Seismic Soundoff

• Digital Twins and Generative AI in Subsurface Geophysics

  "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. Read Felix's article in The Leading Edge, "President's Page: Digital twins in the era of generative AI," at https://doi.org/10.1190/tle42110730.1. GUEST BIO Felix J. Herrmann earned his Ph.D. in engineering physics from Delft University of Technology in 1997, followed by research appointments at Stanford and MIT. He later joined the University of British Columbia faculty in 2002 and moved to the Georgia Institute of Technology in 2017, where he is the Georgia Research Alliance Scholar Chair in Energy with cross-appointments across multiple schools. Dr. Herrmann leads a cross-disciplinary research program in computational imaging, spanning seismic and medical applications, and is recognized for innovations in machine learning, optimization, and high-performance computing that have reduced costs in seismic data acquisition and imaging. A past SEG Distinguished Lecturer and recipient of the SEG Reginald Fessenden Award, he directs the Seismic Laboratory for Imaging and Modeling and co-founded the Center for Machine Learning for Seismic (ML4Seismic) to advance AI-assisted seismic imaging and reservoir monitoring through industry collaboration.

  --------  

  23:25

  --------

  23:25
• Building Geophysical Capacity in Latin America

  "South America is a region with great potential in terms of energy transition, mining, and geothermal. I would like to be part of the next major discoveries in critical minerals and contribute to new technologies for future generations." Ana Curcio shares her journey from academia to industry and highlights the growing role of geophysics in South America’s energy and resource development. She explains the challenges of lithium brine exploration, the promise of geothermal energy, and the importance of connecting geophysics with engineering. Her insights show how geophysicists can play a key role in sustainable resource management and the energy transition. Read her article, "President's Page: Resources and geophysical opportunities in South America," on the SEG Library at https://doi.org/10.1190/tle41040228.1. KEY TAKEAWAYS > Geophysics must integrate with engineering to move exploration into production and add value to resource development. > Lithium brine and geothermal exploration in South America present both technical challenges and major opportunities for innovation. > Building stronger geophysical capacity in Latin America requires investment, education, and closer collaboration with local societies. GUEST BIO Ana Curcio is a Consultant at Proingeo SA and Professor at Buenos Aires University. She earned a Doctor of Engineering and has more than 15 years of experience in hydrocarbons, lithium, and mining. A former SEG Director-at-Large, she has held multiple leadership roles within SEG and currently serves on the board of the Argentinean Association of Petroleum Geologists and Geophysicists. Ana specializes in multiphysics integration for reservoir monitoring, brine prospecting, and anisotropy studies. She is fluent in Spanish, English, Portuguese, and Chinese.

  --------  

  23:26

  --------

  23:26
• The Next Decade of AI in Seismic Imaging

  "Physics-based approaches are like solving a puzzle with a set of rules. Data-driven geophysics is more like giving the puzzle to a computer that can learn the rules itself." Amine Ourabah shares how data-driven geophysics is transforming our understanding of the subsurface by combining physics with the power of machine learning. He explains how new tools, such as nimble nodes and distributed acoustic sensing, are making seismic imaging faster, cheaper, and more accessible across various industries, including oil and gas, geothermal, and carbon storage. Amine also highlights the importance of curiosity, adaptability, and simplicity in shaping the next generation of geophysicists and technologies. Read the September issue of The Leading Edge that features a special section about data-driven geophysics at https://library.seg.org/toc/leedff/44/9. KEY TAKEAWAYS > Data-driven methods reduce uncertainty, speed up workflows, and make seismic imaging more affordable for industries with limited budgets. > Advances in sensing technology and open data sharing are fueling breakthroughs in AI-driven geophysics. > Curiosity, adaptability, and strong fundamentals in physics and data science are essential skills for future geophysicists. GUEST BIO Amine Ourabah serves as Chief Geophysicist at STRYDE’s London office, where he leads a world-class team of imaging experts and drives the company’s data analytics strategy. He focuses on evolving STRYDE’s technology to deliver faster, leaner, and more accurate subsurface insights, particularly in support of the rapidly expanding renewables sector. THIS EPISODE SPONSORED BY KATALYST DATA MANAGEMENT Katalyst Data Management provides the only integrated, end-to-end subsurface data management solution for the oil and gas industry. Its employees operate in North America, Europe, Asia-Pacific, and South America and are dedicated to optimizing the value of subsurface data, including seismic and well data. Katalyst enables clients’ digital transformation of E&P data with digitizing services and digital transformation consulting. Learn more at https://katalystdm.com. THIS EPISODE SPONSORED BY STRYDE STRYDE is the world’s premier provider of ultra-lightweight seismic nodes, revolutionizing high-density subsurface imaging by making it faster, more cost-effective, and environmentally sustainable. Serving industries from oil and gas, geothermal, mining, and CCUS to academic research, STRYDE combines advanced technology, innovative exploration solutions, and expert data processing services to deliver actionable subsurface intelligence like never before. Discover STRYDE at https://stryde.io.

