Boosting-Crystal Graph Convolutional Neural Network for Predicting Highly Imbalanced Data: A Case Study for Metal-Insulator Transition Materials.

Applying machine-learning techniques for imbalanced data sets presents a significant challenge in materials science since the underrepresented characteristics of minority classes are often buried by the abundance of unrelated characteristics in majority of classes. Existing approaches to address this focus on balancing the counts of each class using oversampling or synthetic data generation techniques. However, these methods can lead to loss of valuable information or overfitting. Here, we introduce a deep learning framework to predict minority-class materials, specifically within the realm of metal-insulator transition (MIT) materials. The proposed approach, termed boosting-CGCNN, combines the crystal graph convolutional neural network (CGCNN) model with a gradient-boosting algorithm. The model effectively handled extreme class imbalances in MIT material data by sequentially building a deeper neural network. The comparative evaluations demonstrated the superior performance of the proposed model compared to other approaches. Our approach is a promising solution for handling imbalanced data sets in materials science.

A-Site Effect on the Oxidation Process of Sn-Halide Perovskite: First-Principles Calculations.

Tin-halide perovskite solar cells (Sn-PSCs) are promising candidates as an alternative to toxic lead-halide PSCs. However, Sn2+ is easily oxidized to Sn4+, so Sn-PSCs are unstable in air. Here, we use first-principles density functional theory calculations to elucidate the oxidation process of Sn2+ at the surface of ASnBr3 [A = Cs or CH3NH3 (MA)]. Regardless of the A-site cation, adsorption of O2 leads to the formation of SnO2, which creates a Sn vacancy at the surface. The A-site cation determines whether the created vacancies are stabilized in the bulk or at the surface. For CsSnBr3, the Sn vacancy is stabilized at the surface, so further oxidation is limited. For MASnBr3, the Sn vacancy moves into bulk region, so additional Sn is supplied to the surface; as a result, a continuous oxidation process can occur. The stabilization of Sn vacancy is closely related to the polarization that the A-site cation causes in the system.