worldstrat/worldstrat

The WorldStrat Dataset

42
/ 100
Emerging

This project offers a comprehensive dataset of nearly 10,000 km² of high-resolution satellite imagery, paired with lower-resolution Sentinel-2 images from the same locations and times. It provides tools to explore, extend, and even generate high-resolution images from lower-resolution inputs using machine learning. This is ideal for researchers and practitioners in remote sensing, environmental monitoring, or humanitarian mapping who need diverse, high-quality satellite data.

276 stars. No commits in the last 6 months.

Use this if you need a large, globally stratified dataset of satellite imagery, or if you want to develop and test machine learning models for tasks like super-resolution on satellite data.

Not ideal if you're looking for real-time satellite data analysis or if your work does not involve image processing or machine learning applications.

satellite-imagery remote-sensing environmental-monitoring geospatial-analysis humanitarian-mapping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

276

Forks

31

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Mar 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/worldstrat/worldstrat"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.