Real-time Urban Flood Forecasting: Application Of Hybrid Modelling Using Both Physically Based And Data-driven Models

This article discusses the use of physically based models and data-driven models for urban flood forecasting. Physically based models require continuous access to data and can be challenging and demanding for model calibration or real-time applications. Data-driven models are less data demanding and provide more accuracy for short-term water level/depth of urban flooding. However, these models can be inaccurate when new situations, especially new climate change based extreme events, occur.