Machine learning and atomistic origin of high dielectric permittivity in oxides

Abstract

Discovering new stable materials with large dielectric permittivity is important for future energy storage and electronics applications. Theoretical and computational approaches help design new materials by elucidating microscopic mechanisms and establishing structure–property relations. Ab initio methods can be used to reliably predict the dielectric response, but for fast materials screening, machine learning (ML) approaches, which can directly infer properties from the structural information, are needed. Here, random forest and graph convolutional neural network models are trained and tested to predict the dielectric constant from the structural information. We create a database of the dielectric properties of oxides and design, train, and test the two ML models. Both approaches show similar performance and can successfully predict response based on the structure. The analysis of the feature importance allows identification of local geometric features leading to the high dielectric permittivity of the crystal. Dimensionality reduction and clustering further confirms the relevance of descriptors and compositional features for obtaining high dielectric permittivity.

Dielectric Ceramics Database Automatically Constructed by Data Mining in the Literature

“…Due to the wide dielectric constant distribution, we adopt the decimal logarithm of the average dielectric constant as the output for our machine learning model. Other research studies showed the same compromise when training dielectric constant predictors . With consistent consideration, the minimum, maximum, and average of some other property values had been calculated as part of the input features, following the logarithmic processing.…”

“…Other research studies showed the same compromise when training dielectric constant predictors. 42 With consistent consideration, the minimum, maximum, and average of some other property values had been calculated as part of the input features, following the logarithmic processing. The most frequently appearing phase became an input feature and transformed into a one-hot array.…”

Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multioutput and Multifidelity Machine Learning Approach

“…Previous studies have exclusively concentrated on predicting individual scalar properties, such as the band gap 8−10 and the static dielectric constant, 11,12 without accounting for the frequency dependence of optical properties. While the prediction of spectral properties has only recently emerged in materials science, multiple studies have explored multioutput learning for predicting the electronic and phononic density of states.…”

“…Nevertheless, a gap persists in the literature concerning ML surrogate models capable of accurately predicting the frequency-dependent optical properties of solid materials. Previous studies have exclusively concentrated on predicting individual scalar properties, such as the band gap − and the static dielectric constant, , without accounting for the frequency dependence of optical properties. While the prediction of spectral properties has only recently emerged in materials science, multiple studies have explored multioutput learning for predicting the electronic and phononic density of states. − In the context of optical spectra, a hierarchical-correlation model was utilized to predict the absorption coefficient at different frequencies within the visible range, solely based on the chemical composition within a collection of 69 three-cation metal oxides .…”