Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published January 2019 | Published + Submitted
Journal Article Open

Reliable Real-time Seismic Signal/Noise Discrimination with Machine Learning

Abstract

In earthquake early warning (EEW), every sufficiently impulsive signal is potentially the first evidence for an unfolding large earthquake. More often than not, however, impulsive signals are mere nuisance signals. One of the most fundamental—and difficult—tasks in EEW is to rapidly and reliably discriminate real local earthquake signals from all other signals. This discrimination is necessarily based on very little information, typically a few seconds worth of seismic waveforms from a small number of stations. As a result, current EEW systems struggle to avoid discrimination errors and suffer from false and missed alerts. In this study we show how modern machine learning classifiers can strongly improve real‐time signal/noise discrimination. We develop and compare a series of nonlinear classifiers with variable architecture depths, including fully connected, convolutional and recurrent neural networks, and a model that combines a generative adversarial network with a random forest. We train all classifiers on the same data set, which includes 374 k local earthquake records (M3.0–9.1) and 946 k impulsive noise signals. We find that all classifiers outperform existing simple linear classifiers and that complex models trained directly on the raw signals yield the greatest degree of improvement. Using 3‐s‐long waveform snippets, the convolutional neural network and the generative adversarial network with a random forest classifiers both reach 99.5% precision and 99.3% recall on an independent validation data set. Most misclassifications stem from impulsive teleseismic records, and from incorrectly labeled records in the data set. Our results suggest that machine learning classifiers can strongly improve the reliability and speed of EEW alerts.

Additional Information

© 2018 American Geophysical Union. Received 4 SEP 2018; Accepted 21 DEC 2018; Accepted article online 29 DEC 2018; Published online 25 JAN 2019. This research was supported by a Gordon and Betty Moore Foundation grant to Caltech and by the Swiss National Science Foundation. We thank Yehuda Ben‐Zion, Christopher Johnson, and an anonymous reviewer for their constructive and important comments. The Japanese waveform data can be downloaded from http://www.kik.bosai.go.jp/ (last accessed October 2017). For Southern California we have used waveforms and parametric and waveform data from the Caltech/USGS Southern California Seismic Network (doi:10.7914/SN/CI) stored at the Southern California Earthquake Data Center (doi:10.7909/C3WD3xH1). The waveform and feature data set is available as a single hdf5 file at http://scedc.caltech.edu. The algorithms were written with Python packages TensorFlow (https://tensorflow.org/), TFLearn (http://tflearn.org/), Keras (https://keras.io/), and Scikit‐learn (http://scikit‐learn.org/).

Attached Files

Published - Meier_et_al-2019-Journal_of_Geophysical_Research__Solid_Earth.pdf

Submitted - 1901.03467.pdf

Files

1901.03467.pdf
Files (3.6 MB)
Name Size Download all
md5:94cf9ea5b621025afade9c097845da57
2.1 MB Preview Download
md5:3b52753fd934124bad93ad657af4629a
1.5 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 19, 2023