English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Modeling effective transport properties of 3D porous media, such aspermeability, at multiple scales is challenging as a result of the combinedcomplexity of the pore structures and fluid physics - in particular,confinement effects which vary across the nanoscale to the microscale. Whilenumerical simulation is possible, the computational cost is prohibitive forrealistic domains, which are large and complex. Although machine learningmodels have been proposed to circumvent simulation, none so far hassimultaneously accounted for heterogeneous 3D structures, fluid confinementeffects, and multiple simulation resolutions. By utilizing numerous computerscience techniques to improve the scalability of training, we have for thefirst time developed a general flow model that accounts for the pore-structureand corresponding physical phenomena at scales from Angstrom to the micrometer.Using synthetic computational domains for training, our machine learning modelexhibits strong performance (R$^2$=0.9) when tested on extremely diverse realdomains at multiple scales.

Learning a General Model of Single Phase Flow in Complex 3D Porous Media