Inversion of Time-Lapse Surface Gravity Data for Detection of 3-D CO2 Plumes via Deep Learning

We introduce two algorithms that invert simulated gravity data to 3-D subsurface rock/flow properties. The first algorithm is data-driven, deep learning (DL)-based approach, and the second is also data-driven but considers the temporal evolution of surface gravity events. 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, 3-D subsurface reconstructions in near real-time. In addition, our proposed methods achieve Dice scores of up to 0.8 for predicted plume geometry and near-perfect data misfit in terms of
$\mu $
Gals. These results indicate that combining 4-D surface gravity monitoring (low-cost acquisition) with DL techniques represents an effective and nonintrusive method for monitoring CO2 storage sites.