Paper Title:
Graph Convolutional Networks for Simulating Multi-phase Flow and Transport in Porous Media
Published on:
10 July 2023
Primary Category:
Computational Physics
Paper Authors:
Jiamin Jiang,
Bo Guo
Proposes graph networks for porous flow prediction on unstructured grids
Combines graph and edge convolution to capture pressure and saturation
Models tested on 2D heterogeneous cases with different meshes
Predictions match reference solutions closely despite unseen meshes
Around 200x speedup compared to numerical simulation
Graph networks for porous media flow prediction
This paper proposes graph convolutional networks to learn surrogate models that can rapidly predict multiphase flow dynamics in porous media, for problems with complex geometries. The models are trained on simulation data, then tested on unseen cases. Results show the models accurately predict pressure and saturation evolutions, and generalize to new meshes.
Deep learning model for fluid flow prediction
Learning fluid flow in varying geometries
A Neural Network Unlocks the Physics of Fluid Flow in Porous Rock
Surrogate learning for crash simulations using graph networks
Graph neural network solver for fluid equations
Learning traffic patterns from road network data
No comments yet, be the first to start the conversation...
Sign up to comment on this paper