Machine-learning accelerated identification of exfoliable two-dimensional materials

Abstract

Two-dimensional (2D) materials have been a central focus of recent research because they host a variety of properties, making them attractive both for fundamental science and for applications. It is thus crucial to be able to identify accurately and efficiently if bulk three-dimensional (3D) materials are formed by layers held together by a weak binding energy that, thus, can be potentially exfoliated into 2D materials. In this work, we develop a machine-learning (ML) approach that, combined with a fast preliminary geometrical screening, is able to efficiently identify potentially exfoliable materials. Starting from a combination of descriptors for crystal structures, we work out a subset of them that are crucial for accurate predictions. Our final ML model, based on a random forest classifier, has a very high recall of 98\%. Using a SHapely Additive exPlanations (SHAP) analysis, we also provide an intuitive explanation of the five most important variables of the model. Finally, we compare the performance of our best ML model with a deep neural network architecture using the same descriptors. To make our algorithms and models easily accessible, we publish an online tool on the Materials Cloud portal that only requires a bulk 3D crystal structure as input. Our tool thus provides a practical yet straightforward approach to assess whether any 3D compound can be exfoliated into 2D layers.

References in corpus (23)

• Electric Field Effect in Atomically Thin Carbon Films
• Two-Dimensional Material Nanophotonics
• A Higher-Accuracy van der Waals Density Functional
• On representing chemical environments
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Moiré Excitons in Van der Waals Heterostructures
• The Computational 2D Materials Database: High-Throughput Modeling and Discovery of Atomically Thin Crystals
• Resonantly hybridised excitons in moiré superlattices in van der Waals heterostructures
• Comparing molecules and solids across structural and alchemical space
• Highly crystalline 2D superconductors
• Van der Waals density functional: an appropriate exchange functional
• Materials Cloud, a platform for open computational science
• Topology-Scaling Identification of Layered Solids and Stable Exfoliated 2D Materials
• Performance of arsenene and antimonene double-gate MOSFETs from first principles
• AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance
• Machine learning-guided synthesis of advanced inorganic materials
• Prediction of a large-gap and switchable Kane-Mele quantum spin Hall insulator
• Deep-Learning-Enabled Fast Optical Identification and Characterization of Two-Dimensional Materials
• New Family of Robust 2D Topological Insulators in van der Waals Heterostructures
• Intelligent Identification of Two-Dimensional Structure by Machine-Learning Optical Microscopy
• Shear and breathing modes of layered materials
• Twist-resilient and robust ferroelectric quantum spin Hall insulators driven by van der Waals interactions

Cited by in corpus (2)

• Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
• Phyllosilicates as earth-abundant layered materials for electronics and optoelectronics: Prospects and challenges in their ultrathin limit