Predicting polarizabilities of silicon clusters using local chemical environments

Calculating electronic polarizabilities of large clusters with first-principles techniques is challenging because of the unfavorable scaling of computational cost with cluster size. To address this challenge, we demonstrate that polarizabilities of large hydrogenated silicon clusters containing thousands of atoms can be efficiently calculated with machine learning methods. Specifically, we construct machine learning models based on the smooth overlap of atomic positions (SOAP) descriptor and train the models using a database of calculated random-phase approximation polarizabilities for clusters containing up to 110 silicon atoms. After successfully establishing the predctive capabilities of the model across clusters in the database, we study the machine learning predictions for clusters that are too large for explicit first-principles calculations. We find that the model accurately describes the dependence of the polarizabilities on the ratio of hydrogen to silicon atoms and also predicts a bulk limit that is in good agreement with previous studies.