“Generative modeling is a game-changer. We can now capture high-dimensional statistics that we could never have captured in the past.”
Felix Herrmann explains how digital twins and generative AI are reshaping subsurface geophysics. He highlights the importance of open-source tools, multimodal data, and uncertainty-aware models for better decision-making in energy and storage projects. By combining physics with AI, his work shows how geophysics can move beyond silos and create more reliable and efficient solutions.
Key Takeaways
- Digital twins informed by multimodal data can reduce uncertainty and improve reservoir management.
- Open-source tools and agreed benchmarks are essential for accelerating innovation in geophysics.
- Combining physics-based models with generative AI creates robust, practical solutions for complex subsurface challenges.
Related Links
- Felix J. Herrmann, (2023), “President’s Page: Digital twins in the era of generative AI,” The Leading Edge 42: 730–732.
- Center for Machine Learning for Seismic Industry Partners Program (ML4Seismic)
Guest Bio
Felix J. Herrmann graduated from Delft University of Technology in 1992 and earned his Ph.D. in engineering physics there in 1997. After completing research appointments at Stanford University and the Massachusetts Institute of Technology, he joined the faculty of the University of British Columbia in 2002. In 2017, he moved to the Georgia Institute of Technology, where he now holds the Georgia Research Alliance Scholar Chair in Energy, with cross-appointments in the Schools of Earth & Atmospheric Sciences, Computational Science & Engineering, and Electrical & Computer Engineering.
Dr. Herrmann leads a cross-disciplinary research program in computational imaging, spanning seismic and, more recently, medical imaging. He is widely recognized for addressing complex challenges in the imaging sciences by adapting methods from randomized linear algebra, PDE-constrained and convex optimization, high-performance computing, machine learning, and uncertainty quantification. His innovations have delivered significant cost savings in industrial time-lapse seismic data acquisition and wave-equation–based imaging.
In 2019, he delivered the SEG Distinguished Lecture “Sometimes it pays to be cheap – Compressive time-lapse seismic data acquisition” on a global tour. The following year, he received the SEG Reginald Fessenden Award for his contributions to seismic data acquisition with compressive sensing. At Georgia Tech, he directs the Seismic Laboratory for Imaging and Modeling and co-founded the Center for Machine Learning for Seismic (ML4Seismic), which fosters industry partnerships to advance AI-assisted seismic imaging, interpretation, analysis, and time-lapse monitoring.
Download this Episode
Please visit this page to download this episode as an .MP3 file.
Show Credits
Andrew Geary at TreasureMint hosted, edited, and produced this episode. The SEG podcast team comprises Robin Dupre, Kathy Gamble, and Ally McGinnis.
If you have episode ideas or feedback for the show or want to sponsor a future episode, email the show at [email protected].
