CaltechAUTHORS
  A Caltech Library Service

Predicting Imminence of Analog Megathrust Earthquakes With Machine Learning: Implications for Monitoring Subduction Zones

Corbi, F. and Bedford, J. and Sandri, L. and Funiciello, F. and Gualandi, A. and Rosenau, M. (2020) Predicting Imminence of Analog Megathrust Earthquakes With Machine Learning: Implications for Monitoring Subduction Zones. Geophysical Research Letters, 47 (7). Art. No. e2019GL086615. ISSN 0094-8276. https://resolver.caltech.edu/CaltechAUTHORS:20200408-092222439

[img] PDF - Published Version
Creative Commons Attribution.

9Mb
[img] PDF - Supplemental Material
Creative Commons Attribution.

8Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200408-092222439

Abstract

Subduction zones are monitored using space geodesy with increasing resolution, with the aim of better capturing the deformation accompanying the seismic cycle. Here, we investigate data characteristics that maximize the performance of a machine learning binary classifier predicting slip‐event imminence. We overcome the scarcity of recorded instances from real subduction zones using data from a seismotectonic analog model monitored with a spatially dense, continuously recording onshore geodetic network. We show that a 70–85 km‐wide coastal swath recording interseismic deformation gives the most important information on slip imminence. Prediction performances are mainly influenced by the alarm duration (amount of time that we consider an event as imminent), with density of stations and record length playing a secondary role. The techniques developed in this study are most likely applicable in regions of slow earthquakes, where stick‐slip‐like failures occur at time intervals of months to years.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1029/2019gl086615DOIArticle
ORCID:
AuthorORCID
Corbi, F.0000-0003-2662-3065
Bedford, J.0000-0002-8954-4367
Sandri, L.0000-0002-3254-2336
Funiciello, F.0000-0001-7900-8272
Gualandi, A.0000-0002-3100-8932
Rosenau, M.0000-0003-1134-5381
Additional Information:© 2020 The Authors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. Received 10 DEC 2019; Accepted 9 MAR 2020; Accepted article online 12 MAR 2020. We thank two anonymous reviewers and the editor G. Hayes for their constructive comments. In Figures 1 and 3 we used the perceptually uniform colormap Davos by F. Crameri. The work leading to this publication was supported by the PRIME program of the German Academic Exchange Service (DAAD) with funds from the German Federal Ministry of Education and Research (BMBF). M. R. has benefitted from the inspiring environment of the CRC 1114 “Scaling Cascades in Complex Systems” (funded by Deutsche Forschungsgemeinschaft [DFG]). The Grant to Department of Science, Roma Tre University (MIUR‐Italy Dipartimenti di Eccellenza, ARTICOLO 1, COMMI 314 – 337 LEGGE 232/2016) is gratefully acknowledged.
Group:Seismological Laboratory
Funders:
Funding AgencyGrant Number
Deutscher Akademischer Austauschdienst (DAAD)UNSPECIFIED
Bundesministerium für Bildung und Forschung (BMBF)UNSPECIFIED
Deutsche Forschungsgemeinschaft (DFG)CRC 1114
Roma Tre UniversityUNSPECIFIED
Ministero dell'Istruzione, dell'Universita e della Ricerca (MIUR)337 LEGGE 232/2016
Subject Keywords:megathrust earthquakes; machine learning; analog modeling
Issue or Number:7
Record Number:CaltechAUTHORS:20200408-092222439
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200408-092222439
Official Citation:Corbi, F., Bedford, J., Sandri, L., Funiciello, F., Gualandi, A., & Rosenau, M. (2020). Predicting imminence of analog megathrust earthquakes with machine learning: Implications for monitoring subduction zones. Geophysical Research Letters, 47, e2019GL086615. https://doi.org/10.1029/2019GL086615
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102398
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:08 Apr 2020 16:46
Last Modified:08 Apr 2020 16:46

Repository Staff Only: item control page