
Advanced Science, Journal Year: 2025, Volume and Issue: unknown
Published: April 26, 2025
Abstract Discovering novel infrared functional materials (IRFMs) hold tremendous significance for laser industry. Incorporating artificial intelligence into material discovery has been recognized as a pivotal trend driving advancements in science. In this work, an IRFM predictor based on machine learning (ML) is developed the pre‐selection of most promising candidates, which interpretable analyses reveal prior domain knowledge IRFMs. Under guidance predictor, series selenoborates, ABa 3 (BSe ) 2 X (A = Rb, Cs; Cl, Br, I) are successfully predicted and synthesized. Comprehensive characterizations together with first‐principles that these exhibit preferred properties wide bandgaps (2.92 – 3.04 eV), moderate birefringence (0.145 0.170 at 1064 nm), high laser‐induced damage thresholds (LIDTs) (4 6 Ý AGS) large second harmonic generation (SHG) responses (0.9 1 × AGS). Structure‐property relationship indicate [BSe ] unit can be regarded potential gene exploring This work may open avenue high‐performance materials.
Language: Английский