Prediction of Local Concentration Fields in Porous Media With Chemical Reaction Using a Multi Scale Convolutional Neural Network

Prediction of Local Concentration Fields in Porous Media With Chemical Reaction Using a Multi Scale Convolutional Neural Network

Agnese Marcato, Javier E. Santos, Gianluca Boccardo, Hari Viswanathan, Daniele Marchisio, Maša Prodanović

It is often difficult to rely on detailed computational modeling alone (for example in optimization loops for designing devices, or subsurface flow exploration) due to the heavy computational costs. To this end, a cheaper surrogate model is needed. In this work (available in open access), we show how to use an innovative type of convolutional neural network, with multi-scale capabilities, extended to interpret transport and reaction results coming from detailed simulations. The network is able replicate the full-order 3D results, much faster (almost instantaneously) and with high accuracy.

Chemical Engineering Journal 455, 140367 (2023)
Corresponding Author: Gianluca Boccardo

InterPore Members can promote their publications to the community via the InterPore InJournals Section of the Newsletter. If you wish to do so, please submit your publication highlight to newsletter@InterPore.org. Clearly indicate which of the authors is an InterPore member (or the institute with an Institutional Membership). Note that we will not review the entries nor does InterPore endorse the published work. Furthermore, we publish on a “submitted first, published first” basis. The highlighted publication should be no older than 6 months (available online).

The highlight should be short (max 100 words) and contain an illustration. Please note that we offer this opportunity exclusively to InterPore members. If you would like to become a member, please have a look here.