TY - JOUR
T1 - Machine learning of dual porosity model closures from discrete fracture simulations
AU - Andrianov, Nikolai
AU - Nick, Hamidreza M.
N1 - Funding Information:
This work has been supported by the Advanced Waterflooding program at the Danish Hydrocarbon Research and Technology Centre. The authors are grateful to Dr. Andreas G. Koestler for providing the Lägerdorf quarry data. The anonymous reviewers are thanked sincerely for constructive comments.
Publisher Copyright:
© 2020
PY - 2021/1
Y1 - 2021/1
N2 - Fine-scale discrete fracture simulations provide a natural means to quantify the matrix-fracture fluxes and to specify reference solutions for upscaling approaches such as dual porosity/dual permeability models. Since typically the fine-scale simulations are computationally demanding, and the fractured reservoirs are highly heterogeneous, it is desirable to parametrize the fracture geometry and to obtain coarse-scale model closures using precomputed fine-scale results. We show that this can be done for the case of two-dimensional geometries and compressible single-phase flows. Specifically, a set of parameters linked to a coarse-scale grid block can be mapped to the underlying fracture geometry via a convolutional neural network. In particular, if a matrix-fracture transfer function can be parametrized with a number of parameters spatially varying on a coarse scale, the shape of the transfer function per grid block can be learned from fine-scale simulations.
AB - Fine-scale discrete fracture simulations provide a natural means to quantify the matrix-fracture fluxes and to specify reference solutions for upscaling approaches such as dual porosity/dual permeability models. Since typically the fine-scale simulations are computationally demanding, and the fractured reservoirs are highly heterogeneous, it is desirable to parametrize the fracture geometry and to obtain coarse-scale model closures using precomputed fine-scale results. We show that this can be done for the case of two-dimensional geometries and compressible single-phase flows. Specifically, a set of parameters linked to a coarse-scale grid block can be mapped to the underlying fracture geometry via a convolutional neural network. In particular, if a matrix-fracture transfer function can be parametrized with a number of parameters spatially varying on a coarse scale, the shape of the transfer function per grid block can be learned from fine-scale simulations.
KW - Convolutional neural network
KW - Discrete fracture-matrix (DFM) modelling
KW - Upscaling
UR - http://www.scopus.com/inward/record.url?scp=85097567059&partnerID=8YFLogxK
U2 - 10.1016/j.advwatres.2020.103810
DO - 10.1016/j.advwatres.2020.103810
M3 - Article
AN - SCOPUS:85097567059
SN - 0309-1708
VL - 147
JO - Advances in Water Resources
JF - Advances in Water Resources
M1 - 103810
ER -