Tailoring nanoporous graphene via machine learning: Predicting probabilities and formation times of arbitrary nanopore shapes

Nanopores in graphene, a 2D material, are currently being explored for various applications, such as gas separation, water desalination, and DNA sequencing. The shapes and sizes of nanopores play a major role in determining the performance of devices made out of graphene. However, given an arbitrary nanopore shape, anticipating its creation probability and formation time is a challenging inverse problem, solving which could help develop theoretical models for nanoporous graphene and guide experiments in tailoring pore sizes/shapes. In this work, we develop a machine learning framework to predict these target variables, i.e., formation probabilities and times, based on data generated using kinetic Monte Carlo simulations and chemical graph theory. Thereby, we enable the rapid quantification of the ease of formation of a given nanopore shape in graphene via silicon-catalyzed electron-beam etching and provide an experimental handle to realize it, in practice. We use structural features such as the number of carbon atoms removed, the number of edge atoms, the diameter of the nanopore, and its shape factor, which can be readily extracted from the nanopore shape. We show that the trained models can accurately predict nanopore probabilities and formation times with R-2 values on the test set of 0.97 and 0.95, respectively. Not only that, we obtain physical insight into the working of the model and discuss the role played by the various structural features in modulating nanopore formation. Overall, our work provides a solid foundation for experimental studies to manipulate nanopore sizes/shapes and for theoretical studies to consider realistic structures of nanopores in graphene. Published under an exclusive license by AIP Publishing.

Automated summary

This study develops a machine learning framework to predict the formation probabilities and times of nanopores in graphene. The framework is trained using data generated from kinetic Monte Carlo simulations and chemical graph theory. The trained models accurately predict the nanopore probabilities and formation times, and provide insight into the role of structural features in modulating nanopore formation.