A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Media
This work addresses the need for faster simulations in subsurface applications like carbon capture and storage, offering a domain-specific improvement over existing deep-learning solutions.
The paper tackles the problem of computationally expensive simulation of reactive dissolution in porous media by developing a deep-learning approach that predicts future states of the dissolution process, achieving a speedup of around 10^4 over traditional simulators while maintaining accuracy compared to state-of-the-art methods.
Simulating reactive dissolution of solid minerals in porous media has many subsurface applications, including carbon capture and storage (CCS), geothermal systems and oil & gas recovery. As traditional direct numerical simulators are computationally expensive, it is of paramount importance to develop faster and more efficient alternatives. Deep-learning-based solutions, most of them built upon convolutional neural networks (CNNs), have been recently designed to tackle this problem. However, these solutions were limited to approximating one field over the domain (e.g. velocity field). In this manuscript, we present a novel deep learning approach that incorporates both temporal and spatial information to predict the future states of the dissolution process at a fixed time-step horizon, given a sequence of input states. The overall performance, in terms of speed and prediction accuracy, is demonstrated on a numerical simulation dataset, comparing its prediction results against state-of-the-art approaches, also achieving a speedup around $10^4$ over traditional numerical simulators.