[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3076":3,"related-3076":65},{"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,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":64},3076,"Research on the Inversion Method of Total Phosphorus Concentration in Water Bodies Based on PSO-Adam-BP Neural Network Model","https:\u002F\u002Fdoi.org\u002F10.15244\u002Fpjoes\u002F220960","This study investigated Baiyangdian Lake in the Xiong’an New Area to invert total phosphorus (TP) concentrations using Sentinel-2 multispectral imagery and in situ measurements, aiming to support water-quality assessment and eutrophication management. Based on the multispectral remote sensing data of Sentinel-2 and measured total phosphorus data of water bodies, the study used specific feature combinations such as NDTI, B5, B11-B12 difference, and sensitive combination bands of measured data as model inputs to construct a PSO-Adam-BP neural network machine learning model for total phosphorus concentration inversion. Compared with the traditional BP and PSO-BP baseline models, the proposed framework significantly improved the accuracy of the model, with an R2 value reaching 0.9351. Moreover, it successfully reduced the average relative error by up to 53.5%, from 4.80% to 2.24%, and decreased the maximum relative error by up to 31.7%, from 11.21% to 7.66%, demonstrating the model’s highly robust and precise inversion performance. This study provides a new method for water quality detection in Baiyangdian Lake and is of great significance to the protection and development of the water environment in Xiong’an New Area.","本研究以雄安新区白洋淀为研究对象，利用Sentinel-2多光谱影像和实地测量数据反演总磷（TP）浓度，旨在为水质评价和富营养化管理提供支持。基于Sentinel-2多光谱遥感数据和白洋淀水体总磷实测数据，研究采用NDTI、B5、B11-B12差值等特征组合及实测数据的敏感组合波段作为模型输入，构建了PSO-Adam-BP神经网络机器学习模型用于总磷浓度反演。与传统BP和PSO-BP基准模型相比，所提出的框架显著提高了模型精度，R²值达到0.9351。此外，该模型成功将平均相对误差最多降低53.5%，从4.80%降至2.24%，并将最大相对误差最多降低31.7%，从11.21%降至7.66%，展现出高度稳健且精确的反演性能。本研究为白洋淀水质检测提供了新方法，对雄安新区水环境保护与开发具有重要意义。",null,"Polish Journal of Environmental Studies","2026-09-18T00:00:00Z","论文",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,21,17,13,6,1,"基于Sentinel-2与PSO-Adam-BP模型实现白洋淀总磷浓度高精度反演，方法新颖、数据可靠，对雄安水环境智慧监测有实用价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","机器学习","遥感","水质监测","白洋淀",[33,34],"白洋淀 总磷 遥感反演","Sentinel-2 水质 反演","白洋淀总磷遥感反演-3076",0,"10.15244\u002Fpjoes\u002F220960",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":56,"card":57,"direction":61,"ingested_from":63},"W7213537374",[41,43,45,48,51,53],{"name":42,"orcid":9},"Guanxing Wang",{"name":44,"orcid":9},"Cui Jia",{"name":46,"orcid":47},"Linghan Gao","https:\u002F\u002Forcid.org\u002F0000-0002-8537-8787",{"name":49,"orcid":50},"Shan An","https:\u002F\u002Forcid.org\u002F0000-0001-7796-6952",{"name":52,"orcid":9},"Jia Xi",{"name":54,"orcid":55},"Yaxue Liu","https:\u002F\u002Forcid.org\u002F0009-0006-9025-8030","https:\u002F\u002Fwww.pjoes.com\u002Fpdf-220960-145347?filename=Research-on-the-Inversion.pdf",{"tldr":58,"method":59,"finding":60,"direction":61,"opportunity":62},"用PSO-Adam-BP神经网络结合Sentinel-2影像反演白洋淀总磷浓度。","Sentinel-2多光谱与实测数据，NDTI等特征组合，PSO-Adam-BP","R²达0.9351，平均相对误差由4.80%降至2.24%，精度显著优于BP与PSO-BP。","农业遥感与作物表型","可迁移至其他内陆水体与多参数水质反演，探索时序泛化与跨区域迁移能力。","openalex","2026-09-21T23:30:25.856035Z",{"total":21,"page":22,"page_size":21,"items":66},[67,110,154,186,213,241],{"id":68,"title":69,"url":70,"summary":71,"summary_zh":72,"content":9,"source_name":73,"source_url":70,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":75,"score_detail":76,"sources":81,"tags":83,"search_phrases":85,"slug":88,"view_count":36,"doi":89,"paper":90,"created_at":109},2433,"Hierarchical