New Ways to Discover Novel Nonlinear Optical Materials: Scaling Machine Learning with Chemical Descriptors Information

The efficient experimental exploration of innovative nonlinear optical materials has long been a challenging task due to the vast chemical space and the lack of suitable theoretical prediction frameworks. Herein, a novel theoretical design paradigm is proposed to accelerate the discovery of novel materials with strong second harmonic generation intensity. This challenge is addressed through several key technologies. 1) A high-precision machine learning model is proposed on the maximum nonlinear optical dataset. 2) Descriptors information paves the way to systematically offer valuable chemical insights for designing chemical structures. 3) A flexible and fast chemical space construction and exploration method is proposed. Accordingly, a nonlinear optical crystal is successfully synthesized through the constructed "machine to knowledge" theoretical framework. This novel compound exhibits a stronger second-harmonic generation response and wider optical transmission range. This work introduces novel theoretical design concepts and provides innovative chemical insights into optical materials or other functional materials.