Deep learning models for regional phase detection on seismic stations in Northern Europe and the European Arctic

Abstract

Summary Seismic phase detection and classification using deep learning is so far poorly investigated for regional events since most studies focus on local events and short time windows as the input to the detection models. To evaluate deep learning on regional seismic records, we create a dataset of events in Northern Europe and the European Arctic. This dataset consists of about 151,000 three component event waveforms and corresponding phase arrival picks at stations in mainland Norway, Finland, and Svalbard. We train several state-of-the-art and one newly-developed deep learning model on this dataset to pick P and S wave arrivals. The new method modifies the popular PhaseNet model with new convolutional blocks including transformers. This yields more accurate predictions on the long input time windows associated with regional events. Evaluated on event records not used for training, our new method improves the performance of the current state-of-the-art methods when it comes to recall, precision and pick time residuals. Finally, we test our new model for continuous mode processing on four days of single-station data from the ARCES array. Results show that our new method outperforms the existing array detector at ARCES. This opens up new opportunities to improve automatic array processing with deep learning detectors.