Urban flood pre-warning decisions made upon urban flood modeling is crucial for human and property management in urban area. However, urbanization, changing environmental conditions and climate change are challenging urban sewer models for their adaptability. While hydraulic models are capable of making accurate flood predictions, they are less flexible and more computationally expensive compared with conceptual models, which are simpler and more efficient. In the era of exploding data availability and computing techniques, data-driven models are gaining popularity in urban flood modelling, but meanwhile suffer from data sparseness. To overcome this issue, a hybrid urban flood modeling approach is proposed in this study. It incorporates a conceptual model to account for the dominant sewer hydrological processes and a logistic regression model able to predict the probabilities of flooding on a sub-urban scale. This approach is demonstrated for a highly urbanized area in Antwerp, Belgium. After comparison with a 1D/0D hydrodynamic model, its ability is shown with promising results to make probabilistic flood predictions, regardless of rainfall types or seasonal variation. In addition, the model has higher tolerance on data input quality and is fully adaptive for real time applications.
Point Cloud Data Fusion for Enhancing 2D Urban Flood Modelling
