Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning

TLDR

Earthquake early warning systems suffer false alerts from local impulsive noise. The study trains a generative adversarial network on 300,000 waveforms to learn first‑arrival P‑wave characteristics and mitigate false alerts. The GAN critic extracts features, and a Random Forest classifier is trained on approximately 700,000 earthquake and noise waveforms. The discriminator achieves 99.2 % earthquake and 98.4 % noise detection, promising a substantial reduction in false triggers and revealing GANs’ potential for compact seismic wave representations.

Abstract

Abstract Performance of earthquake early warning systems suffers from false alerts caused by local impulsive noise from natural or anthropogenic sources. To mitigate this problem, we train a generative adversarial network (GAN) to learn the characteristics of first‐arrival earthquake P waves, using 300,000 waveforms recorded in southern California and Japan. We apply the GAN critic as an automatic feature extractor and train a Random Forest classifier with about 700,000 earthquake and noise waveforms. We show that the discriminator can recognize 99.2% of the earthquake P waves and 98.4% of the noise signals. This state‐of‐the‐art performance is expected to reduce significantly the number of false triggers from local impulsive noise. Our study demonstrates that GANs can discover a compact and effective representation of seismic waves, which has the potential for wide applications in seismology.