Learning CO$_2$ plume migration in faulted reservoirs with Graph Neural Networks
This work addresses the problem of efficiently simulating subsurface flow for CO2 storage, particularly in complex geological settings with faults, offering a domain-specific improvement for geoscience applications.
The paper tackled the challenge of accurately modeling CO2 plume migration in faulted reservoirs by developing a graph neural network model combining GConvLSTM and MeshGraphNet, which demonstrated better accuracy and reduced temporal error compared to standard methods, with excellent generalizability to unseen conditions.
Deep-learning-based surrogate models provide an efficient complement to numerical simulations for subsurface flow problems such as CO$_2$ geological storage. Accurately capturing the impact of faults on CO$_2$ plume migration remains a challenge for many existing deep learning surrogate models based on Convolutional Neural Networks (CNNs) or Neural Operators. We address this challenge with a graph-based neural model leveraging recent developments in the field of Graph Neural Networks (GNNs). Our model combines graph-based convolution Long-Short-Term-Memory (GConvLSTM) with a one-step GNN model, MeshGraphNet (MGN), to operate on complex unstructured meshes and limit temporal error accumulation. We demonstrate that our approach can accurately predict the temporal evolution of gas saturation and pore pressure in a synthetic reservoir with impermeable faults. Our results exhibit a better accuracy and a reduced temporal error accumulation compared to the standard MGN model. We also show the excellent generalizability of our algorithm to mesh configurations, boundary conditions, and heterogeneous permeability fields not included in the training set. This work highlights the potential of GNN-based methods to accurately and rapidly model subsurface flow with complex faults and fractures.