[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3797":3,"related-3797":110},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":79,"slug":82,"view_count":69,"doi":83,"paper":84,"created_at":109},3797,"A Next Generation Observing Strategy for On-Farm Crop Management","https:\u002F\u002Fdoi.org\u002F10.22541\u002Fessoar.15009564\u002Fv1","Securing sustainable food production under increasing climate stress is one of the most pressing challenges for the nation. In 2022, U.S. agricultural exports generated $412 billion in economic output, including $214.6 billion in manufacturing, trade, and transportation (Zeng et al 2025). At the same time, rising production costs and increasing vulnerability to drought and extreme weather are threatening national and global food security and economic stability. Timely information on crop health and yield is critical to anticipate short-term disruptions to food supply and inform adaptive management frameworks to enhance socioecological resilience. In practice, information on crop health is leveraged in different ways at every step throughout agricultural supply chains. However, it is arguably most powerful where the action starts: in the hands of farmers making real-time management decisions at the field scale (Parazoo and Fuchs, 2025). While the crop data analysis approaches employed by farmers have advanced significantly in recent years, they rest on a foundation of remote multiband and thermal data that has not changed materially in over two decades. Solar-Induced Chlorophyll Fluorescence (SIF) has potential to transform agricultural monitoring and management because it captures slow- to rapid- changes in how plants absorb and use light throughout the entire crop cycle, from planting to harvest, regardless of canopy density, and under variable environmental and management conditions (Yang et al. 2026). Yet despite its promise to meet agricultural needs, SIF remote sensing has not yet reached the spatial, temporal, and latency requirements necessary for operational use at field and regional scales. There is an opportunity to leverage SIF’s heritage in space and capitalize on ongoing technology developments in imaging spectroscopy and interferometry and the high demand for actionable agricultural data to dramatically advance the state of the art in crop management and yield forecasting with new measurement modalities and architectures for imaging SIF.","在日益加剧的气候压力下保障可持续的粮食生产，是美国面临的最紧迫挑战之一。2022年，美国农产品出口创造了4120亿美元的经济产出，其中包括2146亿美元的制造业、贸易和运输业产值（Zeng et al 2025）。与此同时，不断上升的生产成本以及日益加剧的干旱和极端天气脆弱性，正威胁着国家和全球的粮食安全与经济稳定。及时获取作物健康状况和产量信息，对于预判粮食供应的短期中断、为适应性管理框架提供依据以增强社会生态韧性至关重要。在实践中，作物健康信息在农业供应链的每一个环节都以不同方式得到利用。然而，可以说其作用最大的地方正是行动的起点：即农民在田块尺度上做出实时管理决策时（Parazoo and Fuchs, 2025）。尽管近年来农民所采用的作物数据分析方法已取得显著进步，但它们所依赖的遥感多波段和热红外数据基础在过去二十多年里并未发生实质性变化。日光诱导叶绿素荧光（Solar-Induced Chlorophyll Fluorescence, SIF）有潜力变革农业监测与管理，因为它能够捕捉植物在整个作物周期（从种植到收获）中吸收和利用光的方式的缓慢至快速变化，且不受冠层密度限制，并适用于多变的环境和管理条件（Yang et al. 2026）。然而，尽管SIF遥感在满足农业需求方面前景广阔，但它尚未达到在田块和区域尺度上业务化应用所需的空间、时间和延迟要求。当前存在一个机遇，可以借助SIF在太空领域的发展基础，利用成像光谱学和干涉测量学的持续技术进步，以及对可操作农业数据的高需求，通过新的测量模式和成像SIF架构，大幅推进作物管理和产量预测的技术水平。",null,"OpenAlex","2026-09-28T00:00:00Z","论文",10,false,83,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},22,21,18,13,9,1,"该论文提出基于SIF的新一代农田观测策略，方法新颖且对精准农业与产量预报有实质推动，值得进入每日精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业遥感","产量预测","作物监测","日光诱导叶绿素荧光",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,52,60,67,74],{"code":33,"score":21,"supported":46,"title":47,"abstract":48,"tags":51},true,[],[49,50],"遥感","remote sensing",[29,30,28],{"code":53,"score":54,"supported":46,"title":55,"abstract":56,"tags":59},"A8",6,[],[57,58],"粮食安全","food