Cluster Generation via Deep Energy-Based Model

TL;DR

This paper introduces a deep learning approach using graph convolutional networks to generate stable nanocluster structures by constructing a smooth artificial potential energy surface, capable of extrapolating to larger structures and discovering new stable configurations.

Contribution

The paper presents a novel deep energy-based model that constructs a smooth potential surface for nanoclusters, enabling extrapolation to larger structures and discovery of new stable configurations.

Findings

Successfully generated stable silica clusters with 28 to 51 atoms.

The method is universal across different atomic compositions.

First application to find stable structures with larger atom counts.

Abstract

We present a new approach for the generation of stable structures of nanoclusters using deep learning methods. Our method consists in constructing an artificial potential energy surface, with local minima corresponding to the most stable structures and which is much smoother than "real" potential in the intermediate regions of the configuration space. To build the surface, graph convolutional networks are used. The method can extrapolates the potential surface to cases of structures with larger number of atoms than was used in training. Thus, having a sufficient number of low-energy structures in the training set, the method allows to generate new candidates for the ground-state structures, including ones with larger number of atoms. We applied the approach to silica clusters $(SiO_2)_n$ and for the first time found the stable structures with n=28...51. The method is universal and does not depend on the atomic composition and number of atoms.