[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4893":3,"related-4893":102},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":79,"slug":82,"view_count":83,"doi":84,"paper":85,"created_at":101},4893,"Systematic vegetation index discovery for phenology-based crop mapping","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1911652","Introduction The Systematic Vegetation Index Discovery (SVID) framework generates and evaluates large numbers of vegetation indices (VIs) by combining spectral bands with basic arithmetic operations. We evaluated whether systematically discovered indices could improve agricultural land-cover classification compared with conventional indices such as NDVI while reducing the dimensionality of multitemporal spectral data. Methods We applied SVID to a 323.9 ha agricultural landscape in Andong, South Korea, containing rice paddies, pepper fields, and plastic-covered greenhouses, using 32 cloud‐free Sentinel‐2A images acquired during 2022. Of 1,328 candidate expressions, 1,144 produced numerically valid rasters. A separate Random Forest model was trained for each index using its 32‐date temporal profile and evaluated against 500 independent reference points withheld from training. Before ranking, 388 expressions were identified as algebraically identical to another expression, and a further 355 were strictly monotone transformations and therefore indistinguishable to a rank‐based classifier. Results The 1,144 indices consequently represented 401 distinct features. Several near‐infrared‐to‐visible ratio families outperformed NDVI. The best‐performing index, (NIR – Red)\u002F(Green × Blue), achieved 97.0% overall accuracy and a Kappa coefficient of 0.873, compared with 94.4% and 0.734 for NDVI; this difference was significant by McNemar's test (p = 0.002). The improvement was concentrated in the greenhouse class, whose producer's accuracy increased from 58.6% to 84.5%. A model using all four raw bands across all dates (128 features) achieved 96.0% accuracy and was statistically indistinguishable from the best single index, demonstrating a four‐fold reduction in dimensionality without a detectable loss in accuracy. Rank positions were nevertheless unstable: ten of the 401 features were statistically tied with the best, and mathematically identical formulations differed by up to 3.4 percentage points because of finite‐precision effects. Discussion SVID can identify compact spectral representations that perform as well as or better than conventional indices and full multiband temporal models. However, the instability among top‐ranked indices suggests that results should be reported as index families with confidence intervals rather than as a single winner. Limitations include the use of one site, one year, and four spectral bands; broader testing across sites, years, and spectral configurations is needed.","引言 系统性植被指数发现（Systematic Vegetation Index Discovery, SVID）框架通过将光谱波段与基本算术运算相结合，生成并评估大量植被指数（vegetation indices, VIs）。我们评估了系统性发现的指数能否在降低多时相光谱数据维度的同时，相比NDVI等传统指数提升农业土地覆盖分类性能。方法 我们将SVID应用于韩国安东一处323.9公顷的农业景观，该区域包含稻田、辣椒田和覆膜温室，使用2022年获取的32景无云Sentinel-2A影像。在1,328个候选表达式中，1,144个生成了数值有效栅格。针对每个指数，利用其32个时相的时间剖面分别训练随机森林模型，并在500个未参与训练的独立参考点上进行评估。在排序之前，388个表达式被识别为与另一表达式代数等价，另有355个为严格单调变换，因而对基于秩的分类器不可区分。结果 这1,144个指数因此代表401个不同特征。若干近红外与可见光比值族的表现优于NDVI。表现最佳的指数(NIR – Red)\u002F(Green × Blue)总体精度达到97.0%，Kappa系数为0.873，而NDVI分别为94.4%和0.734；该差异经McNemar检验显著（p = 0.002）。提升主要集中在温室类别，其生产者精度从58.6%提高至84.5%。使用所有时相全部四个原始波段（128个特征）的模型精度为96.0%，与最佳单一指数在统计上不可区分，表明在未检测到精度损失的情况下实现了四倍的维度缩减。然而，排名位置并不稳定：401个特征中有10个与最佳特征在统计上并列，且由于有限精度效应，数学上等价的公式之间差异可达3.4个百分点。讨论 SVID能够识别出性能与常规指数及全多波段时间模型相当或更优的紧凑光谱表示。然而，排名靠前指数之间的不稳定性表明，结果应以指数族及置信区间的形式报告，而非单一最优指数。局限性包括仅使用一个站点、一年数据和四个光谱波段；需要在不同站点、年份和s",null,"Frontiers in Remote Sensing","2026-10-13T00:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,22,18,13,9,1,"提出系统性植被指数发现框架，在韩国安洞农田验证优于NDVI，方法新颖但仅单点单年，属细分领域方法学进展。