,"score":59,"supported":42,"title":199,"abstract":200,"tags":202},"I5",[],[201],"农业传感",[],{"code":204,"score":22,"supported":14,"title":205,"abstract":206,"tags":207},"A8",[],[],[185],{"code":209,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},"I1",[],[],[184],{"code":40,"score":22,"supported":14,"title":214,"abstract":215,"tags":216},[],[],[29],[218,219],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":221,"openalex_id":223,"authors":224,"venue":174,"cited_by_count":80,"oa_url":171,"card":227,"direction":165,"ingested_from":88},"W7223111766",[225],{"name":226,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":228,"method":229,"finding":230,"direction":86,"opportunity":231},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","2026-10-22T11:21:02.682497Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":238,"content":9,"source_name":174,"source_url":236,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":239,"score_detail":240,"sources":242,"tags":244,"primary_topic":247,"secondary_topics":248,"classification":253,"search_phrases":270,"slug":273,"view_count":80,"doi":274,"paper":275,"created_at":285},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。",67,{"impact":21,"substance":18,"depth":19,"authority":17,"freshness":13,"relevant":22,"comment":241},"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。",[243],{"name":174,"url":236},[184,27,245,29,246],"产量预测","可解释性",{"code":48,"slug":112,"name":113,"path":114,"parent_code":115},[249],{"code":40,"slug":250,"name":251,"path":252,"parent_code":115},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":124,"locked":14,"version":35,"method":36,"evidence":254},{"candidates":255,"agricultural_evidence":42},[256,262,266],{"code":48,"score":17,"supported":42,"title":257,"abstract":259,"tags":261},[258],"computer vision",[260],"计算机视觉",[27],{"code":40,"score":21,"supported":42,"title":263,"abstract":264,"tags":265},[],[29,142],[245,29],{"code":209,"score":22,"supported":14,"title":267,"abstract":268,"tags":269},[],[],[184],[271,272],"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":274,"openalex_id":276,"authors":277,"venue":174,"cited_by_count":80,"oa_url":236,"card":280,"direction":86,"ingested_from":88},"W7223114002",[278],{"name":279,"orcid":9},"Kadiatou Barry",{"tldr":281,"method":282,"finding":283,"direction":86,"opportunity":284},"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":287,"title":288,"url":289,"summary":290,"summary_zh":291,"content":9,"source_name":292,"source_url":289,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":293,"score_detail":294,"sources":296,"tags":298,"primary_topic":301,"secondary_topics":306,"classification":312,"search_phrases":368,"slug":371,"view_count":80,"doi":372,"paper":373,"created_at":397},5564,"Dynamic thermal imaging for crop water stress detection across phenological stages: Enhancing irrigation scheduling precision","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.17728","Thermal remote sensing and derived indices such as the crop water stress index (CWSI) can assess crop water status and support precision irrigation. However, most operational and artificial intelligence (AI)-based approaches rely on fixed, season-long thresholds to interpret canopy–air temperature differences and often overlook the influence of crop phenology. This review synthesises evidence from grapevine, wheat, maize, potato and several other crops on how developmental stage affects the non-water-stressed baseline (NWSB), CWSI thresholds and irrigation-scheduling algorithms. It covers CWSI theory and estimation practices; crop-specific, phenology-dependent behaviour of baselines and thresholds; a comparison of threshold-based, machine learning, Internet of Things (IoT), digital twin and Food and Agriculture