Accelerating inverse crystal structure prediction by machine learning: a case study of carbon allotropes

TL;DR

This study demonstrates how machine learning can significantly accelerate the prediction of carbon allotropes' properties, leading to the discovery of a new superhard, semiconducting carbon structure.

Contribution

The paper introduces a machine learning approach integrated with structure prediction to efficiently identify new carbon allotropes with high elastic modulus and novel properties.

Findings

ML model predicts elastic modulus more accurately than existing methods.

Discovery of a new carbon allotrope, Cmcm-C24, with hardness >80 GPa.

The new allotrope is a stable, semiconducting phase with a direct bandgap.

Abstract

Based on structure prediction method, the machine learning method is used instead of the density function theory (DFT) method to predict the material properties, thereby accelerating the material search process. In this paper, we established a data set of carbon materials by high-throughput calculation with available carbon structures obtained from the Samara Carbon Allotrope Database. We then trained an ML model that specifically predicts the elastic modulus (bulk modulus, shear modulus, and the Young's modulus) and confirmed that the accuracy is better than that of AFLOW-ML in predicting the elastic modulus of a carbon allotrope. We further combined our ML model with the CALYPSO code to search for new carbon structures with a high Young's modulus. A new carbon allotrope not included in the Samara Carbon Allotrope Database, named Cmcm-C24, which exhibits a hardness greater than 80 GPa, was firstly revealed. The Cmcm-C24 phase was identified as a semiconductor with a direct bandgap. The structural stability, elastic modulus, and electronic properties of the new carbon allotrope were systematically studied, and the obtained results demonstrate the feasibility of ML methods accelerating the material search process.