A deep learning pipeline for large earthquake analysis using high-rate global navigation satellite system data

Abstract Deep learning techniques for processing large and complex datasets have unlocked new opportunities for fast and reliable earthquake analysis using Global Navigation Satellite System (GNSS) data. This work presents a deep learning model, MagEs, to estimate earthquake magnitudes using data from high-rate GNSS stations. Furthermore, MagEs is integrated with the DetEQ model for earthquake detection within the SAIPy package, creating a comprehensive pipeline for earthquake detection and magnitude estimation using HR-GNSS data. The MagEs model provides magnitude estimates within seconds of detection when using stations within 3 degrees of the epicenter, which are the most relevant for real-time applications. MagEs has also been trained on data from longer distances, up to 7.5 degrees away, and can process data from a single station or combine up to three stations at a time. The model was trained using synthetic data based on rupture scenarios in the Chile subduction zone, and the results confirm strong performance for Chilean earthquakes. Although the model also demonstrated robust performance on data from other regions, further improvements might be achieved through the application of transfer learning using datasets from the specific region of interest. The model has not yet been deployed in an operational real-time monitoring system, but simulation tests that update data in a second-by-second manner demonstrate its potential for future real-time adaptation.