A Caltech Library Service

Machine Learning in Seismology: Turning Data into Insights

Kong, Qingkai and Trugman, Daniel T. and Ross, Zachary E. and Bianco, Michael J. and Meade, Brendan J. and Gerstoft, Peter (2019) Machine Learning in Seismology: Turning Data into Insights. Seismological Research Letters, 90 (1). pp. 3-14. ISSN 0895-0695. doi:10.1785/0220180259.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


This article provides an overview of current applications of machine learning (ML) in seismology. ML techniques are becoming increasingly widespread in seismology, with applications ranging from identifying unseen signals and patterns to extracting features that might improve our physical understanding. The survey of the applications in seismology presented here serves as a catalyst for further use of ML. Five research areas in seismology are surveyed in which ML classification, regression, clustering algorithms show promise: earthquake detection and phase picking, earthquake early warning (EEW), ground‐motion prediction, seismic tomography, and earthquake geodesy. We conclude by discussing the need for a hybrid approach combining data‐driven ML with traditional physical modeling.

Item Type:Article
Related URLs:
URLURL TypeDescription
Trugman, Daniel T.0000-0002-9296-4223
Ross, Zachary E.0000-0002-6343-8400
Additional Information:© 2018 Seismological Society of America. Published Online 14 November 2018. Data and Resources: For further reading on machine learning (ML) fundamentals, we recommend the following textbooks and online course materials. Bishop (2006) is a more introductory text, whereas Murphy (2012) provides a more in‐depth theoretical development. “Deep Learning” (Goodfellow et al., 2016) provides a practical introduction to deep neural networks (NNs). There are also many excellent free online courses, such as Ng’s “Machine Learning,” Hinton’s “Neural Networks for Machine Learning,” Tibshirani and Hastie’s “Statistical Learning,” and Li et al.’s “Convolutional Neural Networks for Visual Recognition.” This is not meant to be an exhaustive list of ML resources, but is a good place to get started. The authors thank Editor‐in‐Chief Zhigang Peng for the invitation to write this frontier article and three anonymous reviewers for their thoughtful comments which greatly improved the article. Q. Kong acknowledges support from the Gordon and Betty Moore Foundation through Grant Number GBMF5230 to UC Berkeley. D. Trugman acknowledges institutional support from the Laboratory Directed Research and Development (LDRD) program at Los Alamos National Laboratory. Z. Ross acknowledges support from The Gordon and Betty Moore Foundation and the National Science Foundation. M. Bianco and P. Gerstoft acknowledge support from the Office of Naval Research (Grant Number N00014‐18‐1‐2118).
Group:Seismological Laboratory
Funding AgencyGrant Number
Gordon and Betty Moore FoundationGBMF5230
Los Alamos National LaboratoryUNSPECIFIED
Office of Naval Research (ONR)N00014-18-1-2118
Issue or Number:1
Record Number:CaltechAUTHORS:20181114-153737375
Persistent URL:
Official Citation:Qingkai Kong, Daniel T. Trugman, Zachary E. Ross, Michael J. Bianco, Brendan J. Meade, Peter Gerstoft; Machine Learning in Seismology: Turning Data into Insights. Seismological Research Letters ; 90 (1): 3–14. doi:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:90904
Deposited By: Tony Diaz
Deposited On:14 Nov 2018 23:50
Last Modified:16 Nov 2021 03:36

Repository Staff Only: item control page