[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5367":3,"related-5367":109},{"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":45,"search_phrases":77,"slug":80,"view_count":81,"doi":82,"paper":83,"created_at":108},5367,"Integration of multi-source UAV remote sensing features and derived features for winter wheat aboveground biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102656","Accurate estimation of winter wheat ( Triticum aestivum L.) aboveground biomass (AGB) is important for crop growth monitoring and field management. However, unmanned aerial vehicle (UAV)-based AGB estimation remains challenging due to variations in canopy conditions across growth stages, and different remote sensing features can capture complementary characteristics related to AGB estimation. This study integrated multi-source UAV-derived features, including vegetation indices (VIs), texture features (TFs), light detection and ranging (LiDAR)-derived features, and derived features (DFs) generated from the original feature sets, with four machine learning algorithms for winter wheat AGB estimation. Results showed that TFs provided better prediction performance than other single-source feature sets. Compared with single-source feature sets, the integration of VIs, TFs, LiDAR-derived features, and DFs further improved AGB estimation, and the random forest (RF) model achieved the best performance among the evaluated models (R² = 0.923, RMSE = 1.731 Mg ha⁻¹). Incremental R² analysis based on a stage-only baseline model showed that the RF model explained additional variation in AGB beyond growth-stage information, with an incremental R² of 0.479. Stage-specific evaluation indicated that model performance varied among growth stages, with the highest accuracy observed at the booting stage (R² = 0.632, RMSE = 1.425 Mg ha⁻¹). Feature contribution analysis based on the full-feature fusion model using all growth-stage data identified canopy coverage and several DFs as important predictors, while stage-specific analyses showed differences in dominant predictors across growth stages. The integration of multi-source UAV-derived features and DFs with machine learning provides an effective approach for winter wheat AGB estimation, while model performance remains strongly dependent on growth stage.","准确估算冬小麦（Triticum aestivum L.）地上生物量（aboveground biomass, AGB）对作物生长监测和田间管理具有重要意义。然而，由于不同生育期冠层条件存在差异，且不同遥感特征能够捕捉与AGB估算相关的互补信息，基于无人机（unmanned aerial vehicle, UAV）的AGB估算仍面临挑战。本研究将多源无人机衍生特征，包括植被指数（vegetation indices, VIs）、纹理特征（texture features, TFs）、激光雷达（light detection and ranging, LiDAR）衍生特征以及由原始特征集生成的衍生特征（derived features, DFs），与四种机器学习算法相结合，用于冬小麦AGB估算。结果表明，TFs的预测性能优于其他单一来源特征集。与单一来源特征集相比，融合VIs、TFs、LiDAR衍生特征和DFs进一步提高了AGB估算精度，其中随机森林（random forest, RF）模型在所评估的模型中表现最佳（R² = 0.923，RMSE = 1.731 Mg ha⁻¹）。基于仅含生育期信息的基线模型进行的增量R²分析表明，RF模型在生育期信息之外解释了AGB的额外变异，增量R²为0.479。分生育期评估表明，模型性能在不同生育期之间存在差异，其中在孕穗期观察到最高精度（R² = 0.632，RMSE = 1.425 Mg ha⁻¹）。基于使用全部生育期数据的全特征融合模型进行的特征贡献分析识别出冠层覆盖度和若干DFs为重要预测因子，而分生育期分析则表明不同生育期的主导预测因子存在差异。将多源无人机衍生特征和DFs与机器学习相结合，为冬小麦AGB估算提供了一种有效方法，但模型性能仍强烈依赖于生育期。",null,"Smart Agricultural Technology","2026-10-17T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,13,8,1,"该研究融合无人机多源遥感特征与衍生特征，用随机森林估算冬小麦地上生物量，方法新颖、结论可靠，对作物长势监测有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","无人机","遥感监测","冬小麦","生物量估算",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[39],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":46,"locked":14,"version":47,"method":48,"evidence":49},"classified","2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":53},[51,58,64,72],{"code":33,"score":52,"supported":53,"title":54,"abstract":56,"tags":57},26,true,[55,34],"winter