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","精准农业","遥感","作物识别","植被指数",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":42,"reason":78},[39,48,55,62,68,73],{"code":40,"score":41,"supported":42,"title":43,"abstract":44,"tags":47},"A1",6,true,[],[45,46],"稻田","rice",[],{"code":49,"score":41,"supported":42,"title":50,"abstract":51,"tags":54},"B7",[],[52,53],"温室","greenhouse",[],{"code":56,"score":57,"supported":42,"title":58,"abstract":59,"tags":61},"B1",3,[],[60],"辣椒",[],{"code":63,"score":64,"supported":14,"title":65,"abstract":66,"tags":67},"I3",2,[],[],[31,29],{"code":69,"score":22,"supported":14,"title":70,"abstract":71,"tags":72},"I1",[],[],[28],{"code":74,"score":22,"supported":14,"title":75,"abstract":76,"tags":77},"I2",[],[],[27],"多个产业证据相当，需要确认主归属",[80,81],"Sentinel-2 作物分类 植被指数","SVID 植被指数 水稻 辣椒","Sentinel-2作物分类植被指数-4893",0,"10.3389\u002Ffrsen.2026.1911652",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":83,"oa_url":93,"card":94,"direction":98,"ingested_from":100},"W7221623694",[88,91],{"name":89,"orcid":90},"Ehsan Rahimi","https:\u002F\u002Forcid.org\u002F0000-0002-8401-472X",{"name":92,"orcid":9},"Chuleui Jung","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1911652\u002Fpdf",{"tldr":95,"method":96,"finding":97,"direction":98,"opportunity":99},"系统生成并评估大量植被指数，用于基于物候的农作物分类，发现优于NDVI的指数。","Sentinel-2A时序影像，组合光谱波段生成1328个指数，随机森林分类。","最佳指数(NIR-Red)\u002F(Green×Blue)精度97.0%，优于NDVI的94.4%，且维度","农业遥感与作物表型","可探索更多波段组合与多站点验证，并研究指数排名不稳定的置信区间报告方法。","openalex","2026-10-14T23:30:20.231693Z",{"total":41,"page":22,"page_size":41,"items":103},[104,198,285,353,412,475],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":109,"content":9,"source_name":110,"source_url":107,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":42,"score":112,"score_detail":113,"sources":119,"tags":121,"primary_topic":124,"secondary_topics":129,"classification":130,"search_phrases":165,"slug":168,"view_count":155,"doi":169,"paper":170,"created_at":197},5382,"Modeling the global potential of smart farming innovations","https:\u002F\u002Fdoi.org\u002F10.1073\u002Fpnas.2530081123","Smart farming innovations can improve agricultural productivity, resilience, and environmental sustainability, yet their real-world impact hinges on their diffusion dynamics, which in turn depend on their economic viability. We present here a global assessment of the profitability of smart farming innovation across croplands at a spatial resolution of ~5 km from the farmers’ and the societal perspectives. We cover application mapping for precision agriculture, automated application of inputs, autonomous weeding machines, GPS steering assistance systems, and autonomous irrigation systems. For this, we compiled a globally comprehensive dataset of smart farming innovation adoption locations (N = 4,422) based on a combination of a survey (N = 2,677) and a meta-analysis (N = 1,745) and combined them with remotely sensed and statistical data to train an ensemble of five geospatial machine learning models (generalized linear models, random forests, support vector machines, maximum entropy, and boosted regression trees), which show the global distribution of the different innovations’ profitability and its overlap with major environmental issues the innovations can help to mitigate. Simulations of future socioeconomic pathways combined with assumptions about future agri-environmental policies reveal that, especially in middle-income countries, the potential of smart farming will grow over time.","智慧农业创新能够提升农业生产力、韧性和环境可持续性，然而其现实影响取决于扩散动态，而扩散动态又取决于其经济可行性。本文从农民和社会两个视角，以约5公里的空间分辨率对全球农田范围内智慧农业创新的盈利能力进行了评估。研究涵盖精准农业的应用测绘、投入品的自动化施用、自主除草机械、GPS转向辅助系统以及自主灌溉系统。为此，我们基于一项调查（N = 2,677）和一项元分析（N = 1,745）相结合，编制了全球范围内较为全面的智慧农业创新采用地点数据集（N = 4,422），并将其与遥感和统计数据相结合，用于训练由五种地理空间机器学习模型（广义线性模型、随机森林、支持向量机、最大熵和提升回归树）组成的集成模型，这些模型揭示了不同创新盈利能力的全球分布及其与这些创新有助于缓解的主要环境问题的重叠情况。对未来社会经济路径的模拟结合对未来农业环境政策的假设表明，智慧农业的潜力将随时间推移而增长，尤其是在中等收入国家。","Proceedings of the National Academy of Sciences","2026-10-19T00:00:00Z",93,{"impact":114,"substance":115,"depth":116,"authority":117,"freshness":21,"relevant":22,"comment":118},26,24,19,15,"PNAS 全球尺度智慧农业盈利性评估，数据规模与方法新颖，结论对智慧农业推广具政策参考价值，值得进入每日精选。",[120],{"name":110,"url":107},[122,27,28,29,123],"智慧农业","全球评估",{"code":74,"slug":125,"name":126,"path":127,"parent_code":128},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":131,"locked":14,"version":35,"method":36,"evidence":132},"classified",{"candidates":133,"agricultural_evidence":42},[134,140,147,154,159],{"code":69,"score":135,"supported":42,"title":136,"abstract":137,"tags":139},11,[],[122,28,138],"precision agriculture",[122,28],{"code":74,"score":141,"supported":42,"title":142,"abstract":143,"tags":146},7,[],[144,145],"机器学习","machine learning",[27],{"code":148,"score":41,"supported":42,"title":149,"abstract":150,"tags":153},"H3",[],[151,152],"灌溉","irrigation",[],{"code":63,"score":155,"supported":42,"title":156,"abstract":157,"tags":158},4,[],[29],[29],{"code":160,"score":57,"supported":42,"title":161,"abstract":162,"tags":164},"F4",[],[163],"除草",[],[166,167],"农业人工智能 全球评估 智慧农业 精准农业","农业人工智能 全球评估","农业人工智能全球评估智慧农业精准农业-5382","10.1073\u002Fpnas.2530081123",{"doi":169,"openalex_id":171,"authors":172,"venue":110,"cited_by_count":83,"oa_url":107,"card":191,"direction":195,"ingested_from":100},"W7222974188",[173,176,179,182,185,188],{"name":174,"orcid":175},"Shahrear Roman","https:\u002F\u002Forcid.org\u002F0009-0006-5659-4292",{"name":177,"orcid":178},"Hadi Hadi","https:\u002F\u002Forcid.org\u002F0000-0002-2410-9751",{"name":180,"orcid":181},"Wyclife Agumba Oluoch","https:\u002F\u002Forcid.org\u002F0000-0003-0803-9279",{"name":183,"orcid":184},"David Zilberman","https:\u002F\u002Forcid.org\u002F0000-0001-5743-5134",{"name":186,"orcid":187},"Robert Finger","https:\u002F\u002Forcid.org\u002F0000-0002-0634-5742",{"name":189,"orcid":190},"David Wuepper","https:\u002F\u002Forcid.org\u002F0000-0002-1344-6023",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"全球5公里尺度评估五类智慧农业创新在农田的盈利性与扩散潜力。","整合4422个采用点调查与元分析数据，用五种地理空间机器学习集成建模。","智慧农业盈利性空间差异显著，中等收入国家未来潜力将随社会经济路径增长。","智慧农业 \u002F 农业物联网","可结合区域政策与农户异质性，细化盈利性预测并评估环境协同效益。","2026-10-20T23:30:08.754594Z",{"id":199,"title":200,"url":201,"summary":202,"summary_zh":203,"content":9,"source_name":204,"source_url":201,"published_at":205,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":206,"score_detail":207,"sources":212,"tags":214,"primary_topic":216,"secondary_topics":221,"classification":222,"search_phrases":260,"slug":263,"view_count":83,"doi":264,"paper":265,"created_at":284},4901,"Feature-level fusion of Sentinel-1 SAR and Sentinel-2 optical imagery for crop-type mapping in humid tropical mountainous terrain","https:\u002F\u002Fdoi.org\u002F10.64960\u002Feasr.2026.263460","Accurate crop-type mapping in humid tropical mountains is challenged by persistent cloud cover, rugged topography, and fragmented smallholder parcels. This study evaluates a feature-level fusion workflow that integrates Sentinel-2 optical indices and Sentinel-1 SAR backscatter for crop-type mapping in Candipuro District, Lumajang, East Java, Indonesia. Sentinel-2 surface reflectance and Sentinel-1 IW data acquired in June–July 2023 were harmonised in Google Earth Engine to a common 10 m pixel grid, so that all comparison maps were evaluated on the same spatial support. The optical component comprised NDVI, NDBI, and NDWI, whereas the radar component used the VH\u002FVV polarisation ratio. A DEM was used only to characterise the mountainous setting and to assist terrain interpretation, and was not included as a predictor in the classifier. The stacked feature image was classified using a Random Forest model trained with 101 field-survey ground control points representing eight land-cover\u002Fcrop-related classes. Accuracy was assessed using 393 stratified random validation points. The fused-image classification achieved an overall accuracy of 93% and a kappa coefficient of 0.90. The fusion workflow yielded richer thematic differentiation than the optical-only comparison scenarios, particularly for water bodies, sugarcane, and shrubland. However, class-level results reveal substantial uncertainty for corn fields and moderate confusion in built-up and water classes. Therefore, the present workflow should be interpreted as a site-specific, single-date proof of concept rather than a fully transferable operational solution. The results indicate that Sentinel-1\u002FSentinel-2 feature fusion is promising for crop-type mapping in cloud-prone mountainous landscapes, while future work should incorporate multi-temporal phenology, richer vegetation indices, SAR texture features, uncertainty mapping, and broader field sampling.","在湿润的热带山区，准确的作物类型制图面临持续云覆盖、崎岖地形和破碎的小农户地块等挑战。