Extrapolation of Low Wavenumbers in FWI Gradients by a Deep Convolutional Neural Network

Pavel Plotnitskii, Vladimir Kazei, Oleg Ovcharenko, Daniel Peter, Tariq Ali Alkhalifah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Seismic full-waveform inversion (FWI) as a non-linear, iterative optimization benefits from low-frequency data to constrain low-wavenumber model updates and to improve model convergence. However, low-frequency data is often limited in active seismic acquisitions. Using a model-domain approach, we attempt to generate low-wavenumber model updates from existing gradients at higher frequencies within a deep learning framework. Namely, we train a convolutional neural network (CNN) to provide missing FWI model updates associated with low-frequency data from higher frequency updates. We test this technique on the Marmousi II model and quantify the goodness of fit of the inversion result using an R2 score model misfit. We observe that predicted low-wavenumber updates differ significantly from model updates using actual low-frequency data. However, comparing the final models of the corresponding multi-scale strategy FWIs we find that resulting differences are negligible.
Original languageEnglish (US)
Title of host publicationEAGE 2020 Annual Conference & Exhibition Online
PublisherEuropean Association of Geoscientists & Engineers
DOIs
StatePublished - Dec 2020

Fingerprint Dive into the research topics of 'Extrapolation of Low Wavenumbers in FWI Gradients by a Deep Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this