loading page

Graph-partitioning based convolutional neural network for earthquake detection using a seismic array
  • +4
  • Keisuke Yano,
  • Takahiro Shiina,
  • Sumito Kurata,
  • Aitaro Kato,
  • Fumiyasu Komaki,
  • Shin'ichi Sakai,
  • Naoshi Hirata
Keisuke Yano
The institute of Statistical Mathematics, The institute of Statistical Mathematics

Corresponding Author:[email protected]

Author Profile
Takahiro Shiina
Geological Survey of Japan, National Institute of Advanced Industrial Science and Technology, Geological Survey of Japan, National Institute of Advanced Industrial Science and Technology
Author Profile
Sumito Kurata
The University of Tokyo, The University of Tokyo
Author Profile
Aitaro Kato
Earthquake Research Institute, The University of Tokyo, Earthquake Research Institute, The University of Tokyo
Author Profile
Fumiyasu Komaki
University of Tokyo, University of Tokyo
Author Profile
Shin'ichi Sakai
University of Tokyo, University of Tokyo
Author Profile
Naoshi Hirata
University of Tokyo, University of Tokyo
Author Profile

Abstract

We present a deep-learning approach for earthquake detection using waveforms from a seismic array consisting of multiple seismographs. Although automated, deep-learning earthquake detection techniques have recently been developed at the single-station level, they have potential difficulty in reducing false detections owing to the presence of local noise inherent to each station. Here, we propose a deep-learning-based approach to efficiently analyze the waveforms observed by a seismic array, whereby we employ convolutional neural networks in conjunction with graph partitioning to group the waveforms from seismic stations within the array. We then apply the proposed method to waveform data recorded by a dense, local seismic array in the regional seismograph network around the Tokyo metropolitan area, Japan. Our method detects more than $97$ percent of the local seismicity catalogue, with less than $4$ percent false positive rate, based on an optimal threshold value of the output earthquake probability of $0.61$. A comparison with conventional deep-learning-based detectors demonstrates that our method yields fewer false detections for a given true earthquake detection rate. Furthermore, the current method exhibits the robustness to poor-quality data and/or data that are missing at several stations within the array. Synthetic tests demonstrate that the present method has the potential to detect earthquakes even when half of the normally available seismic data are missing. We apply the proposed method to analyze 1-hour-long continuous waveforms and identify new seismic events with extremely low signal-to-noise ratios that are not listed in existing catalogs. (241words)
May 2021Published in Journal of Geophysical Research: Solid Earth volume 126 issue 5. 10.1029/2020JB020269