Machine learning for graph-based representations of three-dimensional discrete fracture networks
From MaRDI portal
Abstract: Structural and topological information play a key role in modeling flow and transport through fractured rock in the subsurface. Discrete fracture network (DFN) computational suites such as dfnWorks are designed to simulate flow and transport in such porous media. Flow and transport calculations reveal that a small backbone of fractures exists, where most flow and transport occurs. Restricting the flowing fracture network to this backbone provides a significant reduction in the network's effective size. However, the particle tracking simulations needed to determine the reduction are computationally intensive. Such methods may be impractical for large systems or for robust uncertainty quantification of fracture networks, where thousands of forward simulations are needed to bound system behavior. In this paper, we develop an alternative network reduction approach to characterizing transport in DFNs, by combining graph theoretical and machine learning methods. We consider a graph representation where nodes signify fractures and edges denote their intersections. Using random forest and support vector machines, we rapidly identify a subnetwork that captures the flow patterns of the full DFN, based primarily on node centrality features in the graph. Our supervised learning techniques train on particle-tracking backbone paths found by dfnWorks, but run in negligible time compared to those simulations. We find that our predictions can reduce the network to approximately 20% of its original size, while still generating breakthrough curves consistent with those of the original network.
Recommendations
- Model reduction for fractured porous media: a machine learning approach for identifying main flow pathways
- Identifying backbones in three-dimensional discrete fracture networks: a bipartite graph-based approach
- Machine learning for flux regression in discrete fracture networks
- Robust system size reduction of discrete fracture networks: a multi-fidelity method that preserves transport characteristics
- Physics-informed machine learning for backbone identification in discrete fracture networks
Cites work
- scientific article; zbMATH DE number 3446442 (Why is no real title available?)
- A particle tracking transport method for the simulation of resident and flux-averaged concentration of solute plumes in groundwater models
- An introduction to statistical learning. With applications in R
- Conforming Delaunay triangulation of stochastically generated three dimensional discrete fracture networks: a feature rejection algorithm for meshing strategy
- Particle tracking approach for transport in three-dimensional discrete fracture networks. Particle tracking in 3-D DFNs
- Random forests
- Random walk particle tracking simulations of non-Fickian transport in heterogeneous media
- STACS 2005
- Sequential geophysical and flow inversion to characterize fracture networks in subsurface systems
- Support-vector networks
Cited in
(12)- Random neighborhood graphs as models of fracture networks on rocks: structural and dynamical analysis
- A multi-aggregator graph neural network for backbone exaction of fracture networks
- Parametric generation of conditional geological realizations using generative neural networks
- Robust system size reduction of discrete fracture networks: a multi-fidelity method that preserves transport characteristics
- Fracture network flow prediction with uncertainty using physics-informed graph features
- Machine learning for flux regression in discrete fracture networks
- A probabilistic clustering approach for identifying primary subnetworks of discrete fracture networks with quantified uncertainty
- Identifying backbones in three-dimensional discrete fracture networks: a bipartite graph-based approach
- Multilevel graph partitioning for three-dimensional discrete fracture network flow simulations
- Model reduction for fractured porous media: a machine learning approach for identifying main flow pathways
- Physics-informed machine learning for backbone identification in discrete fracture networks
- Parallel meshing, discretization, and computation of flow in massive discrete fracture networks
This page was built for publication: Machine learning for graph-based representations of three-dimensional discrete fracture networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1710361)
