[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3177":3,"related-3177":58},{"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,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":57},3177,"A comparative analysis on maize yield prediction using sentinel 2A and Landsat 8 satellite image in Sundarganj, Gaibandha, Bangladesh","https:\u002F\u002Fdoi.org\u002F10.3329\u002Fbjar.v51i1.92530","Maize is an important cereal crops in Bangladesh. Over the last two decades, its cultivation has increased promisingly, especially in the Northern part of Bangladesh. The effective estimation of crop yields at a regional scale holds significant importance in facilitating decision-making within the agricultural sector, thereby ensuring grain security. The traditional ground-based measurement techniques suffer from inefficiencies, and there exists a need for a reliable, precise, and effective method for estimating regional crop yields. This study used remote sensing (RS) techniques for forecasting pre-harvest maize yield to improve the management system. Currently, the normalized difference vegetation index (NDVI) is widely used to predict crop yield including maize. However, the present study used Landsat 8 (~ 30 m) and Sentinel 2A (~ 10 m) high resolution data for 2018-2019 and 2019-2020 to predict maize yield based on the year 2020-2021 at Sundarganj Upazila in Gaibandha district. The single cloud free image acquisition date based on maximum NDVI for both satellite images was used for each maize growing period to develop a yield prediction model. A regression model was performed between NDVI values and 20 farmers field-level maize yields. The absolute mean error of prediction was about 10.30% for Landsat 8 and 6.70% for Sentinel 2A compared to the actual maize yield during 2020-2021. The study revealed that NDVI data extracted from Sentinel 2A high resolution satellite images can be successfully used to predict the maize yield with appreciable accuracy. Finally, this study has demonstrated the efficacy of combining multi-temporal remote sensing data for accurate maize yield estimation, aiding agricultural authorities and production enterprises in the timely formulation and refinement of cropping strategies and management policies for the ongoing season. Bangladesh J. Agril. Res. 51(1): 501-521, March 2026","玉米是孟加拉国重要的谷类作物。过去二十年间，其种植面积增长显著，尤其是在孟加拉国北部地区。在区域尺度上有效估算作物产量对于促进农业部门决策、进而保障粮食安全具有重要意义。传统的地面测量技术效率低下，亟需一种可靠、精确且有效的区域作物产量估算方法。本研究采用遥感（RS）技术预测收获前玉米产量，以改进管理体系。目前，归一化植被指数（NDVI）被广泛用于预测包括玉米在内的作物产量。然而，本研究利用Landsat 8（约30 m）和Sentinel 2A（约10 m）高分辨率数据，基于2018—2019年和2019—2020年的数据，对盖班达县孙达尔甘杰乌帕齐拉2020—2021年的玉米产量进行预测。在每个玉米生长期，选取两颗卫星影像中NDVI最大值对应的单幅无云影像获取日期，用于建立产量预测模型。对NDVI值与20户农民田块级玉米产量进行回归建模。与2020—2021年实际玉米产量相比，Landsat 8的绝对平均预测误差约为10.30%，Sentinel 2A约为6.70%。研究表明，利用Sentinel 2A高分辨率卫星影像提取的NDVI数据可成功用于预测玉米产量，且精度令人满意。最后，本研究证明了结合多时相遥感数据进行准确玉米产量估算的有效性，有助于农业主管部门和生产企业在当季及时制定和完善种植策略与管理政策。Bangladesh J. Agril. Res. 51(1): 501-521, March 2026",null,"Bangladesh Journal of Agricultural Research","2026-09-21T00:00:00Z","论文",10,false,65,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":22},8,20,16,13,1,"基于Sentinel 2A与Landsat 8的玉米遥感估产对比研究，方法清晰、误差数据具体，对遥感估产有参考价值，但属区域小尺度研究，公共影响有限。