Deep learning for low-frequency extrapolation from multioffset seismic data

Oleg Ovcharenko, Vladimir Kazei, Mahesh Kalita, Daniel Peter, Tariq Ali Alkhalifah

Research output: Contribution to journalArticlepeer-review

126 Scopus citations

Abstract

Low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties. However, it is challenging to acquire field data with an appropriate signal-to-noise ratio in the low-frequency part of the spectrum. We have extrapolated low-frequency data from the respective higher frequency components of the seismic wavefield by using deep learning. Through wavenumber analysis, we find that extrapolation per shot gather has broader applicability than per-trace extrapolation. We numerically simulate marine seismic surveys for random subsurface models and train a deep convolutional neural network to derive a mapping between high and low frequencies. The trained network is then tested on sections from the BP and SEAM Phase I benchmark models. Our results indicate that we are able to recover 0.25 Hz data from the 2 to 4.5 Hz frequencies. We also determine that the extrapolated data are accurate enough for FWI application.
Original languageEnglish (US)
Pages (from-to)R1001-R1013
Number of pages1
JournalGEOPHYSICS
Volume84
Issue number6
DOIs
StatePublished - Sep 6 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: We are grateful to G. Pratt and W. Mulder for their comments, X. Zhang who advised us on ML, and F. J Simons who shared his expertise on stochastic processes. We also give credit to T. V. Leuween, whose open-source FWI code was used as a building block in our inversion scheme (https://github.com/tleeuwen/SimpleFWI). We thank the members of the Seismic Modeling and Inversion group (SMI) and the Seismic Wave Analysis Group (SWAG) at King Abdullah University of Science and Technology (KAUST) for the constructive discussions. The research reported in this publication was supported by funding from KAUST.

Fingerprint

Dive into the research topics of 'Deep learning for low-frequency extrapolation from multioffset seismic data'. Together they form a unique fingerprint.

Cite this