Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential
This work addresses the scarcity of public dielectric data for material design, offering a novel method to predict directional dielectric tensors, which is important for researchers and developers in materials science and engineering.
The study tackled the problem of predicting dielectric tensors for inorganic materials, which are crucial for technologies like flash memory and photovoltaics, by developing an equivariant model that leverages latent information from a neural network potential, achieving accurate predictions and identifying promising candidates such as Cs2Ti(WO4)3 with a dielectric constant of 180.90 and CsZrCuSe3 with an anisotropic ratio of 121.89.
Dielectrics are crucial for technologies like flash memory, CPUs, photovoltaics, and capacitors, but public data on these materials are scarce, restricting research and development. Existing machine learning models have focused on predicting scalar polycrystalline dielectric constants, neglecting the directional nature of dielectric tensors essential for material design. This study leverages multi-rank equivariant structural embeddings from a universal neural network potential to enhance predictions of dielectric tensors. We develop an equivariant readout decoder to predict total, electronic, and ionic dielectric tensors while preserving O(3) equivariance, and benchmark its performance against state-of-the-art algorithms. Virtual screening of thermodynamically stable materials from Materials Project for two discovery tasks, high-dielectric and highly anisotropic materials, identifies promising candidates including Cs2Ti(WO4)3 (band gap $E_g=2.93 \mathrm{eV}$, dielectric constant $\varepsilon=180.90$) and CsZrCuSe3 (anisotropic ratio $α_r = 121.89$). The results demonstrate our model's accuracy in predicting dielectric tensors and its potential for discovering novel dielectric materials.