A Graph Neural Network Framework for Grid-Based Simulation
This work addresses a domain-specific problem for oil and gas and carbon capture sequestration optimization, offering an incremental improvement by applying a hybrid method to accelerate simulations.
The paper tackles the computational expense of reservoir simulations for well control and placement optimization by proposing a graph neural network (GNN) framework as a surrogate model to replace simulation runs, achieving close matches with simulation results in one-step and rollout predictions after training with 6000 samples.
Reservoir simulations are computationally expensive in the well control and well placement optimization. Generally, numerous simulation runs (realizations) are needed in order to achieve the optimal well locations. In this paper, we propose a graph neural network (GNN) framework to build a surrogate feed-forward model which replaces simulation runs to accelerate the optimization process. Our GNN framework includes an encoder, a process, and a decoder which takes input from the processed graph data designed and generated from the simulation raw data. We train the GNN model with 6000 samples (equivalent to 40 well configurations) with each containing the previous step state variable and the next step state variable. We test the GNN model with another 6000 samples and after model tuning, both one-step prediction and rollout prediction achieve a close match with the simulation results. Our GNN framework shows great potential in the application of well-related subsurface optimization including oil and gas as well as carbon capture sequestration (CCS).