Abstract
The power of generative models have only recently been realized, especially within many well known applications. From realistic images to crafting noval text, the generative model, which stores complex conditional distributions, is a source of wonder, as well as controversy (like copyright issues). Sifting through the cloud of hype, I will explore with you the fundamental concepts behind this power tool, and focus on how we apply it in Earth discovery. We will delve into the concept of priors (expectations) and examine how generative models can incorporate them into solving inverse problems. Specifically, I will discuss the use of the Diffusion model—the engine behind DALL-E 3—in a method we call DiffusionFWI, and the Generative Pre-trained Transformer (GPT)—the engine behind ChatGPT—in a technique we refer to as VelocityGPT, to enhance our ability to invert for the Earth's elastic properties. I asked ChatGPT a question: What kind of a world would we live in without the contribution of Earth Scientists? and this generative model politely responded, and I summarize here: Not a good one, "leading to severe ecological, social, and economic consequences".
Biography
Tariq A. Alkhalifah is a professor in the Physical Sciences and Engineering Division. He joined KAUST in June 2009. Before he joined KAUST, Alkhalifah was research professor and director of the Oil and Gas Research Institute at King Abdulaziz City for Science & Technology (KACST). Previously, he held the positions of associate research professor, assistant research professor, and research assistant at KACST. From 1996 to 1998, Alkhalifah served as a postdoctoral researcher for the Stanford Exploration Project at Stanford University, United States. He received the J. Clarence Karcher Award from the Society of Exploration Geophysicists (SEG) in 1998 and the Conrad Schlumberger Award from the European Association for Geoscientists & Engineers (EAGE) in 2003, and served as an honorary lecturer for the SEG in 2011. He also received the Virgil Kauffman Gold medal from the SEG in 2023. Alkhalifah received his doctoral degree in geophysics and his master’s degree in geophysical engineering, both from the Colorado School of Mines, United States. He holds a bachelor’s degree in geophysics from King Fahd University of Petroleum and Minerals, Saudi Arabia.
Alkhalifah’s research interest include seismic imaging and waveform inversion in complex media, and recently his interest included the utilization of machine learning for such objectives.
Earth Science and Engineering, KAUST