TY - JOUR
T1 - Automated time-window selection based on machine learning for full-waveform inversion
AU - Chen, Yangkang
AU - Hill, Judith C.
AU - Lei, Wenjie
AU - Lefebvre, Matthieu
AU - Bozdag, Ebru
AU - Komatitsch, Dimitri
AU - Tromp, Jeroen
N1 - Funding Information:
This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under contract DE-AC05-00OR22725. The spectral-element software package SPECFEM3D_GLOBE used for simulating the seismograms and the benchmark window selection software package FLEXWIN used in this article are freely available via the Computational Infrastructure for Geodynamics (CIG; geodynamics.org).
Publisher Copyright:
© 2017 SEG.
PY - 2017/8/17
Y1 - 2017/8/17
N2 - Due to increased computational capabilities afforded by modern and future computer architectures, the seismology community is demanding a more comprehensive understanding of full waveform information from recorded seismic data. Full waveform inversion seeks to match observed seismic data with synthesized seismograms by iteratively updating subsurface model parameters. Synthetic data are generated by solving the seismic wave equation using an effective and efficient numerical algorithm. In order to ensure inversion accuracy and stability, both synthesized and observed seismograms must be carefully pre-processed. More specifically, when synthetic and observed data have a large waveform mismatch during the initial iterations, waveforms should be carefully selected for calculating the misfit gradient in order to avoid instability. We introduce a fully automated algorithm based on machine learning (ML) to intelligently select time windows for calculating the misfit between observed and synthetic seismograms. The training dataset can be prepared using time windows obtained based on the FLEXWIN method, in which selection parameters are finely tuned. Results show that automatically selected time windows are of sufficiently high quality compared with the benchmark FLEXWIN method.
AB - Due to increased computational capabilities afforded by modern and future computer architectures, the seismology community is demanding a more comprehensive understanding of full waveform information from recorded seismic data. Full waveform inversion seeks to match observed seismic data with synthesized seismograms by iteratively updating subsurface model parameters. Synthetic data are generated by solving the seismic wave equation using an effective and efficient numerical algorithm. In order to ensure inversion accuracy and stability, both synthesized and observed seismograms must be carefully pre-processed. More specifically, when synthetic and observed data have a large waveform mismatch during the initial iterations, waveforms should be carefully selected for calculating the misfit gradient in order to avoid instability. We introduce a fully automated algorithm based on machine learning (ML) to intelligently select time windows for calculating the misfit between observed and synthetic seismograms. The training dataset can be prepared using time windows obtained based on the FLEXWIN method, in which selection parameters are finely tuned. Results show that automatically selected time windows are of sufficiently high quality compared with the benchmark FLEXWIN method.
UR - http://www.scopus.com/inward/record.url?scp=85093345416&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093345416&partnerID=8YFLogxK
U2 - 10.1190/segam2017-17734162.1
DO - 10.1190/segam2017-17734162.1
M3 - Conference article
AN - SCOPUS:85093345416
SN - 1052-3812
SP - 1604
EP - 1609
JO - SEG Technical Program Expanded Abstracts
JF - SEG Technical Program Expanded Abstracts
T2 - Society of Exploration Geophysicists International Exposition and 87th Annual Meeting, SEG 2017
Y2 - 24 September 2017 through 29 September 2017
ER -