Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Haolin, Liu, Xianyuan, Jungbluth, Anna, Ramadan, Alexandra J., Oliver, Robert D. J., Lu, Haiping
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910174120247296
author Wang, Haolin
Liu, Xianyuan
Jungbluth, Anna
Ramadan, Alexandra J.
Oliver, Robert D. J.
Lu, Haiping
author_facet Wang, Haolin
Liu, Xianyuan
Jungbluth, Anna
Ramadan, Alexandra J.
Oliver, Robert D. J.
Lu, Haiping
contents Accurate bandgap prediction is crucial for semiconductor applications, yet machine learning models trained on computational data often struggle to generalize to experimental bandgap measurements. Challenges related to data fidelity, domain generalization, and model interpretability remain insufficiently addressed in existing evaluation frameworks. To bridge this gap, we introduce RealMat-BaG, a benchmark for assessing model reliability under experimentally relevant conditions. We curate an open-access dataset of experimental bandgaps with aligned crystal structures and compare graph neural networks as well as classical machine learning baselines. Our framework evaluates performance across statistical and domain-based splits, examines transfer from DFT-computed to experimental bandgaps, and analyzes interpretability at both elemental-property and structural levels. Our results reveal the fundamental generalization limitations of current bandgap prediction models and establish a benchmark aligned with experimental measurements for developing more reliable learning strategies for materials discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25568
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings
Wang, Haolin
Liu, Xianyuan
Jungbluth, Anna
Ramadan, Alexandra J.
Oliver, Robert D. J.
Lu, Haiping
Materials Science
Artificial Intelligence
Accurate bandgap prediction is crucial for semiconductor applications, yet machine learning models trained on computational data often struggle to generalize to experimental bandgap measurements. Challenges related to data fidelity, domain generalization, and model interpretability remain insufficiently addressed in existing evaluation frameworks. To bridge this gap, we introduce RealMat-BaG, a benchmark for assessing model reliability under experimentally relevant conditions. We curate an open-access dataset of experimental bandgaps with aligned crystal structures and compare graph neural networks as well as classical machine learning baselines. Our framework evaluates performance across statistical and domain-based splits, examines transfer from DFT-computed to experimental bandgaps, and analyzes interpretability at both elemental-property and structural levels. Our results reveal the fundamental generalization limitations of current bandgap prediction models and establish a benchmark aligned with experimental measurements for developing more reliable learning strategies for materials discovery.
title Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings
topic Materials Science
Artificial Intelligence
url https://arxiv.org/abs/2604.25568