TY - JOUR
T1 - Upscaling of two-phase discrete fracture simulations using a convolutional neural network
AU - Andrianov, Nikolai
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
PY - 2022/10
Y1 - 2022/10
N2 - Upscaling methods such as the dual porosity/dual permeability (DPDP) model provide a robust means for numerical simulation of fractured reservoirs. In order to close the DPDP model, one needs to provide the upscaled fracture permeabilities and the parameters of the matrix-fracture mass transfer for every fractured coarse block in the domain. Obtaining these model closures from fine-scale discrete fracture-matrix (DFM) simulations is a lengthy and computationally expensive process. We alleviate these difficulties by pixelating the fracture geometries and predicting the upscaled parameters using a convolutional neural network (CNN), trained on precomputed fine-scale results. We demonstrate that once a trained CNN is available, it can provide the DPDP model closures for a wide range of modeling parameters, not only those for which the training dataset has been obtained. The performance of the DPDP model with both reference and predicted closures is compared to the reference DFM simulations of two-phase flows using a synthetic and a realistic fracture geometries. While the both DPDP solutions underestimate the matrix-fracture transfer rate, they agree well with each other and demonstrate a significant speedup as compared to the reference fine-scale solution.
AB - Upscaling methods such as the dual porosity/dual permeability (DPDP) model provide a robust means for numerical simulation of fractured reservoirs. In order to close the DPDP model, one needs to provide the upscaled fracture permeabilities and the parameters of the matrix-fracture mass transfer for every fractured coarse block in the domain. Obtaining these model closures from fine-scale discrete fracture-matrix (DFM) simulations is a lengthy and computationally expensive process. We alleviate these difficulties by pixelating the fracture geometries and predicting the upscaled parameters using a convolutional neural network (CNN), trained on precomputed fine-scale results. We demonstrate that once a trained CNN is available, it can provide the DPDP model closures for a wide range of modeling parameters, not only those for which the training dataset has been obtained. The performance of the DPDP model with both reference and predicted closures is compared to the reference DFM simulations of two-phase flows using a synthetic and a realistic fracture geometries. While the both DPDP solutions underestimate the matrix-fracture transfer rate, they agree well with each other and demonstrate a significant speedup as compared to the reference fine-scale solution.
KW - Convolutional neural network
KW - Discrete fracture-matrix (DFM) modelling
KW - Fractured reservoirs
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85131664105&partnerID=8YFLogxK
U2 - 10.1007/s10596-022-10149-3
DO - 10.1007/s10596-022-10149-3
M3 - Article
AN - SCOPUS:85131664105
SN - 1420-0597
VL - 26
SP - 1237
EP - 1259
JO - Computational Geosciences
JF - Computational Geosciences
IS - 5
ER -