Predicting Density of States via Multi-modal Transformer

The density of states (DOS) is a spectral property of materials, which provides fundamental insights on various characteristics of materials. In this paper, we propose a model to predict the DOS by reflecting the nature of DOS: DOS determines the general distribution of states as a function of energy. Specifically, we integrate the heterogeneous information obtained from the crystal structure and the energies via multi-modal transformer, thereby modeling the complex relationships between the atoms in the crystal structure, and various energy levels. Extensive experiments on two types of DOS, i.e., Phonon DOS and Electron DOS, with various real-world scenarios demonstrate the superiority of DOSTransformer. Despite the recent progress of machine learning (ML) in materials science, most ML models developed in the field have been focused on material properties consisting of single-valued properties Kong et al. (2022), e.g., band gap energy Lee et al. (2016), formation energy Ward et al. (2016), and Fermi energy Xie & Grossman (2018). On the other hand, spectral properties are ubiquitous in materials science, characterizing various properties of materials, e.g., X-ray absorption, dielectric function, and electronic density of states Kong et al. (2022) (See Figure 1(a)).