Repository logo
 

A ML framework to predict permeability of highly porous media based on PSD

Published version
Peer-reviewed

Change log

Authors

Yang, H 
Ke, Y 
Zhang, D 

Abstract

jats:titleAbstract</jats:title> jats:pUsing machine learning (ML) method to predict permeability of porous media has shown great potential in recent years. A current problem is the lack of effective models to account for highly porous media with dilated pores. This study includes (1) generation of media (porosity = 0.8) via a Boolean process, (2) the pore size distribution (PSD) control by using different groups of homogeneous packed spherical particles (3) PSD data obtainment using the spherical contact distribution model (4) computation of the permeability via LBM simulations, (4) training of artificial neuron network (ANN) and (5) analysis of the model. It is found that the PSD could outperform the previous geometry descriptors as an input of ML framework to deal with highly porous structures with different fractions of dilated pores, however there is still room for precision enhancement.</jats:p>

Description

Keywords

37 Earth Sciences, 41 Environmental Sciences, 4106 Soil Sciences, Machine Learning and Artificial Intelligence, Networking and Information Technology R&D (NITRD)

Journal Title

IOP Conference Series: Earth and Environmental Science

Conference Name

Journal ISSN

1755-1307
1755-1315

Volume Title

680

Publisher

IOP Publishing