本研究评估了一种特征级融合工作流，该工作流整合了Sentinel-2光学指数与Sentinel-1 SAR后向散射数据，用于印度尼西亚东爪哇省卢马姜县坎迪普罗区的作物类型制图。2023年6月至7月获取的Sentinel-2地表反射率和Sentinel-1 IW数据在Google Earth Engine中统一至共同的10 m像元网格，以确保所有对比制图均在相同的空间支撑上进行评估。光学组分包括NDVI、NDBI和NDWI，雷达组分则使用VH\u002FVV极化比值。DEM仅用于表征山区环境并辅助地形解译，未作为预测变量纳入分类器。堆叠特征影像采用随机森林模型进行分类，该模型以101个野外调查地面控制点进行训练，代表八个土地覆盖\u002F作物相关类别。精度评估使用393个分层随机验证点。融合影像分类的总体精度达到93%，Kappa系数为0.90。与仅光学对比方案相比，融合工作流产生了更丰富的专题区分能力，尤其在水体、甘蔗和灌木地方面。然而，类别层面的结果揭示了玉米田存在较大不确定性，建成区和水体类别存在中等程度的混淆。因此，本工作流应被解读为特定站点的单日期概念验证，而非完全可迁移的业务化方案。结果表明，Sentinel-1\u002FSentinel-2特征融合在多云山区景观的作物类型制图中具有前景，未来工作应纳入多时相物候、更丰富的植被指数、SAR纹理特征、不确定性制图以及更广泛的野外采样。","Engineering and Applied Science Research","2026-10-12T00:00:00Z",66,{"impact":208,"substance":209,"depth":210,"authority":17,"freshness":21,"relevant":22,"comment":211},8,20,17,"方法扎实、精度可观的遥感作物制图概念验证研究，但属单点单时相案例，公共影响有限，适合作为技术参考而非每日精选头条。",[213],{"name":204,"url":201},[122,27,29,30,215],"哨兵卫星",{"code":217,"slug":218,"name":219,"path":220,"parent_code":9},"A","field-crops","大田作物","\u002Ftopic\u002Ffield-crops",[],{"status":223,"locked":14,"version":35,"method":36,"evidence":224},"partial",{"candidates":225,"agricultural_evidence":42,"reason":259},[226,233,240,247,251,255],{"code":227,"score":41,"supported":42,"title":228,"abstract":229,"tags":232},"A3",[],[230,231],"玉米","corn",[],{"code":234,"score":41,"supported":42,"title":235,"abstract":236,"tags":239},"A6",[],[237,238],"甘蔗","sugarcane",[],{"code":241,"score":41,"supported":42,"title":242,"abstract":243,"tags":246},"G2",[],[244,245],"小农户","smallholder",[],{"code":69,"score":22,"supported":14,"title":248,"abstract":249,"tags":250},[],[],[122],{"code":74,"score":22,"supported":14,"title":252,"abstract":253,"tags":254},[],[],[27],{"code":63,"score":22,"supported":14,"title":256,"abstract":257,"tags":258},[],[],[29],"一级领域明确，二级方向需要细分",[261,262],"Sentinel-1 Sentinel-2 作物分类","印尼 东爪哇 作物制图","Sentinel-1Sentinel-2作物分类-4901","10.64960\u002Feasr.2026.263460",{"doi":264,"openalex_id":266,"authors":267,"venue":204,"cited_by_count":83,"oa_url":278,"card":279,"direction":98,"ingested_from":100},"W7221544367",[268,271,274,276],{"name":269,"orcid":270},"Indarto Indarto","https:\u002F\u002Forcid.org\u002F0000-0001-6319-6731",{"name":272,"orcid":273},"Gunawan Gunawan","https:\u002F\u002Forcid.org\u002F0000-0001-7914-3669",{"name":275,"orcid":9},"Mahrus Irsyam",{"name":277,"orcid":9},"Fahmi Arif Kurnanto","https:\u002F\u002Fph01.tci-thaijo.org\u002Findex.php\u002Feasr\u002Farticle\u002Fdownload\u002F263460\u002F176575",{"tldr":280,"method":281,"finding":282,"direction":98,"opportunity":283},"融合Sentinel-1 SAR与Sentinel-2光学特征，在印尼热带山地实现93%精度的作物类","Google Earth Engine中10米格网特征级融合NDVI\u002FNDBI\u002F","融合影像总体精度93%、kappa 0.90，优于仅光学方案，但玉米和建成区仍存在明显混淆。","可引入多时相物候、SAR纹理与不确定性制图，提升热带多云山区小农户破碎地块的作物识别与可迁移性。","2026-10-14T23:30:28.943594Z",{"id":286,"title":287,"url":288,"summary":289,"summary_zh":290,"content":9,"source_name":291,"source_url":288,"published_at":205,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":292,"score_detail":293,"sources":296,"tags":298,"primary_topic":300,"secondary_topics":304,"classification":305,"search_phrases":331,"slug":334,"view_count":22,"doi":335,"paper":336,"created_at":352},4825,"Multi-Source Remote Sensing Fusion and Deep Learning for Intelligent Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206434","The fusion of multi-source remote sensing data and deep learning technology has been increasingly applied in precision agriculture. This review focuses on the perception–decision–execution framework and summarizes the current application status, technical routes, and development trends of