wheat",[35,55,34],[30],{"code":40,"score":17,"supported":53,"title":59,"abstract":61,"tags":63},[60],"remote sensing",[62,60],"遥感",[31,29],{"code":65,"score":66,"supported":53,"title":67,"abstract":68,"tags":71},"I2",6,[],[69,70],"机器学习","machine learning",[],{"code":73,"score":22,"supported":14,"title":74,"abstract":75,"tags":76},"I1",[],[],[27],[78,79],"无人机 多源遥感 冬小麦 生物量","冬小麦 地上生物量 随机森林","无人机多源遥感冬小麦生物量-5367",0,"10.1016\u002Fj.atech.2026.102656",{"doi":82,"openalex_id":84,"authors":85,"venue":10,"cited_by_count":81,"oa_url":6,"card":101,"direction":105,"ingested_from":107},"W7222806066",[86,88,90,92,95,97,99],{"name":87,"orcid":9},"Guangtao Wang",{"name":89,"orcid":9},"Sumei Yao",{"name":91,"orcid":9},"Yanzheng Xie",{"name":93,"orcid":94},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":96,"orcid":9},"Xiangdong Chen",{"name":98,"orcid":9},"Yuhao Zhang",{"name":100,"orcid":9},"Lina Jiang",{"tldr":102,"method":103,"finding":104,"direction":105,"opportunity":106},"融合无人机多源遥感特征与衍生特征，用机器学习估算冬小麦地上生物量。","无人机植被指数、纹理、LiDAR特征及衍生特征结合四种机器学习算法建模。","多源特征融合优于单一特征，随机森林最优（R²=0.923），精度随生育期变化。","农业遥感与作物表型","可探索生育期自适应建模与特征选择，提升跨期生物量估算的稳健性与可迁移性。","openalex","2026-10-20T23:30:03.106267Z",{"total":66,"page":22,"page_size":66,"items":110},[111,187,277,332,428,475],{"id":112,"title":113,"url":114,"summary":115,"summary_zh":116,"content":9,"source_name":117,"source_url":114,"published_at":118,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":120,"sources":124,"tags":126,"primary_topic":130,"secondary_topics":131,"classification":137,"search_phrases":163,"slug":166,"view_count":167,"doi":168,"paper":169,"created_at":186},4433,"PROSAIL-DNN-TL: A Hyperspectral Inversion Framework for Winter Wheat Leaf Chlorophyll Content Based on Fine-Tuned Transfer Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16191971","Accurate and efficient estimation of leaf chlorophyll content (LCC) is essential for crop physiological monitoring and precision agriculture. Current remote sensing approaches for LCC estimation mainly rely on machine learning and deep learning methods, which exhibit strong nonlinear modelling capabilities but require sufficient and representative samples. Radiative transfer models (RTMs) can simulate canopy spectral response based on physical mechanisms and generate large-scale datasets, thereby overcoming the limitations of purely data-driven approaches. However, their applications under diverse environmental conditions remain challenging due to uncertainties caused by model parameterization and discrepancies between simulated and observed data. This study proposed a hybrid framework, PROSAIL-DNN-TL, integrating the PROSAIL RTM with full-network fine-tuned transfer learning for winter wheat LCC estimation. First, 85,680 simulated samples generated by PROSAIL were used to pre-train a deep neural network (DNN), and field observations (n = 270) were subsequently used for full-network fine-tuning. A conventional DNN model trained only with field data and machine learning models based on different feature selection strategies were established for comparison. The results showed that: (1) UVE-selected bands were distributed across visible, red-edge, and near-infrared regions; CARS retained more bands in the visible region, whereas SPA mainly selected near-infrared bands; (2) RR and SVR achieved higher accuracy than KNN, with the full-spectrum and CARS feature sets showing superior performance