A Convolutional Neural Network Model for Predicting Perovskite Bandgaps

View Full Paper

Ask AI

Bookmark

Share

Key Points

This research aims to develop a model for accurately predicting bandgaps in perovskite materials using advanced neural network techniques.
Developed a convolutional neural network model integrated with a channel attention mechanism.
Utilized data from both single and double perovskite structures (ABX3 and A2BB'X6).
Implemented a double pooling structure for feature extraction and performed interpretability analysis to identify key influencing factors.
Achieved R²=0.917 and RMSE=0.493 eV on the test set, outperforming traditional models like XGBoost.
For an external test set, maintained R²=0.936, indicating robust generalization.
Identified crucial features such as formation energy and electronegativity that influence bandgap.

Demonstrates accurate bandgap predictions in perovskite materials, indicating improved design potential.

No abstract yet. The journal hasn't published one we can show.

No takes yet. Share an insight, caveat, or question.

Wang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share