Accessibility navigation


Spinel nitride solid solutions: charting properties in the configurational space with explainable machine learning

Sanchez-Palencia, P., Hamad, S., Palacios, P., Grau-Crespo, R. ORCID: https://orcid.org/0000-0001-8845-1719 and Butler, K. T. (2022) Spinel nitride solid solutions: charting properties in the configurational space with explainable machine learning. Digital Discovery, 1 (5). pp. 665-678. ISSN 2635-098X

[img] Text - Accepted Version
· Restricted to Repository staff only

2MB
[img]
Preview
Text (Open access) - Published Version
· Available under License Creative Commons Attribution.
· Please see our End User Agreement before downloading.

1MB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1039/D2DD00038E

Abstract/Summary

Ab initio prediction of the variation of properties in the configurational space of solid solutions is computationally very demanding. We present an approach to accelerate these predictions via a combination of density functional theory and machine learning, using the cubic spinel nitride GeSn2N4 as a case study, exploring how formation energy and electronic bandgap are affected by configurational variations. Furthermore, we demonstrate the utility of applying explainable machine learning to understand the crystal chemistry origins of the trends that we observe. Different configuration descriptors (Coulomb matrix eigenspectrum, many-body tensor representation, and cluster correlation function vectors) are combined with different models (linear regression, gradient-boosted decision trees, and multi-layer perceptron) to extrapolate the calculation of ab initio properties from a small set of configurations to the full space with thousands of configurations. We discuss the performance of different descriptors and models. SHAP (SHapley Additive exPlanations) analysis of the machine learning models highlights how values of formation energy are dominated by variations in local crystal structure (single polyhedral environments), while values of electronic bandgap are dominated by variations in more extended structural motifs. Finally, we demonstrate the usefulness of this approach by constructing structure-property maps, identifying important configurations of GeSn2N4 with extremal properties, as well as by calculating accurate equilibrium properties using configurational averaging.

Item Type:Article
Refereed:Yes
Divisions:Life Sciences > School of Chemistry, Food and Pharmacy > Department of Chemistry
ID Code:109245
Uncontrolled Keywords:spinel, solar cells, cluster expansion, machine learning
Publisher:Royal Society of Chemistry

Downloads

Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation