REAVER: Real-time Earthquake Prediction with Attention-based Sliding-Window Spectrograms

Abstract

Predicting earthquakes with precision remains an ongoing challenge in earthquake early warning systems (EEWS), that struggle with accuracy and fail to provide timely warnings for impending earthquakes. Recent efforts employing deep learning techniques have shown promise in overcoming these limitations. However, current methods lack the ability to capture subtle frequency changes indicative of seismic activity in real-time, limiting their effectiveness in EEWS. To address this gap, we propose REAVER, a novel approach for real-time prediction of P- and S-waves of earthquakes using attention-based sliding-window spectrograms. REAVER leverages Mel-Spectrogram signal representations to capture temporal frequency changes in seismic signals effectively. By employing an encoder-decoder architecture with attention mechanisms, REAVER accurately predicts the onset of P- and S-waves moments when an earthquake occurs. We benchmark the effectiveness of REAVER, showing its performance in terms of both accuracy and real-time prediction capabilities compared to existing methods. Additionally, we provide a web-based implementation of REAVER, allowing users to monitor seismic activity in real-time and analyze historical earthquake waveforms.