Machine learning guided discovery of Non-Linear Optical materials

Nonlinear optical(NLO) materials are crucial in achieving desired frequencies in solid-state lasers. So far, new NLO materials have been discovered using high-throughput calculations or chemical intuition. This study demonstrates the effectiveness of utiliz- ing a high refractive index as a proxy for a high second harmonic generation(SHG) coefficient. We also emphasize the importance of hardness in screening balanced NLO materials. We develop two machine learning models to predict refractive indices and Vickers hardness. By applying these models to the OQMD database, we identify po- tential NLO candidates based on non-centrosymmetricity, refractive index, hardness value, and bandgap properties. Our findings are validated using density functional theory(DFT) calculations. Notably, our approach successfully identifies several already established NLO materials, reinforcing the validity of our methodology.