[{"_1":2,"_165":-5,"_166":-5},"loaderData",{"_3":4,"_17":18,"_25":26,"_143":144},"root",{"_5":-5,"_6":-7,"_7":8,"_9":-7,"_10":11,"_12":-7,"_13":14,"_15":16},"currentUser","primaryEmail","siteVerification","6LeIxAcTAAAAAJcZVRqyHh71UMIEGNQ_MXjiZKhI","toast","enableDev",false,"incidentStatus","theme","system","contrast","normal","routes/_layout",{"_19":-5,"_20":21,"_22":21,"_23":11,"_24":21},"username","isAskGordonEnabled",true,"isUsingNewTemplate","showMinimalLanding","showHoneypotTrap","routes/_layout.r.$namespace.$reponame",{"_27":28,"_29":-5,"_30":11,"_31":11,"_32":33,"_34":35,"_36":-5,"_37":11,"_38":39,"_91":-5,"_92":93,"_132":-5,"_133":11,"_134":21,"_135":11,"_136":-5,"_137":11,"_138":-5,"_139":140,"_141":94,"_142":-7},"canonicalUrl","https://hub.docker.com/r/dockagile/pygile-plus/tags","mcpServer","canSeeDockerfile","canSeeAutobuilds","namespace","dockagile","reponame","pygile-plus","cloudBuildSource","isAutobuildsAvailable","repo",{"_40":41,"_47":48,"_50":51,"_52":53,"_54":11,"_55":56,"_57":58,"_59":60,"_43":35,"_32":33,"_62":63,"_64":49,"_65":66,"_67":68,"_69":70,"_71":-5,"_72":66,"_73":74,"_75":11,"_76":33,"_77":78,"_83":11,"_84":85,"_89":33,"_90":-5},"categories",[42],{"_43":44,"_45":46},"name","Data science","slug","data-science","content_types",[49],"image","date_registered","2026-08-16T12:38:11.356069Z","description","A headless Docker environment combining SAGA GIS, GRASS GIS, WhiteboxTools, and OTB.","is_private","last_updated","2026-08-16T12:38:11.516104Z","last_modified","2026-08-16T12:41:59.320134Z","media_types",[61],"application/vnd.docker.container.image.v1+json","pull_count",186,"repository_type","star_count",0,"status",1,"status_description","active","source","collaborator_count","full_description","\n \n \n \n \n

Python GeoInformatics Lab Environment-Plus

\n A headless Docker environment combining SAGA GIS, GRASS GIS, WhiteboxTools, and OTB with a complete Python geospatial stack for spatial analysis, remote sensing, and machine learning — with GPU acceleration support.\n

