Compositional and Elemental Descriptors for Perovskite Materials
Abstract
In this extended abstract we compare the performance of different families of descriptors – \textit{molar composition descriptor, weight composition descriptor and elemental descriptor} – for regression task (prediction of bandgap) and include examples of a classification task for perovskite oxide materials with general formulas $ABO_3$, $A_2BB’O_6$, and $A_xA’_{1-x}B_yB’_{1-y}O_6$. The best performance was observed for our elemental descriptor which consisted of $A$-site and $B$-site element information on: Shannon’s ionic radius, ideal bond length, electronegativity, van der Waals radius, ionization energy, molar volume, atomic number, and atomic mass. The weight composition descriptor showed superior results over a simpler molar composition descriptor. The results of principal component analysis, regression models with the hyperparameters optimized using an autoML software and Wasserstein autoencoders are briefly discussed for a possible use in inverse materials design.
Cite
Text
Hostas et al. "Compositional and Elemental Descriptors for Perovskite Materials." ICLR 2023 Workshops: ML4Materials, 2023.Markdown
[Hostas et al. "Compositional and Elemental Descriptors for Perovskite Materials." ICLR 2023 Workshops: ML4Materials, 2023.](https://mlanthology.org/iclrw/2023/hostas2023iclrw-compositional/)BibTeX
@inproceedings{hostas2023iclrw-compositional,
title = {{Compositional and Elemental Descriptors for Perovskite Materials}},
author = {Hostas, Jiri and Lourenço, Maicon Pierre and Garcia, John and Shahmohamadi, Hatef and Tchagang, Alain and Shankar, Karthik and Thangadurai, Venkataraman and Salahub, Dennis R.},
booktitle = {ICLR 2023 Workshops: ML4Materials},
year = {2023},
url = {https://mlanthology.org/iclrw/2023/hostas2023iclrw-compositional/}
}