security",[],{"code":61,"score":54,"supported":46,"title":62,"abstract":63,"tags":66},"H7",[],[64,65],"干旱","drought",[],{"code":68,"score":69,"supported":46,"title":70,"abstract":71,"tags":73},"I6",3,[],[72],"agricultural data",[],{"code":75,"score":22,"supported":14,"title":76,"abstract":77,"tags":78},"I1",[],[],[27],[80,81],"SIF 遥感 作物监测","日光诱导叶绿素荧光 产量预测","SIF遥感作物监测-3797","10.22541\u002Fessoar.15009564\u002Fv1",{"doi":83,"openalex_id":85,"authors":86,"venue":9,"cited_by_count":101,"oa_url":9,"card":102,"direction":106,"ingested_from":108},"W7214677315",[87,89,91,94,96,98],{"name":88,"orcid":9},"Nicholas Parazoo",{"name":90,"orcid":9},"David R. Thompson",{"name":92,"orcid":93},"Jennifer E. Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-2181-8402",{"name":95,"orcid":9},"Ying Sun",{"name":97,"orcid":9},"Jochen Stutz",{"name":99,"orcid":100},"Nicholas Cody Parazoo","https:\u002F\u002Forcid.org\u002F0000-0002-4424-7780",0,{"tldr":103,"method":104,"finding":105,"direction":106,"opportunity":107},"提出利用日光诱导叶绿素荧光（SIF）遥感构建下一代农田作物管理观测策略。","综述SIF遥感在农业监测中的潜力，结合成像光谱与干涉测量技术发展。","SIF可捕捉全生育期作物光利用动态，但尚未满足田间业务化时空与延迟要求。","农业遥感与作物表型","研发满足田间尺度时空与低延迟要求的SIF成像新架构，推动作物管理业务化。","openalex","2026-09-29T23:30:30.321141Z",{"total":54,"page":22,"page_size":54,"items":111},[112,212,269,330,399,448],{"id":113,"title":114,"url":115,"summary":116,"summary_zh":117,"content":9,"source_name":118,"source_url":115,"published_at":119,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":120,"score_detail":121,"sources":125,"tags":127,"primary_topic":131,"secondary_topics":137,"classification":145,"search_phrases":180,"slug":183,"view_count":101,"doi":184,"paper":185,"created_at":211},5573,"Improving alfalfa nitrogen estimation with canopy structural priors from DSSAT–PROSAIL and UAV hyperspectral data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128375","Accurate estimation of nitrogen (N) concentration in alfalfa ( Medicago sativa L .) supports forage quality assessment and harvest scheduling. Empirical remote sensing models often overfit because of confounding effects of three-dimensional canopy structure. Incorporating structural parameters can stabilize biochemical inversions, but concurrent in situ morphological measurements are difficult to acquire at scale. We developed the Morphology-Aware Latent Embedding Network (MALENet), a hybrid framework integrating physiological and morphological mechanisms with hyperspectral data. The Decision Support System for Agrotechnology Transfer (DSSAT), coupled with the PROSAIL radiative transfer model, generated a structurally rich synthetic hyperspectral prior. A convolutional neural network (CNN) with a Squeeze-and-Excitation (SE) attention mechanism, was pre-trained on these data to distill ecophysiological knowledge into a dense latent representation. This mechanistically derived embedding was then fused with empirical hyperspectral measurements collected under diverse field conditions. Evaluation using multi-year field quadrats in the Hexi Corridor showed improved predictive performance ( R² = 0.71, RMSE = 0.30%) relative to conventional machine learning and deep learning models (LASSO-ANN: R² = 0.61; CNN: R² = 0.66). Feature attribution indicated that MALENet used near-infrared multiple scattering (58.3% attribution) as a structural proxy to calibrate nitrogen concentration retrieval against the confounding effects of canopy architecture. Despite constraints imposed by sample size and PROSAIL's 1D canopy assumption, these findings demonstrate the potential of physically guided deep learning to use structural information for agricultural trait retrieval in precision forage management.","准确估算紫花苜蓿（Medicago sativa L.）