Unsupervised large-scale data mining for similar earthquake detection

Clara Yoon, Karianne Bergen, Kexin Rong, Hashem Elezabi, William L. Ellsworth, Gregory C. Beroza, Peter Bailis, & Philip Levis

In Preparation December 10, 2018, SCEC Contribution #8971

Seismology has continuously recorded ground motion spanning up to decades. Blind, uninformed search for similar signal waveforms within this continuous data can detect small earthquakes missing from earthquake catalogs, yet doing so with naive approaches is computationally infeasible. We present results from an improved version of the Fingerprint And Similarity Thresholding (FAST) algorithm, an unsupervised data-mining approach to earthquake detection, now available as open-source software. We use FAST to search for small earthquakes in 6 to 11 years of continuous data from 27 channels over an 11-station local seismic network near the Diablo Canyon nuclear power plant (DCPP) in central California. FAST detected 4,554 earthquakes in this data set with a 7.5% false detection rate: 4,134 of the detected events were previously cataloged earthquakes located across California, and 420 were new local earthquake detections with magnitudes -0.3 <= M_L <= 2.4, of which 224 events were located near the seismic network. Although seismicity rates are low, this study confirms that nearby faults are active. This example shows how seismology can leverage recent advances in data mining algorithms, along with improved computing power, to extract useful additional earthquake information from long-duration continuous data sets.

Citation
Yoon, C., Bergen, K., Rong, K., Elezabi, H., Ellsworth, W. L., Beroza, G. C., Bailis, P., & Levis, P. (2018). Unsupervised large-scale data mining for similar earthquake detection. Bulletin of the Seismological Society of America, (in preparation).

Related Projects & Working Groups
Mining Seismic Wavefields, Seismology