CCSNet: A deep learning modeling suite for CO[formula omitted] storage

Abstract

Numerical simulation is an essential tool for many applications involving subsurface flow and transport, yet often suffers from computational challenges due to the multi-physics nature, highly non-linear governing equations, inherent parameter uncertainties, and the need for high spatial resolutions to capture multi-scale heterogeneity. We developed CCSNet, a deep-learning modeling suite that can act as an alternative to conventional numerical simulators for carbon capture and storage (CCS) problems well-represented by a 2D radial grid, for example, injection into an infinite acting saline formation with no or very small dip. CCSNet consists of a sequence of deep learning models producing all the outputs that a numerical simulator typically provides, including saturation distributions, pressure buildup, dry-out, fluid densities, mass balance, solubility trapping, and sweep efficiency. The results are 103 to 104 times faster than conventional numerical simulators. As an application of CCSNet illustrating the value of its high computational efficiency, we developed rigorous estimation techniques for the sweep efficiency and solubility trapping.