Multi-task multi-station earthquake monitoring: An all-in-one seismic Phase picking, Location, and Association Network (PLAN)

TL;DR

This paper introduces a novel graph neural network that simultaneously performs seismic phase picking, association, and location, leveraging inter-station relationships to improve accuracy and consistency in earthquake monitoring.

Contribution

The study presents the first all-in-one deep learning system integrating phase picking, association, and location using a graph neural network that models inter-station physical relationships.

Findings

Superior performance over previous methods in Ridgecrest and Japan datasets

Achieves physical consistency among predictions

Provides a prototype for next-generation autonomous earthquake monitoring

Abstract

Earthquake monitoring is vital for understanding the physics of earthquakes and assessing seismic hazards. A standard monitoring workflow includes the interrelated and interdependent tasks of phase picking, association, and location. Although deep learning methods have been successfully applied to earthquake monitoring, they mostly address the tasks separately and ignore the geographic relationships among stations. Here, we propose a graph neural network that operates directly on multi-station seismic data and achieves simultaneous phase picking, association, and location. Particularly, the inter-station and inter-task physical relationships are informed in the network architecture to promote accuracy, interpretability, and physical consistency among cross-station and cross-task predictions. When applied to data from the Ridgecrest region and Japan regions, this method showed superior performance over previous deep learning-based phase-picking and localization methods. Overall, our study provides for the first time a prototype self-consistent all-in-one system of simultaneous seismic phase picking, association, and location, which has the potential for next-generation autonomous earthquake monitoring.