and SPA showing the lowest accuracy; (3) PROSAIL-DNN-TL achieved reliable LCC estimation performance, with an average test R2 of 0.79 across 500 repeated experiments, and showed improved performance compared with conventional machine learning models; (4) PROSAIL-DNN-TL achieved reliable predictive performance when evaluated using datasets collected during the 2024 and 2025 growing seasons, with R2 values of 0.75 and 0.92, respectively. Overall, the proposed hybrid framework integrates physical knowledge from RTMs with data-driven modelling through transfer learning, providing a potential approach for crop chlorophyll monitoring. However, the SPAD-to-LCC conversion used in this study was not specifically calibrated for the instrument and crop, and therefore, the absolute LCC values should be interpreted with caution.","准确、高效地估算叶片叶绿素含量（leaf chlorophyll content，LCC）对作物生理监测和精准农业至关重要。当前遥感估算LCC的方法主要依赖机器学习和深度学习方法，这类方法具有较强的非线性建模能力，但需要充足且具有代表性的样本。辐射传输模型（radiative transfer models，RTMs）能够基于物理机制模拟冠层光谱响应并生成大规模数据集，从而克服纯数据驱动方法的局限性。然而，由于模型参数化带来的不确定性以及模拟数据与观测数据之间的差异，其在不同环境条件下的应用仍面临挑战。本研究提出了一种混合框架PROSAIL-DNN-TL，将PROSAIL辐射传输模型与全网络微调迁移学习相结合，用于冬小麦LCC估算。首先，利用PROSAIL生成的85 680个模拟样本预训练深度神经网络（deep neural network，DNN），随后利用田间观测数据（n = 270）进行全网络微调。同时建立了仅使用田间数据训练的传统DNN模型以及基于不同特征选择策略的机器学习模型作为对比。结果表明：（1）UVE选择的波段分布在可见光、红边和近红外区域；CARS在可见光区域保留了更多波段，而SPA主要选择近红外波段；（2）RR和SVR的精度高于KNN，全光谱和CARS特征集表现较优，SPA精度最低；（3）PROSAIL-DNN-TL取得了可靠的LCC估算性能，在500次重复实验中平均测试R²为0.79，且相比传统机器学习模型表现出更优的性能；（4）利用2024年和2025年生长季采集的数据集进行评估时，PROSAIL-DNN-TL均表现出可靠的预测性能，R²分别为0.75和0.92。总体而言，所提出的混合框架通过迁移学习将辐射传输模型的物理知识与数据驱动建模相结合，为作物叶绿素监测提供了一种潜在途径。然而，本研究中使用的SPAD到LCC的转换并未针对仪器和作物进行专门校准，因此绝对LCC值应谨慎解读。","Agronomy","2026-10-07T00:00:00Z",81,{"impact":19,"substance":18,"depth":19,"authority":121,"freshness":122,"relevant":22,"comment":123},14,9,"将PROSAIL辐射传输模型与深度神经网络迁移学习结合，用8万余模拟样本预训练、270个田间样本微调，冬小麦叶绿素反演精度可靠，方法新颖且数据规模扎实，对作物生理监测与精准农业有参考价值。",[125],{"name":117,"url":114},[27,127,30,128,129],"农业遥感","迁移学习","叶绿素监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[132,133],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":65,"slug":134,"name":135,"path":136,"parent_code":44},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":46,"locked":14,"version":47,"method":48,"evidence":138},{"candidates":139,"agricultural_evidence":53},[140,144,150,156],{"code":33,"score":52,"supported":53,"title":141,"abstract":142,"tags":143},[55,34],[35,55,34],[30],{"code":40,"score":145,"supported":53,"title":146,"abstract":148,"tags":149},15,[147],"hyperspectral",[62,60],[127],{"code":65,"score":13,"supported":53,"title":151,"abstract":152,"tags":155},[],[153,69,70,154],"深度学习","deep learning",[128],{"code":73,"score":157,"supported":53,"title":158,"abstract":159,"tags":162},7,[],[160,161],"精准农业","precision agriculture",[27],[164,165],"PROSAIL 冬小麦 叶绿素","高光谱 叶绿素 反演","PROSAIL冬小麦叶绿素-4433",5,"10.3390\u002Fagronomy16191971",{"doi":168,"openalex_id":170,"authors":171,"venue":117,"cited_by_count":81,"oa_url":114,"card":181,"direction":105,"ingested_from":107},"W7220844556",[172,174,176,179],{"name":173,"orcid":9},"Xueqing Zhu",{"name":175,"orcid":9},"Ying Nian",{"name":177,"orcid":178},"Jikai Liu","https:\u002F\u002Forcid.org\u002F0000-0003-2365-5221",{"name":180,"orcid":9},"Xinwei