Japan Geoscience Union Meeting 2023

Presentation information

[J] Online Poster

S (Solid Earth Sciences ) » S-TT Technology & Techniques

[S-TT44] Seismic Big Data Analysis Based on the State-of-the-Art of Bayesian Statistics

Mon. May 22, 2023 10:45 AM - 12:15 PM Online Poster Zoom Room (6) (Online Poster)

convener:Hiromichi Nagao(Earthquake Research Institute, The University of Tokyo), Aitaro Kato(Earthquake Research Institute, the University of Tokyo), Keisuke Yano(The Institute of Statistical Mathematics), Takahiro Shiina(National Institute of Advanced Industrial Science and Technology)

On-site poster schedule(2023/5/21 17:15-18:45)

10:45 AM - 12:15 PM

[STT44-P06] Single-station Seismic Event Classification Based on a Modified Deep Embedded Clustering Architecture and its Application to Harrison County, Eastern Ohio

*Jeffrey Michael Church1,2, Dongdong Yao3,2, Yihe Huang2, Zefeng Li4,5 (1.Graduate School of Information Science and Technology, the Univ. of Tokyo, 2.Dept. of Earth and Environmental Sciences, College of Literature, Science, and the Arts, Univ. of Michigan, 3.National Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, 4.Laboratory of Seismology and Physics of Earth’s Interior, School of Earth and Space Science, Univ. of Science and Technology of China, 5.Mengcheng National Geophysical Observatory, Univ. of Science and Technology of China)

We present a semi-automated pipeline for identifying and classifying different kinds of seismic events recorded in continuous seismograms. The pipeline first utilizes the well-developed PhaseNet picker to identify events of interest, and subsequently applies a modified Deep Embedded Clustering (DEC) architecture to classify them. DEC is a self-supervised deep neural network capable of learning the salient features of a dataset while simultaneously clustering the dataset using those features, eliminating the need for manual feature engineering and labeled dataset preparation. In addition, only minimal data processing is required, adding to the convenience of the method. We test this workflow using a unique dataset recorded by a single station, TA.O53A, located near Harrison County in Eastern Ohio. The dataset contains several well-studied hydraulic fracturing induced earthquake sequences and numerous blasting events. Using the proposed pipeline, we can separate earthquakes from blasting events in the dataset, and successfully uncover active episodes of induced seismicity. These results, coupled with the pipeline’s convenience, indicate the pipeline’s potential as a powerful tool for exploring seismic event occurrence patterns, especially in less-studied regions with sparse or non-existent catalogs.