P-wave arrival picking and first-motion polarity determination with deep learning

TL;DR

This paper presents a deep learning approach using convolutional neural networks to accurately determine P-wave arrival times and first-motion polarities from seismograms, outperforming traditional automated methods and matching expert performance.

Contribution

The authors develop and train CNNs on a large dataset of seismograms to automate P-wave picking and polarity determination with high accuracy, reducing the need for manual analysis.

Findings

Standard deviation of 0.023 seconds in pick differences

95% precision in polarity classification

Almost double the number of focal mechanisms identified

Abstract

Determining earthquake hypocenters and focal mechanisms requires precisely measured P-wave arrival times and first-motion polarities. Automated algorithms for estimating these quantities have been less accurate than estimates by human experts, which is problematic for processing large data volumes. Here, we train convolutional neural networks to measure both quantities, which learn directly from seismograms without the need for feature extraction. The networks are trained on 18.2 million manually picked seismograms for the southern California region. Through cross-validation on 1.2 million independent seismograms, the differences between the automated and manual picks have a standard deviation of 0.023 seconds. The polarities determined by the classifier have a precision of 95% when compared with analyst-determined polarities. We show that the classifier picks more polarities overall than the analysts, without sacrificing quality, resulting in almost double the number of focal mechanisms. The remarkable precision of the trained networks indicates that they can perform as well, or better, than expert seismologists.