Li",{"tldr":182,"method":183,"finding":184,"direction":105,"opportunity":185},"提出PROSAIL-DNN-TL框架，用PROSAIL模拟数据预训练DNN并全网络微调，反演冬小麦叶","PROSAIL辐射传输模型生成85680样本预训练DNN，270个田间样本全网络","500次重复实验平均测试R²为0.79，2024和2025年生长季验证R²分别为0.75和0.92，","SPAD到LCC转换未针对仪器和作物标定，可研究跨传感器、跨作物、跨生长季的迁移学习泛化与绝对叶绿素标定。","2026-10-08T23:30:29.383957Z",{"id":188,"title":189,"url":190,"summary":191,"summary_zh":192,"content":9,"source_name":193,"source_url":190,"published_at":194,"category":12,"cover_url":9,"hotness":13,"is_selected":53,"score":195,"score_detail":196,"sources":199,"tags":201,"primary_topic":205,"secondary_topics":206,"classification":208,"search_phrases":241,"slug":244,"view_count":21,"doi":245,"paper":246,"created_at":276},4087,"Improving regional winter wheat yield estimation by assimilating cross-scale heterogeneity information from UAV and satellite remote sensing","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115701","Accurate high-resolution winter wheat yield estimation remains challenging in heterogeneous agricultural systems. Conventional yield estimation approaches remain limited by high uncertainty (process-based crop models) or weak transferability due to insufficient physical knowledge and scarce sample sizes (statistical models based on remote sensing data). Data assimilation offers a promising approach to overcome these limitations, but its performance is constrained by the neglect of heterogeneous information within assimilation grids, particularly in low-intensity agricultural systems. Therefore, we developed a novel cross-scale data assimilation framework to enhance winter wheat yield estimation by integrating unmanned aerial vehicle (UAV) and satellite remote sensing with the WOFOST crop model. First, UAV-derived crop-soil parameters, including leaf area index (LAI), aboveground biomass (AGB), and soil moisture at 10 and 20 cm depths (SMC-10 and SMC-20), served as a bridge linking in situ sampling data with Sentinel satellite images. Next, a mixture density network (MDN) was employed to construct an upscaling model for predicting probability distributions, thereby obtaining the distribution of crop-soil parameters within each satellite pixel as field heterogeneity information. Finally, these heterogeneity distributions were incorporated into WOFOST through an improved particle filter to generate high-resolution yield (10 m × 10 m) estimates at the regional scale. The results showed that robust crop-soil parameter inversion models were constructed using random forest with multispectral and thermal UAV images (R 2 : 0.73–0.88; NRMSE: 12.30%–22.83%). The MDN quantified within-pixel heterogeneity of crop-soil parameters through a UAV-satellite upscaling approach. The joint assimilation of LAI, AGB, and SMC-10 achieved optimal winter wheat yield estimation performance for MDN-based cross-scale data assimilation (R 2 = 0.83, NRMSE = 15.70% in 2024–2025), outperforming satellite-based and mean-based cross-scale assimilation. The proposed framework showed stable interannual performance in Xianyang (RMSE ≤758 kg ha −1 , NRMSE ≤17.20% in 2017–2023) and reasonable transferability in two external winter wheat regions (RMSE ≤943 kg ha −1 ; NRMSE ≤18.29% in Baoding and Changji). Overall, the cross-scale data assimilation framework exhibited strong performance in wheat yield estimation and would provide scientific support for intensive agricultural development.","在异质性农业系统中，实现准确的高分辨率冬小麦产量估算仍具挑战性。传统产量估算方法受限于较高不确定性（基于过程的作物模型）或可迁移性较弱（基于遥感数据的统计模型），后者源于物理知识不足和样本量稀缺。数据同化为克服这些局限提供了一种有前景的途径，但其性能受到同化网格内异质性信息被忽略的制约，尤其是在低强度农业系统中。因此，我们开发了一种新的跨尺度数据同化框架，通过将无人机（UAV）和卫星遥感与WOFOST作物模型相结合，提升冬小麦产量估算。首先，无人机获取的作物-土壤参数，包括叶面积指数（LAI）、地上生物量（AGB）以及10和20 cm深度土壤水分（SMC-10和SMC-20），作为连接原位采样数据与Sentinel卫星影像的桥梁。接下来，采用混合密度网络（MDN）构建升尺度模型以预测概率分布，从而获得每个卫星像元内作物-土壤参数的分布，作为田块异质性信息。最后，通过改进的粒子滤波器将这些异质性分布纳入WOFOST，以生成区域尺度的高分辨率产量（10 m × 10 m）估算。