Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| 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 |