Paper Info
Title
Deep Learning for Low-Frequency Extrapolation of Multicomponent Data in Elastic FWI
Abstract
Full-waveform inversion (FWI) strongly depends on an accurate starting model to succeed. This is particularly true in the elastic regime: The cycle-skipping phenomenon is more severe in elastic FWI compared to acoustic FWI due to the short S-wave wavelength. In this article, we extend our work on extrapolated FWI (EFWI) by proposing to synthesize the low frequencies of multicomponent elastic seismic records and use those & x201C;artificial & x201D; low frequencies to seed the frequency sweep of elastic FWI. Our solution involves deep learning: we can either train the same convolutional neural network (CNN) on two training datasets, one with vertical components and one with horizontal components of particle velocities, or train with two components together, to extrapolate the low frequencies of elastic data for 2-D elastic FWI. The architecture of this CNN is designed with a large receptive field by dilated convolution. Numerical examples on the Marmousi2 model show that the 2 & x2013;4 Hz low-frequency data extrapolated from band-limited data above 4 Hz provide good starting models for elastic FWI of P- and S-wave velocities. In addition, we study the generalization ability of the proposed neural network from acoustic to elastic data. For elastic test data, collecting the training dataset by elastic simulation shows better extrapolation accuracy than acoustic simulation, i.e., a smaller generalization gap.
Year
DOI
Venue
2022
10.1109/TGRS.2021.3135790
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Keywords
DocType
Volume
Data models, Extrapolation, Convolution, Deep learning, Training, Acoustics, Convolutional neural networks, Computational seismology, controlled source seismology, neural networks, numerical solutions, waveform inversion
Journal
60
ISSN
Citations 
PageRank 
0196-2892
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Hongyu Sun100.34
Laurent Demanet275057.81