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

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.

arXiv comment15 pages, 5 figures

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Cited by in corpus (25)

• Generalized Seismic Phase Detection with Deep Learning
• Seismic Signal Denoising and Decomposition Using Deep Neural Networks
• A Machine-Learning Approach for Earthquake Magnitude Estimation
• 70 years of machine learning in geoscience in review
• PhaseLink: A Deep Learning Approach to Seismic Phase Association
• Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
• Locating earthquakes with a network of seismic stations via a deep learning method
• Reliable Real-time Seismic Signal/Noise Discrimination with Machine Learning
• Deep learning for seismic phase detection and picking in the aftershock zone of 2008 Mw7.9 Wenchuan earthquake
• Neural Network Applications in Earthquake Prediction (1994-2019): Meta-Analytic Insight on their Limitations
• An End-to-End Earthquake Detection Method for Joint Phase Picking and Association using Deep Learning
• Graph Neural Networks for Multivariate Time Series Regression with Application to Seismic Data
• Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale
• Rapid Seismic Waveform Modeling and Inversion with Neural Operators
• Extracting dispersion curves from ambient noise correlations using deep learning
• CREIME: A Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation
• SeisT: A foundational deep learning model for earthquake monitoring tasks
• Data-driven geophysics: from dictionary learning to deep learning
• Efficient wave type fingerprinting and filtering by six-component polarization analysis
• Deep Neural Networks for Creating Reliable PmP Database with a Case Study in Southern California
• Towards fast machine-learning-assisted Bayesian posterior inference of microseismic event location and source mechanism
• EPick: Multi-Class Attention-based U-shaped Neural Network for Earthquake Detection and Seismic Phase Picking
• A Machine Learning-enhanced Robust P-Phase Picker for Real-time Seismic Monitoring
• A Silent Build-up in Seismic Energy Precedes Slow Slip Failure in the Cascadia Subduction Zone
• Deep learning for low-magnitude earthquake detection on a multi-level sensor network