The importance of transfer learning in seismic modeling and imaging

TitleThe importance of transfer learning in seismic modeling and imaging
Publication TypeSubmitted
Year of Publication2019
AuthorsAli Siahkoohi, Mathias Louboutin, Felix J. Herrmann
Keywordsdeep learning, Imaging, Modeling, private, SRME, transfer learning
Abstract

Accurate forward modeling is essential for solving inverse problems in exploration seismology. Unfortunately, it is often not possible to afford being physically or numerically accurate. To overcome this conundrum, we make use of raw and processed data from nearby surveys. We propose to use this data, consisting of shot records or velocity models, to pre-train a neural network to correct for the effects of, for instance, the free surface or numerical dispersion, both of which can be considered as proxies for incomplete or inaccurate physics. Given this pre-trained neural network, we apply transfer learning to finetune this pre-trained neural network so it performs well on its task of mapping low-cost, but low-fidelity, solutions to high-fidelity solutions for the current survey. As long as we can limit ourselves during finetuning to using only a small fraction of high-fidelity data, we gain processing the current survey while using information from nearby surveys. We demonstrate this principle by removing surface-related multiples and ghosts from shot records and the effects of numerical dispersion from migrated images and wave simulations

Notes

Submitted to GEOPHYSICS on February 5, 2019

URLhttps://slim.gatech.edu/Publications/Private/Submitted/2019/siahkoohi2019itl/siahkoohi2019itl.html
Citation Keysiahkoohi2019itl