Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator
Authors:
Open Access
- 14 August 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4184-4194
Abstract
Subsurface simulations use computational models to predict the flow of fluids (e.g., oil, water, gas) through porous media. These simulations are pivotal in industrial applications such as petroleum production, where fast and accurate models are needed for high-stake decision making, for example, for well placement optimization and field development planning. Classical finite difference numerical simulators require massive computational resources to model large-scale real-world reservoirs. Alternatively, streamline simulators and data-driven surrogate models are computationally more efficient by relying on approximate physics models, however they are insufficient to model complex reservoir dynamics at scale. Here we introduce Hybrid Graph Network Simulator (HGNS), which is a data-driven surrogate model for learning reservoir simulations of 3D subsurface fluid flows. To model complex reservoir dynamics at both local and global scale, HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. HGNS is able to scale to grids with millions of cells per time step, two orders of magnitude higher than previous surrogate models, and can accurately predict the fluid flow for tens of time steps (years into the future). Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators, and that it outperforms other learning-based models by reducing long-term prediction errors by up to 21%.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantificationJournal of Computational Physics, 2018
- Reduced-order modeling of CO2 storage operationsInternational Journal of Greenhouse Gas Control, 2018
- Gaussian Processes for history-matching: application to an unconventional gas reservoirComputational Geosciences, 2017
- Fast Multiscale Reservoir Simulations With POD-DEIM Model ReductionSPE Journal, 2016
- Surrogate accelerated sampling of reservoir models with complex structures using sparse polynomial chaos expansionAdvances in Water Resources, 2015
- Application of artificial neural networks in a history matching processJournal of Petroleum Science and Engineering, 2014
- Reduced-Order Modeling for Compositional Simulation by Use of Trajectory Piecewise LinearizationSPE Journal, 2014
- New Frontiers in Large Scale Reservoir Simulation2011
- Development and application of reduced‐order modeling procedures for subsurface flow simulationInternational Journal for Numerical Methods in Engineering, 2008
- Reduced-order optimal control of water flooding using proper orthogonal decompositionComputational Geosciences, 2006