Deep learning for low-frequency extrapolation from multioffset seismic data

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.

Citation

Ovcharenko, O., Kazei, V., Kalita, M., Peter, D., & Alkhalifah, T. (2019). Deep learning for low-frequency extrapolation from multioffset seismic data. GEOPHYSICS, 84(6), R1001–R1013. doi:10.1190/geo2018-0884.1

Sponsors

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.