[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3475":3,"related-3475":90},{"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":58,"slug":61,"view_count":62,"doi":63,"paper":64,"created_at":89},3475,"Cross-sensor urban land-cover characterization using hyperspectral and multispectral satellite imagery","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1908768","Introduction This study establishes a cross-sensor urban remote sensing baseline for future urban digital-intelligence applications by integrating separately classified and validated multispectral (Landsat, Sentinel-2) and hyperspectral (PRISMA) imagery using a common sampling and evaluation framework. Methods Eight land-cover classes — Dense Urban Area, Medium Urban Area, Sparse Urban Area, Tree Cover, Grass, Cropland, Bare Area, and Water — were mapped using Random Forest, Support Vector Machine (SVM), Gradient Boosting Machine, K-Nearest Neighbor, and Classification and Regression Tree algorithms. Performance was evaluated across all three sensors using overall accuracy, Cohen’s kappa, macro-averaged and class-wise F1-scores, class-area composition, spectral profile, Fisher scores, pairwise separability metrics, and principal component analysis (PCA). Results Results demonstrated clear sensor-dependent differences in urban representation and classification accuracy. Sentinel-2 improved spatial characterization of heterogeneous urban surfaces through enhanced spatial resolution and red-edge information. PRISMA produced the highest classification performance, with SVM achieving an overall accuracy of 91.26% and a macro-averaged F1-score of 89.72%. However, this advantage was class-specific rather than uniform across all urban-density classes. Spectral-profile and PCA analysis showed hyperspectral observations substantially improved separability between Medium and Sparse Urban classes (spectral angle: 0.54° Landsat, 1.58° Sentinel-2, 4.11° PRISMA). PRISMA classifications also allocated substantially less area to Sparse Urban Area and more to Bare Area than the multispectral classifications. Discussion This redistribution may reflect improved discrimination of mixed peri-urban surfaces but cannot be considered more accurate without an independent concurrent area-wide reference map. The findings do not establish universal sensor superiority; rather classification outcomes depend jointly on sensor properties, acquisition timing, preprocessing, class definitions, and classifier choice, supporting a complementary interpretation of multispectral and hyperspectral observations.","引言 本研究通过在一个统一的采样与评估框架下，整合分别分类并验证的多光谱（Landsat、Sentinel-2）和高光谱（PRISMA）影像，为未来城市数字智能应用建立了一个跨传感器城市遥感基线。方法 采用随机森林、支持向量机（SVM）、梯度提升机、K近邻以及分类与回归树算法，对八类土地覆盖类型——密集城市区、中等城市区、稀疏城市区、乔木覆盖、草地、农田、裸地和水体——进行制图。利用总体精度、Cohen's kappa系数、宏平均及各类别F1分数、类别面积组成、光谱剖面、Fisher得分、成对可分性指标和主成分分析（PCA），在三种传感器上评估了分类性能。结果 结果表明，城市表征和分类精度存在明显的传感器依赖性差异。Sentinel-2通过增强的空间分辨率和红边信息，改善了对异质城市地表的空间刻画。PRISMA取得了最高的分类性能，其中SVM的总体精度达到91.26%，宏平均F1分数为89.72%。然而，这一优势具有类别特异性，而非在所有城市密度类别上均匀体现。光谱剖面和PCA分析表明，高光谱观测显著改善了中等城市区与稀疏城市区之间的可分性（光谱角：Landsat为0.54°，Sentinel-2为1.58°，PRISMA为4.11°）。与多光谱分类相比，PRISMA分类还将显著更少的面积划为稀疏城市区，而将更多面积划为裸地。讨论 这种面积重分配可能反映了对城乡过渡带混合地表判别能力的提升，但在缺乏独立的同期全域参考图的情况下，不能认为其更为准确。研究结果并未确立某种传感器的普遍优越性；相反，分类结果共同取决于传感器特性、获取时间、预处理、类别定义和分类器选择，这支持对多光谱与高光谱观测进行互补性解读。",null,"Frontiers in Remote Sensing","2026-09-23T00:00:00Z","论文",10,false,66,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":22},8,20,17,13,1,"跨传感器城市土地覆盖分类研究，方法扎实、结论审慎，对农业遥感与国土监测有参考价值，但属专业论文而非产业级事件。",[24],{"name":10,"url":6},[26,27,28,29,30],"农业人工智能","遥感","土地覆盖分类","高光谱遥感","城市遥感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,53],{"code":32,"score":45,"supported":46,"title":47,"abstract":50,"tags":52},27,true,[48,49],"multispectral","hyperspectral",[27,51,48,49],"remote sensing",[27,29],{"code":54,"score":21,"supported":14,"title":55,"abstract":56,"tags":57},"I2",[],[],[26],[59,60],"PRISMA 高光谱 城市土地覆盖","Sentinel-2 Landsat 城市分类","PRISMA高光谱城市土地覆盖-3475",2,"10.3389\u002Ffrsen.2026.1908768",{"doi":63,"openalex_id":65,"authors":66,"venue":10,"cited_by_count":79,"oa_url":80,"card":81,"direction":87,"ingested_from":88},"W7214084535",[67,69,71,73,76],{"name":68,"orcid":9},"Sawaid Abbas",{"name":70,"orcid":9},"Zohaib",{"name":72,"orcid":9},"Nawai Habib",{"name":74,"orcid":75},"Faisal Mueen