Genetic programming-based learning of carbon interatomic potential for materials discovery

TL;DR

This paper introduces a novel genetic programming approach to automatically discover interatomic potential functions for carbon materials, achieving accurate energy predictions with low computational cost.

Contribution

It presents a new strongly typed parallel genetic programming method combined with multi-objective optimization for potential function discovery, improving automation and accuracy.

Findings

Predicted energies within ±7.70 eV of DFT data

Generalized well across multiple carbon structures

Open-source code available for community use

Abstract

Efficient and accurate interatomic potential functions are critical to computational study of materials while searching for structures with desired properties. Traditionally, potential functions or energy landscapes are designed by experts based on theoretical or heuristic knowledge. Here, we propose a new approach to leverage strongly typed parallel genetic programming (GP) for potential function discovery. We use a multi-objective evolutionary algorithm with NSGA-III selection to optimize individual age, fitness, and complexity through symbolic regression. With a DFT dataset of 863 unique carbon allotrope configurations drawn from 858 carbon structures, the generated potentials are able to predict total energies within $\pm 7.70$ eV at low computational cost while generalizing well across multiple carbon structures. Our code is open source and available at \url{http://www.github.com/usccolumbia/mlpotential