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","产量预测","玉米","遥感","NDVI",[32,33],"Sentinel 2A Landsat 8 玉米产量预测","孟加拉国 Sundarganj 玉米遥感估产","Sentinel2ALandsat8玉米产量预测-3177",0,"10.3329\u002Fbjar.v51i1.92530",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":6,"card":50,"direction":54,"ingested_from":56},"W7213918280",[40,42,44,46,48],{"name":41,"orcid":9},"N Mohammad",{"name":43,"orcid":9},"MA Islam",{"name":45,"orcid":9},"MG Mahboob",{"name":47,"orcid":9},"MM Rahman",{"name":49,"orcid":9},"I Ahmed",{"tldr":51,"method":52,"finding":53,"direction":54,"opportunity":55},"用Sentinel 2A与Landsat 8的NDVI回归模型预测孟加拉国玉米产量并比较精度。","基于最大NDVI单期影像与20个农户地块产量做回归，比较两种卫星。","Sentinel 2A预测绝对平均误差6.70%，优于Landsat 8的10.30%。","农业遥感与作物表型","可探索多时相NDVI与机器学习融合，提升小农户尺度玉米估产精度与迁移性。","openalex","2026-09-22T23:30:23.551878Z",{"total":59,"page":21,"page_size":59,"items":60},6,[61,114,166,196,247,303],{"id":62,"title":63,"url":64,"summary":65,"summary_zh":66,"content":9,"source_name":67,"source_url":64,"published_at":68,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":69,"score_detail":70,"sources":75,"tags":77,"search_phrases":79,"slug":82,"view_count":21,"doi":83,"paper":84,"created_at":113},2117,"A source-side trait-mediated framework for dynamic maize yield prediction using UAV multispectral imagery","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112375","Dynamic in-season maize yield prediction is essential for cultivation management and precision decision-making. However, traditional yield prediction models based on vegetation indices often lack physiological interpretability, and integrating multitemporal dynamic information within a unified framework remains challenging. This study proposes a source-side trait-mediated approach for dynamic maize yield prediction using UAV multispectral imagery. Leaf area index (LAI), leaf chlorophyll content (SPAD), and aboveground biomass (AGB) were used as intermediate variables. A cascaded framework linking canopy spectra, source-side agronomic traits, and yield was constructed to improve agronomic interpretability. In addition, the temporal dynamic factor (TDF) was introduced to model stage-dependent trait-yield relationships, enabling dynamic yield prediction. The results showed that increasing planting density significantly enhanced LAI and AGB, whereas yield first increased with planting density and then decreased slightly. For agronomic trait prediction, XGBoost generally outperformed RF. In the independent multi-cultivar test, the XGBoost models achieved coefficients of determination (R 2 ) of 0.8185, 0.8758, and 0.8113 for LAI, SPAD, and AGB, respectively. The TDF fitting results for the 2025 dataset showed that the linear relationship between yield and the Comprehensive Yield Index (CYI) had R 2 values ranging from 0.67 to 0.86 and RMSE values from 0.428 to 0.648 t\u002Fha across growth stages. In the 2024 interannual independent test, the model maintained an R 2 of 0.7803 and an RMSE of 0.6076 t\u002Fha. Furthermore, in a multi-cultivar scenario, yield prediction achieved an R 2 of 0.6824 and an RMSE of 0.3746 t\u002Fha. The proposed framework improved the agronomic interpretability and interannual and cross-cultivar applicability of maize yield prediction using UAV-based multitemporal imagery.","动态的玉米生长季产量预测对栽培管理和精准决策至关重要。