Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm

TL;DR

This paper introduces ParetoCSP, a novel crystal structure prediction algorithm combining multi-objective genetic algorithms with neural network potentials, outperforming existing methods in accuracy and efficiency.

Contribution

The paper presents ParetoCSP, integrating genotypic age into MOGA and employing a neural network inter-atomic potential, significantly improving crystal structure prediction performance.

Findings

ParetoCSP outperforms GN-OA by a factor of 2.562 on benchmark structures.

It generates more valid structures, enhancing search effectiveness.

Demonstrates superior predictive capabilities across diverse benchmarks.

Abstract

While crystal structure prediction (CSP) remains a longstanding challenge, we introduce ParetoCSP, a novel algorithm for CSP, which combines a multi-objective genetic algorithm (MOGA) with a neural network inter-atomic potential (IAP) model to find energetically optimal crystal structures given chemical compositions. We enhance the NSGA-III algorithm by incorporating the genotypic age as an independent optimization criterion and employ the M3GNet universal IAP to guide the GA search. Compared to GN-OA, a state-of-the-art neural potential based CSP algorithm, ParetoCSP demonstrated significantly better predictive capabilities, outperforming by a factor of $2.562$ across $55$ diverse benchmark structures, as evaluated by seven performance metrics. Trajectory analysis of the traversed structures of all algorithms shows that ParetoCSP generated more valid structures than other algorithms, which helped guide the GA to search more effectively for the optimal structures