Qamer","https:\u002F\u002Forcid.org\u002F0000-0003-0434-652X",{"name":77,"orcid":78},"Majid Nazeer","https:\u002F\u002Forcid.org\u002F0000-0002-7631-1599",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1908768\u002Fpdf",{"tldr":82,"method":83,"finding":84,"direction":85,"opportunity":86},"用统一框架对比Landsat、Sentinel-2与PRISMA在城市土地覆盖分类中的表现。","随机森林、SVM等五种分类器，结合光谱剖面、Fisher分数与PCA评估三传感器","PRISMA高光谱分类精度最高（SVM达91.26%），但优势因城市密度类别而异。","农业遥感与作物表型","可探索多源遥感互补融合与跨传感器迁移学习，提升混合地表分类的鲁棒性。","智慧农业 \u002F 农业物联网","openalex","2026-09-25T23:30:11.302770Z",{"total":91,"page":21,"page_size":91,"items":92},6,[93,151,232,307,386,487],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":101,"score_detail":102,"sources":105,"tags":107,"primary_topic":111,"secondary_topics":115,"classification":117,"search_phrases":135,"slug":138,"view_count":79,"doi":139,"paper":140,"created_at":150},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",67,{"impact":17,"substance":18,"depth":19,"authority":103,"freshness":13,"relevant":21,"comment":104},12,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[106],{"name":99,"url":96},[108,26,109,27,110],"智慧农业","产量预测","可解释性",{"code":54,"slug":112,"name":113,"path":114,"parent_code":36},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[116],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":118},{"candidates":119,"agricultural_evidence":46},[120,126,130],{"code":54,"score":103,"supported":46,"title":121,"abstract":123,"tags":125},[122],"computer vision",[124],"计算机视觉",[26],{"code":32,"score":17,"supported":46,"title":127,"abstract":128,"tags":129},[],[27,51],[109,27],{"code":131,"score":21,"supported":14,"title":132,"abstract":133,"tags":134},"I1",[],[],[108],[136,137],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":139,"openalex_id":141,"authors":142,"venue":99,"cited_by_count":79,"oa_url":96,"card":145,"direction":85,"ingested_from":88},"W7223114002",[143],{"name":144,"orcid":9},"Kadiatou Barry",{"tldr":146,"method":147,"finding":148,"direction":85,"opportunity":149},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":152,"title":153,"url":154,"summary":155,"summary_zh":156,"content":9,"source_name":99,"source_url":154,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":157,"score_detail":158,"sources":163,"tags":165,"primary_topic":169,"secondary_topics":175,"classification":182,"search_phrases":216,"slug":219,"view_count":79,"doi":220,"paper":221,"created_at":231},5552,"INTEGRATING IoT, REMOTE SENSING, AND ARTIFICIAL INTELLIGENCE FOR SMART IRRIGATION: A REVIEW OF ARCHITECTURES, METHODS, AND CHALLENGES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531020","This research paper reviews the integration of Internet of Things (IoT), remote sensing, and Artificial Intelligence (AI) in smart irrigation systems. It discusses system architectures, intelligent irrigation techniques, automated water management, key challenges, and future research opportunities to improve water-use efficiency and promote sustainable agriculture.","本文综述了物联网（Internet of Things, IoT）、遥感与人工智能（Artificial Intelligence, AI）在智能灌溉系统中的融合应用，探讨了系统架构、智能灌溉技术、自动化水资源管理、关键挑战及未来研究方向，以提升用水效率并促进可持续农业发展。",75,{"impact":159,"substance":18,"depth":160,"authority":103,"freshness":161,"relevant":21,"comment":162},18,16,9,"系统综述物联网、遥感与AI融合的智能灌溉架构与方法，属智慧农业细分领域有实质增量的国际综述，值得入选。",[164],{"name":99,"url":154},[26,166,27,167,168],"农业物联网","智慧灌溉","节水农业",{"code":170,"slug":171,"name":172,"path":173,"parent_code":174},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[176,181],{"code":177,"slug":178,"name":179,"path":180,"parent_code":36},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":183},{"candidates":184,"agricultural_evidence":46},[185,192,199,204,209],{"code":170,"score":186,"supported":46,"title":187,"abstract":188,"tags":191},19,[171],[189,190,171],"灌溉","水资源",[167,168],{"code":177,"score":159,"supported":46,"title":193,"abstract":195,"tags":198},[194],"IoT",[196,197,194],"物联网","internet of things",[166],{"code":32,"score":200,"supported":46,"title":201,"abstract":202,"tags":203},15,[51],[27,51],[27],{"code":54,"score":103,"supported":46,"title":205,"abstract":207,"tags":208},[206],"artificial intelligence",[206],[26],{"code":210,"score":91,"supported":46,"title":211,"abstract":212,"tags":215},"H8",[],[213,214],"可持续农业","sustainable agriculture",[],[217,218],"IoT 遥感 AI 智能灌溉","农业人工智能 农业物联网 智慧灌溉 