[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4087":3,"related-4087":127},{"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,"primary_topic":31,"secondary_topics":37,"classification":44,"search_phrases":87,"slug":90,"view_count":91,"doi":92,"paper":93,"created_at":126},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。",null,"Remote Sensing of Environment","2026-10-01T00:00:00Z","论文",10,true,83,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,23,15,9,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","作物模型","遥感监测","数据同化","小麦产量",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":45,"locked":46,"version":47,"method":48,"evidence":49},"classified",false,"2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":14},[51,57,64,72,77,82],{"code":32,"score":52,"supported":14,"title":53,"abstract":55,"tags":56},25,[54,33],"winter wheat",[34,54,33],[],{"code":39,"score":17,"supported":14,"title":58,"abstract":60,"tags":63},[59],"remote sensing",[61,59,62],"遥感","multispectral",[28],{"code":65,"score":66,"supported":14,"title":67,"abstract":68,"tags":71},"H2",6,[],[69,70],"土壤","soil",[],{"code":73,"score":21,"supported":46,"title":74,"abstract":75,"tags":76},"I1",[],[],[26],{"code":78,"score":21,"supported":46,"title":79,"abstract":80,"tags":81},"I2",[],[],[27],{"code":83,"score":21,"supported":46,"title":84,"abstract":85,"tags":86},"I5",[],[],[29],[88,89],"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",8,"10.1016\u002Fj.rse.2026.115701",{"doi":92,"openalex_id":94,"authors":95,"venue":10,"cited_by_count":118,"oa_url":6,"card":119,"direction":123,"ingested_from":125},"W7215051418",[96,98,100,102,105,107,110,112,114,116],{"name":97,"orcid":9},"Zhikai Cheng",{"name":99,"orcid":9},"Xiaobo Gu",{"name":101,"orcid":9},"Yang Xu",{"name":103,"orcid":104},"Xiaohai Fang","https:\u002F\u002Forcid.org\u002F0000-0003-1322-1366",{"name":106,"orcid":9},"Zhengtao Zhang",{"name":108,"orcid":109},"Penglin Li","https:\u002F\u002Forcid.org\u002F0009-0005-2706-1326",{"name":111,"orcid":9},"Yupeng Li",{"name":113,"orcid":9},"Shikun Sun",{"name":115,"orcid":9},"Yadan Du",{"name":117,"orcid":9},"Huanjie Cai",0,{"tldr":120,"method":121,"finding":122,"direction":123,"opportunity":124},"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。","农业遥感与作物表型","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。","openalex","2026-10-03T23:30:33.709814Z",{"total":66,"page":21,"page_size":66,"items":128},[129,203,280,339,388,460],{"id":130,"title":131,"url":132,"summary":133,"summary_zh":134,"content":9,"source_name":135,"source_url":132,"published_at":136,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":137,"score_detail":138,"sources":143,"tags":145,"primary_topic":149,"secondary_topics":150,"classification":152,"search_phrases":174,"slug":177,"view_count":118,"doi":178,"paper":179,"created_at":202},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。","Smart Agricultural Technology","2026-10-17T00:00:00Z",77,{"impact":139,"substance":140,"depth":17,"authority":141,"freshness":91,"relevant":21,"comment":142},16,22,13,"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。",[144],{"name":135,"url":132},[26,146,28,147,148],"无人机","冬小麦","生物量估算",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[151],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":46,"version":47,"method":48,"evidence":153},{"candidates":154,"agricultural_evidence":14},[155,160,164,170],{"code":32,"score":156,"supported":14,"title":157,"abstract":158,"tags":159},26,[54,33],[34,54,33],[147],{"code":39,"score":139,"supported":14,"title":161,"abstract":162,"tags":163},[59],[61,59],[148,28],{"code":78,"score":66,"supported":14,"title":165,"abstract":166,"tags":169},[],[167,168],"机器学习","machine