Organization (FAO)-56 approaches with respect to crop phenology; and a conceptual framework for phenology-aware scheduling. Across the reviewed crops, baseline behaviour generally varied systematically across the growing season, the relationship between CWSI and crop water status generally strengthened after canopy closure and CWSI measured during reproductive stages was generally most closely related to yield. A quantitative audit of 56 AI-, thermal-imaging-, or CWSI-based studies found that 78.6 % either did not explicitly incorporate crop phenology or relied on day of year as a temporal proxy, whereas only 5.4 % explicitly encoded phenological stage. The proposed framework considers phenology explicitly in baseline estimation, threshold setting and data fusion or machine learning for irrigation scheduling; the framework will require multi-year, multi-site field validation before operational use. Future research should prioritise standardised phenology definitions and long-term, multi-location studies to establish and validate stage-specific parameters.","热红外遥感及其衍生的作物水分胁迫指数（crop water stress index, CWSI）等指标可评估作物水分状况并支持精准灌溉。然而，大多数业务化方法和基于人工智能（artificial intelligence, AI）的方法依赖固定的全生育期阈值来解释冠层—空气温差，且往往忽视作物物候的影响。本文综述了葡萄、小麦、玉米、马铃薯及其他若干作物在发育阶段如何影响非水分胁迫基线（non-water-stressed baseline, NWSB）、CWSI阈值和灌溉调度算法的相关证据。综述内容涵盖CWSI理论与估算实践；基线和阈值的作物特异性、物候依赖性行为；基于阈值、机器学习、物联网（Internet of Things, IoT）、数字孪生及联合国粮农组织（Food and Agriculture Organization, FAO）-56等方法在作物物候方面的比较；以及物候感知调度的概念框架。在所综述的作物中，基线行为在整个生长季通常呈系统性变化，CWSI与作物水分状况之间的关系在冠层封垄后总体增强，且在生殖阶段测得的CWSI与产量的关系总体最为密切。对56项基于AI、热成像或CWSI的研究进行的定量审查发现，78.6%的研究要么未明确纳入作物物候，要么依赖年积日作为时间代理变量，而仅5.4%的研究明确编码了物候阶段。所提出的框架在基线估算、阈值设定以及用于灌溉调度的数据融合或机器学习中明确考虑物候；该框架在投入业务应用前尚需多年、多站点的田间验证。未来研究应优先建立标准化的物候定义，并开展长期、多地点研究以建立和验证阶段特异性参数。","Plant Science Today",79,{"impact":179,"substance":178,"depth":179,"authority":17,"freshness":104,"relevant":22,"comment":295},"系统综述热成像与CWSI在物候期感知灌溉中的应用，含56项研究量化审计，方法学价值突出，但属综述类论文，影响偏学术层面。",[297],{"name":292,"url":289},[184,27,29,299,300],"作物水分胁迫","精准灌溉",{"code":302,"slug":303,"name":304,"path":305,"parent_code":122},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",[307,308],{"code":48,"slug":112,"name":113,"path":114,"parent_code":115},{"code":198,"slug":309,"name":310,"path":311,"parent_code":115},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":124,"locked":14,"version":35,"method":36,"evidence":313},{"candidates":314,"agricultural_evidence":42},[315,320,324,331,337,341,348,355,362],{"code":302,"score":41,"supported":42,"title":316,"abstract":317,"tags":319},[303],[318,303],"灌溉",[300],{"code":48,"score":13,"supported":42,"title":321,"abstract":322,"tags":323},[],[51,52,194],[27],{"code":198,"score":104,"supported":42,"title":325,"abstract":326,"tags":330},[],[327,328,329],"物联网","internet of things","IoT",[],{"code":209,"score":139,"supported":42,"title":332,"abstract":333,"tags":336},[],[334,335],"数字孪生","digital twin",[184],{"code":40,"score":139,"supported":42,"title":338,"abstract":339,"tags":340},[],[29,142],[29],{"code":342,"score":91,"supported":42,"title":343,"abstract":344,"tags":347},"A2",[],[345,346],"小麦","wheat",[],{"code":349,"score":91,"supported":42,"title":350,"abstract":351,"tags":354},"A3",[],[352,353],"玉米","maize",[],{"code":356,"score":91,"supported":42,"title":357,"abstract":358,"tags":361},"A5",[],[359,360],"马铃薯","potato",[],{"code":363,"score":59,"supported":42,"title":364,"abstract":365,"tags":367},"B2",[],[366],"葡萄",[],[369,370],"热成像 作物水分胁迫","CWSI 灌溉调度","热成像作物水分胁迫-5564","10.14719\u002Fpst.17728",{"doi":372,"openalex_id":374,"authors":375,"venue":292,"cited_by_count":80,"oa_url":289,"card":391,"direction":396,"ingested_from":88},"W7223088921",[376,379,382,385,388],{"name":377,"orcid":378},"R M