Active learning for accelerated design of layered materials

TLDR

Heterostructures of vertically stacked transition metal dichalcogenide monolayers promise optoelectronic and thermoelectric applications, but exhaustive ab initio screening of their vast compositional space is computationally prohibitive and the property–structure relationships are highly nonlinear. The study aims to develop a Gaussian process regression combined with Bayesian active learning to efficiently identify optimal heterostructures with minimal ab initio calculations. The approach models electronic band gap, band dispersions, and thermoelectric performance using data from the Materials Project and BoltzTraP, and employs Bayesian optimization to guide the search. Bayesian optimization markedly lowers the computational cost for discovering optimal structures compared to regression-only strategies, and the resulting models and open‑source software enable predictions for any property.

Abstract

Abstract Hetero-structures made from vertically stacked monolayers of transition metal dichalcogenides hold great potential for optoelectronic and thermoelectric devices. Discovery of the optimal layered material for specific applications necessitates the estimation of key material properties, such as electronic band structure and thermal transport coefficients. However, screening of material properties via brute force ab initio calculations of the entire material structure space exceeds the limits of current computing resources. Moreover, the functional dependence of material properties on the structures is often complicated, making simplistic statistical procedures for prediction difficult to employ without large amounts of data collection. Here, we present a Gaussian process regression model, which predicts material properties of an input hetero-structure, as well as an active learning model based on Bayesian optimization, which can efficiently discover the optimal hetero-structure using a minimal number of ab initio calculations. The electronic band gap, conduction/valence band dispersions, and thermoelectric performance are used as representative material properties for prediction and optimization. The Materials Project platform is used for electronic structure computation, while the BoltzTraP code is used to compute thermoelectric properties. Bayesian optimization is shown to significantly reduce the computational cost of discovering the optimal structure when compared with finding an optimal structure by building a regression model to predict material properties. The models can be used for predictions with respect to any material property and our software, including data preparation code based on the Python Materials Genomics (PyMatGen) library as well as python-based machine learning code, is available open source.