  --------  

  26:33

  --------

  26:33
• How Distributed Chemical Sensing Could Rewrite the Rules of Risk Management

  “Distributed chemical sensing really is the next frontier in fiber-optic monitoring. It adds a new dimension by directly connecting chemical changes in the environment to signals we can read.” Distributed chemical sensing (DCS) is an emerging technology that utilizes fiber optics to measure chemical changes over long distances in real-time. Authors Christian Totland, Thomas Dylan Mikesell, and Peter James Thomas join host Andrew Geary to discuss their new paper, "Distributed chemical sensing: An unexplored frontier in urban, industrial, and environmental monitoring." Unlike traditional point sensors, which only capture data at one location, DCS has the potential to provide continuous chemical information with both high spatial and temporal resolution. This innovation could transform how we monitor pipelines, groundwater, and industrial sites, while also opening new opportunities for collaboration between geophysics, chemistry, and material science. KEY TAKEAWAYS > DCS can detect leaks, contamination, and chemical changes directly, offering more accurate monitoring than pressure or temperature proxies. > The technology is still in its early stages, which means there are many opportunities for research, innovation, and interdisciplinary collaboration. > If developed further, DCS could provide affordable, real-time monitoring for critical infrastructure and environmental systems worldwide. LINKS * Christian Totland, Thomas Dylan Mikesell, and Peter James Thomas, (2025), "Distributed chemical sensing: An unexplored frontier in urban, industrial, and environmental monitoring," The Leading Edge 44: 598–605. - https://doi.org/10.1190/tle44080598.1 * Learn more about this special section on urban and infrastructure geophysics - https://library.seg.org/doi/10.1190/tle44080587.1 * Listen to Haipeng Li's interview (also from this special section) - https://seg.org/podcasts/episode-271-the-low-cost-seismic-revolution-already-buried-in-your-city/

  --------  

  26:46

  --------

  26:46
• The Low-Cost Seismic Revolution Already Buried in Your City

  "By mapping fiber optic cables accurately, we can transform them into dense seismic arrays. This opens the door to city-scale imaging and monitoring." Haipeng Li explains how distributed acoustic sensing (DAS) can turn existing urban fiber optic cables into powerful seismic arrays for near-surface imaging and monitoring. By using everyday traffic and ambient noise, his team can track groundwater changes, detect geohazards, and study fault structures without costly field deployments. This approach offers a new way for geophysicists, engineers, and city planners to work together for safer, more resilient urban environments. KEY TAKEAWAYS > Existing fiber optic cables can be transformed into dense, city-scale seismic arrays using DAS technology. > Vehicle-induced seismic waves provide highly repeatable data for monitoring small subsurface changes, while ambient noise helps extend imaging depth. > Urban DAS monitoring can reveal how infrastructure affects groundwater recharge and can support hazard assessment and infrastructure planning. GUEST BIO Haipeng Li is a third-year Ph.D. candidate in the Geophysics Department at Stanford University, advised by Biondo Biondi in the Stanford Earth Imaging Project (SEP). His research centers on spatiotemporal subsurface monitoring, with a focus on developing efficient and robust time-lapse seismic waveform inversion methods and uncertainty quantification approaches. He applies these techniques to real-world challenges such as geological CO2 sequestration for the energy transition and groundwater monitoring in urban environments, often leveraging Distributed Acoustic Sensing (DAS) data. He is a student member of the AGU, SSA, and SEG. LINKS * Haipeng Li, Jingxiao Liu, and Biondo L. Biondi, (2025), "Near-surface imaging and monitoring enabled by urban distributed acoustic sensing seismic arrays," The Leading Edge 44: 588–597. - https://doi.org/10.1190/tle44080588.1

  --------  

  20:27

  --------

  20:27

More Science podcasts

Trending Science podcasts

About Seismic Soundoff