A pre-seismic anomaly detection approach based on graph attention isomorphism network

Abstract

Pre-seismic anomaly detection plays a crucial role in reducing economic losses and casualties caused by earthquakes. This paper proposes a novel four-step pre-seismic anomaly detection approach. In the first step, a series of pre-seismic features are extracted by analyzing the earthquake catalog and geomagnetic signals. In the second step, the multi-view learning (MVL) strategy is employed to obtain the fusion features. In the third step, multiple seismic stations in one seismic zone are treated as a seismic station network, and a pre-seismic anomaly detection model is constructed based on the station network. In the final step, 4 evaluation indicators (EIs) are introduced to evaluate the detection results comprehensively. Verification results show the proposed method is effective and achieves a better performance than other existing methods.