spectral ensemble with physics-informed augmentation for global water quality retrieval from hyperspectral remote sensing","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1860176","Retrieving water quality variables from remotely sensed reflectance spectra (Rrs) with global-scale, cross-waterbody applicability remains a grand challenge in environmental remote sensing. Here we introduce Hierarchical Spectral Ensemble (HSE), a machine learning pipeline for concurrent retrieval of four ecologically relevant water quality parameters (chlorophyll-a (Chl-a), total suspended solids (TSS), coloured dissolved organic matter absorption coefficient at 440 nm (aCDOM(440)), and Secchi depth (Zsd)), applied to the GLORIA 2022 global dataset of 7,572 co-located hyperspectral in situ ground truth measurements spanning six continents. HSE leverages a combination of five diverse base learners trained with 10-fold out-of-fold stacking, and integrated with a diversity-constrained non-negative least squares (NNLS) meta-learner, supported by a 291-dimensional feature suite spanning spectral, spatial, and temporal representations. We propose Interpolation-based Spectral Data Augmentation (ISDA), an ecologically inspired, class-balance oversampling methodology applied to the training set after the initial stratified split to prevent information leakage. Evaluated on the held-out global test set, HSE attains R2 = 0.822, 0.704, 0.841, and 0.962 for Chl-a, TSS, aCDOM(440), and Zsd respectively (mean R2 = 0.832; all in original physical units following back-transformation). Stratified analysis on a per-quartile basis reveals negative values of R2 in low-concentration regimes for Chl-a, TSS, and aCDOM(440), illustrating how global metrics can mask failures in retrieval across a majority of the distribution, specifically in the oligotrophic regime. This constitutes the primary known limitation of the method: reliable prediction in low-concentration, low-optical-signal regimes remains elusive and is demonstrated only in high-concentration, eutrophic samples where a measurable optical signal exists.","从遥感反射光谱（Rrs）中反演水质变量并实现全球尺度、跨水体的适用性，仍是环境遥感领域的一项重大挑战。本文提出分层光谱集成（Hierarchical Spectral Ensemble, HSE），一种机器学习流程，用于同时反演四个与生态相关的水质参数（叶绿素a（Chl-a）、总悬浮固体（TSS）、440 nm处有色溶解有机物吸收系数（aCDOM(440)）和透明度（Zsd）），并应用于GLORIA 2022全球数据集，该数据集包含横跨六大洲的7,572组同步高光谱原位地面实测数据。HSE结合了五种不同的基学习器，采用10折折外堆叠进行训练，并与多样性约束的非负最小二乘（NNLS）元学习器集成，辅以涵盖光谱、空间和时间表示的291维特征集。我们提出基于插值的光谱数据增强（Interpolation-based Spectral Data Augmentation, ISDA），这是一种受生态学启发的类平衡过采样方法，在初始分层划分后应用于训练集以防止信息泄漏。在留出的全球测试集上评估，HSE在Chl-a、TSS、aCDOM(440)和Zsd上分别达到R2 = 0.822、0.704、0.841和0.962（平均R2 = 0.832；均在反变换后以原始物理单位表示）。基于四分位数的分层分析揭示了Chl-a、TSS和aCDOM(440)在低浓度条件下R2为负值，说明全球指标可能掩盖分布中大多数区域的检索失败，特别是在贫营养条件下。这构成了该方法已知的主要局限性：在低浓度、低光学信号条件下实现可靠预测仍然难以实现，仅在存在可测量光学信号的高浓度、富营养化样本中得到验证。","Frontiers in Remote Sensing","2026-09-11T00:00:00Z",79,{"impact":77,"substance":78,"depth":77,"authority":20,"freshness":79,"relevant":22,"comment":80},18,22,8,"基于GLORIA全球高光谱数据集提出分层光谱集成方法，可同步反演叶绿素a、悬浮物等四项水质参数，方法新颖、数据规模大，但低浓度水体反演失效的局限也交代清楚，对农业水环境遥感监测有参考价值。",[82],{"name":73,"url":70},[27,28,29,30,84],"水环境",[86,87],"农业人工智能 机器学习 水质监测 水环境","农业人工智能 机器学习","农业人工智能机器学习水质监测水环境-2433","10.3389\u002Ffrsen.2026.1860176",{"doi":89,"openalex_id":91,"authors":92,"venue":73,"cited_by_count":36,"oa_url":103,"card":104,"direction":61,"ingested_from":63},"W7212323204",[93,95,97,99,101],{"name":94,"orcid":9},"Amirthalakshmi TM",{"name":96,"orcid":9},"Hemanth S",{"name":98,"orcid":9},"Ganesan PV",{"name":100,"orcid":9},"Rahul