[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4000":3,"related-4000":112},{"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":38,"search_phrases":81,"slug":84,"view_count":85,"doi":86,"paper":87,"created_at":111},4000,"Assessing upper bounds for solar-powered controlled environment agriculture on existing cropland","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1945186","Controlled environment agriculture (CEA) has been proposed as a way of limiting cropland expansion and extending growing seasons, but these systems demand substantial amounts of energy, and their associated environmental impacts remain unclear. Here, we developed a framework to compare global crop area and production (reference year 2020) with an idealized, upper-bound scenario consisting of high-tech greenhouses or vertical farms powered by stand-alone photovoltaics (PV) for wheat, soybeans, potatoes, and tomatoes. The CEA energy calculation was combined with land-use, crop mapping, and PV energy datasets to compare CEA capacity with 2020 global crop production values. Of the 420 Mha of cropland area included in this study, hypothetical high-tech greenhouses and vertical farms powered by stand-alone PV arrays could match 2020 production levels on 313 Mha (74.5% aggregated across the four crops on the studied cropland area) and 275 Mha (65.4%), respectively, in the optimistic upper bound scenario. The modelled potential was greatest in parts of North and South America, South Asia, East Asia, West Africa, the Mediterranean, and Central Asia. These results reflect an idealized comparison, and implementing sustainable CEA at scale would face substantial technical, economic, and societal challenges. However, the framework does illustrate the locations where land and PV energy constraints would be least restrictive for CEA implementation.","受控环境农业（CEA）被视为限制耕地扩张和延长生长季的一种方式，但这些系统需要大量能源，其相关环境影响仍不明确。在此，我们开发了一个框架，将全球作物面积和产量（参考年份2020年）与一个理想化的上限情景进行比较，该情景由独立光伏（PV）供电的高科技温室或垂直农场组成，针对小麦、大豆、马铃薯和番茄。CEA能源计算与土地利用、作物制图和光伏能源数据集相结合，以将CEA产能与2020年全球作物产量值进行比较。在本研究纳入的420 Mha耕地面积中，由独立光伏阵列供电的假设高科技温室和垂直农场在乐观上限情景下，可分别在313 Mha（在研究耕地面积上四种作物合计占74.5%）和275 Mha（65.4%）上匹配2020年产量水平。模拟潜力在南北美洲部分地区、南亚、东亚、西非、地中海和中亚最大。这些结果反映的是一种理想化比较，大规模实施可持续CEA将面临重大技术、经济和社会挑战。然而，该框架确实说明了在哪些地点，土地和光伏能源约束对CEA实施限制最小。",null,"Frontiers in Sustainable Food Systems","2026-10-01T00:00:00Z","论文",10,false,80,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,9,1,"该研究以全球尺度和2020年基准数据量化了光伏驱动设施农业替代耕地的理论上限，方法新颖、数据规模大，对智慧农业与设施农业布局有参考价值，但属理想化情景模拟，落地挑战明显。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","设施农业","垂直农场","光伏农业","农业碳中和",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,50,57,64,70,76],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},6,true,[],[34,33],[],{"code":51,"score":52,"supported":46,"title":53,"abstract":54,"tags":56},"B7",5,[],[55],"温室",[29,28],{"code":58,"score":59,"supported":46,"title":60,"abstract":61,"tags":63},"A4",3,[],[62],"大豆",[],{"code":65,"score":59,"supported":46,"title":66,"abstract":67,"tags":69},"A5",[],[68],"马铃薯",[],{"code":71,"score":59,"supported":46,"title":72,"abstract":73,"tags":75},"B1",[],[74],"番茄",[],{"code":77,"score":21,"supported":14,"title":78,"abstract":79,"tags":80},"I1",[],[],[26],[82,83],"光伏温室 垂直农场 作物产量","可控环境农业 太阳能 耕地","光伏温室垂直农场作物产量-4000",2,"10.3389\u002Ffsufs.2026.1945186",{"doi":86,"openalex_id":88,"authors":89,"venue":10,"cited_by_count":103,"oa_url":6,"card":104,"direction":108,"ingested_from":110},"W7215116626",[90,92,94,96,98,101],{"name":91,"orcid":9},"S. A. Roberts",{"name":93,"orcid":9},"K. Winkler",{"name":95,"orcid":9},"M. D. A. Rounsevell",{"name":97,"orcid":9},"A. Saxena",{"name":99,"orcid":100},"L.F.M. Marcelis","https:\u002F\u002Forcid.org\u002F0000-0002-8088-7232",{"name":102,"orcid":9},"R. Fuchs",0,{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"构建框架评估现有农田上光伏驱动可控环境农业替代全球作物生产的理论上限。","结合CEA能耗、土地利用、作物制图与光伏数据，对2020年四种作物做理想化情景模","乐观上限下，高科技温室和垂直农场分别可在313和275 