Hydrogenated Graphene with Tunable Poisson's Ratio Using Machine Learning: Implication for Wearable Devices and Strain Sensors

Abstract

The Poisson's ratio of two-dimensional materials such as graphene can be tailored by surface hydrogenation. The density and distribution of hydrogenation may significantly affect the Poisson's ratio of the graphene structure. Therefore, optimization of the distribution of hydrogenation is useful to achieve the structure with a targeted Poisson's ratio. For this purpose, we developed an inverse design algorithm based on machine learning using the XGBoost method to reveal the relationship between the Poisson's ratio and distribution of hydrogenation. Based on this relationship, we can optimize the hydrogenated graphene structure to have a low Poisson's ratio. Instead of performing molecular dynamic simulations for all possible structures, we could find the optimal structures using the search algorithm and save significant computational resources. This algorithm could successfully discover structures with low Poisson's ratios around -0.5 after only 1600 simulations in a large design space of approximately 5.2 x 10(6 )possible configurations. Moreover, the optimal structures were found to exhibit excellent flexibility under compression of around -65% without failure and can be used in many applications such as flexible strain sensors. Our results demonstrate the applicability of machine learning to the efficient development of new metamaterials with desired properties.