SG",{"name":102,"orcid":9},"Gayathri M","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1860176\u002Fpdf",{"tldr":105,"method":106,"finding":107,"direction":61,"opportunity":108},"提出分层光谱集成模型HSE，从高光谱遥感反射率中全球尺度反演四种水质参数。","用GLORIA 2022全球7572条高光谱数据，结合10折堆叠集成、NNLS元","整体R²达0.832，但低浓度贫营养水体中Chl-a、TSS、aCDOM(440)的R²为负，反演失","低浓度、弱光学信号水体的反演仍是空白，可探索物理约束与少样本学习提升贫营养水体精度。","2026-09-14T23:30:27.361699Z",{"id":111,"title":112,"url":113,"summary":114,"summary_zh":115,"content":9,"source_name":116,"source_url":113,"published_at":117,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":118,"score_detail":119,"sources":123,"tags":125,"search_phrases":128,"slug":131,"view_count":36,"doi":132,"paper":133,"created_at":153},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",77,{"impact":77,"substance":120,"depth":19,"authority":20,"freshness":121,"relevant":22,"comment":122},20,9,"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。",[124],{"name":116,"url":113},[126,27,28,127,29],"智慧农业","可持续农业",[129,130],"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":132,"openalex_id":134,"authors":135,"venue":116,"cited_by_count":36,"oa_url":113,"card":148,"direction":61,"ingested_from":63},"W7213301703",[136,139,142,145],{"name":137,"orcid":138},"Mihai Valentin Herbei","https:\u002F\u002Forcid.org\u002F0000-0002-3884-3658",{"name":140,"orcid":141},"Ana-Cornelia Badea","https:\u002F\u002Forcid.org\u002F0000-0003-4521-5403",{"name":143,"orcid":144},"Aleksandar Ristić","https:\u002F\u002Forcid.org\u002F0000-0003-0979-3345",{"name":146,"orcid":147},"Paul Sestraș","https:\u002F\u002Forcid.org\u002F0000-0002-8554-0924",{"tldr":149,"method":150,"finding":151,"direction":61,"opportunity":152},"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":155,"title":156,"url":157,"summary":158,"summary_zh":9,"content":9,"source_name":159,"source_url":157,"published_at":160,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":161,"score_detail":162,"sources":164,"tags":166,"search_phrases":168,"slug":171,"view_count":36,"doi":172,"paper":173,"created_at":185},2309,"Modeling Water Quality Parameters in Laga Dadi Reservoir, Ethiopia: An Integrated Remote Sensing and Machine Learning Approach","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10838920\u002Fv1","Modeling Water Quality Parameters in Laga Dadi Reservoir, Ethiopia: An Integrated Remote Sensing and Machine Learning Approach。Research Square","Research Square","2026-09-10T00:00:00Z",55,{"impact":79,"substance":77,"depth":17,"authority":21,"freshness":79,"relevant":22,"comment":163},"埃塞俄比亚水库水质遥感与机器学习建模研究，方法有参考价值但属区域性案例，公共影响有限。",[165],{"name":159,"url":157},[126,28,29,167,30],"水资源管理",[169,170],"水资源管理 智慧农业 机器学习 水质监测","水资源管理 智慧农业","水资源管理智慧农业机器学习水质监测-2309","10.21203\u002Frs.3.rs-10838920\u002Fv1",{"doi":172,"openalex_id":174,"authors":175,"venue":159,"cited_by_count":36,"oa_url":183,"card":9,"direction":184,"ingested_from":63},"W7212151964",[176,178,181],{"name":177,"orcid":9},"Sadirak Tasissa",{"name":179,"orcid":180},"Kenatu Angassa","https:\u002F\u002Forcid.org\u002F0000-0002-1449-2451",{"name":182,"orcid":9},"Workineh Tesfaye","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10838920\u002Flatest.pdf","智慧农业 \u002F 农业物联网","2026-09-13T23:30:12.531084Z",{"id":187,"title":188,"url":189,"summary":190,"summary_zh":9,"content":9,"source_name":191,"source_url":9,"published_at":192,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":118,"score_detail":193,"sources":195,"tags":197,"search_phrases":200,"slug":203,"view_count":36,"doi":9,"paper":204,"created_at":212},2272,"MDPI Remote Sensing 18(18):3107 MODIS NDVI与机器学习作物产量预测比较研究","https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F18\u002F18\u002F3107","Arai与Sanwal在MDPI Remote Sensing发表研究,基于印度2000-2026年州级数据,随机森林在保留时间顺序的走前验证中MAPE=11.4%、R²=0.982,优于梯度提升(MAPE=13.0%)。