1. Digital Twins for Smart and Resilient Infrastructure
Digital twin technology is revolutionizing the way we monitor, assess, and optimize infrastructure systems. By integrating real-time data, AI-driven predictive analytics, and advanced simulation techniques, digital twins enable proactive decision-making for bridges, transportation networks, and urban environments. Dr. Bayat’s research focuses on leveraging digital twins for equitable bridge maintenance, risk assessment, and asset management under extreme conditions, such as coastal floods, earthquakes, and climate change impacts. His work bridges the gap between structural health monitoring, AI-based condition assessment, and sustainable infrastructure planning.
Related Papers:
- Bayat, M., Kharel, S., J. Li, Q. Pan, S. Mattingly, M. Shahandashti (2024). “Leveraging Digital Twins for Equitable Bridge Maintenance Prioritization during Coastal Flood Events.” Structures (Under review).
- Ai, L., Bayat, M., Comert, G., Ziehl, P. (2022). “An Autonomous Bridge Load Rating Framework Using Digital Twin.” Proceedings of the 13th International Workshop on Structural Health Monitoring, Stanford University.
- Ziehl, P., Gurcan C., Bayat, M. (2022). “Digital Twins to Increase Mobility in Rural South Carolina.” Center for Connected Multimodal Mobility (C2M2), SCDOT.
2. 3D Printing and Additive Manufacturing in Structural Engineering
The advancement of 3D printing and digital fabrication has opened new frontiers for sustainable and high-performance structural systems. Dr. Bayat’s research explores carbon-absorbing concrete, topology optimization, and automated form-finding techniques to design and manufacture efficient, lightweight, and resilient structures. His work also focuses on integrating AI-driven computational design approaches to enhance the scalability and sustainability of construction methods, particularly in bridge engineering and affordable housing development.
Related Papers:
- Ai, L., Bianco, D., Soltangharaei, V., Anay, R., Bayat, M., Ziehl, P. (2024). “Evaluating the Impact of Aggregate Size and Reinforcement on Alkali-Silica Reaction in Concrete through Nondestructive Testing Techniques.” Nondestructive Testing and Evaluation (Under review).
- Bayat, M., Kharel, S. (2025). “Digital Twin Framework for Equitable Bridge Maintenance Prioritization During Coastal Floods in Texas.” Engineering Mechanics Institute Conference.
3. AI and Machine Learning for Structural Engineering
Artificial Intelligence (AI) and Machine Learning (ML) are transforming infrastructure analysis, design, and predictive maintenance. Dr. Bayat’s research integrates deep learning, generative adversarial networks (GANs), and AI-powered optimization models to enhance bridge condition prediction, automated damage classification, and infrastructure resilience modeling. His work enables data-driven decision-making in civil engineering applications, significantly improving efficiency, cost-effectiveness, and safety.
Related Papers:
- Bayat, M., Kharel, S. (2024). “Condition Rating Prediction for Off-System Bridges Using Generative Adversarial Networks.” Journal of Infrastructure Systems (Under review).
- Li, S., Cao, M., Bayat, M., Sumarac, D., Wang, J. (2024). “An Intelligent Framework of Upgraded CapsNets with Massive Transmissibility Data for Identifying Damage in Bridges.” Applied Soft Computing, 155, 111459.
- Laxman, K. C., Ross, A., Ai, L., Henderson, A., Elbatanouny, E., Bayat, M., Ziehl, P. (2023). “Determination of Vehicle Loads on Bridges by Acoustic Emission and an Improved Ensemble Artificial Neural Network.” Construction and Building Materials, 364, 129844.
4. Risk and Resilience of Civil Infrastructure under Multi-Hazard Events
Ensuring the resilience of critical infrastructure under extreme events—such as earthquakes, floods, and hurricanes—is essential for mitigating disaster impacts. Dr. Bayat’s research focuses on probabilistic risk assessment, seismic vulnerability modeling, and disaster-informed infrastructure planning. By integrating computational simulations, AI-based risk modeling, and resilience frameworks, his work helps improve emergency response strategies, infrastructure adaptation, and climate-resilient urban planning.
Related Papers:
- Zheng, B., Bayat, M., Shi, Y., Jiang, Y., Qian, X., Novák, D., Cao, M. (2024). “Forecasting Approach of Ultimate Bearing Capacity of Underreamed Anchor Under Local Shear Failure.” Journal of Engineering Research.
- Bayat, M., Ahmadi, H., Hadadi, V. (2024). “Presenting a New Method and X-Index Based on Choi-Williams Distribution and Matrix Density Methods to Detect Damage in Concrete Beams.” Steel and Composite Structures (Accepted).
- Hooshyar, H., Ahmadi, H. R., Bayat, M., Mahdavi, N., Hosseinzadeh, E., Najafi, M. H. (2024). “New Method for Damage Detection in Steel Beam Using Time-Frequency Functions and Machine Learning.” Structures (Revised submission).