Doctoral Dissertations

Keywords and Phrases

Convolutional Neural Network; Earthquake Classification; Machine Learning; Seismology; Shear Wave Splitting

Abstract

"During the past decades, applications of Machine Learning have been explosively developed to solve various academic and industrial problems, and over-human performance has been shown in diverse areas. In geophysical research, Machine Learning, especially Convolutional Neural Network (CNN), has been applied in numerous studies and demonstrated considerable potential. In this study, we applied CNN to solve two geophysical problems, ranking teleseismic shear splitting (SWS) measurements and classifying different types of earthquakes.

For ranking teleseismic SWS measurements, we utilized a 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 98.1% of human-selected measurements as acceptable and revealed ~30% additional measurements.

For classifying different types of earthquakes, we utilized a CNN to classify natural earthquakes, mine collapses, and explosions using seismic waveforms recorded by 287 stations in Shandong Province, China. Cross-validation is employed to scan the whole dataset, and the measurements with different labels between human and the CNN are manually assessed and kept, corrected, or abandoned in the dataset. Testing with the corrected dataset, the classification accuracies of the three types of events increase from 97.3% to 99.2% for earthquakes, from 84.9% to 95.8% for mine collapses, and from 93.6% to 98.1% for explosions"--Abstract, p. iv

Advisor(s)

Gao, Stephen S.

Committee Member(s)

Liu, Kelly H.
Smith, Ryan G.
Hu, Wenqing
Zhang, Guangzhi

Department(s)

Geosciences and Geological and Petroleum Engineering

Degree Name

Ph. D. in Geology and Geophysics

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2022

Pagination

ix, 53 pages

Note about bibliography

Includes_bibliographical_references_(pages 47-52)

Rights

© 2022 Yanwei Zhang, All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12210

Download

Share

 
COinS