TY - JOUR
T1 - Large-Scale Statistical Learning for Mass Transport Prediction in Porous Materials Using 90,000 Artificially Generated Microstructures
AU - Prifling, Benedikt
AU - Röding, Magnus
AU - Townsend, Philip
AU - Neumann, Matthias
AU - Schmidt, Volker
N1 - Publisher Copyright:
Copyright © 2021 Prifling, Röding, Townsend, Neumann and Schmidt.
PY - 2021/12/23
Y1 - 2021/12/23
N2 - Effective properties of functional materials crucially depend on their 3D microstructure. In this paper, we investigate quantitative relationships between descriptors of two-phase microstructures, consisting of solid and pores and their mass transport properties. To that end, we generate a vast database comprising 90,000 microstructures drawn from nine different stochastic models, and compute their effective diffusivity and permeability as well as various microstructural descriptors. To the best of our knowledge, this is the largest and most diverse dataset created for studying the influence of 3D microstructure on mass transport. In particular, we establish microstructure-property relationships using analytical prediction formulas, artificial (fully-connected) neural networks, and convolutional neural networks. Again, to the best of our knowledge, this is the first time that these three statistical learning approaches are quantitatively compared on the same dataset. The diversity of the dataset increases the generality of the determined relationships, and its size is vital for robust training of convolutional neural networks. We make the 3D microstructures, their structural descriptors and effective properties, as well as the code used to study the relationships between them available open access.
AB - Effective properties of functional materials crucially depend on their 3D microstructure. In this paper, we investigate quantitative relationships between descriptors of two-phase microstructures, consisting of solid and pores and their mass transport properties. To that end, we generate a vast database comprising 90,000 microstructures drawn from nine different stochastic models, and compute their effective diffusivity and permeability as well as various microstructural descriptors. To the best of our knowledge, this is the largest and most diverse dataset created for studying the influence of 3D microstructure on mass transport. In particular, we establish microstructure-property relationships using analytical prediction formulas, artificial (fully-connected) neural networks, and convolutional neural networks. Again, to the best of our knowledge, this is the first time that these three statistical learning approaches are quantitatively compared on the same dataset. The diversity of the dataset increases the generality of the determined relationships, and its size is vital for robust training of convolutional neural networks. We make the 3D microstructures, their structural descriptors and effective properties, as well as the code used to study the relationships between them available open access.
KW - deep learning
KW - diffusivity
KW - mass transport
KW - permeability
KW - porous materials
KW - structure-property relationship
KW - virtual materials testing
UR - http://www.scopus.com/inward/record.url?scp=85122371788&partnerID=8YFLogxK
U2 - 10.3389/fmats.2021.786502
DO - 10.3389/fmats.2021.786502
M3 - Article
SN - 2296-8016
VL - 8
JO - Frontiers in Materials
JF - Frontiers in Materials
M1 - 786502
ER -