Real-time earthquake magnitude estimation via a deep learning network based on waveform and text mixed modal

Abstract Rapid and accurate earthquake magnitude estimations are essential for earthquake early warning (EEW) systems. The distance information between the seismometers and the earthquake hypocenter can be important to the magnitude estimation. We designed a deep-learning, multiple-seismometer-based magnitude estimation method using three heterogeneous multimodalities: three-component acceleration seismograms, differential P-arrivals, and differential seismometer locations, with a specific transformer architecture to introduce the implicit distance information. Using a data-augmentation strategy, we trained and selected the model using 5365 and 728 earthquakes. To evaluate the magnitude estimation performance, we use the root mean square error (RMSE), mean absolute error (MAE), and standard deviation error ( ϭ ) between the catalog and the predicted magnitude using the 2051 earthquakes. The model could achieve RMSE, MAE, and ϭ less than 0.38, 0.29, and 0.38 when the passing time of the earliest P-arrival is 3 s and stabilize to the final values of 0.20, 0.15, and 0.20 after 14 s. The comparison between the proposed model and model ii, which is retrained without the specific architecture, indicates that the architecture contributes to the magnitude estimation. The P-arrivals picking error testing indicates the model could provide robust magnitude estimation on EEW with an absolute error of less than 0.2 s. Graphical Abstract