"Sometimes the traditional methods are way more effective or efficient in handling certain things. To succeed in this new paradigm, we need to build on our strong fundamentals and progress further."
Ivan Lim Chen Ning shares how data-driven methods are reshaping geophysics by challenging traditional workflows and opening new possibilities. He highlights the role of AI, machine learning, and fiber-optic sensing in improving seismic interpretation, imaging, and monitoring. His insights show how combining strong fundamentals with modern digital tools can help geophysicists solve problems more effectively.
Read the September issue of TLE about data-driven geophysics at https://library.seg.org/toc/leedff/44/9.
KEY TAKEAWAYS
> AI and data-driven tools open new paths. They help geophysicists move beyond traditional workflows to find faster and simpler solutions.
> Fiber-optic sensing changes monitoring. DAS provides continuous well data, replacing point sensors and revealing signals directly.
> Strong fundamentals still matter. Success comes from combining proven geophysical methods with modern digital skills.
GUEST BIO
Ivan Lim Chen Ning is an Earth Scientist – Fiber Optics at Chevron, where he analyzes Distributed Fiber Optic Sensing (DFOS) data and develops real-time algorithms for field applications. He applies deep learning and signal processing to improve DFOS workflows, advancing distributed acoustic sensing in the energy industry. A member of Chevron’s Emerging Leader 2024 cohort, Ivan is recognized for solving cross-disciplinary challenges and driving innovation to help secure energy for the future.
All content for Seismic Soundoff is the property of Society of Exploration Geophysicists (SEG) and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
"Sometimes the traditional methods are way more effective or efficient in handling certain things. To succeed in this new paradigm, we need to build on our strong fundamentals and progress further."
Ivan Lim Chen Ning shares how data-driven methods are reshaping geophysics by challenging traditional workflows and opening new possibilities. He highlights the role of AI, machine learning, and fiber-optic sensing in improving seismic interpretation, imaging, and monitoring. His insights show how combining strong fundamentals with modern digital tools can help geophysicists solve problems more effectively.
Read the September issue of TLE about data-driven geophysics at https://library.seg.org/toc/leedff/44/9.
KEY TAKEAWAYS
> AI and data-driven tools open new paths. They help geophysicists move beyond traditional workflows to find faster and simpler solutions.
> Fiber-optic sensing changes monitoring. DAS provides continuous well data, replacing point sensors and revealing signals directly.
> Strong fundamentals still matter. Success comes from combining proven geophysical methods with modern digital skills.
GUEST BIO
Ivan Lim Chen Ning is an Earth Scientist – Fiber Optics at Chevron, where he analyzes Distributed Fiber Optic Sensing (DFOS) data and develops real-time algorithms for field applications. He applies deep learning and signal processing to improve DFOS workflows, advancing distributed acoustic sensing in the energy industry. A member of Chevron’s Emerging Leader 2024 cohort, Ivan is recognized for solving cross-disciplinary challenges and driving innovation to help secure energy for the future.
The transformative role of LLMs in geophysics education
Seismic Soundoff
29 minutes 58 seconds
3 months ago
The transformative role of LLMs in geophysics education
“The knowledge we learn may not change. The way we learn will change very fast.”
Dr. Ge Jin explains how large language models are transforming the way geophysics is taught and learned, particularly by enhancing access to clear explanations and accelerating research. He shares why assessment must evolve and how allowing LLMs in coding classes, while focusing on physics and logic, helps students solve harder problems. The conversation explores prompt engineering, secure AI use in industry, transparent writing practices, and the opportunity to build an SEG library-powered model for cutting-edge knowledge.
KEY TAKEAWAYS
> Prompt power: Knowing how to ask AI the right way is becoming as important as knowing where to find the answer - daily practice builds skill and confidence
> Continuous learning boost: LLMs speed up literature research and concept review, letting geophysicists grasp new fields in hours instead of weeks
> Strategy ahead: Training AI on the SEG library could provide reliable, advanced knowledge, alongside company‑specific models that protect data and address language bias.
GUEST BIO
Dr. Ge Jin is Associate Professor of Geophysics and co-PI of Reservoir Characterization Project at Colorado School of Mines. His research focuses on Distributed Fiber-Optic Sensing (DFOS) applications in the fields of oil & gas, geothermal, CO2 sequestration, smart city, and earthquake hazard. He is also interested in machine-learning applications and seismic imaging. He obtained his Ph.D. in Geophysics from Columbia University in the City of New York, and dual B.S. in Geophysics and Computer Science from Peking University in Beijing. He worked as a research geophysicist in the oil industry for five years before joining Colorado School of Mines as a faculty member in 2019.
LINKS
* Read Ge Jin's article, "President's Page: The transformative role of large language models in geophysics education," at https://doi.org/10.1190/tle44050326.1
* Attend IMAGE '25 - https://www.imageevent.org/
* Learn more about the new podcast series, Inside IMAGE, presented by Seismic Soundoff - https://www.imageevent.org/podcast
Seismic Soundoff
"Sometimes the traditional methods are way more effective or efficient in handling certain things. To succeed in this new paradigm, we need to build on our strong fundamentals and progress further."
Ivan Lim Chen Ning shares how data-driven methods are reshaping geophysics by challenging traditional workflows and opening new possibilities. He highlights the role of AI, machine learning, and fiber-optic sensing in improving seismic interpretation, imaging, and monitoring. His insights show how combining strong fundamentals with modern digital tools can help geophysicists solve problems more effectively.
Read the September issue of TLE about data-driven geophysics at https://library.seg.org/toc/leedff/44/9.
KEY TAKEAWAYS
> AI and data-driven tools open new paths. They help geophysicists move beyond traditional workflows to find faster and simpler solutions.
> Fiber-optic sensing changes monitoring. DAS provides continuous well data, replacing point sensors and revealing signals directly.
> Strong fundamentals still matter. Success comes from combining proven geophysical methods with modern digital skills.
GUEST BIO
Ivan Lim Chen Ning is an Earth Scientist – Fiber Optics at Chevron, where he analyzes Distributed Fiber Optic Sensing (DFOS) data and develops real-time algorithms for field applications. He applies deep learning and signal processing to improve DFOS workflows, advancing distributed acoustic sensing in the energy industry. A member of Chevron’s Emerging Leader 2024 cohort, Ivan is recognized for solving cross-disciplinary challenges and driving innovation to help secure energy for the future.