节水农业","IoT遥感AI智能灌溉-5552","10.5281\u002Fzenodo.23531020",{"doi":220,"openalex_id":222,"authors":223,"venue":99,"cited_by_count":79,"oa_url":154,"card":226,"direction":87,"ingested_from":88},"W7223090389",[224],{"name":225,"orcid":9},"Patil",{"tldr":227,"method":228,"finding":229,"direction":87,"opportunity":230},"综述物联网、遥感与人工智能融合的智能灌溉系统架构、方法与挑战。","文献综述，梳理IoT、遥感与AI集成的系统架构与智能灌溉技术。","融合三者可提升用水效率并推动可持续农业，但仍面临关键挑战。","可针对多源数据融合的实时灌溉决策模型与边缘部署开展实证研究。","2026-10-22T11:20:18.028252Z",{"id":233,"title":234,"url":235,"summary":236,"summary_zh":237,"content":9,"source_name":238,"source_url":235,"published_at":239,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":240,"score_detail":241,"sources":244,"tags":246,"primary_topic":248,"secondary_topics":253,"classification":255,"search_phrases":288,"slug":291,"view_count":79,"doi":292,"paper":293,"created_at":306},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":159,"substance":242,"depth":159,"authority":103,"freshness":17,"relevant":21,"comment":243},22,"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[245],{"name":238,"url":235},[108,26,247,109,27],"水稻",{"code":249,"slug":250,"name":247,"path":251,"parent_code":252},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[254],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":256},{"candidates":257,"agricultural_evidence":46},[258,262,266,273,280,284],{"code":249,"score":200,"supported":46,"title":259,"abstract":260,"tags":261},[250],[247,250],[247],{"code":32,"score":17,"supported":46,"title":263,"abstract":264,"tags":265},[],[27,51],[109,27],{"code":267,"score":91,"supported":46,"title":268,"abstract":269,"tags":272},"A8",[],[270,271],"粮食安全","food security",[],{"code":274,"score":275,"supported":46,"title":276,"abstract":277,"tags":279},"J1",3,[],[278],"农业规划",[],{"code":131,"score":21,"supported":14,"title":281,"abstract":282,"tags":283},[],[],[108],{"code":54,"score":21,"supported":14,"title":285,"abstract":286,"tags":287},[],[],[26],[289,290],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":292,"openalex_id":294,"authors":295,"venue":238,"cited_by_count":79,"oa_url":235,"card":301,"direction":85,"ingested_from":88},"W7222942064",[296,298],{"name":297,"orcid":9},"Nayana Venkatesh",{"name":299,"orcid":300},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":302,"method":303,"finding":304,"direction":85,"opportunity":305},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":9,"source_name":313,"source_url":310,"published_at":314,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":315,"score_detail":316,"sources":319,"tags":321,"primary_topic":324,"secondary_topics":325,"classification":332,"search_phrases":360,"slug":363,"view_count":79,"doi":364,"paper":365,"created_at":385},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":103,"substance":317,"depth":19,"authority":20,"freshness":161,"relevant":21,"comment":318},21,"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[320],{"name":313,"url":310},[108,26,27,322,323],"土壤盐渍化","新疆农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[326,331],{"code":327,"slug":328,"name":329,"path":330,"parent_code":174},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"code":54,"slug":112,"name":113,"path":114,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":333},{"candidates":334,"agricultural_evidence":46},[335,339,345,350,356],{"code":32,"score":200,"supported":46,"title":336,"abstract":337,"tags":338},[51],[27,51],[27],{"code":327,"score":340,"supported":46,"title":341,"abstract":342,"tags":344},14,[328],[343,328],"土壤",[],{"code":54,"score":161,"supported":46,"title":346,"abstract":348,"tags":349},[347],"deep learning",[],[26],{"code":351,"score":275,"supported":46,"title":352,"abstract":353,"tags":355},"H7",[],[354],"干旱",[],{"code":131,"score":21,"supported":14,"title":357,"abstract":358,"tags":359},[],[],[108],[361,362],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":364,"openalex_id":366,"authors":367,"venue":313,"cited_by_count":79,"oa_url":310,"card":380,"direction":85,"ingested_from":88},"W7221816183",[368,370,373,375,377],{"name":369,"orcid":9},"Mingjie Qian",{"name":371,"orcid":372},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":374,"orcid":9},"Peng Wang",{"name":376,"orcid":9},"Hangyuan