的氮浓度有助于饲草品质评估和收获期安排。经验性遥感模型常因三维冠层结构的混杂效应而出现过拟合。引入结构参数可以稳定生化反演，但同步开展原位形态学测量难以大规模获取。我们开发了形态感知潜在嵌入网络（Morphology-Aware Latent Embedding Network，MALENet），这是一个将生理与形态机制同高光谱数据相结合的混合框架。农业技术转移决策支持系统（Decision Support System for Agrotechnology Transfer，DSSAT）与PROSAIL辐射传输模型耦合，生成了结构信息丰富的合成高光谱先验数据。在此基础上，预训练了一个带有挤压—激励（Squeeze-and-Excitation，SE）注意力机制的卷积神经网络（convolutional neural network，CNN），将生态生理学知识提炼为稠密潜在表征。随后，将这一机制性导出的嵌入与在不同田间条件下采集的经验性高光谱测量数据相融合。利用河西走廊多年田间样方进行的评估显示，相较于传统机器学习和深度学习模型（LASSO-ANN：R² = 0.61；CNN：R² = 0.66），预测性能有所提升（R² = 0.71，RMSE = 0.30%）。特征归因表明，MALENet利用近红外多次散射（归因占比58.3%）作为结构代理，以校准氮浓度反演，抵御冠层结构的混杂效应。尽管受样本量和PROSAIL一维冠层假设的限制，这些发现表明，物理引导的深度学习有潜力利用结构信息，在精准饲草管理中进行农业性状反演。","European Journal of Agronomy","2026-10-21T00:00:00Z",80,{"impact":122,"substance":17,"depth":19,"authority":123,"freshness":13,"relevant":22,"comment":124},16,14,"该研究将作物模型与辐射传输模型耦合生成结构先验，并结合无人机高光谱数据反演苜蓿氮素，方法新颖、田间验证扎实，对精准饲草管理有参考价值，值得进入每日精选。",[126],{"name":118,"url":115},[27,128,28,129,130],"农业人工智能","氮素监测","紫花苜蓿",{"code":132,"slug":133,"name":134,"path":135,"parent_code":136},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[138,139],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":140,"slug":141,"name":142,"path":143,"parent_code":144},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":40,"locked":14,"version":41,"method":42,"evidence":146},{"candidates":147,"agricultural_evidence":46},[148,153,160,166,176],{"code":33,"score":19,"supported":46,"title":149,"abstract":151,"tags":152},[150],"hyperspectral",[49,50,150],[28],{"code":132,"score":154,"supported":46,"title":155,"abstract":157,"tags":159},15,[156],"alfalfa",[158,156],"苜蓿",[130],{"code":140,"score":13,"supported":46,"title":161,"abstract":162,"tags":165},[],[163,158,164],"饲草","forage",[130],{"code":167,"score":13,"supported":46,"title":168,"abstract":169,"tags":175},"I2",[],[170,171,172,173,174],"深度学习","机器学习","machine learning","deep learning","decision support",[128],{"code":75,"score":22,"supported":14,"title":177,"abstract":178,"tags":179},[],[],[27],[181,182],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573","10.1016\u002Fj.eja.2026.128375",{"doi":184,"openalex_id":186,"authors":187,"venue":118,"cited_by_count":101,"oa_url":115,"card":206,"direction":106,"ingested_from":108},"W7223154576",[188,190,192,194,196,199,201,204],{"name":189,"orcid":9},"Shuai Fu",{"name":191,"orcid":9},"Yunhao Li",{"name":193,"orcid":9},"Chunli Miao",{"name":195,"orcid":9},"Jie Liu",{"name":197,"orcid":198},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":200,"orcid":9},"Yongjia Hu",{"name":202,"orcid":203},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":205,"orcid":9},"吴彩霞",{"tldr":207,"method":208,"finding":209,"direction":106,"opportunity":210},"构建MALENet融合DSSAT-PROSAIL结构先验与无人机高光谱，提升苜蓿氮浓度估算精度。","DSSAT耦合PROSAIL生成合成高光谱先验，预训练CNN-SE网络，再融合田","MALENet精度优于传统机器学习和深度学习模型，R²达0.71，近红外多次散射作为结构代理贡献58","可探索将作物模型结构先验迁移至其他牧草或作物生化参数反演，并缓解PROSAIL一维冠层假设局限。","2026-10-22T11:20:39.622844Z",{"id":213,"title":214,"url":215,"summary":216,"summary_zh":217,"content":9,"source_name":218,"source_url":215,"published_at":119,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":219,"score_detail":220,"sources":226,"tags":228,"primary_topic":230,"secondary_topics":234,"classification":236,"search_phrases":253,"slug":256,"view_count":101,"doi":257,"paper":258,"created_at":268},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)",67,{"impact":221,"substance":222,"depth":223,"authority":224,"freshness":13,"relevant":22,"comment":225},8,20,17,12,"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。",[227],{"name":218,"url":215},[27,128,29,49,229],"可解释性",{"code":167,"slug":231,"name":232,"path":233,"parent_code":37},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[235],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":237},{"candidates":238,"agricultural_evidence":46},[239,245,249],{"code":167,"score":224,"supported":46,"title":240,"abstract":242,"tags":244},[241],"computer