Mha农田上匹配2020年产量。","农业绿色发展与碳","可研究真实技术经济约束下CEA的可行区域，并评估其全生命周期环境与碳足迹。","openalex","2026-10-02T23:30:10.316478Z",{"total":45,"page":21,"page_size":45,"items":113},[114,214,277,343,393,442],{"id":115,"title":116,"url":117,"summary":118,"summary_zh":119,"content":9,"source_name":120,"source_url":117,"published_at":121,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":122,"score_detail":123,"sources":128,"tags":130,"primary_topic":135,"secondary_topics":136,"classification":149,"search_phrases":189,"slug":192,"view_count":103,"doi":193,"paper":194,"created_at":213},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy","2026-10-21T00:00:00Z",77,{"impact":124,"substance":125,"depth":126,"authority":19,"freshness":13,"relevant":21,"comment":127},16,21,17,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[129],{"name":120,"url":117},[26,131,132,133,134],"机器学习","遥感监测","土壤墒情","冬小麦",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[137,143],{"code":138,"slug":139,"name":140,"path":141,"parent_code":142},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":144,"slug":145,"name":146,"path":147,"parent_code":148},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":150},{"candidates":151,"agricultural_evidence":46},[152,158,164,169,177,184],{"code":32,"score":153,"supported":46,"title":154,"abstract":156,"tags":157},26,[155,33],"winter wheat",[34,155,33],[134],{"code":138,"score":159,"supported":46,"title":160,"abstract":161,"tags":163},15,[139],[162,139],"土壤",[133],{"code":144,"score":159,"supported":46,"title":165,"abstract":167,"tags":168},[166],"machine learning",[131,166],[131],{"code":170,"score":13,"supported":46,"title":171,"abstract":172,"tags":176},"I3",[],[173,174,175],"遥感","remote sensing","multispectral",[132],{"code":178,"score":45,"supported":46,"title":179,"abstract":180,"tags":183},"H3",[],[181,182],"灌溉","irrigation",[],{"code":77,"score":185,"supported":46,"title":186,"abstract":187,"tags":188},4,[],[26],[26],[190,191],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":193,"openalex_id":195,"authors":196,"venue":120,"cited_by_count":103,"oa_url":117,"card":206,"direction":212,"ingested_from":110},"W7223156204",[197,200,202,204],{"name":198,"orcid":199},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":201,"orcid":9},"Yi Zhang",{"name":203,"orcid":9},"WEI Lei",{"name":205,"orcid":9},"Chengcai Zhang",{"tldr":207,"method":208,"finding":209,"direction":210,"opportunity":211},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","农业遥感与作物表型","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z",{"id":215,"title":216,"url":217,"summary":218,"summary_zh":9,"content":9,"source_name":219,"source_url":9,"published_at":121,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":220,"score_detail":221,"sources":224,"tags":226,"primary_topic":231,"secondary_topics":232,"classification":242,"search_phrases":264,"slug":267,"view_count":21,"doi":9,"paper":268,"created_at":276},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",82,{"impact":17,"substance":18,"depth":17,"authority":222,"freshness":13,"relevant":21,"comment":223},14,"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。",[225],{"name":219,"url":217},[26,227,228,229,230],"农业遥感","作物表型","无人机多光谱","小麦渍害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[233,237],{"code":170,"slug":234,"name":235,"path":236,"parent_code":148},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"code":238,"slug":239,"name":240,"path":241,"parent_code":142},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"status":39,"locked":14,"version":40,"method":41,"evidence":243},{"candidates":244,"agricultural_evidence":46},[245,250,254,260],{"code":32,"score":246,"supported":46,"title":247,"abstract":248,"tags":249},11,[34],[34],[],{"code":170,"score":246,"supported":46,"title":251,"abstract":252,"tags":253},[229],[],[228,227,229],{"code":238,"score":255,"supported":46,"title":256,"abstract":258,"tags":259},8,[257],"渍害",[],[],{"code":77,"score":21,"supported":14,"title":261