结果表明，利用随机森林结合多光谱和热红外无人机影像构建了稳健的作物-土壤参数反演模型（R²：0.73–0.88；NRMSE：12.30%–22.83%）。MDN通过无人机-卫星升尺度方法量化了作物-土壤参数的像元内异质性。LAI、AGB和SMC-10的联合同化使基于MDN的跨尺度数据同化取得了最优的冬小麦产量估算性能（2024–2025年R² = 0.83，NRMSE = 15.70%），优于基于卫星和基于均值的跨尺度同化。所提出的框架在咸阳表现出稳定的年际性能（2017–2023年RMSE ≤758 kg ha⁻¹，NRMSE ≤17.20%），并在两个外部冬小麦区域具有合理的可迁移性（保定和昌吉RMSE ≤943 kg ha⁻¹；NRMSE ≤18.29%）。总体而言，该跨尺度数据同化框架在小麦产量估算中表现出较强性能，可为集约化农业发展提供科学支持。","Remote Sensing of Environment","2026-10-01T00:00:00Z",83,{"impact":19,"substance":197,"depth":19,"authority":145,"freshness":122,"relevant":22,"comment":198},23,"该研究提出跨尺度数据同化框架，融合无人机与卫星遥感提升区域冬小麦估产精度，方法新颖、验证充分，对精准农业与农业遥感应用具有较高参考价值。",[200],{"name":193,"url":190},[27,202,29,203,204],"作物模型","数据同化","小麦产量",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[207],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":209},{"candidates":210,"agricultural_evidence":53},[211,216,221,228,232,236],{"code":33,"score":212,"supported":53,"title":213,"abstract":214,"tags":215},25,[55,34],[35,55,34],[],{"code":40,"score":19,"supported":53,"title":217,"abstract":218,"tags":220},[60],[62,60,219],"multispectral",[29],{"code":222,"score":66,"supported":53,"title":223,"abstract":224,"tags":227},"H2",[],[225,226],"土壤","soil",[],{"code":73,"score":22,"supported":14,"title":229,"abstract":230,"tags":231},[],[],[27],{"code":65,"score":22,"supported":14,"title":233,"abstract":234,"tags":235},[],[],[202],{"code":237,"score":22,"supported":14,"title":238,"abstract":239,"tags":240},"I5",[],[],[203],[242,243],"无人机 卫星 遥感 冬小麦 估产","WOFOST 数据同化 小麦","无人机卫星遥感冬小麦估产-4087","10.1016\u002Fj.rse.2026.115701",{"doi":245,"openalex_id":247,"authors":248,"venue":193,"cited_by_count":81,"oa_url":190,"card":271,"direction":105,"ingested_from":107},"W7215051418",[249,251,253,255,258,260,263,265,267,269],{"name":250,"orcid":9},"Zhikai Cheng",{"name":252,"orcid":9},"Xiaobo Gu",{"name":254,"orcid":9},"Yang Xu",{"name":256,"orcid":257},"Xiaohai Fang","https:\u002F\u002Forcid.org\u002F0000-0003-1322-1366",{"name":259,"orcid":9},"Zhengtao Zhang",{"name":261,"orcid":262},"Penglin Li","https:\u002F\u002Forcid.org\u002F0009-0005-2706-1326",{"name":264,"orcid":9},"Yupeng Li",{"name":266,"orcid":9},"Shikun Sun",{"name":268,"orcid":9},"Yadan Du",{"name":270,"orcid":9},"Huanjie Cai",{"tldr":272,"method":273,"finding":274,"direction":105,"opportunity":275},"构建跨尺度数据同化框架，融合无人机与卫星遥感提升区域冬小麦产量估算精度。","UAV-Sentinel数据、混合密度网络升尺度、改进粒子滤波同化WOFOST模","联合同化LAI、AGB与SMC-10最优，R²=0.83，跨年与跨区表现稳定。","可探索异质农田下多源遥感与作物模型同化的普适性及低成本无人机采样优化。","2026-10-03T23:30:33.709814Z",{"id":278,"title":279,"url":280,"summary":281,"summary_zh":9,"content":9,"source_name":282,"source_url":9,"published_at":283,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":284,"score_detail":285,"sources":287,"tags":289,"primary_topic":293,"secondary_topics":294,"classification":296,"search_phrases":319,"slug":322,"view_count":315,"doi":9,"paper":323,"created_at":331},3442,"《多因子监测实现小麦晚霜冻害大范围动态预警》——中国农科院资源区划所农业遥感团队","https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F9\u002F202692094936755155648.shtm","中国农科院农业资源与农业区划研究所农业遥感团队针对黄淮海平原冬小麦3至4月拔节至抽穗期频发的晚霜冻害，提出了多因子综合霜冻监测指数。该指数综合高精度气象预报和冬小麦生长进程信息，兼顾低温强度、持续时间及不同生育期敏感性，并利用遥感土壤水分数据构建非线性调节系数精准刻画湿润土壤对低温的缓冲效应。