alterlab-geomaster

name	alterlab-geomaster
description	Covers geospatial science across remote sensing, GIS, spatial analysis, and machine learning for earth observation — satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), raster and DEM operations, spectral indices (NDVI/EVI/NDWI), spatial statistics, point cloud processing, network analysis, and cloud-native workflows (STAC, COG, Planetary Computer), with examples across Python, R, Julia, JavaScript, C++, Java, Go, and Rust. Use for remote sensing workflows, satellite/raster image classification, terrain/slope/hillshade analysis, spatial ML on earth-observation data, hydrological modeling, marine spatial analysis, or atmospheric science. For pure tabular vector work with no raster/EO aspect (plain GeoPandas sjoin, buffer, overlay, dissolve, choropleths) prefer the geopandas skill; for celestial-sphere astronomy coordinates (ICRS/galactic, FITS, WCS) prefer the astropy skill. Part of the AlterLab Academic Skills suite.
license	MIT
allowed-tools	Read Write Edit Bash(uv:*) Bash(python:*)
compatibility	No API key required for local geospatial work. Runs via `uv run python`; cloud-native STAC/Planetary Computer workflows need network access (and provider credentials where applicable).
metadata	{"skill-author":"AlterLab","version":"1.0.0"}

GeoMaster

Comprehensive geospatial science skill covering GIS, remote sensing, spatial analysis, and ML for Earth observation across 70+ topics with 500+ code examples in 8 programming languages.

Installation

Pick ONE package manager for the GDAL-backed stack. Modern pip wheels for rasterio/fiona/pyproj/shapely bundle their own GDAL/GEOS/PROJ, so a pure-pip (uv) env covers the core libs without a system GDAL. Do NOT mix conda-GDAL with pip rasterio/fiona in the same env — the two ship different GDAL binaries and the ABI mismatch segfaults. The standalone gdal Python bindings do NOT bundle binaries (they need a matching system/conda libgdal); PDAL and rsgislib likewise have no reliable pip wheels — get those via conda (Option B).

# Option A — uv/pip env (recommended here): wheels bundle GDAL/GEOS/PROJ.
# rasterio/fiona cover most GDAL needs; standalone `gdal` -> use Option B.
uv pip install rasterio fiona shapely pyproj geopandas
uv pip install torchgeo earthengine-api
uv pip install scikit-learn xgboost torch-geometric
uv pip install osmnx networkx folium keplergl
uv pip install cartopy contextily mapclassify
uv pip install xarray rioxarray dask-geopandas
uv pip install pystac-client planetary-computer odc-stac rio-cogeo
uv pip install laspy[lazrs] open3d        # PDAL: use conda (no pip wheel)

# Option B — conda env (best for PDAL / rsgislib / system GDAL tooling)
conda install -c conda-forge gdal rasterio fiona shapely pyproj geopandas \
    rsgislib pdal python-pdal postgis libspatialite

Quick Start

NDVI from Sentinel-2

import rasterio
import numpy as np

with rasterio.open('sentinel2.tif') as src:
    red = src.read(4).astype(float)   # B04
    nir = src.read(8).astype(float)   # B08
    ndvi = (nir - red) / (nir + red + 1e-8)
    ndvi = np.nan_to_num(ndvi, nan=0)

    profile = src.profile
    profile.update(count=1, dtype=rasterio.float32)

    with rasterio.open(, , **profile)  dst:
        dst.write(ndvi.astype(rasterio.float32), )