|
Abstract:
|
This is about developing a framework for river flood modeling that leverages large hydraulic models and facilitates rapid large-scale flood simulations at a high resolution. Due to global warming, large floods have become a characteristic feature of the climate around the world. This demands attention to more robust, efficient, and real-time flood modeling. For most river engineering problems, there is need for accurate quantification of water depth and elevation. There are numerous hydraulic modeling tools capable of representing this but they are computationally expensive and time consuming. In particular, we aim to establish methodology for building accurate and fast statistical emulators as alternatives to running complex physical models directly using machine learning algorithms with spatial extreme distributions to represent flooding in a complex domain. We use the application of generalized Pareto distribution (GPD) to the statistical analysis of extremes.
|
