# Machine learning for graph-based representations of three-dimensional discrete fracture networks

## TL;DR

This paper introduces a machine learning approach to efficiently identify key fracture networks in 3D discrete fracture systems, significantly reducing computational costs while maintaining accurate flow and transport predictions.

## Contribution

It develops a novel graph-based machine learning method to rapidly predict flow-relevant fracture subnetworks, improving efficiency over traditional particle-tracking simulations.

## Key findings

- Reduces network size to about 20% while preserving flow characteristics.
- Uses random forest and SVM to identify flow backbone from graph features.
- Achieves significant computational speedup with accurate transport predictions.

## 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.