Deep Learning for Low-Frequency Extrapolation of Multicomponent Data in Elastic FWI
- 14 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-11
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 “artificial” 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 2–4 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.Keywords
All Related Versions
Funding Information
- Total
- SEG Scholarships
- MIT MathWorks Science Fellowship
This publication has 50 references indexed in Scilit:
- Multiparameter full-waveform inversion: Marine and land examplesThe Leading Edge, 2013
- Full waveform inversion and distance separated simultaneous sweeping: a study with a land seismic data setGeophysical Prospecting, 2012
- Finite-difference modeling experiments for seismic interferometryGeophysics, 2011
- Elastic full waveform inversion of multicomponent ocean-bottom cable seismic data: Application to Alba Field, U. K. North SeaGeophysics, 2010
- Frequency-Domain Elastic Full Waveform Inversion Using the New Pseudo-Hessian Matrix: Experience of Elastic Marmousi-2 Synthetic DataBulletin of the Seismological Society of America, 2008
- Marmousi2: An elastic upgrade for MarmousiThe Leading Edge, 2006
- Empirical Relations between Elastic Wavespeeds and Density in the Earth's CrustBulletin of the Seismological Society of America, 2005
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Nonlinear two-dimensional elastic inversion of multioffset seismic dataGeophysics, 1987
- A strategy for nonlinear elastic inversion of seismic reflection dataGeophysics, 1986