View Important Policies and System Requirements for this course
Interested in registering 5 or more engineers for a course? Contact us for information and rates.
INSTRUCTORS:
Afsar Ali
J. Ramon Gaxiola-Camacho, Ph.D., M.ASCE
Travis Thonstad
Ruel Sabellano, PE
Zeinab Bandpey, Ph.D.
Course Length: 1 hour
Purpose and Background
These presentations were recorded at Structures Congress 2026.
AI-Driven Bridge Deterioration Prediction Using a Spatiotemporal Deep Learning Framework (12 minutes)
This presentation explores the use of artificial intelligence and deep learning to predict future bridge deterioration using data from the Federal Highway Administration's National Bridge Inventory. The research addresses growing concerns about aging bridge infrastructure, increasing maintenance needs, and funding limitations across the United States. A spatiotemporal deep learning framework was developed to capture how bridge conditions evolve over time while considering structural, traffic, and environmental factors. The study employs advanced feature selection and machine learning techniques to identify the most influential factors contributing to bridge deterioration. Results demonstrate strong predictive performance and provide insights that can support proactive maintenance planning. The presentation also discusses opportunities to integrate the framework with IoT sensors and digital twin technologies for real-time bridge management.
InSAR: An Emerging Technology for Structural Health Monitoring of Bridges (14 minutes)
This presentation introduces Interferometric Synthetic Aperture Radar (InSAR) as a remote sensing technology for structural health monitoring of bridges. Unlike traditional monitoring systems that require physical sensors installed on structures, InSAR uses satellite imagery to measure structural displacement and deformation with high precision. The presenter explains the principles behind InSAR and discusses different processing approaches used to improve measurement accuracy. A case study involving the El Carrizo cable-stayed bridge in Mexico demonstrates how the technology was used to evaluate structural performance following rehabilitation after a fire-related incident. Results showed that displacement levels remained within allowable code limits, confirming the effectiveness of the repairs. The presentation highlights the potential of InSAR as a cost-effective and scalable monitoring solution for bridge infrastructure.
Evaluating Digital Twin Technology for the I-90 Floating Bridge in Seattle (19 minutes)
This presentation examines the development and implementation of a digital twin for the Homer Hadley Memorial Bridge, the floating section of Interstate 90 in Seattle. The project combines three-dimensional bridge visualization, sensor data integration, cloud computing, and real-time monitoring to support maintenance and operational decision-making. The digital twin framework incorporates weather data, GPS measurements, anchor cable tension information, and other monitoring systems to provide a comprehensive view of bridge performance. The project is being developed incrementally, allowing stakeholders to evaluate functionality and refine requirements before expanding capabilities. Particular attention is given to the unique challenges associated with the world's first floating bridge carrying light rail traffic. The presentation demonstrates how digital twins can improve asset management, condition monitoring, and long-term infrastructure resilience.
A Machine Learning Framework for Predicting Deterioration of Concrete Bridges in Maryland (15 minutes)
This presentation presents a machine learning framework developed to predict the deterioration of concrete bridges in Maryland using decades of bridge inspection and inventory data. The study leverages information from bridge inspections, National Bridge Inventory records, environmental data, and traffic characteristics to model bridge health over time. Researchers applied multiple machine learning algorithms and validation techniques to develop reliable prediction models capable of forecasting bridge health conditions up to 20 years into the future. The framework also identifies the most influential deterioration factors and evaluates their impact through sensitivity analysis. Additionally, clustering techniques were used to group bridges exhibiting similar deterioration patterns, providing valuable information for strategic asset management. The presentation demonstrates how predictive analytics can help agencies prioritize maintenance investments and improve long-term infrastructure planning.
Benefits and Learning Outcomes
Upon completion of this course, you will be able to:
- Explain how spatiotemporal deep learning can be used to predict bridge deterioration and support data-driven bridge management decisions.
- Describe how InSAR technology can be used for remote structural health monitoring and performance assessment of bridges.
- Discuss the role of digital twin technology in monitoring, managing, and optimizing bridge infrastructure performance.
- Explain how machine learning can be used to forecast bridge deterioration and support long-term asset management planning.
Assessment of Learning Outcomes
Students' achievement of the learning outcomes will be assessed via a short post-test assessment (true-false, multiple choice, and/or fill in the blank questions).
Who Should Attend?
- Structural Engineers
- Forensic Engineers
- Bridge and Transportation Engineers
- Engineering Managers/Principals
- Building Design and Construction Professionals
- Researchers and Engineering Students
How to Earn your CEUs/PDHs and Receive Your Certificate of Completion
To receive your certificate of completion, you will need to complete a short on-line post-test and receive a passing score of 70% or higher within 365 days of the course purchase.
How do I convert CEUs to PDHs?
1.0 CEU = 10 PDHs [Example: 0.1 CEU = 1 PDH]