Liu",{"name":378,"orcid":379},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":381,"method":382,"finding":383,"direction":85,"opportunity":384},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z",{"id":387,"title":388,"url":389,"summary":390,"summary_zh":391,"content":9,"source_name":392,"source_url":389,"published_at":314,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":393,"score_detail":394,"sources":396,"tags":398,"primary_topic":400,"secondary_topics":401,"classification":409,"search_phrases":459,"slug":462,"view_count":21,"doi":463,"paper":464,"created_at":486},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science",81,{"impact":159,"substance":242,"depth":159,"authority":340,"freshness":161,"relevant":21,"comment":395},"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[397],{"name":392,"url":389},[108,26,109,399,27],"多模态融合",{"code":54,"slug":112,"name":113,"path":114,"parent_code":36},[402,408],{"code":403,"slug":404,"name":405,"path":406,"parent_code":407},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":410},{"candidates":411,"agricultural_evidence":46},[412,420,428,433,440,444,448,454],{"code":54,"score":413,"supported":46,"title":414,"abstract":415,"tags":419},11,[],[416,417,418,347],"深度学习","机器学习","machine learning",[26,399],{"code":403,"score":161,"supported":46,"title":421,"abstract":422,"tags":427},[],[423,424,425,426],"苹果","芒果","orchard","apple",[],{"code":32,"score":17,"supported":46,"title":429,"abstract":430,"tags":432},[],[431,48],"无人机多光谱",[109,27],{"code":131,"score":434,"supported":46,"title":435,"abstract":436,"tags":439},7,[],[437,438],"精准农业","precision agriculture",[108],{"code":327,"score":91,"supported":46,"title":441,"abstract":442,"tags":443},[],[343,328],[],{"code":177,"score":91,"supported":46,"title":445,"abstract":446,"tags":447},[],[196,194],[],{"code":449,"score":275,"supported":46,"title":450,"abstract":451,"tags":453},"H6",[],[452],"农业生态",[],{"code":351,"score":275,"supported":46,"title":455,"abstract":456,"tags":458},[],[457],"气候适应",[],[460,461],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":463,"openalex_id":465,"authors":466,"venue":392,"cited_by_count":79,"oa_url":389,"card":480,"direction":87,"ingested_from":88},"W7221795850",[467,470,472,474,476,478],{"name":468,"orcid":469},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":471,"orcid":9},"Umarfarooque Momin",{"name":473,"orcid":9},"Sudeep Kumar E",{"name":475,"orcid":9},"Itfaq Ahmad Mir",{"name":477,"orcid":9},"Ab Rouf Khan",{"name":479,"orcid":9},"Ghulam Mohammad Mir",{"tldr":481,"method":482,"finding":483,"direction":484,"opportunity":485},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","农业人工智能与决策模型","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","2026-10-15T23:30:08.750140Z",{"id":488,"title":489,"url":490,"summary":491,"summary_zh":492,"content":9,"source_name":493,"source_url":490,"published_at":494,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":495,"score_detail":496,"sources":498,"tags":500,"primary_topic":503,"secondary_topics":504,"classification":505,"search_phrases":520,"slug":523,"view_count":62,"doi":524,"paper":525,"created_at":541},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","2026-10-12T00:00:00Z",73,{"impact":103,"substance":317,"depth":19,"authority":340,"freshness":161,"relevant":21,"comment":497},"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。",[499],{"name":493,"url":490},[26,437,27,501,502],"作物分类","高光谱影像",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":506},{"candidates":507,"agricultural_evidence":46},[508,512,516],{"code":32,"score":186,"supported":46,"title":509,"abstract":510,"tags":511},[49],[27,51,49],[501,27],{"code":131,"score":434,"supported":46,"title":513,"abstract":514,"tags":515},[],[437,438],[437],{"code":54,"score":434,"supported":46,"title":517,"abstract":518,"tags":519},[],[416,347],[26],[521,522],"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":524,"openalex_id":526,"authors":527,"venue":493,"cited_by_count":79,"oa_url":490,"card":536,"direction":85,"ingested_from":88},"W7221518213",[528,530,533],{"name":529,"orcid":9},"Eman N. Abdelhafez",{"name":531,"orcid":532},"Ahmed Hagag","https:\u002F\u002Forcid.org\u002F0000-0003-2631-1846",{"name":534,"orcid":535},"Tamer Ahmed Abassy","https:\u002F\u002Forcid.org\u002F0000-0002-1960-7748",{"tldr":537,"method":538,"finding":539,"direction":85,"opportunity":540},"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"]