CEGNN

CEGNN is a model for predicting the bandgap and band alignment types of transition metal dichalcogenides (TMDs) and organic perovskites (2D-LHPs). This project aims to rapidly screen TMDs/2D-LHPs heterostructures through high-throughput calculations to advance the research and application of optoelectronic materials.

Project Background

Heterostructures formed by transition metal dichalcogenides (TMDs) and two-dimensional layered halide perovskites (2D-LHPs) have garnered widespread attention due to their unique optoelectronic properties. However, theoretical research faces challenges due to the large number of atoms and lattice matching issues. With the discovery of more novel 2D-LHPs, there is an urgent need for a method to quickly predict and screen TMDs/2D-LHPs heterostructures.

This study employs first-principles calculations to perform high-throughput computations on 602 TMDs/2D-LHPs heterostructures.

To overcome the limitations of computational costs, we developed a crystal graph convolutional neural network model based on computational data to predict the electronic properties of TMDs/2D-LHPs heterostructures. Using this model, we predicted the bandgap and band alignment types of 9,360 TMDs/2D-LHPs heterostructures

Dataset

The band structure data is stored at the following link: https://drive.google.com/file/d/1P2aQIQemA2VAMsnLGPXGA4RdDHuKHBRY/view?usp=sharing