[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2169":3},{"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,"view_count":32,"doi":33,"paper":34,"created_at":58},2169,"GeoWombat: Scalable geospatial and remote sensing analysis in Python","https:\u002F\u002Fdoi.org\u002F10.21105\u002Fjoss.10812","GeoWombat is an open-source Python library that provides an end-to-end platform for geospatial raster data processing and remote sensing analysis at scale.Built on xarray (Hoyer & Hamman, 2017), Dask (Rocklin, 2015), and rasterio (Gillies & others, 2013--), GeoWombat simplifies common but complex operations-such as mosaicking multi-tile imagery, reprojecting across coordinate reference systems, aligning rasters of varying resolutions, and performing radiometric corrections-into concise, intuitive commands.The library includes built-in sensor profiles for Landsat 1-8, Sentinel-1 and Sentinel-2, MODIS, and NAIP that automate band naming, scaling, and metadata handling.It supports workflows spanning cloud-based data access via SpatioTemporal Asset Catalogs (STAC) from multiple providers, a full radiometric processing chain (DN-to-reflectance conversion, atmospheric correction, BRDF normalization, and topographic correction), vegetation index computation, raster-vector interoperability, Cython-accelerated moving window statistics, scikit-learn-based (Pedregosa et al., 2011) machine learning classification, deep learning with PyTorch (Paszke et al., 2019), and georeferenced object detection.By leveraging Dask's lazy evaluation and task graphs, GeoWombat enables out-of-core processing of raster datasets of any size on commodity hardware.","GeoWombat是一个开源Python库，为大规模地理空间栅格数据处理和遥感分析提供端到端平台。它构建于xarray（Hoyer & Hamman, 2017）、Dask（Rocklin, 2015）和rasterio（Gillies & others, 2013--）之上，将多瓦片影像镶嵌、跨坐标参考系重投影、不同分辨率栅格对齐以及辐射校正等常见但复杂的操作简化为简洁直观的命令。该库内置了Landsat 1-8、Sentinel-1和Sentinel-2、MODIS以及NAIP的传感器配置文件，可自动完成波段命名、缩放和元数据处理。它支持的工作流涵盖通过来自多个提供商的时空资产目录（STAC）进行云端数据访问、完整的辐射处理链（DN到反射率转换、大气校正、BRDF归一化和地形校正）、植被指数计算、栅格-矢量互操作、Cython加速的移动窗口统计、基于scikit-learn（Pedregosa et al., 2011）的机器学习分类、基于PyTorch（Paszke et al., 2019）的深度学习以及地理参考目标检测。通过利用Dask的惰性求值和任务图，GeoWombat能够在普通硬件上对任意大小的栅格数据集进行外存处理。",null,"The Journal of Open Source Software","2026-09-09T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"开源遥感分析库，集成多源卫星与深度学习能力，对农业遥感监测有实用价值，但属工具类论文，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","遥感","作物监测","开源工具","植被指数",0,"10.21105\u002Fjoss.10812",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":50,"card":51,"direction":55,"ingested_from":57},"W7212022895",[37,40,43,45,48],{"name":38,"orcid":39},"Jordan Graesser","https:\u002F\u002Forcid.org\u002F0000-0002-6137-7050",{"name":41,"orcid":42},"Michael Mann","https:\u002F\u002Forcid.org\u002F0000-0002-6268-6867",{"name":44,"orcid":9},"Leonardo Hardtke",{"name":46,"orcid":47},"Robert Denham","https:\u002F\u002Forcid.org\u002F0000-0002-3342-7970",{"name":49,"orcid":9},"Sharon Xu","https:\u002F\u002Fjoss.theoj.org\u002Fpapers\u002F10.21105\u002Fjoss.10812.pdf",{"tldr":52,"method":53,"finding":54,"direction":55,"opportunity":56},"发布开源Python库GeoWombat，实现大规模地理空间栅格数据与遥感分析的一站式处理。","基于xarray、Dask、rasterio，集成STAC云数据访问、辐射校正、","可借助Dask惰性求值在普通硬件上核外处理任意大小栅格，并内置多传感器配置。","农业遥感与作物表型","可基于该库构建作物表型参数自动化提取与深度学习分类流程，降低大规模遥感分析门槛。","openalex","2026-09-11T23:30:31.360896Z"]