Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface

TL;DR

This paper introduces two machine learning-based acceleration schemes integrated with CALYPSO for large-scale structure prediction, significantly reducing computational costs while accurately predicting structures of medium and large boron clusters.

Contribution

The work develops novel ML-accelerated structure prediction schemes that enable efficient large-system searches, combining pre-constructed and on-the-fly trained ML potentials with CALYPSO.

Findings

Successfully predicted structures of B36 and B40 clusters matching experimental data.

Proposed a new putative global minimum for B84 cluster.

Achieved several orders of magnitude reduction in computational cost compared to DFT.

Abstract

Ab initio structure prediction methods have been nowadays widely used as powerful tools for structure searches and material discovery. However, they are generally restricted to small systems owing to the heavy computational cost of underlying density functional theory (DFT) calculations. In this work, by combining state-of-art machine learning (ML) potential with our in-house developed CALYPSO structure prediction method, we developed two acceleration schemes for structure prediction toward large systems, in which ML potential is pre-constructed to fully replace DFT calculations or trained in an on-the-fly manner from scratch during the structure searches. The developed schemes have been applied to medium- and large-sized boron clusters, which are challenging cases for both construction of ML potentials and extensive structure searches. Experimental structures of B36 and B40 clusters can be readily reproduced, and the putative global minimum structure for B84 cluster is proposed, where substantially less computational cost by several orders of magnitude is evident if compared with full DFT-based structure searches. Our results demonstrate a viable route for structure prediction toward large systems via the combination of state-of-art structure prediction methods and ML techniques.