MODIS NDVI年最大值与粮食产量相关性r≈0.84,提供了可扩展的食品安全评估与农业决策支持实用路线。","MDPI Remote Sensing 18(18):3107","2026-09-09T16:00:00Z",{"impact":77,"substance":78,"depth":77,"authority":20,"freshness":21,"relevant":22,"comment":194},"基于印度2000-2026年州级数据的MODIS NDVI与机器学习产量预测对比研究，方法严谨、结论可靠，对农业遥感估产具有参考价值，但属境外案例、非国内政策或产业突破，适合作为专业精选而非头条。",[196],{"name":191,"url":189},[27,198,28,29,199],"粮食安全","作物产量预测",[201,202],"作物产量预测 农业人工智能 机器学习 粮食安全","作物产量预测 农业人工智能","作物产量预测农业人工智能机器学习粮食安全-2272",{"doi":9,"openalex_id":9,"authors":205,"venue":9,"cited_by_count":36,"oa_url":9,"card":206,"direction":61,"ingested_from":211},[],{"tldr":207,"method":208,"finding":209,"direction":61,"opportunity":210},"基于印度州级MODIS NDVI与机器学习比较作物产量预测，随机森林优于梯度提升。","用2000-2026年印度州级MODIS NDVI年最大值与随机森林、梯度提升走","随机森林MAPE=11.4%、R²=0.982，NDVI与产量相关性r≈0.84。","可在中国等区域验证NDVI-产量模型迁移性，并融合多源遥感与气象提升预测鲁棒性。","agent","2026-09-13T00:04:05.087805Z",{"id":214,"title":215,"url":216,"summary":217,"summary_zh":9,"content":9,"source_name":218,"source_url":9,"published_at":219,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":220,"score_detail":221,"sources":224,"tags":226,"search_phrases":228,"slug":231,"view_count":36,"doi":232,"paper":233,"created_at":240},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":77,"substance":78,"depth":77,"authority":222,"freshness":21,"relevant":22,"comment":223},14,"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。",[225],{"name":218,"url":216},[126,27,28,29,227],"产量估算",[229,230],"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":232,"openalex_id":9,"authors":234,"venue":9,"cited_by_count":36,"oa_url":9,"card":235,"direction":61,"ingested_from":211},[],{"tldr":236,"method":237,"finding":238,"direction":61,"opportunity":239},"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。","2026-09-12T00:06:40.290409Z",{"id":242,"title":243,"url":244,"summary":245,"summary_zh":246,"content":9,"source_name":247,"source_url":244,"published_at":160,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":248,"score_detail":249,"sources":252,"tags":254,"search_phrases":256,"slug":259,"view_count":36,"doi":260,"paper":261,"created_at":276},2180,"Crop Yield Estimation with MODIS Derived Normalized Difference Vegetation Index and Comparative Study on Crop Yield Prediction Among Linear Regression, Random Forest and Gradient Boosting as Well as CatBoost","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183107","This paper presents the design, development, and evaluation of a machine-learning system built to forecast agricultural crop yields across Indian states between 2000 and 2026, together with a complementary, national-scale verification of predicted crop yield using a MODIS-derived NDVI time series (MOD13A3.061 Vegetation Indices Monthly L3 Global 1 km SIN Grid). Although many prior studies address crop-yield prediction with linear regression, random forest, gradient boosting, and related methods, a complementary, aggregate-level verification method for predicted crop yield has rarely been proposed. This article contributes such a method, together with a complementary NDVI-based estimation approach for total foodgrain output. Crop yield and MODIS-derived NDVI are strongly correlated (r = 0.84 for annual maximum NDVI; r = 0.78 for annual mean NDVI), and a simple regression of total foodgrains on annual maximum