Machine Learning Band Gap Predictions: Linking Quasiparticle Self-Consistent GW and LDA-Derived Partial Density of States

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tankano, Shota, Kotani, Takao, Obata, Masao, Sato, Kazunori, Saito, Harutaka, Oda, Tatsuki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915409345642496
author Tankano, Shota
Kotani, Takao
Obata, Masao
Sato, Kazunori
Saito, Harutaka
Oda, Tatsuki
author_facet Tankano, Shota
Kotani, Takao
Obata, Masao
Sato, Kazunori
Saito, Harutaka
Oda, Tatsuki
contents Accurately calculating band gaps for given crystal structures is highly desirable. However, conventional first-principles calculations based on density functional theory (DFT) within the local density approximation (LDA) fail to predict band gaps accurately. To address this issue, the quasi-particle self-consistent GW (QSGW) method is often employed as it is one of the most reliable theoretical approaches for predicting band gaps. Despite its accuracy, QSGW requires significant computational resources. To overcome this limitation, we propose combining QSGW with machine learning. In this study, we applied QSGW to 1,516 materials from the Materials Project [https://materialsproject.org/] and used machine learning to predict QSGW band gaps as a function of the partial density of states (PDOS) in LDA. Our results demonstrate that the proposed model significantly outperforms linear regression approaches with linearly-independent descriptor generation [https://github.com/Hitoshi-FUJII/LIDG]. This model is a prototype for predicting material properties based on PDOS.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine Learning Band Gap Predictions: Linking Quasiparticle Self-Consistent GW and LDA-Derived Partial Density of States
Tankano, Shota
Kotani, Takao
Obata, Masao
Sato, Kazunori
Saito, Harutaka
Oda, Tatsuki
Materials Science
Accurately calculating band gaps for given crystal structures is highly desirable. However, conventional first-principles calculations based on density functional theory (DFT) within the local density approximation (LDA) fail to predict band gaps accurately. To address this issue, the quasi-particle self-consistent GW (QSGW) method is often employed as it is one of the most reliable theoretical approaches for predicting band gaps. Despite its accuracy, QSGW requires significant computational resources. To overcome this limitation, we propose combining QSGW with machine learning. In this study, we applied QSGW to 1,516 materials from the Materials Project [https://materialsproject.org/] and used machine learning to predict QSGW band gaps as a function of the partial density of states (PDOS) in LDA. Our results demonstrate that the proposed model significantly outperforms linear regression approaches with linearly-independent descriptor generation [https://github.com/Hitoshi-FUJII/LIDG]. This model is a prototype for predicting material properties based on PDOS.
title Machine Learning Band Gap Predictions: Linking Quasiparticle Self-Consistent GW and LDA-Derived Partial Density of States
topic Materials Science
url https://arxiv.org/abs/2507.19189