Jeya","https:\u002F\u002Forcid.org\u002F0009-0001-3621-8533",{"name":380,"orcid":381},"P. C. Prabu","https:\u002F\u002Forcid.org\u002F0000-0002-7237-9481",{"name":383,"orcid":384},"K P Ragunath","https:\u002F\u002Forcid.org\u002F0000-0002-7851-4437",{"name":386,"orcid":387},"P. Kannan","https:\u002F\u002Forcid.org\u002F0000-0001-7003-3535",{"name":389,"orcid":390},"P. M. Shanmugam","https:\u002F\u002Forcid.org\u002F0000-0002-6706-8419",{"tldr":392,"method":393,"finding":394,"direction":86,"opportunity":395},"综述物候期对热成像CWSI阈值的影响，提出物候感知灌溉调度框架。","综述葡萄、小麦、玉米等作物的热遥感CWSI研究，并审计56项AI\u002F热成像研究。","78.6%研究未显式纳入物候，仅5.4%编码物候期；CWSI与产量在生殖期关联最强。","可开展多站点多年物候期特异性CWSI阈值标定与标准化物候定义研究。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:24.526683Z",{"id":399,"title":400,"url":401,"summary":402,"summary_zh":403,"content":9,"source_name":174,"source_url":401,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":404,"score_detail":405,"sources":407,"tags":409,"primary_topic":413,"secondary_topics":414,"classification":417,"search_phrases":445,"slug":448,"view_count":80,"doi":449,"paper":450,"created_at":460},5552,"INTEGRATING IoT, REMOTE SENSING, AND ARTIFICIAL INTELLIGENCE FOR SMART IRRIGATION: A REVIEW OF ARCHITECTURES, METHODS, AND CHALLENGES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531020","This research paper reviews the integration of Internet of Things (IoT), remote sensing, and Artificial Intelligence (AI) in smart irrigation systems. It discusses system architectures, intelligent irrigation techniques, automated water management, key challenges, and future research opportunities to improve water-use efficiency and promote sustainable agriculture.","本文综述了物联网（Internet of Things, IoT）、遥感与人工智能（Artificial Intelligence, AI）在智能灌溉系统中的融合应用，探讨了系统架构、智能灌溉技术、自动化水资源管理、关键挑战及未来研究方向，以提升用水效率并促进可持续农业发展。",75,{"impact":179,"substance":18,"depth":128,"authority":17,"freshness":104,"relevant":22,"comment":406},"系统综述物联网、遥感与AI融合的智能灌溉架构与方法，属智慧农业细分领域有实质增量的国际综述，值得入选。",[408],{"name":174,"url":401},[27,410,29,411,412],"农业物联网","智慧灌溉","节水农业",{"code":302,"slug":303,"name":304,"path":305,"parent_code":122},[415,416],{"code":198,"slug":309,"name":310,"path":311,"parent_code":115},{"code":40,"slug":250,"name":251,"path":252,"parent_code":115},{"status":124,"locked":14,"version":35,"method":36,"evidence":418},{"candidates":419,"agricultural_evidence":42},[420,426,430,434,438],{"code":302,"score":421,"supported":42,"title":422,"abstract":423,"tags":425},19,[303],[318,424,303],"水资源",[411,412],{"code":198,"score":179,"supported":42,"title":427,"abstract":428,"tags":429},[329],[327,328,329],[410],{"code":40,"score":41,"supported":42,"title":431,"abstract":432,"tags":433},[142],[29,142],[29],{"code":48,"score":17,"supported":42,"title":435,"abstract":436,"tags":437},[194],[194],[27],{"code":439,"score":91,"supported":42,"title":440,"abstract":441,"tags":444},"H8",[],[442,443],"可持续农业","sustainable agriculture",[],[446,447],"IoT 遥感 AI 智能灌溉","农业人工智能 农业物联网 智慧灌溉 节水农业","IoT遥感AI智能灌溉-5552","10.5281\u002Fzenodo.23531020",{"doi":449,"openalex_id":451,"authors":452,"venue":174,"cited_by_count":80,"oa_url":401,"card":455,"direction":396,"ingested_from":88},"W7223090389",[453],{"name":454,"orcid":9},"Patil",{"tldr":456,"method":457,"finding":458,"direction":396,"opportunity":459},"综述物联网、遥感与人工智能融合的智能灌溉系统架构、方法与挑战。","文献综述，梳理IoT、遥感与AI集成的系统架构与智能灌溉技术。","融合三者可提升用水效率并推动可持续农业，但仍面临关键挑战。","可针对多源数据融合的实时灌溉决策模型与边缘部署开展实证研究。","2026-10-22T11:20:18.028252Z",{"id":462,"title":463,"url":464,"summary":465,"summary_zh":466,"content":9,"source_name":174,"source_url":464,"published_at":467,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":468,"sources":470,"tags":472,"primary_topic":476,"secondary_topics":480,"classification":481,"search_phrases":508,"slug":511,"view_count":80,"doi":512,"paper":513,"created_at":527},5495,"Artificial Neural