sertit/eoreader

Remote-sensing opensource python library reading optical and SAR sensors, loading and stacking bands, clouds, DEM and spectral indices in a sensor-agnostic way.

What it solves

EOReader is a sensor-agnostic Python library designed to simplify the process of reading and preparing satellite imagery. It removes the need for developers to write sensor-specific code to load spectral bands, indices, and other data from various optical and SAR (Synthetic Aperture Radar) constellations, allowing them to focus on extraction algorithms rather than the technicalities of different satellite product formats.

How it works

The library provides a unified interface to open satellite products and load specific data types. It recognizes the constellation from the product structure and maps various sensor-specific bands to generic semantic labels (e.g., RED, GREEN, VV, VH). It uses xarray for raster data and geopandas for vector data, ensuring compatibility with the broader Python geospatial ecosystem. For SAR data, it integrates with ESA SNAP for orthorectification and calibration.

Who it’s for

It is primarily intended for remote sensing researchers, geoinformation specialists, and developers building automated pipelines for disaster mapping (such as flood or fire delineation) who work with data from multiple different satellite constellations.

Highlights

  • Broad Constellation Support: Supports a wide range of optical (e.g., Sentinel-2, Landsat, PlanetScope) and SAR (e.g., Sentinel-1, TerraSAR-X, ICEYE) sensors.
  • Sensor-Agnostic Loading: Load bands, spectral indices, cloud bands, and DEMs using generic labels regardless of the sensor used.
  • Data Stacking: Ability to stack multiple bands into a single file (e.g., GeoTIFF).
  • STAC Integration: Allows the creation of internal STAC catalogs directly from raw satellite data.
  • Legacy Support: Handles older satellite data formats to facilitate the creation of historical catalogs.

Related

  • Project
    ngageoint/sarpy

    A Python library for reading, writing, and processing complex Synthetic Aperture Radar (SAR) data, specifically supporting NGA standards and various commercial SLC formats.

  • Project
    ouster-lidar/ouster-sdk

    A cross-platform C++/Python development toolkit for connecting to, configuring, and visualizing data from Ouster Lidar sensors.

  • Project
    bopen/sarsen

    A Python library for cloud-native Synthetic Aperture Radar (SAR) processing that provides geometric and radiometric terrain correction for Sentinel-1 satellite data.

  • Project
    johntruckenbrodt/pyroSAR

    A Python framework for the scalable organization and processing of SAR satellite data from various missions and software tools.

  • Project
    e-sensing/sits

    SITS is an open‑source R package (with a Python wrapper) for building, regularising, and classifying satellite‑image time‑series data cubes. It connects to many public EO collections, offers a suite of ML/DL models (including GPU‑accelerated CNNs and attention encoders), and provides end‑to‑end tools for training, classification, smoothing, uncertainty estimation, and active learning.