Spinel nitride solid solutions: charting properties in the configurational space with explainable machine learning-Reference-Cited by-同舟云学术

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

Published:2022 Issue:5 Volume:1 Page:665-678
ISSN:2635-098X
Container-title:Digital Discovery
language:en
Short-container-title:Digital Discovery

Author:

Sánchez-Palencia Pablo¹²^ORCID,Hamad Said³^ORCID,Palacios Pablo¹⁴^ORCID,Grau-Crespo Ricardo⁵^ORCID,Butler Keith T.⁶^ORCID

Affiliation:

1. Instituto de Energía Solar, ETSI Telecomunicación, Universidad Politécnica de Madrid, Ciudad Universitaria, s/n, 28040, Madrid, Spain

2. Departamento de Tecnología Fotónica y Bioingeniería, ETSI Telecomunicación, Universidad Politécnica de Madrid, Ciudad Universitaria, s/n, 28040 Madrid, Spain

3. Department of Physical, Chemical and Natural Systems, Universidad Pablo de Olavide, 41013 Sevilla, Spain

4. Departamento de Física aplicada a las Ingenierías Aeronáutica y Naval, ETSI Aeronáutica y del Espacio, Universidad Politécnica de Madrid, Pz. Cardenal Cisneros, 3, 28040 Madrid, Spain

5. Department of Chemistry, University of Reading, Reading RG6 6DX, UK

6. SciML, Scientific Computing Department, Rutherford Appleton Laboratory, Harwell OX11 0QX, UK

Abstract

The thermodynamic and electronic properties of solid solutions are highly tuneable, based on ion arrangement. We use interpretable machine learning to explore the structure-property landscape of a spinel nitride and understand how crystal chemistry affects physical properties.

Funder

Engineering and Physical Sciences Research Council

Ministerio de Ciencia e Innovación

Universidad Politécnica de Madrid

Ministerio de Ciencia, Innovación y Universidades

Erasmus+

Consejería de Conocimiento, Investigación y Universidad, Junta de Andalucía

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2022/DD/D2DD00038E

Reference65 articles.