Quantum-enhanced machine learning technique for rapid post-earthquake assessment of building safety

Abstract

Fast, accurate damage assessment of numerous buildings for large areas is vital for saving lives, enhancing decision-making, and expediting recovery, thereby increasing urban resilience. The traditional methods, relying on expert mobilization, are slow and unsafe. Recent advances in machine learning (ML) have improved assessments; however, quantum-enhanced ML (QML), a rapidly advancing field, offers greater advantages over classical ML (CML) for large-scale data, enhancing the speed and accuracy of damage assessments. This study explores the viability of leveraging QML to evaluate the safety of reinforced concrete buildings after earthquakes, focusing on classification accuracy only. A QML algorithm is trained using simulation datasets and tested on real-world damaged datasets, with its performance compared to various CML algorithms. The classification results demonstrate the potential of QML to revolutionize seismic damage assessments, offering a promising direction for future research and practical applications.