multi-source remote sensing data fusion and deep learning in precision agriculture. It examines the complementary advantages of multimodal data such as optical, thermal infrared (TIR), Light Detection and Ranging (LiDAR), and synthetic aperture radar (SAR) in characterizing crop physiological traits and structural characteristics. At the algorithmic level, this review analyzes the evolution of deep learning architectures from single convolutional neural networks (CNNs) to spatiotemporal fusion networks (STFNs), Transformer-based architectures, and emerging state-space models, with emphasis on their capabilities for heterogeneous feature extraction and cross-modal information integration. This review discusses the transformation mechanism from intelligent perception to executable decision-making and explores the application effectiveness of prescription maps and variable-rate task technology in improving resource utilization. This review proposes forward-looking views on core bottlenecks such as model generalization, physical interpretability, and edge computing. This review not only provides a theoretical analysis of precision agriculture but also provides academic recommendations for the development of intelligent agricultural equipment in the future.","多源遥感数据与深度学习技术的融合已在精准农业中得到日益广泛的应用。本文以“感知—决策—执行”框架为主线，综述了多源遥感数据融合与深度学习在精准农业中的应用现状、技术路线与发展趋势。文章考察了光学、热红外（TIR）、激光雷达（LiDAR）和合成孔径雷达（SAR）等多模态数据在表征作物生理性状与结构特征方面的互补优势。在算法层面，本文分析了深度学习架构从单一卷积神经网络（CNN）向时空融合网络（STFN）、基于Transformer的架构以及新兴状态空间模型的演进，重点探讨了其在异构特征提取与跨模态信息整合方面的能力。本文讨论了从智能感知到可执行决策的转化机制，并探究了处方图与变量作业技术在提升资源利用率方面的应用效果。针对模型泛化能力、物理可解释性与边缘计算等核心瓶颈，本文提出了前瞻性观点。本文不仅为精准农业提供了理论分析，也为未来智能农业装备的发展提供了学术建议。","Sensors",78,{"impact":19,"substance":209,"depth":19,"authority":294,"freshness":208,"relevant":22,"comment":295},14,"系统综述多源遥感融合与深度学习在精准农业中的感知—决策—执行框架，方法脉络清晰、前瞻性强，对智慧农业装备研发有参考价值。",[297],{"name":291,"url":288},[122,27,28,29,299],"多源数据融合",{"code":128,"slug":301,"name":302,"path":303,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":223,"locked":14,"version":35,"method":36,"evidence":306},{"candidates":307,"agricultural_evidence":42,"reason":259},[308,313,319,324],{"code":69,"score":309,"supported":42,"title":310,"abstract":311,"tags":312},16,[138],[28,138],[122,28],{"code":74,"score":117,"supported":42,"title":314,"abstract":316,"tags":318},[315],"deep learning",[317,315],"深度学习",[27],{"code":63,"score":117,"supported":42,"title":320,"abstract":322,"tags":323},[321],"remote sensing",[29,321],[29],{"code":325,"score":141,"supported":42,"title":326,"abstract":327,"tags":330},"I5",[],[328,329],"边缘计算","edge computing",[299],[332,333],"多源遥感 深度学习 精准农业","Transformer 遥感 作物表型","多源遥感深度学习精准农业-4825","10.3390\u002Fs26206434",{"doi":335,"openalex_id":337,"authors":338,"venue":291,"cited_by_count":83,"oa_url":288,"card":347,"direction":98,"ingested_from":100},"W7221565940",[339,342,345],{"name":340,"orcid":341},"Zhen Ma","https:\u002F\u002Forcid.org\u002F0000-0003-4377-9651",{"name":343,"orcid":344},"Xiyuan Chen","https:\u002F\u002Forcid.org\u002F0000-0002-1770-8529",{"name":346,"orcid":9},"Cundeng Wang",{"tldr":348,"method":349,"finding":350,"direction":98,"opportunity":351},"综述多源遥感融合与深度学习在精准农业感知-决策-执行框架中的应用与趋势。","综述光学、热红外、LiDAR、SAR融合及CNN到Transformer、状态空","多模态融合与先进深度学习架构可提升作物感知与处方图决策，但泛化性、可解释性和边缘计算仍是瓶颈。","可探索轻量化状态空间模型与物理约束融合，提升跨区域泛化及边缘端实时决策能力。","2026-10-13T23:30:24.008972Z",{"id":354,"title":355,"url":356,"summary":357,"summary_zh":358,"content":9,"source_name":359,"source_url":356,"published_at":205,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":360,"score_detail":361,"sources":364,"tags":366,"primary_topic":369,"secondary_topics":373,"classification":374,"search_phrases":390,"slug":393,"view_count":64,"doi":394,"paper":395,"created_at":411},4822,"Hybrid transformer and CNN for hyperspectral image classification with spectral band selection","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72102-z","Abstract Hyperspectral images (HSI) play a vital role in remote sensing applications such as surveillance and precision agriculture, yet they face challenges