Indicator-based approach for fluvial flood risk assessment at municipal level in Slovakia.

The article focuses on the mapping and assessment of fluvial flood risk at municipal level of Slovakia. The fluvial floods risk index (FFRI), composed of a hazard component and a vulnerability component, was computed for 2927 municipalities using spatial multicriteria analysis and geographic information systems (GIS). The fluvial flood hazard index (FFHI) was computed based on eight physical-geographical indicators and land cover representing the riverine flood potential and also the frequency of flood events in individual municipalities. The fluvial flood vulnerability index (FFVI) was calculated using seven indicators representing the economic and social vulnerability of municipalities. All of the indicators were normalized and weighted using the rank sum method. By aggregating the weighted indicators, we obtained the FFHI and FFVI in each municipality. The final FFRI is a result of a synthesis of the FFHI and FFVI. The results of this study can be used mainly in the framework of flood risk management at national spatial scale, but also for local governments and periodic update of the Preliminary Flood Risk Assessment document, which is carried out at the national level under the EU Floods Directive.

Novel hybrid models between bivariate statistics, artificial neural networks and boosting algorithms for flood susceptibility assessment.

Across the world, the flood magnitude is expected to increase as well as the damage caused by their occurrence. In this case, the prediction of areas which are highly susceptible to these phenomena becomes very important for the authorities. The present study is focused on the evaluation of flood potential within Trotuș river basin in Romania using six ensemble models created by the combination of Analytical Hierarchy Process (AHP), Certainty Factor (CF) and Weights of Evidence (WOE) on one hand, and Gradient Boosting Trees (GBT) and Multilayer Perceptron (MLP) on the other hand. A number of 12 flood predictors, 172 flood locations and 172 non-flood locations were used. A percentage of 70% of flood and non-flood locations were used as input in models. From the input data, 70% were used as training sample and 30% as validating sample. The highest accuracy was obtained by the MLP-CF model in terms of both training (0.899) and testing (0.889) samples. A percentage between 21.88% and 36.33% of study area is covered with high and very high flood potential. The results validation, performed through the ROC Curve method, highlights that the MLP-CF model provided the most accurate results.