geomaster

What it does

The skill provides instructions for geospatial tasks across remote sensing, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and broad geospatial computation tasks. It emphasizes processing satellite imagery (Sentinel, Landsat, MODIS, SAR, hyperspectral), handling vector and raster data, performing spatial statistics, working with point clouds, and conducting network analysis. It includes guidance and code examples in seven programming languages and offers 500+ code examples.

How it works

The skill lays out concrete, code-oriented workflows and installation steps. It specifies installation commands for core geospatial stacks, remote sensing libraries, GIS software integration, ML for geospatial tasks, point cloud tools, network analysis packages, visualization libraries, big data/cloud tools, and database support. It provides example snippets for reading imagery, calculating indices (NDVI, etc.), performing classification, vector operations (buffering, spatial relationships, overlays), terrain analysis (slope, aspect, hillshade), and network analysis (street networks, routes). It also includes end-to-end workflows such as land cover classification, flood hazard mapping, and vegetation time-series analysis, with concrete code blocks and library references.

When to use it

Use when: you need a comprehensive geospatial workflow covering remote sensing, GIS analysis, or spatial ML; you must process satellite data (Sentinel, Landsat, MODIS, SAR, hyperspectral); you require vector/raster data operations, terrain metrics, or network analyses; you want guidance across multiple programming languages for geospatial tasks; or you are pursuing end-to-end workflows like land cover classification, flood mapping, or vegetation time series.

What it can touch

Core touchpoints include: Python environments with Rasterio, GDAL, Fiona, Shapely, GeoPandas; remote sensing libraries like rsgislib, torchgeo, eo-learn; Earth Engine API; QGIS/ArcPy/GRASS/SAGA integrations; ML libraries (scikit-learn, xgboost, lightgbm, TensorFlow, PyTorch); point cloud tools (laspy, pdal, Open3D); visualization (cartopy, folium, ipyleaflet, keplergl); big data (dask-geopandas, xarray, rioxarray); and database utilities (PostGIS, SpatiaLite, geoalchemy2).

Caveats

License: MIT License. Declares compatibility with multiple languages and dependencies via installation commands. No stated limitations beyond the explicit dependencies and workflows; no risk or licensing caveats beyond the listed licenses and required software installations are included in the provided material.