Accelerated prediction of dielectric functions in solar cell materials with graph neural networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ginter, Caden, Choudhary, Kamal, Mandal, Subhasish
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914085564579840
author Ginter, Caden
Choudhary, Kamal
Mandal, Subhasish
author_facet Ginter, Caden
Choudhary, Kamal
Mandal, Subhasish
contents We present an atomistic line graph neural network (ALIGNN) model for predicting dielectric functions directly from crystal structures. Trained on $\sim$7000 dielectric functions from the JARVIS-DFT database computed with a meta-GGA exchange-correlation functional, the model accurately reproduces spectral features, including peak intensities and overall line shapes, while enabling efficient high-throughput screening. Applied to the recently developed Alexandria materials database, containing over four hundred thousand insulating materials, we uncover a clear elemental trend, with vanadium emerging as a strong indicator of materials with high-spectroscopic limited maximum efficiency (SLME). In particular, vanadium-based perovskite materials show a substantially higher fraction of high-SLME compounds compared to the database average, underscoring their promise for optoelectronic applications.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08738
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
Ginter, Caden
Choudhary, Kamal
Mandal, Subhasish
Materials Science
Other Condensed Matter
We present an atomistic line graph neural network (ALIGNN) model for predicting dielectric functions directly from crystal structures. Trained on $\sim$7000 dielectric functions from the JARVIS-DFT database computed with a meta-GGA exchange-correlation functional, the model accurately reproduces spectral features, including peak intensities and overall line shapes, while enabling efficient high-throughput screening. Applied to the recently developed Alexandria materials database, containing over four hundred thousand insulating materials, we uncover a clear elemental trend, with vanadium emerging as a strong indicator of materials with high-spectroscopic limited maximum efficiency (SLME). In particular, vanadium-based perovskite materials show a substantially higher fraction of high-SLME compounds compared to the database average, underscoring their promise for optoelectronic applications.
title Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
topic Materials Science
Other Condensed Matter
url https://arxiv.org/abs/2510.08738