# sentinel-hub/eo-learn

Earth observation processing framework for machine learning in Python

Repository: https://github.com/sentinel-hub/eo-learn
Canonical: https://ross.abutalabs.com/products/eo-learn
Homepage: https://eo-learn.readthedocs.io/en/latest/
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, eo-data, eo-research, python-package
Last push: 2026-01-15T07:25:25+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 62, release rhythm 8, longevity 100
- inputs: {"age_days": 3016, "days_push": 230, "days_rel": 705, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1247, forks 304 (observed 2026-08-28T04:04:07.560145+00:00)

## What it is
eo-learn is a collection of open-source Python packages for accessing and processing spatio-temporal satellite imagery, built around modular, reusable processing tasks. It bridges Earth observation data (e.g. Copernicus Sentinel and Landsat) with machine learning workflows for extracting information from imagery.

## Use cases
- process satellite imagery for machine learning
- classify land cover from Sentinel-2 data
- build cloud masking pipelines for Earth observation data
- extract water bodies from satellite images using NDWI
- run feature extraction workflows on spatio-temporal image sequences
- prepare Earth observation datasets for deep learning models

## When to choose
- you work with Sentinel, Landsat, or other satellite imagery in Python
- you need modular, reusable processing chains for spatio-temporal EO data
- you want to connect Earth observation data pipelines to ML frameworks
- you need tasks like cloud masking, co-registration, and classification out of the box

## When to avoid
- you only need simple one-off raster operations without workflow structure
- your project deals with non-geospatial imagery
- you need real-time streaming image processing rather than batch workflows
- you require a GUI-based GIS tool instead of a Python library

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, image-processing, etl, data-science, workflow-automation
- domain: machine-learning, data-science, image-processing
- platform: python, cross-platform
- tags: earth-observation, satellite-imagery, sentinel, geospatial, remote-sensing, spatio-temporal, copernicus, landsat, automation, docker

## Member repositories
- sentinel-hub/eo-learn (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.560145+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:59.005214+00:00, confidence not recorded.
  - readme: https://github.com/sentinel-hub/eo-learn (fetched 2026-08-28T04:04:07.560145+00:00, sha 38f7cb7086d6)
  - registry_pypi: https://pypi.org/pypi/eo-learn/json (fetched 2026-08-29T12:19:42.016274+00:00, sha 54a0674edfdf)
- Data as of 2026-08-30T08:39:29.467469+00:00.