Date created: | Last Updated:

Category: Data

Description: Understanding the structure-property relationship is crucial for designing materials with desired properties. The past few years witnessed remarkable progress in machine learning methods for such connection. However, substantial challenges remain, including generalizability of models and prediction of properties with material-dependent output dimensions. Here we present the virtual node graph neural network to address the challenges. By developing three virtual node approaches, we achieve $\Gamma$-phonon spectra and full phonon dispersion prediction from atomic coordinates. We show that, compared to the machine-learning interatomic potentials, our approach achieves orders-of-magnitude higher efficiency with comparable to better accuracy. This allows us to generate databases for $\Gamma$-phonon containing over 146,000 materials and phonon bandstructure of zeolites. Our work provides an avenue for rapid and high-quality prediction of phonon band structures enabling materials design with desired phonon properties. The virtual node method also provides a generic method for machine learning design with a high level of flexibility.