In this talk we introduce algorithms that invert simulated gravity data to 3D subsurface rock/flow properties. The target application of these proposed algorithms is the prediction of subsurface CO2 plumes as a complementary tool for monitoring CO2 sequestration deployments. Each proposed algorithm outperforms traditional inversion methods and produces high-resolution, 3D subsurface reconstructions in near real-time. These results indicate that combining 4D surface gravity monitoring with deep learning techniques represents a low-cost, rapid, and non-intrusive method for monitoring CO2 storage sites.

报告人简介

Mauricio is a Senior Computer Scientist and Senior R&D Manager at TotalEnergies E&P R&T USA. He is also Adjunct Professor at the Earth Enviromental and Planetary Science Department of Rice University and lecturer with the Professional Science master's Program at the Weiss School of Natural Science of the same university, where he teaches computational geophysics. In his role at TotalEnergies, he is currently leading efforts on diverse areas such as: Machine Learning and High-Performance Computing (HPC). Previously, he led Geophysics and Machine Learning efforts for Shell International E&P Inc. Before that, he worked at Repsol USA researching near real-time visualization/computing and HPC for geophysical algorithms. Before that position, he was senior computer scientist at the Barcelona Supercomputing Center for the Kaleidoscope project. He holds a PhD and MSc from INRIA-UNSA in France and Computer Engineering degree from the University of Chile.