Uncertainty Quantification and Deep Learning for Water-Hazard Prediction

Explore uncertainty quantification and deep learning techniques for predicting water hazards in this comprehensive lecture. Delve into the complexities of modeling storm surge events and their impact on urban infrastructure, including the challenges of quantifying uncertainties in flow conditions and structural properties. Learn about innovative approaches combining Bayesian calibration and neural networks to characterize and assess damage from extreme weather events. Discover recent developments in the field as Dr. Ajay B Harish, a lecturer in Engineering Simulation and Data Science, shares insights on modeling water-borne hazards like storm surges and tsunamis. Gain valuable knowledge on numerical methods, data-driven physical simulations, and their applications in enhancing disaster preparedness and response strategies.

Introduction
Lab overview
Tribology
Naval and Sim Center
Open Source Framework
Tsunami 2004
Tsunami 2010
Tsunami 2011
Storm Surge
Tsunami
Modeling approaches
Mechanics course
Ocean floor
Hydrouq
Depth Average
Boundary Conditions
Depth
Steady State
Discretization
Example
Propagation of uncertainties
Engineering judgment
Forward propagation
Reliability analysis
Global sensitivity analysis
Sur surrogate models
Inverse UQ
Questions
QA Session