ArrayNet: A Combined Seismic Phase Classification and Back-Azimuth Regression Neural Network for Array Processing Pipelines

Abstract

Array processing is an integral part of automatic seismic event detection pipelines for measuring apparent velocity and backazimuth of seismic arrivals. Both quantities are usually measured under the plane-wave assumption, and are essential to classify the phase type and to determine the direction toward the event epicenter. However, structural inhomogeneities can lead to deviations from the plane-wave model, which must be taken into account for phase classification and back-azimuth estimation. We suggest a combined classification and regression neural network, which we call ArrayNet, to determine the phase type and backazimuth directly from the arrival-time differences between all combinations of stations of a given seismic array without assuming a plane-wave model. ArrayNet is trained using regional P- and S-wave arrivals of over 30,000 seismic events from reviewed regional bulletins in northern Europe from the past three decades. ArrayNet models are generated and trained for each of the ARCES, FINES, and SPITS seismic arrays. We observe excellent performance for the seismic phase classification (up to 99% accuracy), and the derived back-azimuth residuals are significantly improved in comparison with traditional array processing results using the plane-wave assumption. The SPITS array in Svalbard exhibits particular issues when it comes to array processing in the form of high apparent seismic velocities and a multitude of frost quake signals inside the array, and we show how our new approach better handles these obstacles. Furthermore, we demonstrate the performance of ArrayNet on 20 months of continuous phase detections from the ARCES array and investigate the results for a selection of regional seismic events of interest. Our results demonstrate that automatic event detection at seismic arrays can be further enhanced using a machine learning approach that takes advantage of the unique array data recorded at these stations.