Skip to content

Add EQ-INSAR - synthetic InSAR generator for earthquake ML training#42

Open
kcieslik wants to merge 1 commit intoRadarCODE:masterfrom
kcieslik:master
Open

Add EQ-INSAR - synthetic InSAR generator for earthquake ML training#42
kcieslik wants to merge 1 commit intoRadarCODE:masterfrom
kcieslik:master

Conversation

@kcieslik
Copy link
Copy Markdown

Adding EQ-INSAR

Link: https://github.com/kcieslik/eq-insar
PyPI: https://pypi.org/project/eq-insar/
Preprint: https://doi.org/10.31223/X5T19M

EQ-INSAR is an open-source Python package that generates synthetic InSAR
interferograms from earthquake point sources (Davis 1986 elastic half-space
model). It supports 9 SAR satellite geometries (Sentinel-1, ALOS-2,
TerraSAR-X, etc.) and is specifically designed for ML training data
generation — producing labeled time series with binary segmentation masks
in (N, T, H, W) format for PyTorch/TensorFlow.

Key facts:

  • NumPy-only core (no heavy dependencies)
  • MIT license, published on PyPI
  • Archived on Zenodo (DOI: 10.5281/zenodo.18647189)
  • Peer-reviewed preprint on EarthArXiv

Placed under: Radar-Related GitHub Repos > InSAR modeling tools

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant