Time-domain-based convolutional neural network model for seismic phase recognition and application thereof

The invention provides a time-domain-based convolutional neural network model for seismic facies recognition and an application thereof. The model is constructed by the following steps: (1) dividing a seismic waveform data set into a training set, a verification set and a test set; (2) combining a convolutional neural network (CNN) with a time domain neural network (TCN) to construct an S-TCN model, inputting the training set into three continuous convolution blocks for feature learning, and inputting data after feature learning into a main TCN block and two continuous auxiliary TCN blocks for total feature extraction of seismic P waves and S waves and extraction of context information, and finally, sending the outputs of the two continuous auxiliary TCN blocks respectively to two parallel branches of a GRU module and a TimeDistrided module for seismic phase identification and seismic phase pickup; and (3) training the S-TCN model, and verifying to obtain a seismic phase identification and pickup result. The