learning",[],{"code":73,"score":21,"supported":46,"title":171,"abstract":172,"tags":173},[],[],[26],[175,176],"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","10.1016\u002Fj.atech.2026.102656",{"doi":178,"openalex_id":180,"authors":181,"venue":135,"cited_by_count":118,"oa_url":132,"card":197,"direction":123,"ingested_from":125},"W7222806066",[182,184,186,188,191,193,195],{"name":183,"orcid":9},"Guangtao Wang",{"name":185,"orcid":9},"Sumei Yao",{"name":187,"orcid":9},"Yanzheng Xie",{"name":189,"orcid":190},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":192,"orcid":9},"Xiangdong Chen",{"name":194,"orcid":9},"Yuhao Zhang",{"name":196,"orcid":9},"Lina Jiang",{"tldr":198,"method":199,"finding":200,"direction":123,"opportunity":201},"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。","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。","2026-10-20T23:30:03.106267Z",{"id":204,"title":205,"url":206,"summary":207,"summary_zh":208,"content":9,"source_name":209,"source_url":206,"published_at":210,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":211,"score_detail":212,"sources":216,"tags":218,"primary_topic":222,"secondary_topics":223,"classification":225,"search_phrases":241,"slug":244,"view_count":245,"doi":246,"paper":247,"created_at":279},2522,"Estimation of Grain Yield and Quality in Awned and Awnless Wheat Genotypes Using UAV and Proximal Multispectral Sensors","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fplants15182819","This study aimed to evaluate the complementary potential of UAV-based and proximal multispectral sensing using the Plant-O-Meter (POM) sensor for the assessment of wheat grain yield and quality across different phenological stages and two growing seasons. The analysis was based on three vegetation indices, the Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), and Normalized Difference Red Edge Index (NDRE), and included two morphologically distinct genotype groups, awned and awnless. The study included nine awned and nine awnless genotypes. Vegetation indices showed pronounced seasonal dynamics, with higher values during intensive vegetative development and a decline during later growth stages. The strongest relationship with grain yield was observed for GNDVI-A during the heading to beginning of flowering stage (BBCH 51–61) in Season I (r = 0.85), whereas in Season II, the strongest relationship was observed for NDRE-A during the flag leaf stage (BBCH 37–39) (r = 0.80). Awned genotypes generally showed stronger VI–yield relationships, while associations with grain quality parameters varied among genotype groups and seasons. Linear mixed-effects models showed that both VI-related effects and genotype variability contributed to the variation in grain yield and quality. For yield, marginal R2 was 0.43 in Season I and 0.50 in Season II, while conditional R2 was 0.78 and 0.64, respectively. For protein and wet gluten content, model performance was more variable, with marginal R2 values ranging from 0.30 to 0.39 for protein and from 0.31 to 0.33 for wet gluten. Genotype-level LOGO cross-validation further indicated variation in model performance when genotypes not included in model development were evaluated. Overall, the results indicate that relationships between multispectral vegetation indices and wheat grain yield and quality depend on sensing method, phenological stage, genotype characteristics, and growing season. The findings provide an exploratory basis for the application of multispectral sensing in wheat phenotyping and assessment of grain yield and quality, while further validation across broader genetic and environmental conditions is required.","本研究旨在评估基于无人机与近地多光谱传感（采用Plant-O-Meter（POM）传感器）在不同物候期和两个生长季中对小麦籽粒产量和品质评估的互补潜力。分析基于三个植被指数，即归一化差异植被指数（NDVI）、绿色归一化差异植被指数（GNDVI）和归一化差异红边指数（NDRE），并纳入两个形态学上不同的基因型组，即有芒和无芒。研究包括9个有芒基因型和9个无芒基因型。植被指数表现出明显的季节性动态变化，在旺盛营养发育期数值较高，在生长后期下降。与籽粒产量关系最强的是抽穗至开花初期（BBCH 51–61）第I季的GNDVI-A（r = 0.85），而在第II季，关系最强的是旗叶期（BBCH 37–39）的NDRE-A（r = 0.80）。有芒基因型总体上表现出更强的植被指数-产量关系，而与籽粒品质参数的关联因基因型组和季节而异。线性混合效应模型表明，植被指数相关效应和基因型变异均对籽粒产量和品质的变异有贡献。对于产量，第I季的边际R²为0.43，第II季为0.50，而条件R²分别为0.78和0.64。对于蛋白质和湿面筋含量，模型表现更为多变，蛋白质的边际R²范围为0.30至0.39，湿面筋为0.31至0.33。基因型水平的LOGO交叉验证进一步表明，在评估未纳入模型开发的基因型时，模型表现存在变异。总体而言，结果表明多光谱植被指数与小麦籽粒产量和品质之间的关系取决于传感方法、物候期、基因型特征和生长季。研究结果为多光谱传感在小麦表型分析及籽粒产量和品质评估中的应用提供了探索性依据，但仍需在更广泛的遗传和环境条件下进一步验证。","Plants","2026-09-14T00:00:00Z",75,{"impact":19,"substance":213,"depth":214,"authority":141,"freshness":20,"relevant":21,"comment":215},21,17,"该研究利用无人机与近地多光谱传感器评估有芒\u002F无芒小麦产量与品质，方法新颖、数据跨两季，对智慧农业遥感育种有参考价值，但属探索性论文，产业影响有限。",[217],{"name":209,"url":206},[26,219,220,221,28],"产量预测","小麦育种","作物表型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[224],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":46,"version":47,"method":48,"evidence":226},{"candidates":227,"agricultural_evidence":14},[228,232,237],{"code":32,"score":19,"supported":14,"title":229,"abstract":230,"tags":231},[33],[34,33],[220],{"code":39,"score":233,"supported":14,"title":234,"abstract":235,"tags":236},14,[62],[62],[219,221,28],{"code":73,"score":21,"supported":46,"title":238,"abstract":239,"tags":240},[],[],[26],[242,243],"产量预测 作物表型 小麦育种 智慧农业","产量预测 作物表型","产量预测作物表型小麦育种智慧农业-2522",2,"10.3390\u002Fplants15182819",{"doi":246,"openalex_id":248,"authors":249,"venue":209,"cited_by_count":118,"oa_url":206,"card":274,"direction":123,"ingested_from":125},"W7212560710",[250,253,256,259,262,265,268,271],{"name":251,"orcid":252},"Irina Marina","https:\u002F\u002Forcid.org\u002F0000-0002-5894-363X",{"name":254,"orcid":255},"Vesna Kandić","https:\u002F\u002Forcid.org\u002F0000-0003-1999-2030",{"name":257,"orcid":258},"Marko Kostić","https:\u002F\u002Forcid.org\u002F0000-0001-9446-994X",{"name":260,"orcid":261},"Nataša Ljubičić","https:\u002F\u002Forcid.org\u002F0000-0001-5982-9401",{"name":263,"orcid":264},"Biljana Bošković","https:\u002F\u002Forcid.org\u002F0000-0003-4977-3170",{"name":266,"orcid":267},"Kosta Gligorević","https:\u002F\u002Forcid.org\u002F0000-0001-5783-4637",{"name":269,"orcid":270},"Miloš Pajić","https:\u002F\u002Forcid.org\u002F0000-0002-8905-3293",{"name":272,"orcid":273},"Milan Dražić","https:\u002F\u002Forcid.org\u002F0000-0002-0416-5174",{"tldr":275,"method":276,"finding":277,"direction":123,"opportunity":278},"用无人机与近地多光谱传感器评估有芒\u002F无芒小麦产量与品质，比较不同生育期和年份的植被指数关系。","无人机与Plant-O-Meter多光谱传感器，NDVI\u002FGNDVI\u002FNDRE，","GNDVI与NDRE在抽穗至开花期和旗叶期与产量相关性最强，有芒基因型关系更强，模型对品质预测较弱。","可探索多源遥感融合与基因型分层建模，提升跨年份、跨环境的小麦产量与品质预测泛化能力。","2026-09-15T23:30:17.124343Z",{"id":281,"title":282,"url":283,"summary":284,"summary_zh":9,"content":9,"source_name":285,"source_url":9,"published_at":286,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":287,"score_detail":288,"sources":290,"tags