然而，传统的基于植被指数的产量预测模型往往缺乏生理可解释性，且在统一框架内整合多时相动态信息仍具挑战性。本研究提出了一种基于源端性状介导的方法，利用无人机多光谱影像进行玉米动态产量预测。以叶面积指数（LAI）、叶片叶绿素含量（SPAD）和地上生物量（AGB）作为中间变量，构建了连接冠层光谱、源端农艺性状与产量的级联框架，以提高农艺可解释性。此外，引入时间动态因子（TDF）来建模阶段依赖的性状-产量关系，从而实现动态产量预测。结果表明，增加种植密度显著提高了LAI和AGB，而产量随种植密度先增加后略有下降。在农艺性状预测方面，XGBoost通常优于RF。在独立多品种测试中，XGBoost模型对LAI、SPAD和AGB的决定系数（R²）分别为0.8185、0.8758和0.8113。2025年数据集的TDF拟合结果显示，在各生育阶段，产量与综合产量指数（CYI）之间的线性关系R²范围为0.67至0.86，RMSE范围为0.428至0.648 t\u002Fha。在2024年际独立测试中，模型保持了0.7803的R²和0.6076 t\u002Fha的RMSE。此外，在多品种场景下，产量预测的R²为0.6824，RMSE为0.3746 t\u002Fha。所提出的框架提高了基于无人机多时相影像的玉米产量预测的农艺可解释性以及年际和跨品种适用性。","Computers and Electronics in Agriculture","2026-09-10T00:00:00Z",80,{"impact":71,"substance":72,"depth":71,"authority":73,"freshness":17,"relevant":21,"comment":74},18,22,14,"提出源端性状中介的无人机多光谱玉米动态产量预测框架，方法新颖、跨年跨品种验证扎实，对精准农业决策有实质参考价值。",[76],{"name":67,"url":64},[26,78,27,28,29],"无人机",[80,81],"产量预测 智慧农业 无人机 玉米","产量预测 智慧农业","产量预测智慧农业无人机玉米-2117","10.1016\u002Fj.compag.2026.112375",{"doi":83,"openalex_id":85,"authors":86,"venue":67,"cited_by_count":35,"oa_url":64,"card":108,"direction":54,"ingested_from":56},"W7212127922",[87,89,91,93,96,99,101,103,105],{"name":88,"orcid":9},"Chengxin Bai",{"name":90,"orcid":9},"Xiaoyuan Bao",{"name":92,"orcid":9},"Baoyuan Zhang",{"name":94,"orcid":95},"Congcong Guo","https:\u002F\u002Forcid.org\u002F0000-0002-8231-7655",{"name":97,"orcid":98},"Xinying Li","https:\u002F\u002Forcid.org\u002F0000-0002-4256-589X",{"name":100,"orcid":9},"Fuyang Cui",{"name":102,"orcid":9},"Hong Fan",{"name":104,"orcid":9},"Cai Zhao",{"name":106,"orcid":107},"Xiaohe Gu","https:\u002F\u002Forcid.org\u002F0000-0002-7102-1939",{"tldr":109,"method":110,"finding":111,"direction":54,"opportunity":112},"提出基于无人机多光谱的源端性状中介框架，实现玉米动态产量预测。","用LAI、SPAD、AGB作中间变量，构建冠层光谱-性状-产量级联框架，引入时间","框架提升农学可解释性，跨年独立测试R²=0.78，多品种场景R²=0.68。","可探索将源端性状框架扩展至其他作物或结合多源遥感数据，提升跨区域泛化能力。","2026-09-11T23:30:01.789186Z",{"id":115,"title":116,"url":117,"summary":118,"summary_zh":119,"content":9,"source_name":67,"source_url":117,"published_at":120,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":69,"score_detail":121,"sources":123,"tags":125,"search_phrases":127,"slug":130,"view_count":35,"doi":131,"paper":132,"created_at":165},2016,"Transfer learning integrated with SCOPE model for maize yield prediction based on spectral data for different spatial scales","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112381","Transfer learning integrated with SCOPE model for maize yield prediction based on spectral data for different spatial scales。