Short Course

SC-15: Introduction to Scientific Machine Learning for Geophysicists

Monday, 25 August | 8:00 a.m.–5:00 p.m. | George R. Brown Convention Center

Sponsored by the Society of Exploration Geophysicists (SEG)

This one-day course will cover theoretical concepts associated with physics-informed neural networks and neural operators. Subsequently, these methods will be used to solve geophysical forward and inverse problems, followed by emerging research trends related to the topic.

The following topics will be covered during this short course:
• Introduction to PINNs
• PINNs for solving forward and inverse problems in Geophysics
• Introduction to Neural Operators
• Solution of forward and inverse problems using neural operators
• Physics-informed Neural Operators
• Emerging trends in Scientific Machine Learning

Co-Leaders

Guest Speakers

Course Leader(s)

The course is targeted toward computational geophysicists who have some familiarity with neural networks and programming in Python.
The rapid evolution of machine learning technologies has revolutionized numerous fields, including geophysics, by offering advanced solutions to complex problems that were previously intractable. Geophysical modeling and inversion, critical to the exploration of Earth’s subsurface, have significantly benefited from these advancements. The core objective of this course is to explain basic theories of scientific machine learning (SciML) and equip participants with skills in implementing these tools to solve partial differential equations (PDEs) and the associated inverse problems, with a particular focus on eikonal and wave equations.