Extending the reach of quantum computing for materials science with machine learning potentials

TL;DR

This paper introduces a novel approach combining quantum computing and machine learning potentials to enable large-scale materials simulations, overcoming current quantum limitations and demonstrating practical application on IBM Quantum hardware.

Contribution

It presents the first machine learning potential trained on quantum data from real quantum hardware, extending quantum simulation capabilities to larger systems.

Findings

Machine learning potentials can be trained on noisy quantum data.

The approach enables stable molecular dynamics simulations.

Demonstrated on IBM Quantum hardware for hydrogen molecules.

Abstract

Solving electronic structure problems represents a promising field of application for quantum computers. Currently, much effort has been spent in devising and optimizing quantum algorithms for quantum chemistry problems featuring up to hundreds of electrons. While quantum algorithms can in principle outperform their classical equivalents, the polynomially scaling runtime, with the number of constituents, can still prevent quantum simulations of large scale systems. We propose a strategy to extend the scope of quantum computational methods to large scale simulations using a machine learning potential, trained on quantum simulation data. The challenge of applying machine learning potentials in today's quantum setting arises from the several sources of noise affecting the quantum computations of electronic energies and forces. We investigate the trainability of a machine learning potential selecting various sources of noise: statistical, optimization and hardware noise.Finally, we construct the first machine learning potential from data computed on actual IBM Quantum processors for a hydrogen molecule. This already would allow us to perform arbitrarily long and stable molecular dynamics simulations, outperforming all current quantum approaches to molecular dynamics and structure optimization.