Computers and Electronics in Agriculture","基于光谱数据的不同空间尺度玉米产量预测中，将迁移学习与SCOPE模型相结合","2026-09-09T00:00:00Z",{"impact":71,"substance":72,"depth":71,"authority":73,"freshness":17,"relevant":21,"comment":122},"将迁移学习与SCOPE辐射传输模型结合，实现跨空间尺度光谱数据的玉米产量预测，方法新颖且对遥感估产有实用价值，值得进入每日精选。",[124],{"name":67,"url":117},[26,126,27,28,29],"农业人工智能",[128,129],"农业人工智能 产量预测 智慧农业 玉米","农业人工智能 产量预测","农业人工智能产量预测智慧农业玉米-2016","10.1016\u002Fj.compag.2026.112381",{"doi":131,"openalex_id":133,"authors":134,"venue":67,"cited_by_count":35,"oa_url":9,"card":160,"direction":54,"ingested_from":56},"W7211999297",[135,137,140,143,145,147,149,152,154,156,158],{"name":136,"orcid":9},"Ruomei Zhao",{"name":138,"orcid":139},"Yanling Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-2323-2600",{"name":141,"orcid":142},"Weimin Guo","https:\u002F\u002Forcid.org\u002F0000-0003-4318-7154",{"name":144,"orcid":9},"Wei Liu",{"name":146,"orcid":9},"Long Zhao",{"name":148,"orcid":9},"Xiaoyuan Tian",{"name":150,"orcid":151},"Yelu Zeng","https:\u002F\u002Forcid.org\u002F0000-0003-4267-1841",{"name":153,"orcid":9},"Lulu An",{"name":155,"orcid":9},"Aiguo Wang",{"name":157,"orcid":9},"Qiang Xu",{"name":159,"orcid":9},"Hong Sun",{"tldr":161,"method":162,"finding":163,"direction":54,"opportunity":164},"结合迁移学习与SCOPE模型，利用不同空间尺度光谱数据预测玉米产量。","迁移学习与SCOPE辐射传输模型，多尺度光谱数据。","该方法能跨空间尺度提升玉米产量预测精度。","可探索迁移学习在跨区域、跨年份及多作物产量预测中的泛化能力。","2026-09-10T23:30:01.419872Z",{"id":167,"title":168,"url":169,"summary":170,"summary_zh":9,"content":9,"source_name":171,"source_url":169,"published_at":172,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":173,"score_detail":174,"sources":177,"tags":179,"search_phrases":181,"slug":184,"view_count":35,"doi":185,"paper":186,"created_at":195},3152,"An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23311932.2026.2725400","An integrated IoT and machine learning framework for maize yield prediction and smart agriculture in Tanzania。Cogent Food & Agriculture","Cogent Food & Agriculture","2026-09-22T00:00:00Z",69,{"impact":175,"substance":71,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":176},12,"论文提出物联网与机器学习融合的玉米产量预测框架，方法有新意但属区域性应用研究，影响力有限，时效性强。",[178],{"name":171,"url":169},[26,126,27,180,28],"物联网",[182,183],"坦桑尼亚 玉米 产量预测","物联网 机器学习 智慧农业","坦桑尼亚玉米产量预测-3152","10.1080\u002F23311932.2026.2725400",{"doi":185,"openalex_id":187,"authors":188,"venue":171,"cited_by_count":35,"oa_url":169,"card":9,"direction":194,"ingested_from":56},"W7213978365",[189,192],{"name":190,"orcid":191},"Alcardo Alex Barakabitze","https:\u002F\u002Forcid.org\u002F0000-0001-8960-8415",{"name":193,"orcid":9},"Yasinta Nzogera","智慧农业 \u002F 农业物联网","2026-09-22T23:30:10.178097Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":201,"content":9,"source_name":67,"source_url":199,"published_at":202,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":203,"score_detail":204,"sources":207,"tags":209,"search_phrases":211,"slug":214,"view_count":35,"doi":215,"paper":216,"created_at":246},3006,"Explainable spectral–image fusion multi-task learning for maize canopy biochemical and structural trait retrieval","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112450","Accurate and interpretable estimation of multiple maize canopy traits is important for proximal crop monitoring and high-throughput phenotyping. This study developed a spectral–image fusion multi-task learning framework (MM-MTL) for the simultaneous retrieval of chlorophyll index (Chl index), leaf area index (LAI), nitrogen balance index (NBI), and anthocyanin index (Anth index). Proximal hyperspectral observations were collected using a Specim IQ camera covering 400–1000 nm with 204 spectral bands. For each observation, an ROI-mean spectral vector was extracted to retain fine-grained canopy reflectance information, while a co-registered pseudo-RGB image derived from visible bands of the same hyperspectral cube preserved two-dimensional canopy structure and visible appearance. MM-MTL integrates spectral and image feature extraction, task-specific fusion, and uncertainty-weighted multi-task learning to jointly estimate the four traits. A total of 1,023 valid samples collected from nine field campaigns across the 2024 and 2025 growing seasons were used for model development and evaluation. Under plot-grouped five-fold cross-validation, MM-MTL achieved R 2 values of 0.872, 0.885, 0.722, and 0.807 for Chl index, LAI, NBI, and Anth index, respectively, and consistently outperformed the single-task, single-representation, and conventional regression baselines. Performance decreased under more challenging generalization settings, with R 2 values ranging from 0.543 to 0.680 under leave-one-campaign-out validation and from 0.425 to 0.640 under bidirectional cross-year validation. Ablation and post-hoc analyses further showed that preserving image spatial organization improved prediction, while task-wise routing, input-representation masking, wavelength perturbation, and cross-fold stability analyses revealed trait-dependent use of spectral and spatial information. These results demonstrate that complementary spectral and spatial representations derived from the same hyperspectral observation can improve multi-trait maize canopy retrieval, while transfer across acquisition campaigns, years, and field environments remains an important direction for further improvement.","准确且可解释地估算多个玉米冠层性状，对于近地作物监测和高通量表型分析具有重要意义。本研究开发了一种光谱—图像融合多任务学习框架（MM-MTL），用于同时反演叶绿素指数（Chl index）、叶面积指数（LAI）、氮平衡指数（NBI）和花青素指数（Anth index）。近地高光谱观测使用Specim IQ相机采集，覆盖400–1000 nm，共204个光谱波段。对于每次观测，提取ROI均值光谱向量以保留细粒度冠层反射率信息，同时从同一高光谱立方体的可见光波段生成配准的伪RGB图像，以保留二维冠层结构和可见外观。MM-MTL集成了光谱与图像特征提取、任务特定融合以及不确定性加权多任务学习，以联合估算这四种性状。研究使用2024年和2025年生长季9次田间试验采集的共计1,023个有效样本进行模型开发与评估。在按小区分组的五折交叉验证下，MM-MTL对Chl index、LAI、NBI和Anth index的R²分别为0.872、0.885、0.722和0.807，且持续优于单任务、单表征和传统回归基线。在更具挑战性的泛化设置下，模型性能有所下降，留一试验验证的R²范围为0.543–0.680，双向跨年验证的R²范围为0.425–0.640。消融分析和事后分析进一步表明，保留图像空间组织可提升预测性能，而任务路由、输入表征掩蔽、波长扰动和跨折稳定性分析揭示了光谱与空间信息的性状依赖性利用方式。这些结果表明，从同一高光谱观测中提取的互补光谱与空间表征可改善多性状玉米冠层反演，而跨采集试验、年份和田间环境的迁移仍是未来改进的重要方向。","2026-09-19T00:00:00Z",81,{"impact":71,"substance":72,"depth":71,"authority":73,"freshness":205,"relevant":21,"comment":206},9,"提出光谱-图像融合多任务学习框架，1023份样本跨两年验证，方法新颖且结论可靠，对作物高通量表型研究有实质参考价值。",[208],{"name":67,"url":199},[26,126,28,29,210],"高通量表型",[212,213],"玉米冠层 多任务学习 高光谱","Specim IQ 玉米 表型","玉米冠层多任务学习高光谱-3006","10.1016\u002Fj.compag.2026.112450",{"doi":215,"openalex_id":217,"authors":218,"venue":67,"cited_by_count":35,"oa_url":199,"card":241,"direction":54,"ingested_from":56},"W7213658705",[219,221,223,225,226,227,229,232,234,236,238],{"name":220,"orcid":9},"Penglei