including limited labeled samples and class imbalance. This paper presents a new method for HSI classification by integrating spectral band selection with advanced deep learning techniques. First, we propose an optimized band selection method alongside data augmentation using crop-and-resize transformations to enhance feature diversity. Second, we introduce a hybrid convolution-transformer framework that combines Vision Transformer (ViT) and 2D-CNN architectures, supplemented with a sequence aggregation layer to mitigate overfitting on small datasets. This hybrid model effectively captures both spatial and spectral features while preserving critical spectral details. Finally, we employ a support vector machine for robust classification. Extensive experiments on three widely used HSI datasets demonstrate that our proposed ViT-CNN-BS framework achieves superior classification accuracy compared to state-of-the-art few-shot learning methods and traditional approaches. Beyond achieving higher accuracy, our approach also reduces computational complexity, making it suitable for resource-constrained applications. The findings highlight the potential of hybrid deep learning frameworks for advancing remote sensing analytics, with possible extensions to environmental monitoring, disaster management, and precision agriculture.","高光谱图像（HSI）在监视和精准农业等遥感应用中发挥着重要作用，但仍面临标注样本有限和类别不平衡等挑战。本文提出了一种将光谱波段选择与先进深度学习技术相结合的高光谱图像分类新方法。首先，我们提出了一种优化的波段选择方法，并利用裁剪与缩放变换进行数据增强，以提升特征多样性。其次，我们引入了一种混合卷积-Transformer框架，将视觉Transformer（ViT）与二维卷积神经网络（2D-CNN）架构相结合，并辅以序列聚合层以缓解小数据集上的过拟合问题。该混合模型在保留关键光谱细节的同时，有效捕捉了空间和光谱特征。最后，我们采用支持向量机进行稳健分类。在三个广泛使用的高光谱图像数据集上进行的大量实验表明，我们提出的ViT-CNN-BS框架相比最先进的少样本学习方法和传统方法，实现了更优的分类精度。除了达到更高的精度外，我们的方法还降低了计算复杂度，使其适用于资源受限的应用场景。研究结果凸显了混合深度学习框架在推动遥感分析方面的潜力，并可扩展应用于环境监测、灾害管理和精准农业等领域。","Scientific Reports",73,{"impact":17,"substance":362,"depth":210,"authority":294,"freshness":21,"relevant":22,"comment":363},21,"高光谱遥感分类新方法，方法新颖且面向精准农业等应用，但属实验室数据集验证，产业落地影响有限。",[365],{"name":359,"url":356},[27,28,29,367,368],"作物分类","高光谱影像",{"code":63,"slug":370,"name":371,"path":372,"parent_code":128},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[],{"status":131,"locked":14,"version":35,"method":36,"evidence":375},{"candidates":376,"agricultural_evidence":42},[377,382,386],{"code":63,"score":116,"supported":42,"title":378,"abstract":380,"tags":381},[379],"hyperspectral",[29,321,379],[367,29],{"code":69,"score":141,"supported":42,"title":383,"abstract":384,"tags":385},[],[28,138],[28],{"code":74,"score":141,"supported":42,"title":387,"abstract":388,"tags":389},[],[317,315],[27],[391,392],"高光谱影像 分类 ViT-CNN","光谱波段选择 精准农业","高光谱影像分类ViT-CNN-4822","10.1038\u002Fs41598-026-72102-z",{"doi":394,"openalex_id":396,"authors":397,"venue":359,"cited_by_count":83,"oa_url":356,"card":406,"direction":98,"ingested_from":100},"W7221518213",[398,400,403],{"name":399,"orcid":9},"Eman N. Abdelhafez",{"name":401,"orcid":402},"Ahmed Hagag","https:\u002F\u002Forcid.org\u002F0000-0003-2631-1846",{"name":404,"orcid":405},"Tamer Ahmed Abassy","https:\u002F\u002Forcid.org\u002F0000-0002-1960-7748",{"tldr":407,"method":408,"finding":409,"direction":98,"opportunity":410},"提出结合波段选择与ViT-CNN混合框架的高光谱图像分类方法，提升小样本分类精度。","优化波段选择、裁剪缩放数据增强、ViT与2D-CNN混合模型及SVM分类。","在三个高光谱数据集上分类精度优于少样本学习与传统方法，且计算复杂度更低。","可探索轻量化混合模型在资源受限的田间实时作物分类与病害监测中的部署。","2026-10-13T23:30:23.758699Z",{"id":413,"title":414,"url":415,"summary":416,"summary_zh":417,"content":9,"source_name":418,"source_url":415,"published_at":419,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":420,"score_detail":421,"sources":423,"tags":425,"primary_topic":9,"secondary_topics":427,"classification":428,"search_phrases":449,"slug":452,"view_count":22,"doi":453,"paper":454,"created_at":474},4322,"Ensemble Machine Learning for Farm-Level Rainfall Forecasting Based on Satellite Observations","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs41976-026-00312-0","Ensemble Machine Learning for Farm-Level Rainfall Forecasting Based on Satellite Observations。Remote Sensing in Earth Systems Sciences","基于卫星观测的农场级降雨预测的集成机器学习。