[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5535":3,"related-5535":90},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":21,"tags":23,"primary_topic":29,"secondary_topics":35,"classification":48,"search_phrases":75,"slug":78,"view_count":19,"doi":8,"paper":79,"created_at":89},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%。",null,"智慧农业（中英文）2026-10-21","2026-10-21T00:00:00Z","论文",10,false,82,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":12,"relevant":19,"comment":20},18,22,14,1,"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。",[22],{"name":9,"url":6},[24,25,26,27,28],"智慧农业","农业遥感","作物表型","无人机多光谱","小麦渍害",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[36,42],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":49,"locked":13,"version":50,"method":51,"evidence":52},"classified","2026-10-22.2","rules",{"candidates":53,"agricultural_evidence":56},[54,60,64,70],{"code":30,"score":55,"supported":56,"title":57,"abstract":58,"tags":59},11,true,[32],[32],[],{"code":43,"score":55,"supported":56,"title":61,"abstract":62,"tags":63},[27],[],[26,25,27],{"code":37,"score":65,"supported":56,"title":66,"abstract":68,"tags":69},8,[67],"渍害",[],[],{"code":71,"score":19,"supported":13,"title":72,"abstract":73,"tags":74},"I1",[],[],[24],[76,77],"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":8,"openalex_id":8,"authors":80,"venue":8,"cited_by_count":81,"oa_url":8,"card":82,"direction":86,"ingested_from":88},[],0,{"tldr":83,"method":84,"finding":85,"direction":86,"opportunity":87},"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%。","农业遥感与作物表型","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",{"total":91,"page":19,"page_size":91,"items":92},6,[93,145,205,287,362,429],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":8,"content":8,"source_name":98,"source_url":8,"published_at":99,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":100,"score_detail":101,"sources":106,"tags":108,"primary_topic":109,"secondary_topics":110,"classification":113,"search_phrases":133,"slug":136,"view_count":81,"doi":8,"paper":137,"created_at":144},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":102,"substance":103,"depth":104,"authority":18,"freshness":65,"relevant":19,"comment":105},16,21,17,"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。",[107],{"name":98,"url":96},[24,25,26,27,28],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[111,112],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},{"status":49,"locked":13,"version":50,"method":51,"evidence":114},{"candidates":115,"agricultural_evidence":56},[116,120,124,128],{"code":30,"score":55,"supported":56,"title":117,"abstract":118,"tags":119},[32],[32],[],{"code":37,"score":55,"supported":56,"title":121,"abstract":122,"tags":123},[67],[67],[],{"code":43,"score":55,"supported":56,"title":125,"abstract":126,"tags":127},[27],[],[26,25,27],{"code":71,"score":129,"supported":56,"title":130,"abstract":131,"tags":132},4,[],[24],[24],[134,135],"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":8,"openalex_id":8,"authors":138,"venue":8,"cited_by_count":81,"oa_url":8,"card":139,"direction":86,"ingested_from":88},[],{"tldr":140,"method":141,"finding":142,"direction":86,"opportunity":143},"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":146,"title":147,"url":148,"summary":149,"summary_zh":8,"content":8,"source_name":150,"source_url":8,"published_at":151,"category":11,"cover_url":8,"hotness":152,"is_selected":13,"score":153,"score_detail":154,"sources":156,"tags":160,"primary_topic":164,"secondary_topics":165,"classification":168,"search_phrases":193,"slug":196,"view_count":197,"doi":8,"paper":198,"created_at":204},2997,"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方法","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7685741381196825088","江苏省农业科学院农业信息研究所梁万杰等联合中国农科院农业环境与可持续发展研究所、湖北粮作所、扬州大学等团队，针对小麦渍害防控提出基于无人机多光谱图像和VGG21模型的快速无损识别方法。