New to RISC-KIT?
We are an EU-funded project developing risk management tools, with the help of End Users, to help deal with hazards and storm impacts in vulnerable coastal areas.
See the TOOLKIT:
 
Keep in Touch
Don’t miss a beat. Keep in touch with all the latest news and events.
Sign up for the newsletter

A new Master's Thesis for RISC-KIT

Congratulations to Laurens Poelhekke on the successful completion of his Masters studies.
         

 

 

Laurens Poelhekke, a student of TUDelft working with the Deltares team in the Netherlands, successfully defended his Masters thesis on 5th of October 2015. His thesis entitled, "Predicting coastal hazards with a Bayesian network," feeds in to RISC-KIT by contributing to the development of an operational Early Warning System (EWS) for hotspot areas. 

 

This research, carried out at Praia de Faro, in the RISC-KIT Case Study site of the Ria Formosa, Portugal, applied a new Bayesian model to probabilistically predict the impact of low-frequency high-impact meteorological events on sandy shores (beaches and dunes). The pathways of floods in sandy areas are subject to morphological changes and current flood hazard models do not incorporate morphological processes and are therefore not appropriate to model coastal hazards on sandy coastlines.

 

A process based model such as XBeach is capable of modeling the coastal response in two dimensions (2D), however, coming at the cost of much longer computational runtimes making it not a very useful part of an EWS. A solution is found in utilizing a probabilistic model as a surrogate for a process based model. The probabilistic model is fed with data created with the process based model. The process based model essentially trains the probabilistic model allowing it to take over its function. More specifically a Bayesian Network (BN) has been trained to replace an XBeach model.

 

The full text thesis is available to download from the TUDelft website, here.

 

Abstract

Recent and historic events have demonstrated the European vulnerability to coastal floods. Larger and more extreme events in Asia and the Americas have shown the devastating effects that these low-frequency high-impact floods can have. This thesis contributes to the development of an Early Warning System (EWS) for marine coastal hazards. The relevance of an EWS is supported by the UN who have identified it as key in reducing casualties and economic losses due to flood events (UNISDR, 2002).

 

For coastlines with sandy shores (beaches and dunes) the response of the coastline to high impact events is very large (e.g. dune and beach erosion). Current flood hazard models do not include these morphological processes and are therefore not sufficient for these types of coastlines. Process based models such as XBeach (Roelvink et al., 2009) are capable of modeling the coastal response but are not very useful as an EWS due to the long duration of the computations.

 

A solution is found in utilizing a probabilistic model as a surrogate for a process based model. The probabilistic model is fed with data that is created with the process based model. This way the probabilistic model gains the same knowledge about the processes within the bounds that it is trained. More specifically a Bayesian Network (BN) is used as a surrogate for an XBeach model. As a case study site for the development and initial implementation the beach settlement of Faro, Praia de Faro, has been selected. Praia de Faro is pestered by yearly recurring overwash events and has experienced damages to houses and infrastructure due to severe erosion of the coastline. To be able to feed the BN with data a large storm dataset is needed. This dataset is created by using a local storm dataset to create bivariate distributions using copulas. These bivariate distributions are then used to sample a synthetic dataset that mimics the characteristics of the original dataset. The final BN is able to translate offshore storm boundary conditions to onshore hazard intensities. It can, however, only do this with relatively low complexity. For it to be useful in an operational EWS it will either need extra training data or increased complexity which implicitly also means more training data is needed. 

 

waiaaa europa Deltares Ecologic CFR UAlg IMDC IO-BAS LIENSs-CNRS TUD WMO UPC CIMA BAW EurOcean SEI MU-FHRC UniCaen UCAM-CCRU UNESCO-IHE