Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Automatic speech recognition predicts contemporaneous earthquake fault displacement

Journal Article · · Nature Communications
 [1];  [2];  [1]
  1. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
  2. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States); ExxonMobil Technology and Engineering Company, Los Alamos, NJ (United States)
+ Show Author Affiliations
Significant progress has been made in probing the state of an earthquake fault by applying machine learning to continuous seismic waveforms. The breakthroughs were originally obtained from laboratory shear experiments and numerical simulations of fault shear, then successfully extended to slow-slipping faults. Here we apply the Wav2Vec-2.0 self-supervised framework for automatic speech recognition to continuous seismic signals emanating from a sequence of moderate magnitude earthquakes during the 2018 caldera collapse at the Kīlauea volcano on the island of Hawai’i. We pre-train the Wav2Vec-2.0 model using caldera seismic waveforms and augment the model architecture to predict contemporaneous surface displacement during the caldera collapse sequence, a proxy for fault displacement. We find the model displacement predictions to be excellent. The model is adapted for near-future prediction information and found hints of prediction capability, but the results are not robust. The results demonstrate that earthquake faults emit seismic signatures in a similar manner to laboratory and numerical simulation faults, and artificial intelligence models developed for encoding audio of speech may have important applications in studying active fault zones.
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE; USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC), Basic Energy Sciences (BES)
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2507113
Alternate ID(s):
OSTI ID: 2570780
Report Number(s):
LA-UR--24-28409; 2041-1723; 10.1038/s41467-025-55994-9
Journal Information:
Nature Communications, Journal Name: Nature Communications Journal Issue: 1 Vol. 16; ISSN 2041-1723
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (33)

Machine Learning Predicts Laboratory Earthquakes: MACHINE LEARNING PREDICTS LAB QUAKES journal September 2017
Estimating Fault Friction From Seismic Signals in the Laboratory journal February 2018
Seismic and geodetic progression of the 2018 summit caldera collapse of Kīlauea volcano journal June 2020
Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress journal November 2022
Explainable machine learning for labquake prediction using catalog-driven features journal November 2023
Earthquake Catalog‐Based Machine Learning Identification of Laboratory Fault States and the Effects of Magnitude of Completeness journal December 2018
Machine Learning Can Predict the Timing and Size of Analog Earthquakes journal February 2019
Predicting Imminence of Analog Megathrust Earthquakes With Machine Learning: Implications for Monitoring Subduction Zones journal March 2020
Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning journal August 2020
Learning the Low Frequency Earthquake Activity on the Central San Andreas Fault journal July 2021
Predicting Future Laboratory Fault Friction Through Deep Learning Transformer Models journal October 2022
Forecasting Surface Velocity Fields Associated With Laboratory Seismic Cycles Using Deep Learning journal August 2022
Seismic Features Predict Ground Motions During Repeating Caldera Collapse Sequence journal June 2024
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking journal August 2020
An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia journal August 2020
Machine learning and earthquake forecasting—next steps journal August 2021
Predicting fault slip via transfer learning journal December 2021
Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes journal June 2023
Similarity of fast and slow earthquakes illuminated by machine learning journal December 2018
Continuous chatter of the Cascadia subduction zone revealed by machine learning journal December 2018
Rainfall an unlikely factor in Kīlauea’s 2018 rift eruption journal February 2022
Physics informed neural network can retrieve rate and state friction parameters from acoustic monitoring of laboratory stick-slip experiments journal October 2024
Laboratory earthquake forecasting: A machine learning competition journal January 2021
Unsupervised clustering of catalogue-driven features for characterizing temporal evolution of labquake stress journal February 2024
Unsupervised Clustering of Seismic Signals Using Deep Convolutional Autoencoders journal November 2019
The 2018 rift eruption and summit collapse of Kīlauea Volcano journal December 2018
Cyclic lava effusion during the 2018 eruption of Kīlauea Volcano journal December 2019
Characterizing Acoustic Signals and Searching for Precursors during the Laboratory Seismic Cycle Using Unsupervised Machine Learning journal March 2019
Deep Clustering to Identify Sources of Urban Seismic Noise in Long Beach, California journal December 2020
An Overview of End-to-End Automatic Speech Recognition journal August 2019
Depth dependence of coseismic off-fault damage conference April 2023
Kilauea Volcano 2018 dataset January 2019
Hawaiian Volcano Observatory Network dataset January 1956

Similar Records

Related Subjects

58 GEOSCIENCES
geophysics
seismology