Quantum and Hybrid Machine-Learning Models for Materials-Science Tasks

TL;DR

This paper explores the application of quantum and hybrid quantum-classical machine learning models, specifically QSVM and QNN, to materials science tasks like predicting stacking fault energies and ductilizing solutes in magnesium, achieving high validation scores.

Contribution

It introduces the adaptation and systematic testing of quantum algorithms for specific materials science problems, demonstrating their effectiveness with optimized hyperparameters.

Findings

Quantum models achieved approximately 90% validation scores.

Optimized quantum models successfully predict solutes based on elemental properties.

Hybrid quantum neural networks perform comparably to quantum support vector machines.

Abstract

Quantum computing has become increasingly practical in solving real-world problems due to advances in hardware and algorithms. In this paper, we aim to design and estimate quantum machine learning and hybrid quantum-classical models in a few practical materials science tasks, i.e., predicting stacking fault energies and solutes that can ductilize magnesium. To this end, we adopt two different representative quantum algorithms, i.e., quantum support vector machines (QSVM) and quantum neural networks (QNN), and adjust them to our application scenarios. We systematically test the performance with respect to the hyperparameters of selected ansatzes. We identify a few combinations of hyperparameters that yield validation scores of approximately 90\% for QSVM and hybrid QNN in both tasks. Eventually, we construct quantum models with optimized parameters for regression and classification that predict targeted solutes based on the elemental volumes, electronegativities, and bulk moduli of chemical elements.