Chemical Environment Adaptive Learning for Optical Band Gap Prediction of Doped Graphitic Carbon Nitride Nanosheets

TL;DR

This paper introduces ChemGNN, a graph neural network model that significantly improves the accuracy of optical band gap predictions in doped graphitic carbon nitride nanosheets, facilitating faster materials discovery.

Contribution

The study develops a novel ChemGNN model that captures local chemical environments, achieving over 100% accuracy improvement in band gap prediction for doped g-C3N4 compared to existing GNNs.

Findings

ChemGNN achieves >100% accuracy improvement over existing GNNs.

The model accurately predicts band gaps of various doped g-C3N4 structures.

ChemGNN enables high-throughput materials property prediction.

Abstract

This study presents a novel Machine Learning Algorithm, named Chemical Environment Graph Neural Network (ChemGNN), designed to accelerate materials property prediction and advance new materials discovery. Graphitic carbon nitride (g-C3N4) and its doped variants have gained significant interest for their potential as optical materials. Accurate prediction of their band gaps is crucial for practical applications, however, traditional quantum simulation methods are computationally expensive and challenging to explore the vast space of possible doped molecular structures. The proposed ChemGNN leverages the learning ability of current graph neural networks (GNNs) to satisfactorily capture the characteristics of atoms' local chemical environment underlying complex molecular structures. Our benchmark results demonstrate more than 100% improvement in band gap prediction accuracy over existing GNNs on g-C3N4. Furthermore, the general ChemGNN model can precisely foresee band gaps of various doped g-C3N4 structures, making it a valuable tool for performing high-throughput prediction in materials design and development.