Zhang",{"name":222,"orcid":9},"Tianbo Hao",{"name":224,"orcid":9},"Zhuoyuan Zhao",{"name":159,"orcid":9},{"name":150,"orcid":151},{"name":228,"orcid":9},"Zheng Cui",{"name":230,"orcid":231},"Ta Na","https:\u002F\u002Forcid.org\u002F0000-0002-1348-5655",{"name":233,"orcid":9},"Lang Qiao",{"name":235,"orcid":9},"Durval Dourado Neto",{"name":237,"orcid":9},"Feng Yang",{"name":239,"orcid":240},"Jingzhu Wu","https:\u002F\u002Forcid.org\u002F0000-0002-8386-1038",{"tldr":242,"method":243,"finding":244,"direction":54,"opportunity":245},"提出光谱-图像融合多任务学习框架，同时反演玉米冠层四个生化与结构性状。","Specim IQ高光谱与伪RGB融合，不确定性加权多任务学习，1023样本交叉","融合模型精度优于单任务基线，但跨年份与跨环境泛化性能明显下降。","可研究跨年份\u002F跨环境域适应与迁移学习，提升多性状反演泛化能力。","2026-09-20T23:30:01.739142Z",{"id":248,"title":249,"url":250,"summary":251,"summary_zh":252,"content":9,"source_name":253,"source_url":250,"published_at":254,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":255,"score_detail":256,"sources":259,"tags":261,"search_phrases":263,"slug":265,"view_count":35,"doi":266,"paper":267,"created_at":302},2505,"A continually evolving knowledge-guided deep learning framework for daily maize yield formation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104981","CONTEXT As multi-source agricultural datasets expand, accurate and interpretable simulation of crop yield formation is increasingly feasible and important for food security. Process-based models are widely used for yield forecasting but require laborious regional calibration. Artificial intelligence models learn physiological patterns from large datasets but lack physiological consistency and generalize poorly under data-scarce conditions. OBJECTIVE We developed AgroEvoDeep-Yield, a knowledge-guided model that encodes mechanistic understanding through its neural architecture, enabling explicit and interpretable simulation of daily maize yield formation from flowering to maturity. We further established a framework that supports continual model evolution as new data become available. METHODS The model was pretrained on APSIM-simulated grain number and daily grain biomass sequences to impose physiological consistency. Following pretraining, the model evolved through two continual learning stages. First, field-level continual learning using 796 field observations reduced biases inherited from APSIM. The model was then adapted to regional-scale multi-source inputs using long-term records from 945 meteorological stations and expert-constrained cultivar-parameter optimization. RESULTS AND CONCLUSIONS After field-level continual learning, AgroEvoDeep-Yield reduced grain number and yield simulation errors by 29% and 24%, respectively, relative to APSIM, and outperformed conventional machine learning models in out-of-region prediction. Region-level continual learning reduced yield RMSE to 1.09 t\u002Fha, and expert-constrained cultivar-parameter optimization further reduced it to 0.80 t\u002Fha. SIGNIFICANCE This study demonstrates how a knowledge-guided model can be repeatedly adapted as new data become available, providing a practical framework for continual model evolution and a basis for future agricultural decision support.","背景 随着多源农业数据集的不断扩展，准确且可解释地模拟作物产量形成过程日益可行，对粮食安全也愈发重要。