A Review on Quantum Machine Learning in Applied Systems and Engineering

Abstract

Quantum Machine Learning (QML) has emerged as a promising frontier within artificial intelligence, offering enhanced data-driven modeling through quantum-augmented representation, optimization, and learning capabilities, particularly in applied systems and engineering. This review comprehensively analyzes QML applications across various fields, including healthcare, communications, energy, space technology, transportation, and finance. The studies are categorized by learning modalities, QML architectures, and domain-specific use cases, emphasizing hybrid quantum-classical models deployed on current quantum hardware and simulators. Key insights underscore QML's strengths in handling high-dimensional, low-sample, and time-sensitive tasks. The review addresses critical infrastructural, operational, and ethical considerations for real-world implementation. The goal is to inform system engineers, researchers, and practitioners about the evolving capabilities and challenges of applying QML in practical domains.