English

Spatio-Temporal Graph Structure Learning for Earthquake Detection

Machine Learning 2025-03-17 v1

Abstract

Earthquake detection is essential for earthquake early warning (EEW) systems. Traditional methods struggle with low signal-to-noise ratios and single-station reliance, limiting their effectiveness. We propose a Spatio-Temporal Graph Convolutional Network (GCN) using Spectral Structure Learning Convolution (Spectral SLC) to model static and dynamic relationships across seismic stations. Our approach processes multi-station waveform data and generates station-specific detection probabilities. Experiments show superior performance over a conventional GCN baseline in terms of true positive rate (TPR) and false positive rate (FPR), highlighting its potential for robust multi-station earthquake detection. The code repository for this study is available at https://github.com/SuchanunP/eq_detector.

Keywords

Cite

@article{arxiv.2503.11215,
  title  = {Spatio-Temporal Graph Structure Learning for Earthquake Detection},
  author = {Suchanun Piriyasatit and Ercan Engin Kuruoglu and Mehmet Sinan Ozeren},
  journal= {arXiv preprint arXiv:2503.11215},
  year   = {2025}
}

Comments

7 pages

R2 v1 2026-06-28T22:20:20.822Z