":292,"primary_topic":296,"secondary_topics":297,"classification":305,"search_phrases":326,"slug":329,"view_count":21,"doi":9,"paper":330,"created_at":338},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","2026-10-21T00:00:00Z",82,{"impact":17,"substance":140,"depth":17,"authority":233,"freshness":13,"relevant":21,"comment":289},"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。",[291],{"name":285,"url":283},[26,293,221,294,295],"农业遥感","无人机多光谱","小麦渍害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[298,299],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":300,"slug":301,"name":302,"path":303,"parent_code":304},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":45,"locked":46,"version":47,"method":48,"evidence":306},{"candidates":307,"agricultural_evidence":14},[308,313,317,322],{"code":32,"score":309,"supported":14,"title":310,"abstract":311,"tags":312},11,[34],[34],[],{"code":39,"score":309,"supported":14,"title":314,"abstract":315,"tags":316},[294],[],[221,293,294],{"code":300,"score":91,"supported":14,"title":318,"abstract":320,"tags":321},[319],"渍害",[],[],{"code":73,"score":21,"supported":46,"title":323,"abstract":324,"tags":325},[],[],[26],[327,328],"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":331,"venue":9,"cited_by_count":118,"oa_url":9,"card":332,"direction":123,"ingested_from":337},[],{"tldr":333,"method":334,"finding":335,"direction":123,"opportunity":336},"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":340,"title":341,"url":342,"summary":343,"summary_zh":9,"content":9,"source_name":344,"source_url":9,"published_at":345,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":346,"score_detail":347,"sources":349,"tags":351,"primary_topic":352,"secondary_topics":353,"classification":356,"search_phrases":376,"slug":379,"view_count":118,"doi":9,"paper":380,"created_at":387},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":139,"substance":213,"depth":214,"authority":233,"freshness":91,"relevant":21,"comment":348},"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。",[350],{"name":344,"url":342},[26,293,221,294,295],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[354,355],{"code":300,"slug":301,"name":302,"path":303,"parent_code":304},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":46,"version":47,"method":48,"evidence":357},{"candidates":358,"agricultural_evidence":14},[359,363,367,371],{"code":32,"score":309,"supported":14,"title":360,"abstract":361,"tags":362},[34],[34],[],{"code":300,"score":309,"supported":14,"title":364,"abstract":365,"tags":366},[319],[319],[],{"code":39,"score":309,"supported":14,"title":368,"abstract":369,"tags":370},[294],[],[221,293,294],{"code":73,"score":372,"supported":14,"title":373,"abstract":374,"tags":375},4,[],[26],[26],[377,378],"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":381,"venue":9,"cited_by_count":118,"oa_url":9,"card":382,"direction":123,"ingested_from":337},[],{"tldr":383,"method":384,"finding":385,"direction":123,"opportunity":386},"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":389,"title":390,"url":391,"summary":392,"summary_zh":393,"content":9,"source_name":394,"source_url":391,"published_at":395,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":396,"score_detail":397,"sources":399,"tags":401,"primary_topic":404,"secondary_topics":405,"classification":411,"search_phrases":436,"slug":439,"view_count":440,"doi":441,"paper":442,"created_at":459},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