验证表明该指数对县级小麦产量具有显著指示作用，突破了气象站点的空间局限，可为农业主产区风险精细化管控和科学减灾提供技术支撑。","《欧洲农学杂志（European Journal of Agronomy）》","2026-09-20T00:00:00Z",82,{"impact":18,"substance":197,"depth":19,"authority":121,"freshness":167,"relevant":22,"comment":286},"国家级科研团队在核心期刊提出多因子霜冻监测指数，方法新颖、验证扎实，对黄淮海主产区减灾有实用价值，值得入选。",[288],{"name":282,"url":280},[290,29,30,291,292],"农业气象","灾害预警","晚霜冻害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[295],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":297},{"candidates":298,"agricultural_evidence":53},[299,304,308,313],{"code":33,"score":300,"supported":53,"title":301,"abstract":302,"tags":303},12,[35],[35],[30],{"code":40,"score":300,"supported":53,"title":305,"abstract":306,"tags":307},[62],[62],[29],{"code":222,"score":309,"supported":53,"title":310,"abstract":311,"tags":312},3,[],[225],[],{"code":314,"score":315,"supported":14,"title":316,"abstract":317,"tags":318},"H7",2,[],[],[290,291],[320,321],"中国农科院 冬小麦 晚霜冻害","黄淮海 小麦 遥感监测","中国农科院冬小麦晚霜冻害-3442",{"doi":9,"openalex_id":9,"authors":324,"venue":9,"cited_by_count":81,"oa_url":9,"card":325,"direction":105,"ingested_from":330},[],{"tldr":326,"method":327,"finding":328,"direction":105,"opportunity":329},"提出多因子综合霜冻监测指数，实现黄淮海冬小麦晚霜冻害大范围动态预警。","融合高精度气象预报、小麦生长进程与遥感土壤水分，构建非线性调节系数。","该指数对县级小麦产量有显著指示作用，突破气象站点空间局限。","可结合多源遥感与机器学习，构建不同作物、区域的霜冻风险动态预警与保险定损模型。","agent","2026-09-25T00:09:34.300809Z",{"id":333,"title":334,"url":335,"summary":336,"summary_zh":337,"content":9,"source_name":338,"source_url":335,"published_at":339,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":340,"score_detail":341,"sources":343,"tags":345,"primary_topic":347,"secondary_topics":348,"classification":350,"search_phrases":375,"slug":378,"view_count":309,"doi":379,"paper":380,"created_at":427},3354,"Optimizing canopy nitrogen retrieval in wheat from high-resolution UAV hyperspectral data using RTM-based Gaussian process regression","https:\u002F\u002Fdoi.org\u002F10.1080\u002F01904167.2026.2736627","The canopy nitrogen content (CNC) is one of the vital crop health indicators directly influencing the crop growth, yield, and nutritional status. Unmanned aerial vehicles (UAVs) that acquired hyperspectral imagery opened a new path for nondestructive, accurate, and timely estimation of CNC, facilitating the adoption of smart agro practices in precision agriculture for site-specific nutrient management. With the purpose of processing such hyperspectral data into CNC maps, two hybrid retrieval approaches, protein-based (CNCprot) and chlorophyll-based (CNCchl) models, were built by combining a radiative transfer model with a machine learning Gaussian process regression (GPR) algorithm. The GPR retrieval models were trained using synthetic spectral data from the PROSAIL-PRO model, and the sampling was optimized using the Euclidean distance-based diversity (EBD) active learning (AL) technique. The CNC models were applied to a UAV-borne hyperspectral image in the spectral range of 400-1000 nm with an ultrahigh spatial resolution of 4 cm, acquired over the experimental wheat field of Indian Council of Agricultural Research (ICAR) -Indian Agricultural Research Institute (IARI), New Delhi, India. The GPR models yielded good prediction accuracies with R2 values of 0.74 and 0.56 and NRMSE of 13.62 and 23.82% for CNCchl and CNCprot, respectively. The consistent prediction accuracies and low associated uncertainties revealed that CNC was more accurately mapped using chlorophyll-based CNC retrieval applied to a Vis-NIR-based hyperspectral data. These promising results demonstrated the possibility of applying hybrid GPR models at ultrahigh resolution and the operational viability of UAV datasets for regular CNC monitoring.","冠层氮含量（CNC）是直接影响作物生长、产量和营养状况的重要作物健康指标之一。无人机（UAV）获取的高光谱影像为无损、精准、及时地估算CNC开辟了新途径，有助于在精准农业中采用智能农业实践进行定点养分管理。为了将此类高光谱数据处理为CNC分布图，本研究通过将辐射传输模型与机器学习高斯过程回归（GPR）算法相结合，构建了两种混合反演方法：基于蛋白质的模型（CNCprot）和基于叶绿素的模型（CNCchl）。GPR反演模型使用PROSAIL-PRO模型生成的合成光谱数据进行训练，并采用基于欧氏距离的多样性（EBD）主动学习（AL）技术优化采样。