Machine learning for glass science and engineering: A review

The design of new glasses is often plagued by poorly efficient Edisonian “trial-and-error” discovery approaches. As an alternative route, the Materials Genome Initiative has largely popularized new approaches relying on artificial intelligence and machine learning for accelerating the discovery and...

Full description

Saved in:
Bibliographic Details
Published in:Journal of non-crystalline solids Vol. 557; no. C; p. 119419
Main Authors: Liu, Han, Fu, Zipeng, Yang, Kai, Xu, Xinyi, Bauchy, Mathieu
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01.04.2021
Elsevier
Subjects:
Artificial neuron network
Bayesian optimization
Composition-property relationship
Molecular dynamics simulation
Structural signature
Structural signature
Artificial neuron network
Composition-property relationship
Molecular dynamics simulation
Bayesian optimization
ISSN:0022-3093, 1873-4812
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The design of new glasses is often plagued by poorly efficient Edisonian “trial-and-error” discovery approaches. As an alternative route, the Materials Genome Initiative has largely popularized new approaches relying on artificial intelligence and machine learning for accelerating the discovery and optimization of novel, advanced materials. Here, we review some recent progress in adopting machine learning to accelerate the design of new glasses with tailored properties. •We review some recent progress in machine learning applied to glass science.•We provide an introduction to common machine learning techniques.•We highlight the benefits of “physics-informed machine learning.”•We show how machine learning and physics-based modeling can be used in synergy.•We discuss some potential future directions in the use of machine learning in glass science.
Bibliography:USDOE
ISSN:0022-3093
1873-4812
DOI:10.1016/j.jnoncrysol.2019.04.039