SCEC Award Number 21047 View PDF
Proposal Category Individual Proposal (Data Gathering and Products)
Proposal Title Machine Learning for Classifying Patterns of Earthquake Seismicity: Forecasting, Nowcasting, and Tsunami Early Warning
Investigator(s)
Name Organization
John Rundle University of California, Davis
Other Participants Graduate Student Researcher VII
SCEC Priorities 5a, 5b, 5c SCEC Groups CS, SDOT, EFP
Report Due Date 03/15/2022 Date Report Submitted 10/25/2022
Project Abstract
 Nowcasting is a term originating from economics, finance and meteorology. It refers to the process of determining the uncertain state of the economy, markets or the weather at the current time by indirect means. In this paper we describe a simple 2-parameter data analysis that reveals hidden order in otherwise seemingly chaotic earthquake seismicity. One of these parameters relates to a mechanism of seismic quiescence arising from the physics of strain-hardening of the crust prior to major events. We observe an earthquake cycle associated with major earthquakes in California, similar to what has long been postulated. An estimate of the earthquake hazard revealed by this state variable timeseries can be can be optimized by the use of machine learning in the form of the Receiver Operating Characteristic skill score.
Intellectual Merit Anticipating earthquakes. We show that a method for computing a state variable (proxy) timeseries (t) can be computed with results similar to previous methods. This new method is by far the simplest and most transparent, involving 1) an exponential moving average of the regional seismicity, involving a number of weights N; and 2) an assumption that, as a major earthquake approaches, there is a transition in the small earthquake seismicity from unstable stick-slip to stable sliding.
Broader Impacts More accurately anticipating earthquakes will help in planning and response.
Exemplary Figure Figure 1
Linked Publications

Add missing publication or edit citation shown. Enter the SCEC project ID to link publication.