Classification analysis of transition-metal chalcogenides and oxides using quantum machine learning

TL;DR

This paper evaluates quantum machine learning algorithms for classifying transition-metal chalcogenides and oxides, demonstrating high accuracy and discussing their potential in accelerating materials discovery with NISQ devices.

Contribution

It compares the performance of VQE, QSVM, and QNN algorithms in classifying complex materials, highlighting QSVM's superior accuracy and exploring quantum circuit properties.

Findings

QML achieves up to 98-99% accuracy in material classification.

Classical ML reaches 100% accuracy with feature selection.

Quantum circuits' expressibility and entangling capability influence overfitting.

Abstract

Quantum machine learning (QML) leverages the potential from machine learning to explore the subtle patterns in huge datasets of complex nature with quantum advantages. This exponentially reduces the time and resources necessary for computations. QML accelerates materials research with active screening of chemical space, identifying novel materials for practical applications and classifying structurally diverse materials given their measured properties. This study analyzes the performance of three efficient quantum machine learning algorithms viz., variational quantum eigen solver (VQE), quantum support vector machine (QSVM) and quantum neural networks (QNN) for the classification of transition metal chalcogenides and oxides (TMCs &TMOs). The analysis is performed on three datasets of different sizes containing 102, 192 and 350 materials with TMCs and TMOs labelled as +1 and -1 respectively. By employing feature selection, classical machine learning achieves 100% accuracy whereas QML achieves the highest performance of 99% and 98% for test and train data respectively on QSVC. This study establishes the competence of QML models in materials classification and explores the quantum circuits in terms of over-fitting using the circuit descriptors expressibility and entangling capability. In addition, the perspectives on QML in materials research with noisy intermediate scale quantum (NISQ) devices is given.