在小麦拔节-抽穗和抽穗-灌浆两个阶段开展对照、渍水胁迫、硅肥调控和氨基酸调控4个类别数据集，大疆精灵4多光谱无人机采集小麦冠层多光谱图像，测产评估调控效果。","智慧农业(中英文)2026,8(4):60-69","2026-09-15T12:42:00Z",25,78,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":91,"relevant":19,"comment":155},"多机构协作提出无人机多光谱结合VGG21的小麦渍害无损识别方法，方法新颖、数据扎实，对智慧农业植保监测有参考价值。",[157,158],{"name":150,"url":148},{"name":159,"url":96},"智慧农业(中英文)8(4) 60-69(2026)",[24,161,162,28,163],"农业人工智能","无人机遥感","多光谱成像",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[166,167],{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":49,"locked":13,"version":50,"method":51,"evidence":169},{"candidates":170,"agricultural_evidence":56},[171,176,180,184,188],{"code":43,"score":172,"supported":56,"title":173,"abstract":174,"tags":175},13,[27],[27],[163,162],{"code":30,"score":55,"supported":56,"title":177,"abstract":178,"tags":179},[32],[32],[],{"code":37,"score":55,"supported":56,"title":181,"abstract":182,"tags":183},[67],[67],[],{"code":71,"score":19,"supported":13,"title":185,"abstract":186,"tags":187},[],[],[24],{"code":189,"score":19,"supported":13,"title":190,"abstract":191,"tags":192},"I2",[],[],[161],[194,195],"江苏省农科院 小麦渍害 无人机多光谱","VGG21 小麦 渍害识别","江苏省农科院小麦渍害无人机多光谱-2997",3,{"doi":8,"openalex_id":8,"authors":199,"venue":8,"cited_by_count":81,"oa_url":8,"card":200,"direction":86,"ingested_from":88},[],{"tldr":140,"method":201,"finding":202,"direction":86,"opportunity":203},"大疆精灵4多光谱无人机采集冠层图像，构建VGG21分类模型。","该方法可快速无损识别渍害及硅肥、氨基酸调控效果。","可探索多光谱与深度学习结合评估其他逆境调控措施，并迁移至多作物场景。","2026-09-20T00:03:07.858899Z",{"id":206,"title":207,"url":208,"summary":209,"summary_zh":210,"content":8,"source_name":211,"source_url":208,"published_at":212,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":213,"score_detail":214,"sources":217,"tags":219,"primary_topic":223,"secondary_topics":224,"classification":230,"search_phrases":262,"slug":265,"view_count":266,"doi":267,"paper":268,"created_at":286},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":16,"substance":17,"depth":16,"authority":18,"freshness":215,"relevant":19,"comment":216},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。",[218],{"name":211,"url":208},[24,25,220,221,222],"冬小麦","迁移学习","叶绿素监测",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[225,226],{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},{"code":189,"slug":227,"name":228,"path":229,"parent_code":47},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":49,"locked":13,"version":50,"method":51,"evidence":231},{"candidates":232,"agricultural_evidence":56},[233,239,247,255],{"code":30,"score":234,"supported":56,"title":235,"abstract":237,"tags":238},26,[236,31],"winter wheat",[32,236,31],[220],{"code":43,"score":240,"supported":56,"title":241,"abstract":243,"tags":246},15,[242],"hyperspectral",[244,245],"遥感","remote sensing",[25],{"code":189,"score":12,"supported":56,"title":248,"abstract":249,"tags":254},[],[250,251,252,253],"深度学习","机器学习","machine learning","deep learning",[221],{"code":71,"score":256,"supported":56,"title":257,"abstract":258,"tags":261},7,[],[259,260],"精准农业","precision agriculture",[24],[263,264],"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":267,"openalex_id":269,"authors":270,"venue":211,"cited_by_count":81,"oa_url":208,"card":280,"direction":86,"ingested_from":285},"W7220844556",[271,273,275,278],{"name":272,"orcid":8},"Xueqing Zhu",{"name":274,"orcid":8},"Ying Nian",{"name":276,"orcid":277},"Jikai Liu","https:\u002F\u002Forcid.org\u002F0000-0003-2365-5221",{"name":279,"orcid":8},"Xinwei