Upscaling of two-phase discrete fracture simulations using a convolutional neural network

DOI10.1007/s10596-022-10149-3zbMath1496.86002OpenAlexW4281769109MaRDI QIDQ2085098

Nikolai Andrianov

Publication date: 14 October 2022

Published in: Computational Geosciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10596-022-10149-3

zbMATH Keywords

machine learningfractured reservoirsconvolutional neural networkdiscrete fracture-matrix (DFM) modelling

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Brittle fracture (74R10) Finite element methods applied to problems in solid mechanics (74S05) Flows in porous media; filtration; seepage (76S05) Finite volume methods applied to problems in fluid mechanics (76M12) Dimensional analysis and similarity applied to problems in fluid mechanics (76M55) Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Computational methods for problems pertaining to geophysics (86-08) Homogenization applied to problems in fluid mechanics (76M50) Mathematical modeling or simulation for problems pertaining to mechanics of deformable solids (74-10)

Uses Software

• Gmsh
• Matlab
• MRST
• ALUGrid
• DuMuX
• DUNE-ALUGrid
• Keras
• Adam
• dfnWorks
• GitHub

Cites Work

• Unnamed Item
• Unnamed Item
• An efficient multi-point flux approximation method for discrete fracture-matrix simulations
• A quasi steady state method for solving transient Darcy flow in complex 3D fractured networks accounting for matrix to fracture flow
• Use of border regions for improved permeability upscaling
• Comparison of the response to geometrical complexity of methods for unstationary simulations in discrete fracture networks with conforming, polygonal, and non-matching grids
• Conforming, non-conforming and non-matching discretization couplings in discrete fracture network simulations
• FraC: a new conforming mesh method for discrete fracture networks
• A hybrid-dimensional discrete fracture model for non-isothermal two-phase flow in fractured porous media
• Basic concepts in the theory of seepage of homogeneous liquids in fissured rocks [strata]
• Flow Simulation in Three-Dimensional Discrete Fracture Networks
• Gmsh: A 3-D finite element mesh generator with built-in pre- and post-processing facilities
• Upscaling: a review
• An Introduction to Reservoir Simulation Using MATLAB/GNU Octave

This page was built for publication: Upscaling of two-phase discrete fracture simulations using a convolutional neural network