olliestephenson/dpm-rnn-public

Damage mapping with deep learning on satellite data

35
/ 100
Emerging

This project helps disaster response and monitoring teams quickly assess damage from natural hazards like earthquakes, floods, or wildfires using satellite data. It takes a series of radar images from before an event and one image from during the event, then automatically identifies and maps affected areas. The output is a "damage proxy map" that pinpoints where the hazard caused significant changes on the ground, making it easier for analysts to focus their efforts.

No commits in the last 6 months.

Use this if you are a geospatial analyst, disaster relief coordinator, or researcher experienced with satellite radar data (specifically InSAR coherence time series) and need to generate rapid damage assessments after a natural disaster.

Not ideal if you lack familiarity with Synthetic Aperture Radar (SAR) or Interferometric SAR (InSAR) data processing, as you will need to prepare your own coherence image stacks.

disaster-response damage-assessment satellite-imagery geospatial-analysis remote-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Python

License

MIT

Last pushed

Jul 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/olliestephenson/dpm-rnn-public"

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