ChenHongruixuan/BRIGHT

[ESSD 2025 & IEEE GRSS DFC 2025] Bright: A globally distributed multimodal VHR dataset for all-weather disaster response

53
/ 100
Established

This project provides a comprehensive collection of satellite images to help scientists and disaster response teams assess damage after natural and man-made disasters. It takes in very high-resolution, multi-modal satellite imagery (like optical and radar) from before and after an event. The output is data that helps train and evaluate AI models for tasks such as identifying damaged buildings or changes on the ground, even in bad weather. It is used by researchers and practitioners involved in disaster management, humanitarian aid, and remote sensing analysis.

208 stars.

Use this if you need diverse, globally distributed satellite imagery to develop or test AI models for rapid, all-weather disaster assessment and change detection.

Not ideal if you are looking for real-time operational tools for immediate disaster response rather than a dataset for model development and evaluation.

disaster-response remote-sensing damage-assessment humanitarian-aid geospatial-analysis
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

208

Forks

31

Language

Python

License

Apache-2.0

Last pushed

Feb 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ChenHongruixuan/BRIGHT"

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