Inverse design of two-dimensional materials with invertible neural networks

TL;DR

This paper introduces an inverse design framework using invertible neural networks to efficiently generate two-dimensional materials with desired properties, demonstrated on band gap engineering in MoS2.

Contribution

The novel framework enables bidirectional mapping between material design space and properties, facilitating efficient inverse design of 2D materials.

Findings

Generated diverse high-fidelity material candidates with near-chemical accuracy.

Extended the framework to predict metal-insulator transitions in MoS2.

Applicable to various materials and design spaces beyond the case study.

Abstract

The ability to readily design novel materials with chosen functional properties on-demand represents a next frontier in materials discovery. However, thoroughly and efficiently sampling the entire design space in a computationally tractable manner remains a highly challenging task. To tackle this problem, we propose an inverse design framework (MatDesINNe) utilizing invertible neural networks which can map both forward and reverse processes between the design space and target property. This approach can be used to generate materials candidates for a designated property, thereby satisfying the highly sought-after goal of inverse design. We then apply this framework to the task of band gap engineering in two-dimensional materials, starting with MoS2. Within the design space encompassing six degrees of freedom in applied tensile, compressive and shear strain plus an external electric field, we show the framework can generate novel, high fidelity, and diverse candidates with near-chemical accuracy. We extend this generative capability further to provide insights regarding metal-insulator transition, important for memristive neuromorphic applications among others, in MoS2 which is not otherwise possible with brute force screening. This approach is general and can be directly extended to other materials and their corresponding design spaces and target properties.