Search

Halide perovskite materials have broad prospects for applications in various fields such as solar cells, LED devices, photodetectors, fluorescence labeling, bioimaging, and photocatalysis due to their bandgap characteristics. This study compiled experimental data from the published literature and utilized the excellent predictive capabilities, low overfitting risk, and strong robustness of ensemble learning models to analyze the bandgaps of halide perovskite compounds. The results demonstrate the effectiveness of ensemble learning decision tree models, especially the gradient boosting decision tree model, with a root mean square error of 0.090 eV, a mean absolute error of 0.053 eV, and a determination coefficient of 93.11%. Research on data related to ratios calculated through element molar quantity normalization indicates significant influences of ions at the X and B positions on the bandgap. Additionally, doping with iodine atoms can effectively reduce the intrinsic bandgap, while hybridization of the s and p orbitals of tin atoms can also decrease the bandgap. The accuracy of the model is validated by predicting the bandgap of the photovoltaic material MASn1−xPbxI3. In conclusion, this study emphasizes the positive impact of machine learning on material development, especially in predicting the bandgaps of halide perovskite compounds, where ensemble learning methods demonstrate significant advantages. [ABSTRACT FROM AUTHOR]

Mapping impervious surface area (ISA) dynamics at the regional and global scales is an important task that supports the management of the urban environment and urban ecological systems. In this study, we aimed to develop a new method for ISA percentage (ISA%) mapping using Nighttime Light (NTL) and MODIS products. The proposed method consists of three major steps. First, we calculated the Enhanced Vegetation Index (EVI)-adjusted NTL index (EANTLI) and performed intra-annual and inter-annual corrections on the DMSP-OLS data. Second, based on the geographically weighted regression (GWR) model, we built a consistent NTL product from 2000 to 2019 by performing an intercalibration between DMSP-OLS and VIIRS images. Third, we adopted a GA-BP neural network model to monitor ISA% dynamics using NTL imagery, MODIS imagery, and population data. Taking the Guangdong–Hong Kong–Macao Greater Bay as the study area, our results indicate that the ISA% in our study area increased from 7.97% in 2000 to 17.11% in 2019, with a mean absolute error (MAE) of 0.0647, root mean square error (RMSE) of 0.1003, Pearson's coefficient of 0.9613, and R2 (R-squared) of 0.9239. Specifically, these results demonstrate the effectiveness of the proposed method in mapping ISA and investigating ISA dynamics using temporal features extracted from consistent NTL and MODIS products. The proposed method is feasible when generating ISA% at a large scale at high frequency, given the ease of implementation and the availability of input data sources. [ABSTRACT FROM AUTHOR]