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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The permeability of complex porous materials can be obtained via direct flowsimulation, which provides the most accurate results, but is verycomputationally expensive. In particular, the simulation convergence timescales poorly as simulation domains become tighter or more heterogeneous.Semi-analytical models that rely on averaged structural properties (i.e.porosity and tortuosity) have been proposed, but these features only summarizethe domain, resulting in limited applicability. On the other hand, data-drivenmachine learning approaches have shown great promise for building more generalmodels by virtue of accounting for the spatial arrangement of the domains solidboundaries. However, prior approaches building on the Convolutional NeuralNetwork (ConvNet) literature concerning 2D image recognition problems do notscale well to the large 3D domains required to obtain a RepresentativeElementary Volume (REV). As such, most prior work focused on homogeneoussamples, where a small REV entails that that the global nature of fluid flowcould be mostly neglected, and accordingly, the memory bottleneck of addressing3D domains with ConvNets was side-stepped. Therefore, important geometries suchas fractures and vuggy domains could not be well-modeled. In this work, weaddress this limitation with a general multiscale deep learning model that isable to learn from porous media simulation data. By using a coupled set ofneural networks that view the domain on different scales, we enable theevaluation of large images in approximately one second on a single GraphicsProcessing Unit. This model architecture opens up the possibility of modelingdomain sizes that would not be feasible using traditional direct simulationtools on a desktop computer.

Computationally Efficient Multiscale Neural Networks Applied To Fluid Flow In Complex 3D Porous Media