The Application of Supervised Learning Algorithms in Predicting the Formation Energy of NLO Crystals

Abstract

AbstractNonlinear optical crystals (NLO) are a key class of functional materials in the field of laser technology due to their excellent frequency conversion effects and physical–chemical stability. The research aims to find NLO crystals with superior stability by predicting their formation energy. In this study, only compositional information is utilized as input features and models are constructed using regression algorithms such as Random Forest Regression (RFR), Support Vector Regression (SVR), and Gradient Boosting Regression (GBR). Notably, the GBR model exhibited outstanding predictive performance, with an R2 value of 0.935 and root mean square error (RMSE) of 0.248 eV per atom. Additionally, SHapley Additive exPlanations (SHAP) analysis is employed to elucidate the fundamental principles behind the predictions by assessing the contribution of each feature to the formation energy. To validate the reliability of the models, first‐principles calculations are conducted to predict the formation energy of materials of GaP, ZnGeP2, and CdSiP2. The error range between the model predictions and the Generalized Gradient Approximation (GGA) calculated values is ≈0.1 eV per atom, confirming the accuracy of the models.