Network-Based Prediction and Mapping of Elephant Corridors in West Bengal Using Geospatial and Environmental Variables","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23496876","The fragmentation of forest habitats and increasing anthropogenic pressures have significantly altered elephant movementpatternsinWestBengal,India,resultinginanescalatinghuman-elephantconflict.Accurateidentification and mapping of elephant corridors are essential for landscape-level conservation planning and mitigation.Traditional corridor mapping methods, including expert-based delineation and least-cost path analyses, oftenstruggle to capture the complex and nonlinear relationships between environmental variables influencing elephant movement. This study proposes an Artificial Neural Network (ANN)-based framework to predict potential elephant corridors across West Bengal using remotely sensed and geographic information system (GIS) datasets. The predictor variables included forest cover, normalized difference vegetation index (NDVI), elevation, slope,proximity to water sources, distance from roads, railways, settlements, agricultural land, and historical elephant occurrence records. The ANN model was trained using known elephant movement locations and validated using independent datasets. The predicted suitable surface was integrated into a GIS environment to identify probable movement corridors and prioritize areas for conservation. The proposed approach demonstrates the ability of machine learning to improve corridor prediction compared with conventional GIS-based techniques and provides a decision support tool for forest managers and policymakers.","森林栖息地的破碎化和日益增加的人为压力显著改变了印度西孟加拉邦大象的活动模式，导致人象冲突不断加剧。准确识别和绘制大象廊道对于景观层面的保护规划和冲突缓解至关重要。传统的廊道制图方法，包括基于专家的 delineation（边界划定）和最小成本路径分析，往往难以捕捉影响大象活动的环境变量之间复杂的非线性关系。本研究提出了一种基于人工神经网络（Artificial Neural Network, ANN）的框架，利用遥感数据和地理信息系统（Geographic Information System, GIS）数据集预测西孟加拉邦潜在的大象廊道。预测变量包括森林覆盖、归一化植被指数（Normalized Difference Vegetation Index, NDVI）、海拔、坡度、距水源的邻近度、距道路、铁路、居民点、农田的距离以及历史大象出现记录。ANN模型利用已知的大象活动位置进行训练，并使用独立数据集进行验证。将预测得到的适宜性表面整合到GIS环境中，以识别可能的迁移廊道并确定保护优先区域。所提出的方法展示了机器学习相较于传统基于GIS的技术在改进廊道预测方面的能力，并为森林管理者和政策制定者提供了决策支持工具。","2026-10-20T00:00:00Z",{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":104,"relevant":22,"comment":469},"该研究用人工神经网络结合遥感与GIS预测大象迁徙走廊，方法新颖、数据扎实，对生态保护与乡村人兽冲突治理有参考价值，但属区域性研究，公共影响有限。",[471],{"name":174,"url":464},[27,29,473,474,475],"GIS","野生动物保护","人兽冲突",{"code":115,"slug":477,"name":478,"path":479,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":482,"locked":14,"version":35,"method":36,"evidence":483},"partial",{"candidates":484,"agricultural_evidence":42,"reason":507},[485,490,497,502],{"code":48,"score":13,"supported":42,"title":486,"abstract":487,"tags":489},[],[51,52,488],"decision support",[27],{"code":491,"score":13,"supported":42,"title":492,"abstract":493,"tags":496},"I4",[],[494,473,495],"地理信息","geographic information",[473],{"code":40,"score":498,"supported":42,"title":499,"abstract":500,"tags":501},4,[],[29],[29],{"code":503,"score":22,"supported":14,"title":504,"abstract":505,"tags":506},"H6",[],[],[474],"一级领域明确，二级方向需要细分",[509,510],"西孟加拉邦 大象走廊","人工神经网络 大象走廊","西孟加拉邦大象走廊-5495","10.5281\u002Fzenodo.23496876",{"doi":512,"openalex_id":514,"authors":515,"venue":174,"cited_by_count":80,"oa_url":464,"card":522,"direction":165,"ingested_from":88},"W7222999966",[516,518,520],{"name":517,"orcid":9},"Bhutia Dechen Doma",{"name":519,"orcid":9},"Swarup Das",{"name":521,"orcid":9},"Mandal Rakesh Kumar",{"tldr":523,"method":524,"finding":525,"direction":86,"opportunity":526},"用人工神经网络结合遥感与GIS变量预测并制图西孟加拉邦大象迁徙廊道。","ANN模型，输入遥感与GIS环境变量及历史象群出现记录，GIS集成制图。","ANN能刻画环境变量非线性关系，廊道预测优于传统GIS方法，可作决策支持工具。","可将ANN廊道预测与人类活动、农田冲突热点耦合，探索农业景观中野生动物通道与作物保护的协同规划。","2026-10-21T23:30:43.936453Z"]