Presenter
Jun-Whan Lee, Ph.D.
Assistant Professor
Department of Civil Architectural and Environmental Engineering
The University of Texas at Austin
Description
Coastal regions are facing more uncertainties and risks from coastal hazards like tsunamis and storm surges because of growing populations and rising sea levels. Even though computers have become more powerful, physics-based models struggle to find the right balance between accuracy, efficiency, and reliability. As a result, there's growing interest in using machine learning to address these challenges. However, traditional machine learning methods face difficulties due to the complexity of coastal hazard data. To overcome this obstacle, we've improved tsunami machine learning modeling by adopting domain knowledge and improved the storm surge machine learning modeling by combining clustering and data reduction with deep learning. This talk will introduce these machine-learning approaches and explore their applications in coastal hazard forecasting, hazard assessment, and risk assessment.
