[S-TT44] 最先端ベイズ統計学が拓く地震ビッグデータ解析

[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 Church^1,2、Dongdong Yao^3,2、Yihe Huang²、Zefeng Li^4,5 (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.