《地球系统科学中的遥感》","Remote Sensing in Earth Systems Sciences","2026-10-05T00:00:00Z",67,{"impact":17,"substance":19,"depth":309,"authority":20,"freshness":208,"relevant":22,"comment":422},"该论文提出基于卫星观测的集成机器学习农场级降雨预报方法，方法新颖且对精准农业有实用价值，但属细分领域研究，影响范围有限。",[424],{"name":418,"url":415},[122,27,28,29,426],"农业气象",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":429},{"candidates":430,"agricultural_evidence":14,"reason":448},[431,435,439,443],{"code":74,"score":117,"supported":42,"title":432,"abstract":433,"tags":434},[145],[144,145],[27],{"code":63,"score":141,"supported":42,"title":436,"abstract":437,"tags":438},[],[29,321],[29],{"code":69,"score":64,"supported":14,"title":440,"abstract":441,"tags":442},[],[],[122,28],{"code":444,"score":22,"supported":14,"title":445,"abstract":446,"tags":447},"H7",[],[],[426],"农业相关性需要复核",[450,451],"卫星遥感 降雨预测 农场","集成机器学习 降雨预报","卫星遥感降雨预测农场-4322","10.1007\u002Fs41976-026-00312-0",{"doi":453,"openalex_id":455,"authors":456,"venue":418,"cited_by_count":83,"oa_url":9,"card":468,"direction":473,"ingested_from":100},"W7220415700",[457,459,461,463,465],{"name":458,"orcid":9},"Yash Pawar",{"name":460,"orcid":9},"Saee Mane",{"name":462,"orcid":9},"Sachi Bote",{"name":464,"orcid":9},"Vineet Yelleswarapu",{"name":466,"orcid":467},"Shalaka Prasad Deore","https:\u002F\u002Forcid.org\u002F0000-0002-5322-779X",{"tldr":469,"method":470,"finding":471,"direction":98,"opportunity":472},"基于卫星观测，用集成机器学习为农场尺度做降雨预报。","集成机器学习，结合卫星遥感观测数据。","集成方法可提升农场尺度降雨预报精度。","可探索多源卫星融合与作物物候耦合的田块级降雨预报。","农业人工智能与决策模型","2026-10-06T23:30:38.412053Z",{"id":476,"title":477,"url":478,"summary":479,"summary_zh":480,"content":9,"source_name":481,"source_url":478,"published_at":482,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":483,"score_detail":484,"sources":486,"tags":488,"primary_topic":490,"secondary_topics":495,"classification":503,"search_phrases":548,"slug":551,"view_count":155,"doi":552,"paper":553,"created_at":575},3918,"UAV-based RGB imagery and supervised–unsupervised machine learning for estimating sorghum biomass and grain yield under water and nitrogen stress","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffenvs.2026.1928610","Precision agriculture emerged as a key strategy for rational management of water and nutrients amid growing food demand driven by global population expansion. Therefore, timely monitoring of field crops is crucial in maintaining adequate nutrient and water levels in the crop fields. Vegetation indices are increasingly being studied for their use in plant nutrient management and in guiding fertilizer recommendations. However, these indices were not adequately evaluated for nutrient management of crops grown with different water and nitrogen application levels. This study investigated the potential application of RGB imagery from low-cost Unmanned Aerial Vehicles (UAVs), combined with machine learning techniques, for quantifying water and nutrient stress in sorghum [ Sorghum bicolor (L.) Moench] crop performance. The field experimental setup at Prairie View A&M University, located in Southeast Texas, applied four irrigation levels (0, 75, 100, and 125% of irrigation; the 100% irrigation level is a fully irrigated treatment with no water stress) and four nitrogen application rates (0, 90, 180, and 360 kg N ha −1 ). The RGB images were captured before harvesting the grain sorghum. Image segmentation for filtering sorghum crops from soil and weeds was performed using K-means clustering and a Convolutional Neural Network (CNN). The vegetation indices, including the Green-Red Vegetation Index (GRVI), Green Leaf Index (GLI), and Excess Green Index (ExG), derived from the segmented images were used to predict sorghum grain and biomass yields using multiple linear regression, Partial least squares regression, Ridge regression, and XGBoost. The results indicated that no single model consistently outperformed the others across both segmentation approaches and response variables, suggesting that the predictive information in the RGB indices is meaningful with selected ML