Lab Home | Phone | Search
Center for Nonlinear Studies  Center for Nonlinear Studies
 Colloquia Archive 
 Postdoc Seminars Archive 
 Quantum Lunch 
 CMS Colloquia 
 Q-Mat Seminars 
 Q-Mat Seminars Archive 
 Kac Lectures 
 Dist. Quant. Lecture 
 Ulam Scholar 
 Summer Research 
 Past Visitors 
 History of CNLS 
 Maps, Directions 
 CNLS Office 
Thursday, October 04, 2018
2:00 PM - 3:00 PM
CNLS Conference Room (TA-3, Bldg 1690)

Postdoc Seminar

System-size reduction for fractured porous media: A machine-learning approach for identifying flow backbones of variable size

Shriram Srinivasan

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