Graph Convolution Networks for Seismic Events Classification Using Raw Waveform Data From Multiple Stations
- Authors
- Kim, Gwantae; Ku, Bonhwa; Ahn, Jae-Kwang; Ko, Hanseok
- Issue Date
- Nov-2021
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Adaptation models; Convolution; Convolution neural network (CNN); Convolutional neural networks; Data models; Earthquakes; Feature extraction; Neural networks; deep learning; graph convolution network (GCN); multiple station; seismic event classification
- Citation
- IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, v.19
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
- Volume
- 19
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/135976
- DOI
- 10.1109/LGRS.2021.3127874
- ISSN
- 1545-598X
- Abstract
- This letter proposes a multiple station-based seismic event classification model using a deep convolution neural network (CNN) and graph convolution network (GCN). To classify various seismic events, such as natural earthquakes, artificial earthquakes, and noise, the proposed model consists of weight-shared convolution layers, graph convolution layers, and fully connected layers. We employed graph convolution layers in order to aggregate features from multiple stations. Representative experimental results with the Korean peninsula earthquake datasets from 2016 to 2019 showed that the proposed model is superior to the single-station based state-of the-art methods. Moreover, the proposed model significantly reduced false alarms when using continuous waveforms of long duration. The code is available at.(1)
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholar.korea.ac.kr/handle/2021.sw.korea/135976)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.