Model reduction for fractured porous media: a machine learning approach for identifying main flow pathways

• Published in: Computational geosciences Vol. 23; no. 3; pp. 617 - 629
• Main Authors: Srinivasan, Shriram, Karra, Satish, Hyman, Jeffrey, Viswanathan, Hari, Srinivasan, Gowri
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.06.2019; Springer Nature B.V; Springer
• Subjects: Artificial intelligence; Backbone; Classification; Classifiers; Computational efficiency; Computer applications; Computer Science; Computing time; Discrete fracture networks; Divergence; Earth and Environmental Science; Earth Sciences; Errors; Fractured porous media; Fractures; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Learning algorithms; Learning behaviour; Machine learning; Mathematical Modeling and Industrial Mathematics; Mathematics; MATHEMATICS AND COMPUTING; Model reduction; Porous media; Random forests; Sampling error; Soil Science & Conservation; Subsurface flow and transport; Transport; Transport properties; Travel time; Uncertainty; Fractured porous media; Discrete fracture networks; Subsurface flow and transport; Random forests; Machine learning; Classification

Discrete fracture networks (DFN) are often used to model flow and transport in fractured porous media. The accurate resolution of flow and transport behavior on a large DFN involving thousands of fractures is computationally expensive. This makes uncertainty quantification studies of quantities of i...