基于过程的模型广泛用于产量预测，但需要耗费大量精力进行区域校准。人工智能模型能够从大规模数据集中学习生理模式，但缺乏生理一致性，在数据稀缺条件下泛化能力较差。目标 我们开发了AgroEvoDeep-Yield，这是一种知识引导模型，通过其神经网络架构编码机理认识，能够对玉米从开花到成熟的逐日产量形成过程进行显式且可解释的模拟。我们还建立了一个框架，以支持在新数据可用时模型的持续演化。方法 该模型在APSIM模拟的粒数和逐日籽粒生物量序列上进行预训练，以施加生理一致性约束。预训练后，模型通过两个持续学习阶段进行演化。首先，利用796个田间观测数据进行田块级持续学习，以减少继承自APSIM的偏差。随后，利用945个气象站的长期记录和专家约束的品种参数优化，将模型适配到区域尺度多源输入。结果与结论 经过田块级持续学习后，AgroEvoDeep-Yield相对于APSIM将粒数和产量模拟误差分别降低了29%和24%，并在区域外预测中优于传统机器学习模型。区域级持续学习将产量RMSE降至1.09 t\u002Fha，专家约束的品种参数优化进一步将其降至0.80 t\u002Fha。意义 本研究表明，知识引导模型可以在新数据可用时被反复适配，为模型持续演化提供了实用框架，并为未来农业决策支持奠定了基础。","Agricultural Systems","2026-09-14T00:00:00Z",85,{"impact":72,"substance":257,"depth":71,"authority":73,"freshness":17,"relevant":21,"comment":258},23,"知识引导的深度学习框架实现玉米逐日产量形成模拟，误差显著低于APSIM且支持持续学习，方法新颖、数据规模扎实，对智慧农业决策支持有参考价值。",[260],{"name":253,"url":250},[26,126,27,28,262],"作物模型",[264,129],"农业人工智能 产量预测 作物模型 智慧农业","农业人工智能产量预测作物模型智慧农业-2505","10.1016\u002Fj.agsy.2026.104981",{"doi":266,"openalex_id":268,"authors":269,"venue":253,"cited_by_count":35,"oa_url":250,"card":296,"direction":300,"ingested_from":56},"W7212532256",[270,272,274,277,280,283,285,288,290,293],{"name":271,"orcid":9},"Junji Ou",{"name":273,"orcid":9},"Wenyao Yan",{"name":275,"orcid":276},"Fangzheng Chen","https:\u002F\u002Forcid.org\u002F0009-0006-5061-6227",{"name":278,"orcid":279},"Tao Ye","https:\u002F\u002Forcid.org\u002F0000-0002-5037-8410",{"name":281,"orcid":282},"Ke Liu","https:\u002F\u002Forcid.org\u002F0000-0002-8343-0449",{"name":284,"orcid":9},"Matthew Tom Harrison",{"name":286,"orcid":287},"William D. Batchelor","https:\u002F\u002Forcid.org\u002F0000-0002-3881-6246",{"name":289,"orcid":9},"Yong Chen",{"name":291,"orcid":292},"Kelin Hu","https:\u002F\u002Forcid.org\u002F0000-0001-9321-0821",{"name":294,"orcid":295},"Puyu Feng","https:\u002F\u002Forcid.org\u002F0000-0003-4845-9876",{"tldr":297,"method":298,"finding":299,"direction":300,"opportunity":301},"提出知识引导的深度学习框架AgroEvoDeep-Yield，实现玉米逐日产量形成的可解释模拟与持续","基于APSIM模拟数据预训练，结合796个田间观测和945个气象站数据持续学习。","田间持续学习使粒数和产量误差比APSIM降低29%和24%，区域优化后RMSE降至0.80 t\u002Fha","农业人工智能与决策模型","可探索将知识引导与持续学习框架迁移至其他作物，并融合实时遥感与物联网数据实现动态产量预测。","2026-09-15T23:30:04.611750Z",{"id":304,"title":305,"url":306,"summary":307,"summary_zh":308,"content":9,"source_name":309,"source_url":306,"published_at":68,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":310,"score_detail":311,"sources":314,"tags":316,"search_phrases":319,"slug":322,"view_count":35,"doi":323,"paper":324,"created_at":334},2332,"Wheat Nitrogen Fertilizer Management Using GreenSeeker Handheld Crop Canopy Sensor","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijaes.vol.11.no3.2025.pg12.22","One of the essential factors in increasing agricultural yields of cereal crops is increasing the grain yield without increasing production costs. Wheat (Triticum aestivum L.) is the main crop in the food basket of the entire world. Therefore, it