 |
Center for Nonlinear Studies |
Discrete fracture networks (DFN) are often used to accurately model flow and transport in fractured porous media.High-fidelity flow and transportsimulation on a large DFN involving thousands of fractures is computationally expensive. This makes uncertainty quantification studies of quantities of interest such as travel time through the network computationally intractable, since hundreds to thousands of runs of the DFN model are required to get good bounds on the uncertainty of the predictions.In this context, we present a system-reduction technique for DFNs using supervised machine-learning via a Random Forest Classifier. Thein-sample errors (in terms of precision and recall scores) of the trained classifier are found to be very accurate indicators of the out-of-sample errors, thus exhibiting that the classifier generalizes well to test data. Moreover, this system-reduction technique yields sub-networks as small as 12\% of the full DFN that still recovertransport characteristics of the full network such as the peak dosage and tailing behaviour for late times. Most importantly, the sub-networksdo not get disconnected, and their size can be controlled by a single dimensionless parameter.Furthermore, measures of KL-divergence and KS-statistic for the breakthrough curves of the sub-networks with respect to the full networkshow physically realistic trends in that the measures decrease monotically as the size of the sub-networks increase.
Host: David Métivier