Title: Nowcasting Earthquakes: Imaging the Earthquake Cycle in California With Machine Learning

Journal Article · · Earth and Space Science
ORCiD logo [1]; ORCiD logo [2];  [3];  [4]; ORCiD logo [5]
  1. University of California, Davis, CA (United States); California Institute of Technology (CalTech), Pasadena, CA (United States). Jet Propulsion Laboratory (JPL); Santa Fe Institute (SFI), Santa Fe, NM (United States); University of California Davis
  2. California Institute of Technology (CalTech), Pasadena, CA (United States). Jet Propulsion Laboratory (JPL)
  3. Indiana University, Bloomington, IN (United States)
  4. University of California, Davis, CA (United States)
  5. City University of New York (CUNY), NY (United States)

We propose a new machine learning-based method for nowcasting earthquakes to image the time-dependent earthquake cycle. The result is a timeseries that may correspond to the process of stress accumulation and release. The timeseries are constructed by using principal component analysis of regional seismicity. The patterns are found as eigenvectors of the cross-correlation matrix of a collection of seismicity timeseries in a coarse grained regional spatial grid (pattern recognition via unsupervised machine learning). The eigenvalues of this matrix represent the relative importance of the various eigenpatterns. Using the eigenvectors and eigenvalues, we compute the weighted correlation timeseries of the regional seismicity. This timeseries has the property that the weighted correlation generally decreases prior to major earthquakes in the region, and increases suddenly just after a major earthquake occurs. As in a previous paper, we find that this method produces a nowcasting timeseries that resembles the hypothesized regional stress accumulation and release process characterizing the earthquake cycle. We then address the problem of whether the timeseries contain information regarding future large earthquakes. For this, we compute a receiver operating characteristic and determine the decision thresholds for several future time periods of interest (optimization via supervised machine learning). We find that signals can be detected that can be used to characterize the information content of the timeseries. These signals may be useful in assessing present and near-future seismic hazards.

Research Organization:
University of California, Davis, CA (United States)
Sponsoring Organization:
National Aeronautics and Space Administration (NASA); National Science Foundation (NSF); Southern California Earthquake Center; USDOE Office of Science (SC); United States Geological Survey (USGS)
Grant/Contract Number:
SC0017324
OSTI ID:
1978503
Journal Information:
Earth and Space Science, Journal Name: Earth and Space Science Journal Issue: 12 Vol. 8; ISSN 2333-5084
Publisher:
American Geophysical Union (AGU)Copyright Statement
Country of Publication:
United States
Language:
English

References (34)

Study of the temporal correlations in the magnitude time series before major earthquakes in Japan journal November 2014
Nowcasting earthquakes: Nowcasting Earthquakes journal November 2016
Machine Learning Predicts Laboratory Earthquakes: MACHINE LEARNING PREDICTS LAB QUAKES journal September 2017
A Mathematical Theory of Communication journal July 1948
Natural Time Analysis: The New View of Time book January 2011
Stochastic Modeling of Earthquake Interevent Counts (Natural Times) in Northwest Himalaya and Adjoining Regions book January 2020
Pattern Dynamics and Forecast Methods in Seismically Active Regions journal August 2002
Nowcasting Earthquakes: A Comparison of Induced Earthquakes in Oklahoma and at the Geysers, California journal September 2017
Natural Time, Nowcasting and the Physics of Earthquakes: Estimation of Seismic Risk to Global Megacities journal November 2017
Natural Time and Nowcasting Earthquakes: Are Large Global Earthquakes Temporally Clustered? journal January 2018
Seismic Electric Signals: An additional fact showing their physical interconnection with seismicity journal March 2013
The Mechanics of Earthquakes and Faulting book December 2018
Eigenpatterns in southern California seismicity: EIGENPATTERNS IN SOUTHERN CALIFORNIA SEISMICITY journal December 2002
Global Seismic Nowcasting With Shannon Information Entropy journal January 2019
Nowcasting Earthquakes in Southern California With Machine Learning: Bursts, Swarms, and Aftershocks May Be Related to Levels of Regional Tectonic Stress journal September 2020
Were changes in stress state responsible for the 2019 Ridgecrest, California, earthquakes? journal June 2020
Continuous chatter of the Cascadia subduction zone revealed by machine learning journal December 2018
The complex dynamics of earthquake fault systems: new approaches to forecasting and nowcasting of earthquakes journal May 2021
Natural time and nowcasting induced seismicity at the Groningen gas field in the Netherlands journal July 2018
Long-range correlations in the electric signals that precede rupture journal July 2002
Scale-free networks of earthquakes and aftershocks journal June 2004
Similarity of fluctuations in correlated systems: The case of seismicity journal October 2005
Earthquake correlations and networks: A comparative study journal April 2011
Self-organized criticality in a continuous, nonconservative cellular automaton modeling earthquakes journal February 1992
Universal Earthquake-Occurrence Jumps, Correlations with Time, and Anomalous Diffusion journal October 2006
Introduction To Percolation Theory January 2017
Remarkable changes in the distribution of the order parameter of seismicity before mainshocks journal November 2012
A remarkable change of the entropy of seismicity in natural time under time reversal before the super-giant M9 Tohoku earthquake on 11 March 2011 journal November 2018
Fluctuations of the entropy change under time reversal: Further investigations on identifying the occurrence time of an impending major earthquake journal May 2020
Self-organized criticality and earthquake predictability: A long-standing question in the light of natural time analysis journal October 2020
Space-Time Correlations of Seismotectonic Parameters: Examples from Japan and from Turkey Preceding the Izmit Earthquake journal February 2002
Generic Earthquake Simulator journal November 2012
Nowcasting Avalanches as Earthquakes and the Predictability of Strong Avalanches in the Olami-Feder-Christensen Model journal October 2020
Non-extensivity and long-range correlations in the earthquake activity at the West Corinth rift (Greece) journal September 2013