CNC模型被应用于一幅无人机载高光谱影像，光谱范围为400-1000 nm，空间分辨率高达4 cm，该影像获取自印度农业研究理事会（ICAR）-印度农业研究所（IARI）位于印度新德里的实验麦田。GPR模型取得了良好的预测精度，CNCchl和CNCprot的R²值分别为0.74和0.56，NRMSE分别为13.62%和23.82%。一致的预测精度和较低的相关不确定性表明，将基于叶绿素的CNC反演应用于基于可见光-近红外（Vis-NIR）的高光谱数据能够更准确地制图CNC。这些有前景的结果证明了在超高分辨率下应用混合GPR模型的可能性，以及无人机数据集用于常规CNC监测的可行性。","Journal of Plant Nutrition","2026-09-23T00:00:00Z",79,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":342},"将辐射传输模型与高斯过程回归结合，用4厘米超高分辨率无人机高光谱实现小麦冠层氮素精准反演，方法新颖、结论可靠，对精准农业养分管理有实操参考价值。",[344],{"name":338,"url":335},[27,28,35,62,346],"氮素监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[349],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":351},{"candidates":352,"agricultural_evidence":53},[353,357,361,365,369],{"code":33,"score":300,"supported":53,"title":354,"abstract":355,"tags":356},[34],[34],[35],{"code":40,"score":300,"supported":53,"title":358,"abstract":359,"tags":360},[147],[147],[62],{"code":73,"score":157,"supported":53,"title":362,"abstract":363,"tags":364},[],[160,161],[27],{"code":65,"score":66,"supported":53,"title":366,"abstract":367,"tags":368},[],[69,70],[],{"code":370,"score":309,"supported":53,"title":371,"abstract":372,"tags":374},"F3",[],[373],"养分管理",[],[376,377],"无人机 高光谱 小麦 氮素","PROSAIL 高斯过程回归 小麦","无人机高光谱小麦氮素-3354","10.1080\u002F01904167.2026.2736627",{"doi":379,"openalex_id":381,"authors":382,"venue":338,"cited_by_count":81,"oa_url":9,"card":421,"direction":426,"ingested_from":107},"W7214104831",[383,385,387,390,393,395,397,400,403,406,408,411,413,415,418],{"name":384,"orcid":9},"R. G. Rejith",{"name":386,"orcid":9},"Rabi N. Sahoo",{"name":388,"orcid":389},"Shalini Gakhar","https:\u002F\u002Forcid.org\u002F0000-0001-5717-1714",{"name":391,"orcid":392},"Jochem Verrelst","https:\u002F\u002Forcid.org\u002F0000-0002-6313-2081",{"name":394,"orcid":9},"Amrita Bhandari",{"name":396,"orcid":9},"Tarun Kondraju",{"name":398,"orcid":399},"Rajeev Ranjan","https:\u002F\u002Forcid.org\u002F0000-0003-2233-9147",{"name":401,"orcid":402},"Mahesh C. Meena","https:\u002F\u002Forcid.org\u002F0000-0001-5386-883X",{"name":404,"orcid":405},"Abir Dey","https:\u002F\u002Forcid.org\u002F0000-0002-5009-9518",{"name":407,"orcid":9},"Joydeep Mukherjee",{"name":409,"orcid":410},"Sudhir Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-1089-7435",{"name":412,"orcid":9},"Mahesh Kumar",{"name":414,"orcid":9},"Raju Dhandapani",{"name":416,"orcid":417},"Anchal Dass","https:\u002F\u002Forcid.org\u002F0000-0003-3909-1803",{"name":419,"orcid":420},"Viswanathan Chinnusamy","https:\u002F\u002Forcid.org\u002F0000-0003-2174-9064",{"tldr":422,"method":423,"finding":424,"direction":105,"opportunity":425},"用PROSAIL-PRO与高斯过程回归从无人机高光谱数据反演小麦冠层氮含量。","PROSAIL-PRO合成光谱训练GPR，EBD主动学习采样，4cm无人机高光谱","叶绿素基模型精度更高，R²达0.74，NRMSE为13.62%，优于蛋白基模型。","可探索多生育期、多品种迁移能力及主动学习采样策略对反演精度的提升空间。","智慧农业 \u002F 农业物联网","2026-09-24T23:30:10.311254Z",{"id":429,"title":430,"url":431,"summary":432,"summary_zh":9,"content":9,"source_name":433,"source_url":9,"published_at":434,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":435,"score_detail":436,"sources":438,"tags":440,"primary_topic":441,"secondary_topics":442,"classification":444,"search_phrases":463,"slug":466,"view_count":309,"doi":9,"paper":467,"created_at":474},2996,"基于高光谱遥感和跨区域迁移学习的冬小麦叶绿素含量评估","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7686128266574430720","甘肃农业大学李怡悦等与中国农业科学院作物科学研究所肖永贵、孟亚雄研究员团队合作，针对高光谱遥感跨区域叶绿素评估中因\"域偏移\"导致的模型泛化性能下降问题，提出一种稳健自适应迁移学习框架（RATL），通过自适应特征选择、特征权重调整与域适应训练3模块协同实现跨区域知识有效迁移。