is necessary to determine the appropriate nitrogen (N) requirements to obtain the optimal production of wheat crops by investigating the impact of different N levels on the wheat crop yield in the Al-Muthanna region, as well as determining the possibility of predicting grain yield using the GreenSeeker handheld proximal crop canopy sensorbased differences vegetative difference index (NDVI). Thus, there is a need to re-evaluate the previous recommendations using remote sensing techniques. The experimental treatments were five levels of N fertilizer including (0 Kg N ha-1 , 50 kg N ha-1 , 100 kg N ha-1 ,150 kg N ha-1, and 200 kg N ha-1, and each N level was divided into 100%, 70%, 50% percentages, respectively. This study was conducted at the Experiment Station and Agriculture Research of the College of AgricultureAl-Muthanna University. The NDVI measurements were obtained at FK5, FK7, and FK9 according to the Feekes scale growth stage. The results indicated significant differences in grain yield between different levels of N fertilizer and a 70% percentage outperformed on the 100% and 50% treatments for each of the two N levels of 200 and 150 kg ha-1 . The results also show significant differences between NDVI values for different N fertilizer levels. The NDVI readings and wheat yield values increased and followed a similar pattern with increasing N fertilizer levels. This suggests that NDVI can predict wheat grain yield when the NDVI is not saturated. This study showed the potential of using GreenSeeker proximal crop canopy sensor-based NDVI readings as a useful tool to predict wheat grain yield.","提高谷类作物农业产量的关键因素之一是在不增加生产成本的前提下提高谷物产量。小麦（Triticum aestivum L.）是全球粮食结构中的主要作物。因此，有必要通过研究不同氮水平对Al-Muthanna地区小麦作物产量的影响，确定获得小麦作物最佳产量所需的适宜氮（N）需求量，并确定利用基于GreenSeeker手持式近地作物冠层传感器的归一化植被差异指数（NDVI）预测谷物产量的可能性。因此，需要利用遥感技术重新评估以往的推荐方案。试验处理包括五个氮肥水平（0 kg N ha⁻¹、50 kg N ha⁻¹、100 kg N ha⁻¹、150 kg N ha⁻¹和200 kg N ha⁻¹），每个氮水平分别按100%、70%、50%的比例施用。本研究在Al-Muthanna大学农学院实验站与农业研究中心进行。NDVI测定根据Feekes尺度生育阶段在FK5、FK7和FK9时期进行。结果表明，不同氮肥水平间谷物产量存在显著差异，在200和150 kg ha⁻¹两个氮水平下，70%施用量处理均优于100%和50%处理。结果还显示，不同氮肥水平间NDVI值存在显著差异。随着氮肥水平的提高，NDVI读数和小麦产量值均增加并呈现相似的变化趋势。这表明在NDVI未饱和时，NDVI可以预测小麦谷物产量。本研究表明，利用基于GreenSeeker近地作物冠层传感器的NDVI读数作为预测小麦谷物产量的有用工具具有潜力。","INTERNATIONAL JOURNAL OF AGRICULTURE AND EARTH SCIENCE",61,{"impact":175,"substance":71,"depth":312,"authority":13,"freshness":59,"relevant":21,"comment":313},15,"基于GreenSeeker手持冠层传感器NDVI预测小麦产量并优化氮肥用量，方法实用但属区域性田间试验，产业影响有限。",[315],{"name":309,"url":306},[26,317,318,29,30],"精准施肥","小麦",[320,321],"智慧农业 精准施肥 小麦 遥感","智慧农业 精准施肥","智慧农业精准施肥小麦遥感-2332","10.56201\u002Fijaes.vol.11.no3.2025.pg12.22",{"doi":323,"openalex_id":325,"authors":326,"venue":309,"cited_by_count":35,"oa_url":9,"card":329,"direction":54,"ingested_from":56},"W7212289620",[327],{"name":328,"orcid":9},"Mohammed A. Naser",{"tldr":330,"method":331,"finding":332,"direction":54,"opportunity":333},"用GreenSeeker手持冠层传感器NDVI预测小麦产量并优化氮肥管理。","伊拉克田间试验，5个氮水平，Feekes 5\u002F7\u002F9期测NDVI。","NDVI与产量随氮肥增加同步上升，未饱和时可预测产量，70%氮量表现更优。","可探索NDVI饱和条件下的替代植被指数及不同品种\u002F气候区的氮肥推荐模型迁移。","2026-09-13T23:30:26.260534Z"]