Arnab Dhara discusses his paper, “Physics-guided deep autoencoder to overcome the need for a starting model in full-waveform inversion,” in the June issue of The Leading Edge.
In recent years, physics-driven machine learning applications have been proposed wherein physics is integrated into the data-driven model to improve the ability of the machine learning methods to generalize and potentially overcome gaps in the physical theories. Solving geophysical problems by using hybrid physics-based and data-driven solutions has the potential to address simplifications in the physical models as well as overcome shortcomings with training data sets. Ultimately, they may refine and improve our understanding of the physics underpinning data sets.
In this conversation, Arnab proposes employing deep learning as a regularization in full-waveform inversion. He explains why physics-based solutions with machine learning are challenging to develop, how he made it possible to train the network without known answers, and why he tested his approach with the Marmousi and SEAM models. Arnab also shares why this research took over 20 years to build on the initial idea and how he used full-waveform inversion without a starting model. This is a cutting-edge conversation that may represent the future of FWI.
- Arnab Dhara and Mrinal K. Sen, (2022), “Physics-guided deep autoencoder to overcome the need for a starting model in full-waveform inversion,” The Leading Edge 41: 375–381.
- Simon Shaw, Sam Kaplan, and Chengbo Li, (2022), “Introduction to this special section: Physics-driven machine learning,” The Leading Edge 41: 374–374.
- Read the June 2022 special section: Physics-driven machine learning
Subscribers can read the full articles in the SEG Library, and abstracts are always free.
SEG produces Seismic Soundoff to benefit its members, and the scientific community and inform the public on the value of geophysics. To show your support for the show, please leave a 5-star rating on Apple Podcasts and Spotify. It takes less than five seconds to leave a 5-star rating and is the number one action you can take to show your appreciation for this free resource. And follow the podcast while you are on the app to be notified when each new episode releases.
Original music created by Zach Bridges. This episode was hosted, edited, and produced by Andrew Geary at 51 features, LLC. Thank you to the SEG podcast team: Jennifer Cobb, Kathy Gamble, and Ally McGinnis.