An Attention-Based Framework With Multistation Information for Earthquake Early Warnings

Earthquake early warning systems play crucial roles in reducing the risk of seismic disasters. Previously, the dominant modeling system was the single-station models. Such models digest signal data received at a given station and predict earthquake parameters, such as the p-phase arrival time, intensity, and magnitude at that location. Various methods have demonstrated adequate performance. However, most of these methods present the challenges of the difficulty of speeding up the alarm time, providing early warning for distant areas, and considering global information to enhance performance. Recently, deep learning has significantly impacted many fields, including seismology. Thus, this paper proposes a deep learning-based framework, called SENSE<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>, for the intensity prediction task of earthquake early warning systems. To explicitly consider global information from a regional or national perspective, the input to the SENSE model includes features derived from multiple stations within a specific region or country. The SENSE model is designed to learn the relationships among these input stations and to derive locality-specific embeddings for each station individually, further enhancing prediction performance. Thus, SENSE is not only expected to provide more reliable forecasts by considering multistation data but also has the ability to provide early warnings to distant areas that have not yet received signals. This study conducted extensive experiments on datasets from Japan and Taiwan. The results revealed that SENSE can deliver competitive or even better performances compared with other advanced deep learning-based methods.