Topic: Application of Machine Learning to 2D Materials

Two-dimensional (2D) materials have been considered wonder materials ever since the discovery of graphene, derived from graphite in 2004. This groundbreaking revelation paved the way for identifying numerous elemental 2D materials, such as silicene, germanene, stanine, phosphorene, arsenene, and antimonene. In addition, compound 2D materials have been successfully synthesized, with transition metal-dichalcogenides (TMDs), including MoS₂, MoSe₂, WS₂, and WSe₂, emerging as the most extensively studied family within this realm. Over the years, various techniques have been employed to exfoliate or synthesize 2D materials, enabling comprehensive investigations into their structures, properties, and applications. These studies have unveiled plenty of fascinating mechanical, optical, and electrical properties, setting the stage for diverse potential applications in electronics, optoelectronics, sensors, energy storage, surface catalysis, biology, etc.

However, conventional experimental and computational methods are difficult to keep up with the rapidly growing demands in the study of 2D materials. In response, machine learning (ML) approaches have proven to be effective tools for studying a wide variety of materials, with 2D materials no exception. Therefore, high-throughput experimental or computational methods are desperately needed to provide extensive datasets for ML applications, which can, in return, complement experimental work. Although abundant studies have focused on 2D materials in recent years, more aspects on microstructures, properties, and applications still call for ML and other approaches to provide more insights. The huge compositional space of 2D materials offers limitless opportunities for academic and industrial research and development.

This Special Issue aims to present the most recent advancements in ML-based approaches for the study of 2D materials. The scope includes a wide range of topics but not limited to:
● Data-driven approaches;
● ML algorithms;
● Multiscale modeling;
● ML interatomic potentials;
● High-throughput experiments.

12 May 2024