Graph Transformer Networks for Accurate Band Structure Prediction: An End-to-End Approach
This work addresses a gap in materials science by providing an efficient end-to-end solution for band structure prediction, which is incremental over existing ML methods that focus on band gaps or indirect estimations.
The paper tackles the problem of predicting electronic band structures from crystal structures by introducing a graph Transformer-based end-to-end model that directly predicts band structures with high accuracy, demonstrating its ability to derive properties like band gap and band dispersion on large datasets.
Predicting electronic band structures from crystal structures is crucial for understanding structure-property correlations in materials science. First-principles approaches are accurate but computationally intensive. Recent years, machine learning (ML) has been extensively applied to this field, while existing ML models predominantly focus on band gap predictions or indirect band structure estimation via solving predicted Hamiltonians. An end-to-end model to predict band structure accurately and efficiently is still lacking. Here, we introduce a graph Transformer-based end-to-end approach that directly predicts band structures from crystal structures with high accuracy. Our method leverages the continuity of the k-path and treat continuous bands as a sequence. We demonstrate that our model not only provides accurate band structure predictions but also can derive other properties (such as band gap, band center, and band dispersion) with high accuracy. We verify the model performance on large and diverse datasets.