A Seismic Phase Recognition Algorithm Based on Time Convolution Networks

Abstract

Over recent years, frequent earthquakes have caused huge losses in human life and property. Rapid and automatic earthquake detection plays an important role in earthquake warning systems and earthquake operation mechanism research. Temporal convolution networks (TCNs) are frameworks that use expansion convolution and expansion, which have large and temporal receptive fields and can adapt to time series data. Given the excellent performance of temporal convolution networks using time series data, this paper proposes a deep learning framework based on the temporal convolution network model, which can be used to detect and obtain the accurate start times of seismic phases. In addition, a convolutional neural network (CNN) was added to the temporal convolution network model to automatically extract the deep features of seismic waves and the expansion convolution of each level was added to optimize its structure, which not only reduced the experimental parameters but also produced high-precision seismic phase detection results. Finally, the model was compared to the TCN, CNN-LSTM, SELD-TCN and the traditional AR-AIC methods. Our experimental results showed that the S-TCN method demonstrated great advantages in the accuracy and performance of seismic phase detection.