,"abstract":262,"tags":263},[],[],[26],[265,266],"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":269,"venue":9,"cited_by_count":103,"oa_url":9,"card":270,"direction":210,"ingested_from":275},[],{"tldr":271,"method":272,"finding":273,"direction":210,"opportunity":274},"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":278,"title":279,"url":280,"summary":281,"summary_zh":282,"content":9,"source_name":283,"source_url":280,"published_at":284,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":122,"score_detail":285,"sources":287,"tags":289,"primary_topic":292,"secondary_topics":293,"classification":295,"search_phrases":314,"slug":317,"view_count":103,"doi":318,"paper":319,"created_at":342},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",{"impact":124,"substance":18,"depth":17,"authority":19,"freshness":255,"relevant":21,"comment":286},"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。",[288],{"name":283,"url":280},[26,290,132,134,291],"无人机","生物量估算",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[294],{"code":170,"slug":234,"name":235,"path":236,"parent_code":148},{"status":39,"locked":14,"version":40,"method":41,"evidence":296},{"candidates":297,"agricultural_evidence":46},[298,302,306,310],{"code":32,"score":153,"supported":46,"title":299,"abstract":300,"tags":301},[155,33],[34,155,33],[134],{"code":170,"score":124,"supported":46,"title":303,"abstract":304,"tags":305},[174],[173,174],[291,132],{"code":144,"score":45,"supported":46,"title":307,"abstract":308,"tags":309},[],[131,166],[],{"code":77,"score":21,"supported":14,"title":311,"abstract":312,"tags":313},[],[],[26],[315,316],"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":318,"openalex_id":320,"authors":321,"venue":283,"cited_by_count":103,"oa_url":280,"card":337,"direction":210,"ingested_from":110},"W7222806066",[322,324,326,328,331,333,335],{"name":323,"orcid":9},"Guangtao Wang",{"name":325,"orcid":9},"Sumei Yao",{"name":327,"orcid":9},"Yanzheng Xie",{"name":329,"orcid":330},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":332,"orcid":9},"Xiangdong Chen",{"name":334,"orcid":9},"Yuhao Zhang",{"name":336,"orcid":9},"Lina Jiang",{"tldr":338,"method":339,"finding":340,"direction":210,"opportunity":341},"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":344,"title":345,"url":346,"summary":347,"summary_zh":9,"content":9,"source_name":348,"source_url":9,"published_at":284,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":349,"score_detail":350,"sources":352,"tags":354,"primary_topic":359,"secondary_topics":360,"classification":361,"search_phrases":381,"slug":384,"view_count":103,"doi":9,"paper":385,"created_at":392},5365,"基于经济型多光谱成像与知识蒸馏模型压缩的小麦线条花叶病毒早期检测","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-10\u002F20261017000601916.htm","研究人员利用配备六个光谱滤光片的消费级数码单反(DSLR)相机在自然环境条件下获取了一个新的小麦线条花叶病毒(WhSMV)多光谱数据集。评估十二个深度学习模型识别 WhSMV 感染不同阶段的性能,并首次将模型压缩技术应用于多光谱图像用于 WhSMV 感染的早期检测。比较了深度学习算法与压缩模型的性能,揭示压缩模型达到与大型深度学习模型相当的性能。WhSMV 是小麦土传媒介传播病毒,巴西与南非均有报道。","Smart Agricultural Technology 2026-10-17",78,{"impact":17,"substance":18,"depth":126,"authority":19,"freshness":255,"relevant":21,"comment":351},"该研究构建了新的多光谱数据集，并首次将模型压缩用于小麦病毒早期检测，方法新颖、结论可靠，对智慧农业植保具有参考价值。",[353],{"name":348,"url":346},[26,355,356,357,358],"农业人工智能","多光谱成像","小麦病害","模型压缩",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":362},{"candidates":363,"agricultural_evidence":46},[364,368,373,377],{"code":32,"score":246,"supported":46,"title":365,"abstract":366,"tags":367},[34],[34],[],{"code":144,"score":185,"supported":46,"title":369,"abstract":370,"tags":372},[],[371],"深度学习",[355],{"code":77,"score":21,"supported":14,"title":374,"abstract":375,"tags":376},[],[],[26],{"code":170,"score":21,"supported":14,"title":378,"abstract":379,"tags":380},[],[],[356],[382,383],"小麦线条花叶病毒 多光谱 检测","知识蒸馏 模型压缩 