Abstract
The discrimination between earthquakes and explosions is a serious issue in seismic signal analysis. This paper proposes a seismic discrimination method using support vector machine (SVM), wherein the amplitudes of the P-wave and the S-wave of the seismic signals are selected as feature vectors. Furthermore, to improve the seismic discrimination performance using a heterodyne laser interferometer for seismic wave detection, the Hough transform is applied as a compensation method for the periodic nonlinearity error caused by the frequency-mixing in the laser interferometric seismometer. In the testing procedure, different kernel functions of SVM are used to discriminate between earthquakes and explosions. The outstanding performance of a laser interferometer and Hough transform method for precision seismic measurement and nonlinearity error compensation is confirmed through some experiments using a linear vibration stage. In addition, the effectiveness of the proposed discrimination method using a heterodyne laser interferometer is verified through a receiver operating characteristic curve and other performance indices obtained from practical experiments.
Highlights
The discrimination between earthquakes and explosions is a serious issue in seismology.Seismometers at seismic stations record all types of earth vibrations in the region without the ability to clarify their origin
A support vector machine (SVM)-based seismic discrimination method is proposed by using the amplitudes of the P-wave and the S-wave as the feature vectors
Hough transformation method was applied to compensate for the nonlinearity error of the measurements and to obtain accurate feature vectors from the body wave
Summary
The discrimination between earthquakes and explosions is a serious issue in seismology. The precisely measured seismic data after the compensation of the nonlinearity error in laser interferometer is used as a test data for the discrimination of earthquake and explosion. To discriminate between earthquakes and explosions, support vector machine (SVM) is applied as a machine learning model, and the amplitudes of the P-wave and the S-wave of the seismic signals are used to form the feature vectors, simplifying the early data processing procedure and the computing process in building the SVM classifier. Owing to the wide dynamic range and high resolution, the microseismic waves measured by a laser interferometer can be used as a seismic data for SVM classifier. The amplitudes of the P-wave and the S-wave could be measured more precisely using Hough transformation-based nonlinearity error compensation in a laser interferometer.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