":17,"substance":140,"depth":17,"authority":233,"freshness":20,"relevant":21,"comment":398},"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。",[400],{"name":394,"url":391},[26,293,147,402,403],"迁移学习","叶绿素监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[406,407],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":78,"slug":408,"name":409,"path":410,"parent_code":43},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":45,"locked":46,"version":47,"method":48,"evidence":412},{"candidates":413,"agricultural_evidence":14},[414,418,423,429],{"code":32,"score":156,"supported":14,"title":415,"abstract":416,"tags":417},[54,33],[34,54,33],[147],{"code":39,"score":19,"supported":14,"title":419,"abstract":421,"tags":422},[420],"hyperspectral",[61,59],[293],{"code":78,"score":13,"supported":14,"title":424,"abstract":425,"tags":428},[],[426,167,168,427],"深度学习","deep learning",[402],{"code":73,"score":430,"supported":14,"title":431,"abstract":432,"tags":435},7,[],[433,434],"精准农业","precision agriculture",[26],[437,438],"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":441,"openalex_id":443,"authors":444,"venue":394,"cited_by_count":118,"oa_url":391,"card":454,"direction":123,"ingested_from":125},"W7220844556",[445,447,449,452],{"name":446,"orcid":9},"Xueqing Zhu",{"name":448,"orcid":9},"Ying Nian",{"name":450,"orcid":451},"Jikai Liu","https:\u002F\u002Forcid.org\u002F0000-0003-2365-5221",{"name":453,"orcid":9},"Xinwei Li",{"tldr":455,"method":456,"finding":457,"direction":123,"opportunity":458},"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":461,"title":462,"url":463,"summary":464,"summary_zh":465,"content":9,"source_name":466,"source_url":463,"published_at":467,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":468,"score_detail":469,"sources":473,"tags":475,"primary_topic":477,"secondary_topics":478,"classification":481,"search_phrases":512,"slug":515,"view_count":21,"doi":516,"paper":517,"created_at":544},3863,"Species identification of crops and weeds in wheat fields using hyperspectral data and machine learning algorithms","https:\u002F\u002Fdoi.org\u002F10.31489\u002F2026feb3\u002F137-151","Based on establishing the relationship between the morphological and anatomical properties of plant tissues and the recognition efficiency of the machine learning algorithm, a comprehensive assessment of the limitations of ML algorithms (using Random Forest as an example) in the multiclass identification of crops and weeds in the agroecosystems of northeastern Kazakhstan was carried out for the first time. The study substantiates the principal biological causes manifested in the optical overlap of classes in the hyperspectral feature space. Data collection was performed with a hyperspectral sensor in the VIS-NIR range. The analysis of spectral profiles was carried out based on variance distribution assessment using principal component analysis and the construction of reflectance curves. Classification of the extracted data was performed using the Random Forest algorithm. Spring wheat (Triticum aestivum) crops at different phenological phases and five dominant weed species (Euphorbia virgata, Descurainia sophia, Vicia hirsuta, Fallopia convolvulus, Echinochloa crus-galli) were selected as research objects. The algorithm demonstrated \"crop-weed\" segregation efficiency with an overall classification accuracy on test data of 72.94%. High identification accuracy was revealed for wheat (MCC=0.994) due to