Li",{"tldr":281,"method":282,"finding":283,"direction":86,"opportunity":284},"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。","openalex","2026-10-08T23:30:29.383957Z",{"id":288,"title":289,"url":290,"summary":291,"summary_zh":292,"content":8,"source_name":293,"source_url":290,"published_at":294,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":295,"score_detail":296,"sources":298,"tags":300,"primary_topic":304,"secondary_topics":305,"classification":307,"search_phrases":323,"slug":326,"view_count":327,"doi":328,"paper":329,"created_at":361},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":240,"substance":103,"depth":104,"authority":172,"freshness":215,"relevant":19,"comment":297},"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。",[299],{"name":293,"url":290},[24,301,302,26,303],"产量预测","小麦育种","遥感监测",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[306],{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},{"status":49,"locked":13,"version":50,"method":51,"evidence":308},{"candidates":309,"agricultural_evidence":56},[310,314,319],{"code":30,"score":240,"supported":56,"title":311,"abstract":312,"tags":313},[31],[32,31],[302],{"code":43,"score":18,"supported":56,"title":315,"abstract":317,"tags":318},[316],"multispectral",[316],[301,26,303],{"code":71,"score":19,"supported":13,"title":320,"abstract":321,"tags":322},[],[],[24],[324,325],"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":328,"openalex_id":330,"authors":331,"venue":293,"cited_by_count":81,"oa_url":290,"card":356,"direction":86,"ingested_from":285},"W7212560710",[332,335,338,341,344,347,350,353],{"name":333,"orcid":334},"Irina Marina","https:\u002F\u002Forcid.org\u002F0000-0002-5894-363X",{"name":336,"orcid":337},"Vesna Kandić","https:\u002F\u002Forcid.org\u002F0000-0003-1999-2030",{"name":339,"orcid":340},"Marko Kostić","https:\u002F\u002Forcid.org\u002F0000-0001-9446-994X",{"name":342,"orcid":343},"Nataša Ljubičić","https:\u002F\u002Forcid.org\u002F0000-0001-5982-9401",{"name":345,"orcid":346},"Biljana Bošković","https:\u002F\u002Forcid.org\u002F0000-0003-4977-3170",{"name":348,"orcid":349},"Kosta Gligorević","https:\u002F\u002Forcid.org\u002F0000-0001-5783-4637",{"name":351,"orcid":352},"Miloš Pajić","https:\u002F\u002Forcid.org\u002F0000-0002-8905-3293",{"name":354,"orcid":355},"Milan Dražić","https:\u002F\u002Forcid.org\u002F0000-0002-0416-5174",{"tldr":357,"method":358,"finding":359,"direction":86,"opportunity":360},"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":363,"title":364,"url":365,"summary":366,"summary_zh":367,"content":8,"source_name":368,"source_url":365,"published_at":369,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":370,"score_detail":371,"sources":373,"tags":375,"primary_topic":378,"secondary_topics":379,"classification":381,"search_phrases":400,"slug":403,"view_count":81,"doi":404,"paper":405,"created_at":428},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":102,"substance":17,"depth":16,"authority":172,"freshness":65,"relevant":19,"comment":372},"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。",[374],{"name":368,"url":365},[24,376,303,220,377],"无人机","生物量估算",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[380],{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},{"status":49,"locked":13,"version":50,"method":51,"evidence":382},{"candidates":383,"agricultural_evidence":56},[384,388,392,396],{"code":30,"score":234,"supported":56,"title":385,"abstract":386,"tags":387},[236,31],[32,236,31],[220],{"code":43,"score":102,"supported":56,"title":389,"abstract":390,"tags":391},[245],[244,245],[377,303],{"code":189,"score":91,"supported":56,"title":393,"abstract":394,"tags":395},[],[251,252],[],{"code":71,"score":19,"supported":13,"title":397,"abstract":398,"tags":399},[],[],[24],[401,402],"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":404,"openalex_id":406,"authors":407,"venue":368,"cited_by_count":81,"oa_url":365,"card":423,"direction":86,"ingested_from":285},"W7222806066",[408,410,412,414,417,419,421],{"name":409,"orcid":8},"Guangtao Wang",{"name":411,"orcid":8},"Sumei Yao",{"name":413,"orcid":8},"Yanzheng Xie",{"name":415,"orcid":416},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":418,"orcid":8},"Xiangdong