The importance of transfer learning in seismic modeling and imaging

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 have used these data, consisting of shot records or velocity models, to pretrain 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 pretrained neural network, we apply transfer learning to fine-tune this pretrained 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 fine-tuning to using only a small fraction of high-fidelity data, we gain processing the current survey while using information from nearby surveys. We examined this principle by removing surface-related multiples and ghosts from shot records and the effects of numerical dispersion from migrated images and wave simulations.

Surface-related multiple elimination with deep learning

“…The required runtime in our experiments may not be less than the time needed to apply EPSI, but it might be computationally favorable when applied in a 3D seismic survey. Also, in case there exists pairs of raw and processed (via EPSI) shot records from a proximal survey, by pre-training a neural network on the mentioned data, we can significantly reduce the time needed to fine-tune the network to the pertinent survey (Siahkoohi et al, 2019).…”

“…This can become challenging because of the Earth's heterogeneity and differing acquisition settings. While we have successfully demonstrated that transfer learning (Yosinski et al, 2014) can be used in situations where the neural network is initially trained on data from a proximal survey (Siahkoohi et al, 2019), we chose in this contribution to work with half of the shot records in the survey for training as a proof of concept to see whether neural networks can handle the intricacies of field data.…”

“…Machine learning is rapidly attracting interest in the exploration seismology research community. In the past few years, there has been numerous attempts to deploy deep learning algorithms to address problems in active research areas in the field of seismic, including but not limited to pre-stack seismic data processing (Mikhailiuk and Faul, 2018;Siahkoohi et al, 2018a;Ovcharenko et al, 2018;Sun and Demanet, 2018;Siahkoohi et al, 2018b), modeling and imaging (Moseley et al, 2018;Siahkoohi et al, 2019;Rizzuti et al, 2019), and inversion (Lewis and Vigh, 2017;Araya-Polo et al, 2018;Richardson, 2018;Das et al, 2018;Kothari et al, 2019).…”

Seismic data interpolation using deep learning with generative adversarial networks

“…Siahkoohi et al . (2019) used transfer learning with GANs for seismic modelling and imaging applications. Li and Luo (2019) and Mosser et al .…”

“…Picetti et al (2018), Herrmann et al (2019), Oliveira et al (2019) and Kaur et al (2019aKaur et al ( , 2020 adopted GANs for seismic imaging applications. Siahkoohi et al (2019) used transfer learning with GANs for seismic modelling and imaging applications. Li and Luo (2019) and Mosser et al (2020) applied GANs for seismic inversion.…”