2023
DOI: 10.26434/chemrxiv-2022-frcns-v2
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Materials discovery for high-temperature, clean-energy applications using graph neural network models of vacancy defects and free-energy calculations

Abstract: We present a graph neural network modeling approach that fully automates the prediction of the DFT-relaxed vacancy formation enthalpy of any crystallographic site from its DFT-relaxed host structure. Applicable to arbitrary structures with an accuracy limited principally by the amount/diversity of the data on which it is trained, this model accelerates the screening of vacancy defects by many orders of magnitude by replacing the DFT supercell relaxations required for each symmetrically unique crystal site. It … Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 50 publications
0
1
0
Order By: Relevance
“…Due to lengthy experiments needed to measure and characterize cycling's effect on hydrogen capacity, literature data remain relatively scarce and no sufficiently large database (∼100 s of training examples) has been assembled from which an ML model could readily be trained to predict aspects of capacity degradation. However, recent ML work on automated vacancy prediction 50 could be used in conjunction with hydride thermodynamic ML models discussed here to target high-entropy alloys that simultaneously have favorable hydride thermodynamics and a low propensity for vacancy formation and therefore may improve cycling capacity.…”
Section: ■ Conclusionmentioning
confidence: 99%
“…Due to lengthy experiments needed to measure and characterize cycling's effect on hydrogen capacity, literature data remain relatively scarce and no sufficiently large database (∼100 s of training examples) has been assembled from which an ML model could readily be trained to predict aspects of capacity degradation. However, recent ML work on automated vacancy prediction 50 could be used in conjunction with hydride thermodynamic ML models discussed here to target high-entropy alloys that simultaneously have favorable hydride thermodynamics and a low propensity for vacancy formation and therefore may improve cycling capacity.…”
Section: ■ Conclusionmentioning
confidence: 99%