# satellite-image-deep-learning/datasets

Datasets for deep learning with satellite & aerial imagery

Repository: https://github.com/satellite-image-deep-learning/datasets
Canonical: https://ross.abutalabs.com/products/satellite-image-deep-learning-datasets
License Family: other
Topics: datasets, remote-sensing, earth-observation, satellite-data, satellite-imagery, sentinel
Last push: 2026-08-02T12:20:28+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 98
- inputs: {"age_days": 1377, "days_push": 31, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1192, forks 132 (observed 2026-08-28T04:03:56.272739+00:00)

## What it is
A curated catalog of datasets for deep learning with satellite and aerial imagery, including Sentinel missions, remote sensing hubs, and benchmark dataset lists. It serves as a discovery resource linking to open geospatial datasets across platforms like AWS, Google Earth Engine, and Microsoft Planetary Computer.

## Use cases
- find datasets for training deep learning models on satellite imagery
- locate Sentinel-1 SAR datasets for flood mapping
- discover remote sensing change detection benchmarks
- find aerial imagery datasets for segmentation tasks
- look up Copernicus Sentinel data sources
- find satellite image time series datasets

## When to choose
- you need to discover open satellite or aerial imagery datasets for machine learning
- you want a curated index of remote sensing benchmarks and hubs
- you are researching earth observation data sources for deep learning

## When to avoid
- you need the actual imagery data rather than links to it
- you need a tool or library for processing satellite imagery
- you need non-geospatial machine learning datasets

## Facets
- artifact type: dataset
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, computer-vision, data-science, awesome-lists
- platform: cross-platform
- tags: remote-sensing, satellite-imagery, earth-observation, sentinel, geospatial, curated-list, awesome-list

## Member repositories
- satellite-image-deep-learning/datasets (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.272739+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 2026-08-30T06:22:38.640120+00:00, confidence not recorded.
  - readme: https://github.com/satellite-image-deep-learning/datasets (fetched 2026-08-28T04:03:56.272739+00:00, sha a8065aceb652)
- Data as of 2026-08-30T08:39:29.467469+00:00.