A rapid flood inundation model for urban flood analyses.

An efficient inundation model is required for flood early warning systems in urban areas. A 2D flood model uses a governing shallow water equation, and this model is computationally expensive despite benefiting from parallel computing techniques. As an alternative to conventional flood models, cellular automata (CA) and DEM-based models (DBMs) have been studied. CA flood models simulate floods efficiently. However, a small time step is required to ensure model stability when the grid size decreases due to its diffusive characteristics. Conversely, DBM models produce results quickly, but they only show the maximum flood extent. Additionally, pre- and postprocessing are required, which take considerable time. This study proposes a hybrid inundation model that combines the two alternative approaches, and it efficiently produces a high- resolution flood map without complex pre- and postprocessing. The hybrid model is also integrated with a 1D drainage module, and thus, the model reliably simulates urban area floods.•The rapid flood inundation model integrates CA module to simulate temporal distribution of floods and DEM module to provide details of floods.•A 1D Saint Venant equation is also solved in the rapid flood inundation model to simulate the drainage sytems in urban areas.•Two-way coupling between 2D-surface and 1D-drainag models are considered in the rapid flood inundation model.

Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting.

Extreme weather events cause stream overflow and lead to urban inundation. In this study, a decentralized flood monitoring system is proposed to provide water level predictions in streams three hours ahead. The customized sensor in the system measures the water levels and implements edge computing to produce future water levels. It is very different from traditional centralized monitoring systems and considered an innovation in the field. In edge computing, traditional physics-based algorithms are not computationally efficient if microprocessors are used in sensors. A correlation analysis was performed to identify key factors that influence the variations in the water level forecasts. For example, the second-order difference in the water level is considered to represent the acceleration or deacceleration of a water level rise. According to different input factors, three artificial neural network (ANN) models were developed. Four streams or canals were selected to test and evaluate the performance of the models. One case was used for model training and testing, and the others were used for model validation. The results demonstrated that the ANN model with the second-order water level difference as an input factor outperformed the other ANN models in terms of RMSE. The customized microprocessor-based sensor with an embedded ANN algorithm can be adopted to improve edge computing capabilities and support emergency response and decision making.