approaches. For example, biomass prediction using ridge regression yielded a Pearson correlation coefficient (r) of 0.65 and an RMSE of 0.72 for K-means clustering-derived indices. The models exhibited moderate, stage-specific predictive performance, with no single regression method consistently outperforming the others across both segmentation approaches and response variables. Because imagery was acquired only once during the late reproductive period, the RGB indices primarily reflected canopy condition, maturity, and senescence at that time. The findings demonstrate the feasibility of a low-cost, single-date UAV RGB workflow for late-season sorghum assessment, while emphasizing the need for multi-temporal imagery and independent validation before application to season-long stress diagnosis or operational yield forecasting.","精准农业已成为在水资源与养分合理管理中的关键策略，以应对全球人口增长所驱动的日益增长的粮食需求。因此，及时监测田间作物对于维持作物田块中适宜的养分和水分水平至关重要。植被指数在植物养分管理和指导施肥推荐中的应用正日益受到研究。然而，这些指数尚未在不同水分和氮素施用水平下对作物养分管理进行充分评估。本研究探讨了来自低成本无人机（UAV）的RGB影像结合机器学习技术在量化高粱[Sorghum bicolor (L.) Moench]作物表现中水分和养分胁迫方面的潜在应用。位于德克萨斯州东南部的Prairie View A&M大学的田间试验设置了四个灌溉水平（灌溉量的0%、75%、100%和125%；100%灌溉水平为充分灌溉处理，无水分胁迫）和四个氮素施用量（0、90、180和360 kg N ha⁻¹）。RGB图像在收获籽粒高粱前采集。使用K-means聚类和卷积神经网络（CNN）进行图像分割，以将高粱作物与土壤和杂草分离。从分割图像中提取的植被指数，包括绿红植被指数（GRVI）、绿叶指数（GLI）和过量绿指数（ExG），被用于通过多元线性回归、偏最小二乘回归、岭回归和XGBoost预测高粱籽粒和生物量产量。结果表明，在两种分割方法和响应变量下，没有单一模型始终优于其他模型，这表明RGB指数中的预测信息在所选机器学习方法下具有意义。例如，使用岭回归进行生物量预测时，基于K-means聚类所得指数的Pearson相关系数（r）为0.65，RMSE为0.72。这些模型表现出中等、特定阶段的预测性能，在两种分割方法和响应变量下，没有单一回归方法始终优于其他方法。由于影像仅在生殖后期采集一次，RGB指数主要反映当时的冠层状况、成熟度和衰老程度。研究结果证明了低成本、","Frontiers in Environmental Science","2026-09-30T00:00:00Z",69,{"impact":17,"substance":209,"depth":309,"authority":20,"freshness":208,"relevant":22,"comment":485},"低成本无人机RGB影像结合机器学习估算高粱生物量与产量的方法学研究，结论审慎，对精准农业养分水分管理有参考价值，但属单点单期试验，影响范围有限。",[487],{"name":481,"url":478},[122,27,28,29,489],"高粱",{"code":491,"slug":492,"name":493,"path":494,"parent_code":217},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains",[496,497],{"code":74,"slug":125,"name":126,"path":127,"parent_code":128},{"code":498,"slug":499,"name":500,"path":501,"parent_code":502},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",{"status":131,"locked":14,"version":35,"method":36,"evidence":504},{"candidates":505,"agricultural_evidence":42},[506,511,515,522,527,531,538,544],{"code":491,"score":117,"supported":42,"title":507,"abstract":509,"tags":510},[508],"sorghum",[489,508],[489],{"code":74,"score":117,"supported":42,"title":512,"abstract":513,"tags":514},[145],[144,145],[27],{"code":498,"score":21,"supported":42,"title":516,"abstract":517,"tags":521},[],[518,519,520],"施肥","养分管理","fertilizer",[],{"code":148,"score":21,"supported":42,"title":523,"abstract":524,"tags":526},[],[151,525,152],"水资源",[],{"code":69,"score":208,"supported":42,"title":528,"abstract":529,"tags":530},[],[28,138],[122,28],{"code":532,"score":41,"supported":42,"title":533,"abstract":534,"tags":537},"H2",[],[535,536],"土壤","soil",[],{"code":539,"score":57,"supported":42,"title":540,"abstract":541,"tags":543},"A7",[],[542],"间作",[],{"code":63,"score":22,"supported":14,"title":545,"abstract":546,"tags":547},[],[],[29],[549,550],"Prairie View A&M University 高粱 无人机","高粱 生物量 产量 无人机 RGB","PrairieViewAMUniversity高粱无人机-3918","10.3389\u002Ffenvs.2026.1928610",{"doi":552,"openalex_id":554,"authors":555,"venue":481,"cited_by_count":83,"oa_url":478,"card":570,"direction":473,"ingested_from":100},"W7214994063",[556,558,561,563,566,568],{"name":557,"orcid":9},"Anoop Valiya Veettil",{"name":559,"orcid":560},"Ripendra Awal","https:\u002F\u002Forcid.org\u002F0000-0002-2453-2592",{"name":562,"orcid":9},"Ali Fares",{"name":564,"orcid":565},"Binita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-7093-4915",{"name":567,"orcid":9},"Almoutaz Elhassan",{"name":569,"orcid":9},"Atikur Rahman",{"tldr":571,"method":572,"finding":573,"direction":98,"opportunity":574},"用无人机RGB影像与机器学习估算水分氮胁迫下高粱生物量和产量。","低成本无人机RGB影像，K-means与CNN分割，多种回归模型预测。","单一模型未持续最优，RGB指数在特定时期具中等预测能力。","可研究多时相RGB影像与深度学习融合，提升胁迫下作物产量预测精度。","2026-10-01T23:30:54.379150Z"]