\n\n\n## What is included\n\n### GIS platforms\n\n- SAGA GIS 9.3.2\n- GRASS GIS 8.4.2\n- WhiteboxTools 2.4.0\n- Orfeo ToolBox 9.1.1\n\n### Python stack\n\n- Core geospatial libraries: GDAL 3.12.2, PROJ 9.7.1, GEOS 3.14.1,\n Shapely, Fiona, Rasterio, GeoPandas\n- Scientific computing: NumPy, SciPy, Pandas, Xarray\n- Terrain and hydrology: RichDEM, pysheds, Landlab, TopoToolbox,\n xarray-spatial\n- Machine learning: PyTorch, TensorFlow, scikit-learn, scikit-image\n- GPU computing: CuPy, CUDA-enabled PyTorch and TensorFlow\n- Visualization: Matplotlib, Plotly, Folium, Holoviews, Seaborn\n- Image processing: OpenCV, scikit-image\n- Web mapping: Leafmap, Geemap, ipyleaflet, localtileserver\n- Cloud and remote sensing tools: Earth Engine API, STAC tools,\n odc-stac, Planetary Computer\n- Point clouds: laspy, PDAL\n- Documentation tools: Sphinx, Jupyter Book\n- Jupyter Lab\n\n### Core characteristics\n\n- Headless operation\n- Preconfigured environment\n- Version-pinned and reproducible: every package is fixed to an exact\n version, and a build manifest is written into the image\n- CLI and Python access to supported tools\n- Docker and Apptainer workflows\n- GPU-capable machine learning stack, subject to host driver\n compatibility\n\n## Getting started\n\n### Pull from Docker Hub\n\n``` bash\ndocker pull dockagile/pygile-plus\n```\n\n### Build from source\n\n``` bash\ngit clone https://github.com/Geoinformatics-Lab/PyGILE-Plus.git\ncd PyGILE-Plus/docker\ndocker build -t pygile-plus .\n```\n\nThe Dockerfile is self-contained; no additional files are required.\n\n## Run\n\n### CPU\n\n``` bash\ndocker run -it --name pygile-plus \\\n -p 8888:8888 \\\n -v $(pwd)/data:/workspace/data \\\n dockagile/pygile-plus\n```\n\n### GPU\n\n``` bash\ndocker run -it --name pygile-plus \\\n --gpus all \\\n -p 8888:8888 \\\n -v $(pwd)/data:/workspace/data \\\n dockagile/pygile-plus\n```\n\nGPU use requires: - NVIDIA GPU - compatible NVIDIA driver - NVIDIA\nContainer Toolkit on the host\n\nJupyter Lab starts automatically at `http://localhost:8888`.\n\nOnly `/workspace/data` is mounted in the examples above. Files written\nelsewhere in the container are lost when it is removed. Mount the whole\n`/workspace` directory to persist notebooks and outputs as well.\n\nFor more detailed Docker usage, see `docker/README.md`.\n\n\n## Usage inside container\n\n``` bash\nconda activate pygile\n```\n\n### Basic checks\n\n```bash\npython -c \"import grass.script as g; print('GRASS OK')\"\ngrass --version\nsaga_cmd --version\nwhitebox_tools --version\notbcli_BandMath -help\n```\n\n## GPU verification\n\n``` bash\npython -c \"import torch; print(torch.cuda.is_available())\"\npython -c \"import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))\"\npython -c \"import cupy; print(cupy.cuda.runtime.getDeviceCount())\"\n```\n\nIf GPU is not detected, verify host driver compatibility.\n\n## Reproducibility\n\nEvery package is pinned to an exact version, and source tarballs are\nchecksum-verified during the build. A manifest recording engine\nversions, compiler, checksums, library linkage, and the full resolved\npackage list is written into the image:\n\n``` bash\ndocker run --rm dockagile/pygile-plus \\\n cat /opt/manifest/build_manifest.txt\n```\n\nAlso in `/opt/manifest/`: `conda_explicit.txt` (exact conda package URLs\nand build hashes) and `pip_freeze.txt`.\n\nThe environment can be verified at any time:\n\n``` bash\ndocker run --rm dockagile/pygile-plus pygile-verify\n```\n\nDeterministic numerics are enabled by default (`OMP_NUM_THREADS=1` and\nequivalents) so floating-point results are reproducible across runs.\nOverride at run time if throughput matters more than bit-identical\noutput.\n\nFor citation, record the image digest:\n\n``` bash\ndocker inspect --format='{{index .RepoDigests 0}}' \\\n dockagile/pygile-plus\n```\n\n## Known limitations\n\n- OTB Python bindings (`otbApplication`) target Python 3.8 and are\n unavailable in this Python 3.11 environment. The OTB CLI is fully\n functional.\n- `saga_cmd` returns exit code 134 on teardown despite writing correct\n output. When scripting SAGA, check for output files rather than\n return codes.\n- SAGA links the system GDAL 3.0.4 while the Python stack uses GDAL\n 3.12.2. Raster read and write are bit-identical between the two, so\n values are unaffected.