CCSNet: a deep learning modeling suite for CO$_2$ storage

TL;DR

CCSNet is a deep learning suite designed to efficiently simulate CO2 storage in saline aquifers, offering results thousands of times faster than traditional methods and enabling advanced estimation of key storage metrics.

Contribution

This work introduces CCSNet, a novel deep learning framework that replaces conventional numerical simulators for CCS, providing rapid and comprehensive modeling capabilities.

Findings

CCSNet achieves 10^3 to 10^4 times faster simulation speeds.

It accurately predicts saturation, pressure, and trapping metrics.

Enables rigorous estimation of sweep efficiency and solubility trapping.

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 general-purpose deep-learning modeling suite that can act as an alternative to conventional numerical simulators for carbon capture and storage (CCS) problems where CO$_2$ is injected into saline aquifers in 2d-radial systems. 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 10$^3$ to 10$^4$ 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.