Building Machine Learning systems for multi-atoms structures: CH₃NH₃PbI₃ perovskite nanoparticles

In this study, we built a variety of Machine Learning (ML) systems over 23 different sizes of CH₃NH₃PbI₃ perovskite nanoparticles (NPs) to predict the atoms in the NPs from their geometric locations. Our findings show that a specific type of ML algorithms, tree-based models which are Random Forest (RF), Extreme Gradient Boosting (XGBoost), Decision Trees (DT), can perfectly learn CH₃NH₃PbI₃ perovskite NPs. Surprisingly, some popular ML algorithms such as Naive Bayes (NB), Support Vector Machines (SVM), Partial Least Squares (PLS), Regularized Logistic Regression (LR), Neural Networks (NN), Stacked Auto-Encoder Deep Neural Network (DNN), K-Nearest Neighbor (KNN) fail to learn CH₃NH₃PbI₃ perovskite NPs.