Abstract Accepted to EAGE2025 Physics-Driven Self-Supervised Deep Learning for Free-Surface Multiple Elimination

I am pleased to announce that our paper, titled “Physics-Driven Self-Supervised Deep Learning for Free-Surface Multiple Elimination,” has been accepted for the upcoming EAGE2025. This research presents an approach that differs from traditional supervised learning methods - the DL model learns to effectively parameterize the free-surface multiple-free wavefield from the full wavefield by incorporating the underlying physics (the SRME equation) in the loss function. This, in turn, yields high-quality estimates without ever being shown any ‘ground truth’ data

This is a collaborative work with Dr. Jing Sun and Dr. Eric Verschuur from Delft University of Technology, and my colleague Dr. Ivan Vasconcelos. We look forward to presenting our findings to the global community and engaging in meaningful discussions at the conference.