Real-time Seismic Intensity Prediction using Self-supervised Contrastive GNN for Earthquake Early Warning

TL;DR

This paper introduces SC-GNN, a self-supervised contrastive graph neural network that predicts seismic intensity accurately from minimal initial seismic data, improving earthquake early warning systems.

Contribution

The paper presents a novel deep learning model combining GNN and contrastive learning for real-time seismic intensity prediction using limited initial waveforms.

Findings

SC-GNN outperforms existing methods in accuracy and robustness.

It maintains high performance with only 5 seconds of initial seismic data.

Demonstrates significant reduction in mean squared error across datasets.

Abstract

Seismic intensity prediction from early or initial seismic waves received by a few seismic stations can enhance Earthquake Early Warning (EEW) systems, particularly in ground motion-based approaches like PLUM. While many operational EEW systems currently utilize point-source-based models that estimate the warning area based on magnitude and distance measures, direct intensity prediction offers a potential improvement in accuracy and reliability. In this paper, we propose a novel deep learning approach, Seismic Contrastive Graph Neural Network (SC-GNN), for highly accurate seismic intensity prediction using a small portion of initial seismic waveforms from a few seismic stations. The SC-GNN consists of two key components: (i) a graph neural network (GNN) to propagate spatiotemporal information through a graph-like structure representing seismic station distribution and wave propagation, and (ii) a self-supervised contrastive learning component to train the network with larger time windows and enable predictions using shorter initial waveforms. The efficacy of our approach is demonstrated through experiments on three real-world seismic datasets, where it shows superior performance over existing techniques, including a significant reduction in mean squared error (MSE) and the lowest standard deviation of error, indicating its robustness, reliability, and strong positive relationship between predicted and actual values. Notably, the SC-GNN model maintains superior performance even with 5s input waveforms, making it especially suitable for enhancing EEW applications.