NDVI alone reaches R2 = 0.70. Four modeling approaches—linear regression, random forest, gradient boosting, and CatBoost—were built and compared using a chronology-preserving, expanding-window walk-forward validation procedure with a final, untouched 2024–2026 holdout, rather than a random split; a companion leakage check confirmed that reported production is almost algebraically identical to reported yield and therefore had to be excluded from the feature set. Random forest produced the most reliable and consistent forecasts, reaching a mean absolute percentage error (MAPE) of 11.4% and R2 = 0.982 on the final holdout, ahead of CatBoost (MAPE = 11.6%, R2 = 0.969) and gradient boosting (MAPE = 13.0%, R2 = 0.908), and substantially ahead of linear regression, which failed to generalize to the holdout period (R2 = −10.67); across the walk-forward folds preceding this holdout, however, the three tree ensembles were statistically indistinguishable. A four-configuration ablation study confirms that most of this performance gain is attributable to the inclusion of MODIS-derived NDVI rather than to model choice alone. Prediction error varies considerably by crop, from under 10% MAPE for major staples (rice, wheat, maize, sugarcane, moong) to well over 80% MAPE for several lower-volume crops (soyabean, garlic, Sunn hemp, tobacco, potato). The paper also documents two consequential data-quality findings—a near-perfect algebraic relationship between production and yield, and a structural administrative reporting gap in 2020—and closes with directions for future work, including higher-resolution satellite inputs, temporal deep-learning architectures, additional environmental covariates, and explainable-AI analysis of feature contributions.","本文介绍了一个机器学习系统的设计、开发与评估，该系统用于预测2000年至2026年间印度各邦的农作物产量，并辅以一项基于MODIS衍生的NDVI时间序列（MOD13A3.061植被指数月度L3全球1 km SIN网格）在全国尺度上对预测作物产量的验证。尽管此前已有许多研究采用线性回归、随机森林、梯度提升及相关方法进行作物产量预测，但针对预测作物产量的补充性、聚合层面的验证方法却鲜有提出。本文提出了这样一种方法，并辅以一种基于NDVI的粮食总产量估算方法。作物产量与MODIS衍生的NDVI高度相关（年最大NDVI的r = 0.84；年均NDVI的r = 0.78），仅以年最大NDVI对粮食总产量进行简单回归即可达到R² = 0.70。本文构建了四种建模方法——线性回归、随机森林、梯度提升和CatBoost——并采用保持时间顺序的扩展窗口前向验证程序进行比较，最终以2024—2026年作为未触碰的留出集，而非随机划分；一项配套的泄漏检查证实，报告产量与报告单产在代数上几乎完全相同，因此必须将其从特征集中排除。随机森林产生了最可靠且一致的预测，在最终留出集上达到平均绝对百分比误差（MAPE）为11.4%、R² = 0.982，优于CatBoost（MAPE = 11.6%，R² = 0.969）和梯度提升（MAPE = 13.0%，R² = 0.908），并大幅优于线性回归，后者未能泛化至留出期（R² = −10.67）；然而在此留出集之前的各前向验证折中，三种树集成方法在统计上无法区分。一项四配置消融研究证实，大部分性能提升归因于纳入MODIS衍生的NDVI，而非仅归因于模型选择。预测误差因作物而异，主要粮食作物（水稻、小麦、玉米、甘蔗、绿豆）的MAPE低于10%，而若干低产量作物（大豆、大蒜、菽麻、烟草、马铃薯）的MAPE则远超80%。本文还记录了两项重要的数据质量发现——产量与单产之间近乎完美的代数关系，以及2020年结构性的行政报告缺口——并在结尾提出了未来研究方向。","Remote Sensing",81,{"impact":77,"substance":250,"depth":77,"authority":222,"freshness":79,"relevant":22,"comment":251},23,"基于MODIS NDVI与多种机器学习模型的作物产量预测研究，方法严谨、结论可靠，对农业遥感估产有实质参考价值。",[253],{"name":247,"url":244},[27,198,28,29,255],"作物估产",[257,258],"农业人工智能 作物估产 机器学习 粮食安全","农业人工智能 作物估产","农业人工智能作物估产机器学习粮食安全-2180","10.3390\u002Frs18183107",{"doi":260,"openalex_id":262,"authors":263,"venue":247,"cited_by_count":36,"oa_url":244,"card":270,"direction":275,"ingested_from":63},"W7212191753",[264,267],{"name":265,"orcid":266},"Kohei Arai","https:\u002F\u002Forcid.org\u002F0009-0001-6433-1592",{"name":268,"orcid":269},"Sara Sanwal","https:\u002F\u002Forcid.org\u002F0009-0003-7944-0948",{"tldr":271,"method":272,"finding":273,"direction":61,"opportunity":274},"用MODIS NDVI与四种回归模型预测印度各邦作物产量，并做全国尺度验证。","MODIS NDVI时序、线性回归、随机森林、梯度提升、CatBoost及前向验","随机森林最优（MAPE 11.4%），NDVI贡献主要增益，主粮误差低而小作物误差高。","可探索多源遥感与深度模型融合，并针对小作物和行政数据缺口改进预测。","农业人工智能与决策模型","2026-09-11T23:30:52.943993Z"]