vision",[243],"计算机视觉",[128],{"code":33,"score":221,"supported":46,"title":246,"abstract":247,"tags":248},[],[49,50],[29,49],{"code":75,"score":22,"supported":14,"title":250,"abstract":251,"tags":252},[],[],[27],[254,255],"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":257,"openalex_id":259,"authors":260,"venue":218,"cited_by_count":101,"oa_url":215,"card":263,"direction":106,"ingested_from":108},"W7223114002",[261],{"name":262,"orcid":9},"Kadiatou Barry",{"tldr":264,"method":265,"finding":266,"direction":106,"opportunity":267},"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":270,"title":271,"url":272,"summary":273,"summary_zh":9,"content":9,"source_name":274,"source_url":9,"published_at":119,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":275,"score_detail":276,"sources":278,"tags":280,"primary_topic":284,"secondary_topics":289,"classification":296,"search_phrases":317,"slug":320,"view_count":22,"doi":9,"paper":321,"created_at":329},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21",82,{"impact":19,"substance":17,"depth":19,"authority":123,"freshness":13,"relevant":22,"comment":277},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[279],{"name":274,"url":272},[27,28,281,282,283],"作物表型","无人机多光谱","小麦渍害",{"code":285,"slug":286,"name":287,"path":288,"parent_code":136},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[290,291],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":61,"slug":292,"name":293,"path":294,"parent_code":295},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":40,"locked":14,"version":41,"method":42,"evidence":297},{"candidates":298,"agricultural_evidence":46},[299,304,308,313],{"code":285,"score":300,"supported":46,"title":301,"abstract":302,"tags":303},11,[287],[287],[],{"code":33,"score":300,"supported":46,"title":305,"abstract":306,"tags":307},[282],[],[281,28,282],{"code":61,"score":221,"supported":46,"title":309,"abstract":311,"tags":312},[310],"渍害",[],[],{"code":75,"score":22,"supported":14,"title":314,"abstract":315,"tags":316},[],[],[27],[318,319],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":9,"openalex_id":9,"authors":322,"venue":9,"cited_by_count":101,"oa_url":9,"card":323,"direction":106,"ingested_from":328},[],{"tldr":324,"method":325,"finding":326,"direction":106,"opportunity":327},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z",{"id":331,"title":332,"url":333,"summary":334,"summary_zh":335,"content":9,"source_name":336,"source_url":333,"published_at":337,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":338,"score_detail":339,"sources":341,"tags":343,"primary_topic":345,"secondary_topics":349,"classification":351,"search_phrases":380,"slug":383,"view_count":101,"doi":384,"paper":385,"created_at":398},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":19,"substance":17,"depth":19,"authority":224,"freshness":221,"relevant":22,"comment":340},"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[342],{"name":336,"url":333},[27,128,344,29,49],"水稻",{"code":346,"slug":347,"name":344,"path":348,"parent_code":136},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice",[350],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":352},{"candidates":353,"agricultural_evidence":46},[354,358,362