小麦","小麦线条花叶病毒多光谱检测-5365",{"doi":9,"openalex_id":9,"authors":386,"venue":9,"cited_by_count":103,"oa_url":9,"card":387,"direction":210,"ingested_from":275},[],{"tldr":388,"method":389,"finding":390,"direction":210,"opportunity":391},"用经济型多光谱成像结合知识蒸馏压缩模型，实现小麦线条花叶病毒早期检测。","消费级单反加六波段滤光片采集多光谱数据，评估12个深度学习模型并做模型压缩。","压缩模型性能与大型深度学习模型相当，可用于WhSMV感染早期识别。","可探索低成本多光谱设备与轻量模型在田间病害早期预警中的部署与跨区域泛化。","2026-10-20T02:47:54.487590Z",{"id":394,"title":395,"url":396,"summary":397,"summary_zh":9,"content":9,"source_name":398,"source_url":9,"published_at":399,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":400,"score_detail":401,"sources":403,"tags":405,"primary_topic":409,"secondary_topics":410,"classification":411,"search_phrases":430,"slug":433,"view_count":103,"doi":9,"paper":434,"created_at":441},5362,"深度语义分割模型的时序泛化评估:无人机小麦倒伏监测 5 年跨年测试","https:\u002F\u002Fbioengineer.org\u002Fai-models-trained-on-one-year-of-wheat-fail-the-next-five-year-drone-study-shows\u002F","Zhang G., Wang X., Wang D., Sun D., Zhang Y., Zhang D. (2026) 利用 5 年田间试验评估深度语义分割模型在无人机(UAV)小麦倒伏监测中的时序泛化能力。研究发现:同年内高精度不能保证跨年可靠性,模型从训练年份迁移到其他年份时性能显著下降,基于注意力的模型通常比全卷积网络更稳健,可能因为层级窗口自注意力能整合更长范围上下文,而卷积强调局部模式;即便最优架构在大时序漂移下也出现严重退化。强调时序泛化测试应成为农业 AI 模型部署前的必备环节。DOI: 10.1016\u002Fj.atech.2026.102631。","Smart Agricultural Technology Vol.15 Article 102631 2026-10-16","2026-10-16T00:00:00Z",79,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":255,"relevant":21,"comment":402},"基于5年跨年田间试验揭示农业AI模型时序泛化瓶颈，结论扎实且具部署指导价值，值得入选。",[404],{"name":398,"url":396},[26,355,406,407,408],"无人机遥感","小麦倒伏","模型泛化",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":412},{"candidates":413,"agricultural_evidence":46},[414,418,422,426],{"code":32,"score":246,"supported":46,"title":415,"abstract":416,"tags":417},[34],[34],[],{"code":77,"score":21,"supported":14,"title":419,"abstract":420,"tags":421},[],[],[26],{"code":144,"score":21,"supported":14,"title":423,"abstract":424,"tags":425},[],[],[355],{"code":170,"score":21,"supported":14,"title":427,"abstract":428,"tags":429},[],[],[406],[431,432],"无人机 小麦倒伏 监测","深度语义分割 时序泛化","无人机小麦倒伏监测-5362",{"doi":9,"openalex_id":9,"authors":435,"venue":9,"cited_by_count":103,"oa_url":9,"card":436,"direction":210,"ingested_from":275},[],{"tldr":437,"method":438,"finding":439,"direction":210,"opportunity":440},"用5年田间试验评估深度语义分割模型在无人机小麦倒伏监测中的跨年泛化能力。","5年无人机小麦倒伏影像，对比注意力模型与全卷积网络的跨年迁移表现。","同年内高精度不能保证跨年可靠，注意力模型比全卷积网络更稳健，但大时序漂移下仍严重退化。","可研究时序域自适应与跨年增量学习，建立农业AI模型部署前的时序泛化评测基准。","2026-10-20T02:47:54.289085Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":9,"content":9,"source_name":447,"source_url":9,"published_at":399,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":448,"score_detail":449,"sources":451,"tags":453,"primary_topic":454,"secondary_topics":455,"classification":458,"search_phrases":477,"slug":480,"view_count":103,"doi":9,"paper":481,"created_at":488},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))",76,{"impact":124,"substance":125,"depth":126,"authority":222,"freshness":255,"relevant":21,"comment":450},"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。",[452],{"name":447,"url":445},[26,227,228,229,230],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[456,457],{"code":238,"slug":239,"name":240,"path":241,"parent_code":142},{"code":170,"slug":234,"name":235,"path":236,"parent_code":148},{"status":39,"locked":14,"version":40,"method":41,"evidence":459},{"candidates":460,"agricultural_evidence":46},[461,465,469,473],{"code":32,"score":246,"supported":46,"title":462,"abstract":463,"tags":464},[34],[34],[],{"code":238,"score":246,"supported":46,"title":466,"abstract":467,"tags":468},[257],[257],[],{"code":170,"score":246,"supported":46,"title":470,"abstract":471,"tags":472},[229],[],[228,227,229],{"code":77,"score":185,"supported":46,"title":474,"abstract":475,"tags":476},[],[26],[26],[478,479],"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":482,"venue":9,"cited_by_count":103,"oa_url":9,"card":483,"direction":210,"ingested_from":275},[],{"tldr":484,"method":485,"finding":486,"direction":210,"opportunity":487},"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"]