SC-PSNET: A deep neural network for automatic P- and S-phase detection and arrival-time picker using 1C recordings

Abstract

<jats:p> It is important to autopick an event’s arrival time and classify the corresponding phase for seismic data processing. Traditional arrival-time picking algorithms usually need 3C seismograms to classify event phase. However, a large number of borehole seismic data sets are recorded by arrays of hydrophones or distributed acoustic sensing elements whose sensors are 1C and cannot be analyzed for particle motion or phase polarization. With the development of deep learning techniques, researchers have tried data mining with the convolutional neural network (CNN) for seismic phase autopicking. In the previous work, CNN was applied to process 3C seismograms to detect phase and pick arrivals. We have extended this work to process 1C seismic data and focused on two main points. One is the effect of the label vector on the phase detection performance. The other is to propose an architecture to deal with the challenge from the insufficiency of training data in the coverage of different scenarios of [Formula: see text] ratios. Two novel points are summarized after this analysis. First, the width of the label vector can be designed through signal time-frequency analysis. Second, a combination of CNN and recurrent neural network architecture is more suitable for designing a P- and S-phase detector to deal with the challenge from the insufficiency of training data for 1C recordings in time-lapse seismic monitoring. We perform experiments and analysis using synthetic and field time-lapse seismic recordings. The experiments show that it is effective for 1C seismic data processing in time-lapse monitoring surveys. </jats:p>

DeepPhasePick: A method for detecting and picking seismic phases from local earthquakes based on highly optimized convolutional and recurrent deep neural networks

“…RNN-based networks have been used for P-wave identification (Zhu et al 2020), seismic phase association (Ross et al 2019b) and for predicting approximate earthquake times and locations (Panakkat & Adeli 2009). Model architectures based on combinations of CNN and RNN networks have been implemented for earthquake detection (Mousavi et al 2019c) and combined event detection and phase picking (Zhou et al 2019;Zheng et al 2020) tasks. Recently, novel models which apply attention mechanism on a CNN+LSTM-based network architecture (Mousavi et al 2020c) and utilize a capsule neural network (Saad & Chen 2020) have also been used for combined event detection and phase picking.…”

A Comparative Analysis of Machine Learning Models for First-break Arrival Picking

“…In SC-PSNET [29], the authors extend 3C seismograms processing with CNN to 1C seismic processing. Their study showed that CNN in combination with RNN is more promising for P-and S-detection when there are not enough training data available.…”

Detecting local earthquakes via fiber-optic cables in telecommunication conduits under Stanford University campus using deep learning

“…Once a machine learning (ML) model is trained, application to newly acquired fiber data, possibly even continuously, can potentially remove many bottlenecks of traditional processing. Neural networks have been shown to be successful at earthquake detection on seismometer recordings (Perol et al, 2018;Huot, Biondi, & Beroza, 2018;Zhang et al, 2019;Zheng et al, 2020). Recent studies demonstrate that they also have great potential for waveform-based event detection on continuous fiber recordings in the presence of coherent noise (Huot et al, 2017;.…”