Seismic wave propagation and inversion with Neural Operators | Zachary E. Ross

Speaker: Dr Zachary E. Ross, William H. Hurt Scholar and Assistant Professor of Geophysics at the Seismological Laboratory of the California Institute of Technology

Seismic waveform modeling is a powerful tool for determining earth structure models and unraveling earthquake rupture processes, but it is computationally expensive. We introduce a scheme to vastly accelerate these calculations with a recently developed machine learning paradigm called the neural operator. Once trained, these models can simulate a full wavefield for arbitrary velocity models at negligible cost. We use a U-shaped neural operator to learn a general solution operator to the elastodynamic wave equations from an ensemble of numerical simulations performed with random velocity models and source locations. We show that full waveform modeling with neural operators is nearly two orders of magnitude faster than conventional numerical methods, and more importantly, the trained model enables accurate simulation for arbitrary velocity models, source locations, and mesh discretization, even when distinctly different from the training dataset. The method also enables efficient full-waveform inversion with automatic differentiation.

This talk is part of the Liverpool Virtual Seminar Series on Data Intensive Science; more information can be found at https://indico.ph.liv.ac.uk/e/data_sc...

#datascience #bigdata #seminar #science #machinelearning #ai