Zhenhua Shi

Missouri University of Science and Technology

Papers

Total Citations

H-Index

About

Zhenhua Shi is a leading researcher in the intersection of structural engineering and artificial intelligence, with a primary focus on deep learning for automated infrastructure inspection and nondestructive evaluation. His most impactful work addresses the critical challenge of domain shift in deep learning-based bridge element segmentation, where he developed a class-wise histogram matching technique for domain adaptation—a breakthrough that enables models trained on one bridge to perform accurately on others with different shapes, textures, and lighting conditions. This work, published in 2025, has already garnered 4 citations, reflecting its immediate relevance to the field. Shi has also pioneered deep spatiotemporal fusion networks for vision-based robotic inspection, enhancing the ability of drones and robots to detect structural defects over time. His comprehensive review on aerial nondestructive testing and evaluation (aNDT&E) has become a foundational reference for researchers exploring drone-based bridge inspections beyond visual line of sight. With a career marked by innovative solutions to real-world infrastructure challenges, Shi’s work is essential reading for anyone interested in the future of automated, AI-driven structural health monitoring.