Computational discovery of new 2D materials using deep learning generative models
This work addresses the challenge of discovering new 2D materials for materials scientists, offering a computational approach to explore a vast chemical design space.
This paper proposes a deep learning generative model combined with a random forest classifier to discover new 2D materials. They identified 267,489 new potential 2D material compositions and confirmed the stability of twelve 2D/layered materials using DFT calculations.
Two dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties. While several thousand 2D materials have been screened in existing materials databases, discovering new 2D materials remains to be challenging. Herein we propose a deep learning generative model for composition generation combined with random forest based 2D materials classifier to discover new hypothetical 2D materials. Furthermore, a template based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. So far, we have discovered 267,489 new potential 2D materials compositions and confirmed twelve 2D/layered materials by DFT formation energy calculation. Our results show that generative machine learning models provide an effective way to explore the vast chemical design space for new 2D materials discovery.