Learning the matrix-fractures transfer rate using a convolutional neural network

N. Andrianov, H.M. Nick

Publikation: KonferencebidragArtikel ved konferencepeer review

Resumé

One of the key elements in constructing of representative dual porosity/dual permeability models is to provide the mass transfer rate between the matrix and the fractures. Whereas it is possible to compute numerically this transfer rate for specific geometries, it is challenging to estimate the transfer function without running the CPU intensive computations. In this work, we demonstrate that a convolutional neural network can approximate a transfer function using the encoded fracture geometry and the precomputed fine-scale simulation results.

OriginalsprogEngelsk
Antal sider5
DOI
StatusUdgivet - 2020
Udgivet eksterntJa
Begivenhed1st EAGE Digitalization Conference and Exhibition - Vienna, Østrig
Varighed: 30 nov. 20203 dec. 2020
Konferencens nummer: 1

Konference

Konference1st EAGE Digitalization Conference and Exhibition
Land/OmrådeØstrig
ByVienna
Periode30/11/203/12/20

Programområde

  • Programområde 3: Energiressourcer

Fingeraftryk

Dyk ned i forskningsemnerne om 'Learning the matrix-fractures transfer rate using a convolutional neural network'. Sammen danner de et unikt fingeraftryk.

Citationsformater