Name
Title | ||
|---|---|---|
Machine learning for graph-based representations of three-dimensional discrete fracture networks. |
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 (Hyman et al. Comput. Geosci. , 10–19 ) 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 , 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. |
Year | DOI | Venue |
|---|---|---|
2017 | https://doi.org/10.1007/s10596-018-9720-1 | Computational Geosciences |
Keywords | Field | DocType |
Machine learning,Discrete fracture networks,Support vector machines,Random forest,Centrality | lambda-connectedness,Uncertainty quantification,Centrality,Power graph analysis,Supervised learning,Artificial intelligence,Computational learning theory,Subnetwork,Mathematics,Graph (abstract data type),Machine learning | Journal |
Volume | Issue | ISSN |
abs/1705.09866 | 3 | Computational Geosciences 22, 695-710 (2018) |
Citations | PageRank | References |
3 | 0.38 | 10 |
Authors | ||
9 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Manuel Valera | 1 | 3 | 0.38 |
| Zhengyang Guo | 2 | 3 | 0.38 |
| Priscilla Kelly | 3 | 3 | 0.38 |
| Sean Matz | 4 | 3 | 0.38 |
| Adrian Cantu | 5 | 3 | 0.38 |
| Allon G. Percus | 6 | 288 | 24.31 |
| Jeffrey D. Hyman | 7 | 31 | 4.29 |
| G. Srinivasan | 8 | 7 | 3.85 |
| Hari S. Viswanathan | 9 | 22 | 4.19 |