Machine learning for 2D material–based devices

Abstract

Two-dimensional (2D) materials have emerged as a cornerstone for next-generation electronics, offering unprecedented opportunities for device miniaturization, energy-efficient computing, and novel functional applications. Their atomic-scale thickness, coupled with exceptional electrical, mechanical, and optical properties, makes them highly promising for applications ranging from ultra-scaled transistors to neuromorphic and quantum devices. However, optimizing these materials for device fabrication remains a complex and resource-intensive challenge due to the vast parameter space involved in their synthesis, processing, and integration. Machine learning (ML), a pivotal aspect of artificial intelligence (AI), has emerged as a powerful tool to accelerate the development of 2D material–based electronics by extracting insights from large experimental datasets and automating decision-making in high-throughput experimentation. This review highlights the critical role of ML in advancing 2D material research, focusing on growth optimization through material selection and morphology control, characterization for quality assessment, and device design through fabrication parameter optimization and performance prediction. This work aims to provide a comprehensive overview of the synergistic relationship between ML and 2D materials, outlining current advancements, challenges, and future prospects in AI-assisted material and device engineering.