Machine learning for graph-based representations of three-dimensional discrete fracture networks
[5];
[5];
[5]
- San Diego State Univ., San Diego, CA (United States). Computational Science Research Center; Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- C2FO, Leawood, KS (United States). Data & Decision Sciences
- an Diego State Univ., San Diego, CA (United States). Computational Science Research Center; Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
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 (Hyman et al. Comput. Geosci. 84, 10–19 2015) 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 this 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. In conclusion, 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.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- Grant/Contract Number:
- AC52-06NA25396
- OSTI ID:
- 1479976
- Report Number(s):
- LA-UR-17-24300
- Journal Information:
- Computational Geosciences, Vol. 22, Issue 3; ISSN 1420-0597
- Publisher:
- SpringerCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Similar Records
Identifying Backbones in Three-Dimensional Discrete Fracture Networks: A Bipartite Graph-Based Approach
Advancing graph-based algorithms for predicting flow and transport in fractured rock