Investigating the effect of structural variations on the band gap of titanium dioxide using machine learning
Physica Scripta · 23.01.2026 · 101 (3) · 036003
DOI: 10.1088/1402-4896/ae35e8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 20.01.2026. Verfasst von Zihe Cao und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.
Abstract (Originalsprache)
Predicting the band gap of titanium dioxide (TiO 2 ) is crucial for its photocatalytic applications, yet first-principles calculations of band gap properties are often computationally expensive. Machine learning offers an efficient alternative, but predictive accuracy strongly depends on how structural features are represented. In this work, we investigate the structure–property relationships governing the TiO 2 band gap by comparing different feature construction strategies. Traditional structure descriptors based on local atomic environments show limitations in effectively encoding complex structural correlations. In contrast, graph neural network (GNN) models more effectively learn structure–property relationships and achieve higher prediction accuracy. Further deconstruction of the model reveals that its predictive performance relies on a synergistic integration of chemical identity, local geometry, and non-local structural information. Feature visualization further shows that the model learns task-adaptive representations. These findings highlight the necessity of incorporating non-local structural information for predicting global properties and provide new insights into the machine learning driven materials design.
Förderung
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
Zitieren
APA
Cao, Z., Wang, H., Shi, C., Yang, Y., Chen, X., Zhang, W., Yu, Z., Lu, Q., & Zhang, B. (2026). Investigating the effect of structural variations on the band gap of titanium dioxide using machine learning. Physica Scripta, 101(3), 036003. https://doi.org/10.1088/1402-4896/ae35e8
Vancouver
Cao Z, Wang H, Shi C, Yang Y, Chen X, Zhang W, et al. Investigating the effect of structural variations on the band gap of titanium dioxide using machine learning. Physica Scripta. 2026;101(3):036003. doi:10.1088/1402-4896/ae35e8
BibTeX
@article{Cao2026,
author = {Cao, Zihe and Wang, Huan and Shi, Changli and Yang, Yi and Chen, Xiaolu and Zhang, Wenming and Yu, Zhangqi and Lu, Qiang and Zhang, Bing},
title = {Investigating the effect of structural variations on the band gap of titanium dioxide using machine learning},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {3},
pages = {036003},
doi = {10.1088/1402-4896/ae35e8}
}
EUVIMED