,366,372,376],{"code":346,"score":154,"supported":46,"title":355,"abstract":356,"tags":357},[347],[344,347],[344],{"code":33,"score":221,"supported":46,"title":359,"abstract":360,"tags":361},[],[49,50],[29,49],{"code":53,"score":54,"supported":46,"title":363,"abstract":364,"tags":365},[],[57,58],[],{"code":367,"score":69,"supported":46,"title":368,"abstract":369,"tags":371},"J1",[],[370],"农业规划",[],{"code":75,"score":22,"supported":14,"title":373,"abstract":374,"tags":375},[],[],[27],{"code":167,"score":22,"supported":14,"title":377,"abstract":378,"tags":379},[],[],[128],[381,382],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":384,"openalex_id":386,"authors":387,"venue":336,"cited_by_count":101,"oa_url":333,"card":393,"direction":106,"ingested_from":108},"W7222942064",[388,390],{"name":389,"orcid":9},"Nayana Venkatesh",{"name":391,"orcid":392},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":394,"method":395,"finding":396,"direction":106,"opportunity":397},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":400,"title":401,"url":402,"summary":403,"summary_zh":9,"content":9,"source_name":404,"source_url":9,"published_at":405,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":406,"score_detail":407,"sources":409,"tags":411,"primary_topic":412,"secondary_topics":413,"classification":416,"search_phrases":436,"slug":439,"view_count":101,"doi":9,"paper":440,"created_at":447},5296,"雷添杰研究员团队《基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别》","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-16\u002Fdoc-inivmprm8363597.shtml","《智慧农业(中英文)》2026年第8卷第4期刊载梁万杰、刘晓君、雷添杰等论文,在小麦拔节—抽穗和抽穗—灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控、氨基酸调控控制试验;利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像建立数据集,基于VGG21模型构建识别模型,发现硅肥调控样本识别性能最好,识别精度最高,具良好鲁棒性和可扩展性,可为小麦渍害综合防控提供理论与技术支持。","智慧农业(中英文)(2026,8(4))","2026-10-16T00:00:00Z",76,{"impact":122,"substance":18,"depth":223,"authority":123,"freshness":221,"relevant":22,"comment":408},"核心期刊论文，方法新颖、结论可靠，对小麦渍害防控有实用价值，值得进入每日精选。",[410],{"name":404,"url":402},[27,28,281,282,283],{"code":285,"slug":286,"name":287,"path":288,"parent_code":136},[414,415],{"code":61,"slug":292,"name":293,"path":294,"parent_code":295},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":417},{"candidates":418,"agricultural_evidence":46},[419,423,427,431],{"code":285,"score":300,"supported":46,"title":420,"abstract":421,"tags":422},[287],[287],[],{"code":61,"score":300,"supported":46,"title":424,"abstract":425,"tags":426},[310],[310],[],{"code":33,"score":300,"supported":46,"title":428,"abstract":429,"tags":430},[282],[],[281,28,282],{"code":75,"score":432,"supported":46,"title":433,"abstract":434,"tags":435},4,[],[27],[27],[437,438],"雷添杰 小麦渍害 无人机多光谱","VGG21 小麦渍害 识别模型","雷添杰小麦渍害无人机多光谱-5296",{"doi":9,"openalex_id":9,"authors":441,"venue":9,"cited_by_count":101,"oa_url":9,"card":442,"direction":106,"ingested_from":328},[],{"tldr":443,"method":444,"finding":445,"direction":106,"opportunity":446},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4采集冠层多光谱图像，构建VGG21识别模型。","硅肥调控样本识别性能最好、精度最高，模型鲁棒可扩展。","可探索多生育期多光谱特征与不同调控措施的耦合机制，并扩展到其他作物渍害监测。","2026-10-19T00:07:48.071055Z",{"id":449,"title":450,"url":451,"summary":452,"summary_zh":453,"content":9,"source_name":454,"source_url":451,"published_at":405,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":455,"score_detail":456,"sources":458,"tags":460,"primary_topic":463,"secondary_topics":464,"classification":465,"search_phrases":477,"slug":480,"view_count":101,"doi":481,"paper":482,"created_at":503},5243,"Identificación de índices de vegetación relacionados con componentes de rendimiento de frijol común (Phaseolus vulgaris L.) mediante el uso de sensores multiespectrales","https:\u002F\u002Fdoi.org\u002F10.18845\u002Ftm.v39i4.8378","Bean production in Costa Rica supplies only 20 % of domestic consumption, requiring the importation of the remaining amount; this situation highlights the need to know in advance the actual productive capacity of local farmers to improve planning, agronomic management, and import regulation. Therefore, the objective of this study was to evaluate the use of multispectral data and vegetation indices to analyze their relationship with yield components in bean varieties cultivated in different production areas of Costa Rica and to identify the yield component with the greatest spectral association. The research was conducted at three sites located in Alajuela, Costa Rica. Multispectral reflectance data were collected during the R5 phenological stage using an airborne multispectral sensor. Subsequently, yield components were quantified per meter of crop row, including 100-grain weight, number of pods per meter, number of plants, number of grains, and total grain weight. The number of pods showed the highest association with spectral variables and was therefore identified as the yield component with the greatest potential for analysis through remote sensing. The SR (Simple Ratio) and GCI (Green Chlorophyll Index) indices showed correlations greater than 0.7 with this variable, being identified as the vegetation indices with the highest spectral association during the R5 stage of the crop.","哥斯达黎加的菜豆（bean）产量仅能满足国内消费量的20%，其余部分需要进口；这一状况凸显了提前了解当地农民实际生产能力的必要性，以改进生产规划、农艺管理和进口调控。因此，本研究旨在评估多光谱数据和植被指数（vegetation indices）的应用，分析其与哥斯达黎加不同产区菜豆品种产量构成因素（yield components）之间的关系，并确定与光谱关联性最强的产量构成因素。研究在哥斯达黎加阿拉胡埃拉（Alajuela）的三个地点开展。在R5物候期使用机载多光谱传感器采集多光谱反射率数据。随后，按每米作物行量化产量构成因素，包括百粒重、每米豆荚数、植株数、籽粒数和籽粒总重。豆荚数与光谱变量的关联性最高，因此被确定为最具遥感分析潜力的产量构成因素。SR（简单比值，Simple Ratio）和GCI（绿色叶绿素指数，Green Chlorophyll Index）与该变量的相关系数大于0.7，被确定为作物R5期光谱关联性最高的植被指数。","Revista Tecnología en Marcha",62,{"impact":221,"substance":19,"depth":154,"authority":224,"freshness":21,"relevant":22,"comment":457},"该研究利用机载多光谱传感器识别与菜豆产量组分相关的植被指数，方法清晰、结论具体，但属于哥斯达黎加的小区域研究，公共影响有限，可作为遥感作物监测领域的技术性资讯收录。",[459],{"name":454,"url":451},[27,29,49,461,462],"植被指数","菜豆",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":466},{"candidates":467,"agricultural_evidence":46},[468,473],{"code":33,"score":224,"supported":46,"title":469,"abstract":470,"tags":472},[],[49,50,471],"multispectral",[29,461,49],{"code":75,"score":22,"supported":14,"title":474,"abstract":475,"tags":476},[],[],[27],[478,479],"哥斯达黎加 菜豆 多光谱 遥感","Phaseolus vulgaris 植被指数 产量","哥斯达黎加菜豆多光谱遥感-5243","10.18845\u002Ftm.v39i4.8378",{"doi":481,"openalex_id":483,"authors":484,"venue":454,"cited_by_count":101,"oa_url":497,"card":498,"direction":106,"ingested_from":108},"W7222720635",[485,488,491,494],{"name":486,"orcid":487},"Guillermo Vargas-Hernández","https:\u002F\u002Forcid.org\u002F0000-0003-1410-3898",{"name":489,"orcid":490},"Eddison José Araya-Morales","https:\u002F\u002Forcid.org\u002F0009-0001-0550-414X",{"name":492,"orcid":493},"Juan Carlos Hernández","https:\u002F\u002Forcid.org\u002F0000-0002-1915-3213",{"name":495,"orcid":496},"Ignacio Mora-Cordero","https:\u002F\u002Forcid.org\u002F0009-0007-0925-0099","https:\u002F\u002Frevistas.tec.ac.cr\u002Findex.php\u002Ftec_marcha\u002Farticle\u002Fdownload\u002F8378\u002F8641",{"tldr":499,"method":500,"finding":501,"direction":106,"opportunity":502},"用机载多光谱传感器评估菜豆产量构成与植被指数的关系。","机载多光谱遥感获取R5期反射率，结合地面产量构成测定与相关分析。","豆荚数与光谱变量关联最强，SR和GCI指数与其相关系数超过0.7。","可探索将SR\u002FGCI用于菜豆产量早期预测，并扩展到多品种、多生育期与无人机高光谱验证。","2026-10-18T23:30:20.259545Z"]