\n- PyTorch is present as both a conda build and a CUDA wheel; the wheel\n takes precedence in `site-packages`.\n\n## Tool locations\n\n``` python\nconda_env_path = \"/opt/conda/envs/pygile\"\nsaga_cmd = \"/opt/saga/bin/saga_cmd\"\ngrass_command = \"grass\"\notb_bin = \"/opt/otb/bin\"\nwhitebox_tools = \"/opt/conda/envs/pygile/bin/whitebox_tools\"\nbuild_manifest = \"/opt/manifest/build_manifest.txt\"\n```\n\n## Applications\n\n- Remote sensing analysis and classification\n- Raster and vector processing\n- Terrain and hydrological analysis across multiple engines\n- Spatial statistics and geostatistics\n- Machine learning on geospatial data\n- Educational and research workflows\n- Web mapping and interactive visualization\n- Cloud-based geospatial analysis\n- HPC workflows through Apptainer\n\n## System requirements\n\n- Docker\n- Recommended memory: 8 GB minimum, more for large workloads\n- Recommended storage: about 25 GB or more for the image and data\n- Network access for initial pull or build\n- For GPU use: NVIDIA GPU and compatible host setup\n- For HPC: Apptainer or Singularity with `--nv` support when GPU\n passthrough is needed\n\n## HPC and Apptainer\n\n``` bash\napptainer pull docker://dockagile/pygile-plus\napptainer run --nv pygile-plus_latest.sif\n```\n\n## License information\n\nAll included software remains under its respective upstream license.\nRefer to the original project documentation for specific license terms.\n\n## Reference and citation\n\nAwasthi, B., Ninsawat, S., Raghavan, V., & Nemoto, T. (2026). Geoinformatics-Lab/PyGILE-Plus: PyGILE-Plus v1.1.0 (v1.1.0). Zenodo. https://doi.org/10.5281/zenodo.18512474\n\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.18512474.svg)]( https://doi.org/10.5281/zenodo.18512474)\n\nAwasthi, B., Ninsawat, S., Raghavan, V., & Nemoto, T. (2025). PyGILE-Plus: Python GeoInformatics Lab Environment-Plus (1.0.0). Zenodo. https://doi.org/10.5281/zenodo.16146572\n\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.16146572.svg)](https://doi.org/10.5281/zenodo.16146572)\n","has_starred","hub_user","immutable_tags_settings",{"_79":11,"_80":81},"enabled","rules",[82],".*","is_automated","permissions",{"_86":21,"_87":11,"_88":11},"read","write","admin","user","storage_size","orgData","recentTags",[94],{"_95":49,"_96":97,"_98":99,"_100":101,"_102":103,"_104":105,"_55":121,"_122":97,"_123":33,"_124":61,"_43":125,"_126":127,"_128":112,"_129":121,"_130":70,"_131":21},"content_type","creator",35407947,"digest","sha256:9f8bac3bcc66d7007b5d3619ca6125c2f127accb6837ffbe715ab3e55be50e4c","full_size",8487424754,"id",1272068032,"images",[106],{"_107":108,"_98":99,"_109":110,"_111":112,"_113":114,"_115":116,"_117":110,"_118":-5,"_119":101,"_67":70,"_120":-5},"architecture","amd64","features","","last_pulled","2026-10-04T16:33:29.106313273Z","last_pushed","2026-08-16T12:38:10.832624301Z","os","linux","os_features","os_version","size","variant","2026-08-16T12:38:11.335401Z","last_updater","last_updater_username","media_type","latest","repository",32165889,"tag_last_pulled","tag_last_pushed","tag_status","v2","sbxKitMetadata","isPotentialSpam","isHubSbxKitsEnabled","showSbxLogoOverride","sbxTrademarkText","displaySecurityMetadata","tagAttestations","tagsHaveAttestations",[],"selectedTag","attestationsUrl","routes/_layout.r.$namespace.$reponame.tags",{"_38":145,"_153":154,"_139":163,"_164":11},{"_40":146,"_47":148,"_50":51,"_52":53,"_54":11,"_55":56,"_57":58,"_59":149,"_43":35,"_32":33,"_62":63,"_64":49,"_65":66,"_67":68,"_69":70,"_71":-5,"_72":66,"_73":74,"_75":11,"_76":33,"_77":150,"_83":11,"_84":152,"_89":33,"_90":-5},[147],{"_43":44,"_45":46},[49],[61],{"_79":11,"_80":151},[82],{"_86":21,"_87":11,"_88":11},"tags",{"_155":68,"_156":-5,"_157":-5,"_158":159},"count","next","previous","results",[160],{"_95":49,"_96":97,"_98":99,"_100":101,"_102":103,"_104":161,"_55":121,"_122":97,"_123":33,"_124":61,"_43":125,"_126":127,"_128":112,"_129":121,"_130":70,"_131":21},[162],{"_107":108,"_98":99,"_109":110,"_111":112,"_113":114,"_115":116,"_117":110,"_118":-5,"_119":101,"_67":70,"_120":-5},[],"canDeleteTags","actionData","errors"]

dockagile/pygile-plus

Tags for dockagile/pygile-plus