Accelerating Discovery of Infrared Nonlinear Optical Materials with High Lattice Thermal Conductivity: Combining Machine Learning and First‐Principles Calculations

Abstract The exploration of mid/far‐infrared (mid/far‐IR) nonlinear optical (NLO) materials with high lattice thermal conductivity (LTC) is urgent in advancing laser technology, as LTC enhances resistance to high laser‐induced damage. To address the issue of the existing methods being time‐consuming when measuring LTC, this study employed machine learning (ML) methods to efficiently predict к L based on a high‐quality dataset. Seven ML models are trained, and the most optimal model is selected for identifying promising NLO materials with high LTC ( к L > 1.0 W m −1 K −1 ). The application of the model to predict the LTC led to the discovery of LiZnGaSe 3 and BeAl 2 Se 4 as potential chalcogenide candidates from the NLO materials database. The integration of ML methods with first‐principles calculations confirmed the mechanical properties and high LTC of LiZnGaSe 3 and BeAl 2 Se 4 . The chemical heatmaps of chalcogenides with high LTC are recommended. This approach facilitates the rapid screening and discovery of promising mid/far‐IR NLO materials with balanced properties and complements the к L data in the NLO materials database as an additional screening parameter for material properties.