The effects of five types of oxygen-containing functional groups (–COOH, –COC–, –OH, –CHO, and –OCH₃) on graphene quantum dots (GQDs) are investigated using time-dependent density functional theory (TD-DFT).

Graph neural networks (GNNs) have been used previously for identifying new crystalline materials. However, geometric structure is not usually taken into consideration, or only partially. Here, we develop a geometric-information-enhanced crystal graph neural network (GeoCGNN) to predict the properties of crystalline materials. By considering the distance vector between each node and its neighbors, our model can learn full topological and spatial geometric structure information. Furthermore, we incorporate an effective method based on the mixed basis functions to encode the geometric information into our model, which outperforms other GNN methods in a variety of databases. For example, for predicting formation energy our model is 25.6%, 14.3% and 35.7% more accurate than CGCNN, MEGNet and iCGCNN models, respectively. For band gap, our model outperforms CGCNN by 27.6% and MEGNet by 12.4%.

By the TD-DFT approach, we demonstrate that heteroatoms can assist charge transfer and alter the distribution of electron densities in doped-GQDs.