基于2023—2024年冬小麦灌浆后期新乡与周口两地共1491份冠层高光谱与叶片SPAD数据，设置4种场景比较RATL与直接迁移、迁移成分分析和相关对齐之间的精度。","智慧农业(中英文)2026,8(4):47-59","2026-09-16T13:43:00Z",76,{"impact":17,"substance":18,"depth":19,"authority":121,"freshness":66,"relevant":22,"comment":437},"方法新颖、数据扎实的跨区域叶绿素遥感评估研究，对智慧农业遥感应用有参考价值。",[439],{"name":433,"url":431},[27,62,30,128,129],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[443],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":445},{"candidates":446,"agricultural_evidence":53},[447,451,455,459],{"code":33,"score":300,"supported":53,"title":448,"abstract":449,"tags":450},[35],[35],[30],{"code":40,"score":300,"supported":53,"title":452,"abstract":453,"tags":454},[62],[62],[62],{"code":73,"score":22,"supported":14,"title":456,"abstract":457,"tags":458},[],[],[27],{"code":65,"score":22,"supported":14,"title":460,"abstract":461,"tags":462},[],[],[128],[464,465],"冬小麦 叶绿素 高光谱遥感","跨区域迁移学习 冬小麦","冬小麦叶绿素高光谱遥感-2996",{"doi":9,"openalex_id":9,"authors":468,"venue":9,"cited_by_count":81,"oa_url":9,"card":469,"direction":105,"ingested_from":330},[],{"tldr":470,"method":471,"finding":472,"direction":105,"opportunity":473},"提出RATL迁移学习框架，解决高光谱遥感跨区域冬小麦叶绿素评估的域偏移问题。","基于新乡与周口1491份冠层高光谱与SPAD数据，对比RATL与直接迁移、TCA","RATL通过自适应特征选择、权重调整与域适应训练，有效提升跨区域叶绿素评估泛化精度。","可探索多作物、多生育期及不同传感器间的迁移学习，构建通用跨域叶绿素评估模型。","2026-09-20T00:03:07.685193Z",{"id":476,"title":477,"url":478,"summary":479,"summary_zh":9,"content":9,"source_name":480,"source_url":9,"published_at":481,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":482,"score_detail":483,"sources":487,"tags":489,"primary_topic":493,"secondary_topics":494,"classification":497,"search_phrases":523,"slug":526,"view_count":315,"doi":9,"paper":527,"created_at":534},2854,"面向冬小麦水分含量的无人机遥感自动机器学习预测——MDPI Remote Sensing","https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F18\u002F18\u002F3161","本研究探索了无人机遥感快速准确评估冬小麦水分含量的潜力。在开花期和灌浆期使用配备多光谱、RGB和热红外相机的无人机获取高分辨率冠层遥感图像。集成地面真值采样数据与无人机遥感数据,使用自动机器学习(AutoML)框架建立回归模型预测冬小麦水分含量(MC)。结果表明,MC预测在灌浆期表现最佳,TIR传感器精度最高(R²=0.812,MAE=0.0204,RMSE=0.0274)。多传感器融合相比单传感器方法进一步提升预测性能,MC预测的R²达0.876、MAE 0.0191、RMSE 0.0259。来自中国农业科学院农田灌溉研究所。","MDPI Remote Sensing","2026-09-15T00:00:00Z",74,{"impact":145,"substance":484,"depth":485,"authority":20,"freshness":21,"relevant":22,"comment":486},21,17,"中国农科院团队用AutoML融合多光谱、RGB与热红外无人机数据预测冬小麦水分含量，多传感器融合R²达0.876，方法新颖、结论可靠，对精准灌溉有实用价值，值得进入每日精选。",[488],{"name":480,"url":478},[27,490,491,30,492],"农业人工智能","无人机遥感","多传感器融合",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[495,496],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":65,"slug":134,"name":135,"path":136,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":498},{"candidates":499,"agricultural_evidence":53},[500,505,509,513,519],{"code":40,"score":501,"supported":53,"title":502,"abstract":503,"tags":504},20,[62,60],[62],[491],{"code":33,"score":300,"supported":53,"title":506,"abstract":507,"tags":508},[35],[35],[30],{"code":65,"score":300,"supported":53,"title":510,"abstract":511,"tags":512},[69],[69],[490],{"code":514,"score":309,"supported":53,"title":515,"abstract":516,"tags":518},"H3",[],[517],"灌溉",[],{"code":73,"score":22,"supported":14,"title":520,"abstract":521,"tags":522},[],[],[27],[524,525],"农业人工智能 多传感器融合 无人机遥感 智慧农业","农业人工智能 多传感器融合","农业人工智能多传感器融合无人机遥感智慧农业-2854",{"doi":9,"openalex_id":9,"authors":528,"venue":9,"cited_by_count":81,"oa_url":9,"card":529,"direction":105,"ingested_from":330},[],{"tldr":530,"method":531,"finding":532,"direction":105,"opportunity":533},"用无人机多传感器遥感结合AutoML预测冬小麦水分含量。","无人机多光谱、RGB、热红外图像+地面真值，AutoML回归建模。","灌浆期热红外精度最高，多传感器融合将R²提升至0.876。","可探索不同生育期与品种的泛化性，及将水分预测接入灌溉决策系统。","2026-09-18T00:03:30.758419Z"]