its spectral stability and pronounced red edge features (680-730 nm). Reduced accuracy in intra-class weed separation is driven by species-specific anatomy: thick cuticles in Euphorbia virgata increase reflectance, complex structure in Vicia hirsuta causes spectral dispersion, and mesophyll similarity between Echinochloa crus-galli and grasses leads to optical overlap with crop features. Thus, the model enables reliable crop-weed differentiation, a key requirement for precision agriculture and targeted agrochemical application.","在建立植物组织形态解剖特性与机器学习算法识别效率之间关系的基础上，首次对机器学习算法（以随机森林为例）在哈萨克斯坦东北部农业生态系统中作物与杂草多类识别方面的局限性进行了综合评估。研究证实了在高光谱特征空间中表现为类别光谱重叠的主要生物学成因。数据采集使用VIS-NIR波段的高光谱传感器完成。光谱剖面分析基于主成分分析的方差分布评估及反射率曲线构建进行。提取数据的分类采用随机森林算法完成。选取不同物候期的春小麦（Triticum aestivum）作物及五种优势杂草物种（Euphorbia virgata、Descurainia sophia、Vicia hirsuta、Fallopia convolvulus、Echinochloa crus-galli）作为研究对象。该算法在测试数据上实现了“作物-杂草”分离，总体分类精度为72.94%。小麦因其光谱稳定性及显著的红边特征（680-730 nm）而表现出较高的识别精度（MCC=0.994）。杂草类内分离精度降低由物种特异性解剖结构所致：Euphorbia virgata的厚角质层增加了反射率，Vicia hirsuta的复杂结构导致光谱离散，而Echinochloa crus-galli与禾本科植物之间的叶肉相似性导致其与作物特征发生光谱重叠。因此，该模型能够实现可靠的作物-杂草区分，这是精准农业和靶向农化施用的关键要求。","Fundamental and Experimental Biology","2026-09-29T00:00:00Z",70,{"impact":470,"substance":471,"depth":214,"authority":470,"freshness":20,"relevant":21,"comment":472},12,20,"高光谱结合机器学习实现麦田作物与杂草识别，方法新颖、结论具体，对精准农业有参考价值，但属细分领域研究，影响范围有限。",[474],{"name":466,"url":463},[26,167,34,476,61],"杂草识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[479,480],{"code":78,"slug":408,"name":409,"path":410,"parent_code":43},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":46,"version":47,"method":48,"evidence":482},{"candidates":483,"agricultural_evidence":14},[484,488,492,496,500,507],{"code":32,"score":19,"supported":14,"title":485,"abstract":486,"tags":487},[33],[34,33],[34],{"code":78,"score":19,"supported":14,"title":489,"abstract":490,"tags":491},[168],[167,168],[167],{"code":39,"score":470,"supported":14,"title":493,"abstract":494,"tags":495},[420],[420],[61],{"code":73,"score":430,"supported":14,"title":497,"abstract":498,"tags":499},[],[433,434],[26],{"code":501,"score":502,"supported":14,"title":503,"abstract":504,"tags":506},"H6",3,[],[505],"农业生态",[],{"code":508,"score":21,"supported":46,"title":509,"abstract":510,"tags":511},"F4",[],[],[476],[513,514],"高光谱 小麦 杂草 识别","随机森林 作物 杂草 分类","高光谱小麦杂草识别-3863","10.31489\u002F2026feb3\u002F137-151",{"doi":516,"openalex_id":518,"authors":519,"venue":466,"cited_by_count":118,"oa_url":9,"card":538,"direction":543,"ingested_from":125},"W7214771122",[520,523,526,529,532,535],{"name":521,"orcid":522},"Rimma Meyramovna Ualiyeva","https:\u002F\u002Forcid.org\u002F0000-0003-3551-5007",{"name":524,"orcid":525},"Mariya M. Kaverina","https:\u002F\u002Forcid.org\u002F0000-0002-3838-7656",{"name":527,"orcid":528},"Александра Викторовна Осипова","https:\u002F\u002Forcid.org\u002F0000-0002-3947-5252",{"name":530,"orcid":531},"E. Koppayev","https:\u002F\u002Forcid.org\u002F0009-0004-0476-9017",{"name":533,"orcid":534},"М. А. Чайзабекова","https:\u002F\u002Forcid.org\u002F0009-0004-0468-956X",{"name":536,"orcid":537},"Sayan Berikovich Zhangazin","https:\u002F\u002Forcid.org\u002F0000-0002-5813-8331",{"tldr":539,"method":540,"finding":541,"direction":123,"opportunity":542},"利用高光谱数据与随机森林识别哈萨克斯坦东北部麦田作物与杂草，并分析误判的生物学原因。","VIS-NIR高光谱传感器采集数据，PCA分析光谱，随机森林分类春小麦与五种杂草","作物-杂草总体分类精度72.94%，小麦识别精度高（MCC=0.994），杂草种间分离受解剖结构影响","可探索融合形态解剖特征与深度学习，提升杂草种间分类精度，服务精准施药。","农业人工智能与决策模型","2026-09-30T23:30:54.952093Z"]