Chen",{"name":420,"orcid":8},"Yuhao Zhang",{"name":422,"orcid":8},"Lina Jiang",{"tldr":424,"method":425,"finding":426,"direction":86,"opportunity":427},"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":430,"title":431,"url":432,"summary":433,"summary_zh":434,"content":8,"source_name":435,"source_url":432,"published_at":436,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":213,"score_detail":437,"sources":440,"tags":442,"primary_topic":445,"secondary_topics":446,"classification":449,"search_phrases":496,"slug":499,"view_count":327,"doi":500,"paper":501,"created_at":520},4575,"A review of remote sensing for agricultural drought: technologies, indices, modelling advances and future prospects","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15481603.2026.2738981","Agricultural drought is a complex hazard that jeopardises food security and progress toward the Sustainable Development Goals. We systematically reviewed peer-reviewed English-language literature published between 2015 and 2025, focusing on Remote Sensing (RS)-driven agricultural drought monitoring and prediction. Eligible studies were identified from the Web of Science and Scopus databases (last searched in August 2025); review articles, duplicates, and irrelevant studies were excluded, resulting in 181 articles. This review critically examined the evolution of sensors, drought indices, modelling approaches, and emerging technologies used to assess agricultural drought across diverse agro-ecological regions. Specifically, we (1) systematically evaluated the use of optical, thermal, and microwave RS platforms, along with satellite-based, model-based, and reanalysis products for agricultural drought monitoring; (2) reviewed widely used RS-based drought indices, including single indices grouped into nine categories, as well as composite indices; (3) reviewed software or programming languages applied; (4) assessed the progression of modelling approaches from traditional statistical and time-series methods to machine learning (ML) and deep learning (DL) frameworks; and (5) examined validation strategies applied to agricultural drought assessment. The analysis reveals a growing research interest in this topic, with a strong geographic concentration in Asia, particularly China. Optical and thermal platforms (e.g. MODIS and Landsat) dominate the literature (~54%) due to their accessibility, followed by satellite-derived precipitation products (17%), while microwave soil-moisture missions remain underutilized (~7%). Regarding RS-based indices, most studies employed more than one index: 44% analysed multiple individual indices, 51% used composite indices (either alone or in combination with individual indices), and only 5% relied on a single index. Vegetation indices, such as NDVI, remain workhorses; however, their sensitivity to soil background effects and canopy saturation has driven increased adoption of thermal composites (e.g. VHI), as well as adaptive weighting schemes and principal component analysis-based approaches. Moreover, computational tools used in drought research can be broadly grouped into geospatial and RS platforms for large-scale data processing and analysis (e.g. QGIS, GEE), and general-purpose programming languages (e.g. R, Python) for model development and advanced analytics. Regarding the methodology, statistical and time-series approaches account for 64% of the reviewed studies, followed by ML models (20%) and DL methods (15%), while explainable artificial intelligence (XAI) remains nascent. Techniques, such as random forests, support vector machines, and CNN and LSTM architectures, generally outperform traditional models but require large training datasets and raise concerns related to interpretability and ethics. In terms of validation, hydro-climatic indices