Classification of Teleseismic Shear Wave Splitting Measurements: A Convolutional Neural Network Approach
Abstract
Shear wave splitting (SWS) analysis is widely used to provide critical constraints on crustal and mantle structure and dynamic models. In order to obtain reliable splitting measurements, an essential step is to visually verify all the measurements to reject problematic measurements, a task that is increasingly time consuming due to the exponential increase in the amount of data. In this study, we utilized a convolutional neural network (CNN) based method to automatically select reliable SWS measurements. The CNN was trained by human-verified teleseismic SWS measurements and tested using synthetic SWS measurements. Application of the trained CNN to broadband seismic data recorded in south central Alaska reveals that CNN classifies 97.0% of human selected measurements as acceptable, and revealed ∼30% additional measurements. To our knowledge, this is the first study to systematically explore the potential of a machine-learning based technique to assist with SWS analysis.
Recommended Citation
Y. Zhang and S. S. Gao, "Classification of Teleseismic Shear Wave Splitting Measurements: A Convolutional Neural Network Approach," Geophysical Research Letters, vol. 49, no. 12, article no. e2021GL097101, American Geophysical Union (AGU), Jun 2022.
The definitive version is available at https://doi.org/10.1029/2021GL097101
Department(s)
Geosciences and Geological and Petroleum Engineering
Keywords and Phrases
Convolutional Neural Network; Data Mining; Machine Learning; Seismic Anisotropy; Shear Wave Splitting
International Standard Serial Number (ISSN)
1944-8007; 0094-8276
Document Type
Article - Journal
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 2022 Wiley; American Geophysical Union, All rights reserved.
Publication Date
28 Jun 2022
Comments
IRIS Data Services are funded through the Seismological Facilities for the Advancement of Geoscience (SAGE) Award of the National Science Foundation under Cooperative Support Agreement EAR-1851048. The study was partially supported by the U.S. National Science Foundation under awards 1830644 and 1919789 to S.G.