Infrared window properties of AB₂C₄ (A=Zn; BIn, Ga; CTe, Se) materials via machine learning and density functional theory

Changcheng Chen, Chunlian Xiong, Xinhui Zhang, Chunling Zhang, Yue Cheng, Weijun Wang, Wenkang Yu, Xunzhe Zhang, Jinkang Yu, Zhengjun Wang, Xiaoning Guan, Jiangzhou Xie, Yaxin Xu, Gang Liu, Pengfei Lu,
Infrared window properties of AB₂C₄ (A=Zn; BIn, Ga; CTe, Se) materials via machine learning and density functional theory,
Journal of Alloys and Compounds,
Volume 1044,
2025,
184560,
ISSN 0925-8388,
https://doi.org/10.1016/j.jallcom.2025.184560.
(https://www.sciencedirect.com/science/article/pii/S0925838825061225)
Abstract: This study employs an integrated machine learning (ML) and density functional theory (DFT) approach to accelerate the discovery of Zn-based AB₂C₄ (A=Zn; BIn/Ga; CTe/Se) infrared window materials. Using XGBoost and SHAP algorithms, we identify key bandgap-governing features, notably spatial symmetry and electronic properties. Four promising candidates—ZnIn₂Te₄, ZnIn₂Se₄, ZnGa₂Te₄, ZnGa₂Se₄—are screened, among which ZnGa₂Se₄ exhibits optimal long-wave infrared performance with high transparency, low absorption, and exceptional hardness. This work validates an efficient "ML→DFT" paradigm for rapid development of high-performance IR materials.
Keywords: Infrared window material; Machine learning; DFT calculation; Optical properties; Mechanical stability