such as SPI and SPEI are most commonly used (32%), followed by crop yield and yield anomaly data (19%). This review further identifies key research gaps across sensors, indices, and modelling approaches and proposes a roadmap for developing equitable, interpretable, and resilient agricultural drought monitoring systems. Emerging opportunities include context-aware and interpretable AI, multi-sensor and multi-scale data fusion across optical, thermal, and microwave domains, integration of physiologically meaningful indicators such as sun-induced chlorophyll fluorescence (SIF), robust uncertainty quantification, and the development of hybrid and physics-informed modelling frameworks.","农业干旱是一种复杂的灾害，威胁粮食安全和可持续发展目标的实现。我们系统综述了2015年至2025年间发表的同行评议英文文献，聚焦于遥感（RS）驱动的农业干旱监测与预测。符合条件的研究通过Web of Science和Scopus数据库检索确定（最后检索时间为2025年8月）；综述文章、重复文献及不相关研究被排除，最终纳入181篇文献。本综述批判性地审视了用于评估不同农业生态区农业干旱的传感器、干旱指数、建模方法及新兴技术的演变。具体而言，我们（1）系统评估了光学、热红外和微波遥感平台，以及基于卫星、基于模型和再分析产品在农业干旱监测中的应用；（2）综述了广泛使用的基于遥感的干旱指数，包括归为九类的单一指数以及复合指数；（3）综述了所应用的软件或编程语言；（4）评估了建模方法从传统统计和时间序列方法向机器学习（ML）和深度学习（DL）框架的演进；（5）考察了应用于农业干旱评估的验证策略。分析显示，该主题的研究兴趣日益增长，地理上高度集中于亚洲，尤其是中国。光学和热红外平台（如MODIS和Landsat）因其可获取性在文献中占主导地位（约54%），其次是卫星降水产品（17%），而微波土壤水分任务仍未得到充分利用（约7%）。在基于遥感的指数方面，大多数研究采用了不止一种指数：44%分析了多个单一指数，51%使用了复合指数（单独使用或与单一指数结合使用），仅5%依赖单一指数。植被指数（如NDVI）仍是主力工具；然而，其对土壤背景效应和冠层饱和的敏感性推动了热红外复合指数（如VHI）以及自适应权重方案和基于主成分分析的方法得到更多采用。此外，干旱研究中使用的计算工具可大致分为用于大规模数据处理和分析的地理空间与遥感平台（如QGIS、GEE），以及用于模型开发的通用编程语言（如R、Python）。","GIScience & Remote Sensing","2026-10-08T00:00:00Z",{"impact":16,"substance":17,"depth":438,"authority":18,"freshness":65,"relevant":19,"comment":439},19,"系统综述181篇文献，梳理遥感干旱监测的传感器、指数与建模进展，方法学价值高，但属学术综述，产业落地影响有限。",[441],{"name":435,"url":432},[24,443,251,303,444],"粮食安全","农业干旱",{"code":43,"slug":44,"name":45,"path":46,"parent_code":47},[447,448],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"code":189,"slug":227,"name":228,"path":229,"parent_code":47},{"status":49,"locked":13,"version":50,"method":51,"evidence":450},{"candidates":451,"agricultural_evidence":56},[452,456,462,467,473,480,486,492],{"code":43,"score":240,"supported":56,"title":453,"abstract":454,"tags":455},[245],[244,245],[303],{"code":37,"score":18,"supported":56,"title":457,"abstract":459,"tags":461},[458],"drought",[460,458],"干旱",[],{"code":189,"score":12,"supported":56,"title":463,"abstract":464,"tags":466},[],[250,251,252,253,465],"artificial intelligence",[251],{"code":468,"score":256,"supported":56,"title":469,"abstract":470,"tags":472},"A8",[],[443,471],"food security",[443],{"code":474,"score":91,"supported":56,"title":475,"abstract":476,"tags":479},"H2",[],[477,478],"土壤","soil",[],{"code":481,"score":197,"supported":56,"title":482,"abstract":483,"tags":485},"D",[],[484],"水产",[],{"code":487,"score":197,"supported":56,"title":488,"abstract":489,"tags":491},"H6",[],[490],"农业生态",[],{"code":71,"score":19,"supported":13,"title":493,"abstract":494,"tags":495},[],[],[24],[497,498],"遥感 农业干旱 监测","GIScience Remote Sensing 干旱指数","遥感农业干旱监测-4575","10.1080\u002F15481603.2026.2738981",{"doi":500,"openalex_id":502,"authors":503,"venue":435,"cited_by_count":81,"oa_url":513,"card":514,"direction":519,"ingested_from":285},"W7221081979",[504,507,510],{"name":505,"orcid":506},"Fatemeh Saba","https:\u002F\u002Forcid.org\u002F0000-0001-6171-155X",{"name":508,"orcid":509},"Nima Ahmadian","https:\u002F\u002Forcid.org\u002F0000-0003-3676-1840",{"name":511,"orcid":512},"Olena Dubovyk","https:\u002F\u002Forcid.org\u002F0000-0002-7338-3167","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F15481603.2026.2738981?needAccess=true",{"tldr":515,"method":516,"finding":517,"direction":86,"opportunity":518},"系统综述2015-2025年遥感农业干旱监测与预测的传感器、指数、建模及验证进展。","基于Web of Science与Scopus的181篇文献系统综述，涵盖光学\u002F","光学热红外平台占主导，微波土壤水分利用不足；复合指数与机器学习建模成为趋势。","微波土壤水分数据融合与深度学习干旱预测模型在数据稀缺区验证是潜在研究空白。","智慧农业 \u002F 农业物联网","2026-10-10T23:30:14.933078Z"]