ML Screening and DFT Validation of BeA 2 X 4 (A = Al, Ga, In; X = Se, Te) Ternary Compounds: Design and Optimization for Infrared Optoelectronic Materials

Machine-learning-accelerated discovery of monoclinic BeA 2 X 4 (A = Al, Ga, In; X = Se, Te) yields six infrared-absorbing chalcogenides with thickness-tunable absorptance. A 3814-compound prototype library was stability- and gap-screened to 1268 candidates; XGBoost ( R 2 = 0.939, MAE = 0.241 eV) nominated BeAl 2 Se 4, BeGa 2 Se 4, BeIn 2 Se 4, BeAl 2 Te 4, BeGa 2 Te 4, and BeIn 2 Te 4 . Hybrid-DFT (HSE06) and 10,000 fs ab initio molecular dynamics (AIMD) simulations at 300 K confirm the monoclinic Pm structure with thermal robustness. BeGa 2 Se 4 exhibits the highest Vickers hardness (1.59 GPa), and BeAl 2 Te 4 exhibits the largest Poisson ratio (0.44). The strong anisotropic absorption spans 0.5–1.6 eV, peaking at 1.21 × 10 5 cm –1 (BeIn 2 Se 4 ) and 1.16 × 10 5 cm –1 (BeAl 2 Te 4, 0.5–1 eV). Absorptance scales linearly with thickness: 0.747 (500 nm BeAl 2 Se 4 ), 0.726 (450 nm BeGa 2 Se 4 ), and 0.650 (300 nm BeIn 2 Se 4 ), defining a 300–500 nm design window that balances absorption gain against carrier transport loss. Direct band gaps eliminate phonon bottlenecks, while their systematic narrowing with A/X cation radii enables continuous spectral tuning across the near- to mid-infrared. The quantitative structure–absorption map provides experimentally accessible guidelines for next-generation infrared absorption coatings and photodetector absorber layers.