Graph Representations of Flow and Transport in Fracture Networks using Machine Learning
Abstract
Flow and transport of fluids through fractured systems is governed by the properties and interactions at the micro-scale. Retaining information about the micro-structure such as fracture length, orientation, aperture and connectivity in mesh-based computational models results in solving for millions to billions of degrees of freedom and quickly renders the problem computationally intractable. Our approach depicts fracture networks graphically, by mapping fractures to nodes and intersections to edges, thereby greatly reducing computational burden. Additionally, we use machine learning techniques to build simulators on the graph representation, trained on data from the mesh-based high fidelity simulations to speed up computation by orders of magnitude. We demonstrate our methodology on ensembles of discrete fracture networks, dividing up the data into training and validation sets. Our machine learned graph-based solvers result in over 3 orders of magnitude speedup without any significant sacrifice in accuracy.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2017
- Bibcode:
- 2017AGUFMNG52A..01S
- Keywords:
-
- 0609 Antennas;
- ELECTROMAGNETICS;
- 4430 Complex systems;
- NONLINEAR GEOPHYSICS;
- 5104 Fracture and flow;
- PHYSICAL PROPERTIES OF ROCKS;
- 8010 Fractures and faults;
- STRUCTURAL GEOLOGY