Efficient and accurate streamflow predictions are important for urban water management. Data-driven models, especially neural network (NN) models can predict streamflow fast, while the results are uncertain in some complex river systems. Physically based models can reveal the underlying physics, but it is relatively slow and computationally costly. This work focuses on evaluating the reliability of three NN models (artificial neural networks (ANN), long short-term memory networks (LSTM), adaptive neuro-fuzzy inference system (ANFIS)) and one physically based model (SOBEK) in terms of efficiency and accuracy for average and peak streamflow simulation. All the models are applied for a tidal river and a mountainous river in Shenzhen. The results show that, the ANN model calculates fastest since the hidden layer's structure is simple. The LSTM model is reliable in average streamflow simulation in tidal river with the lowest bias while the ANFIS model has the best accuracy for peak streamflow simulation. Furthermore, the SOBEK model shows reliability in simulating average and peak streamflow in mountainous river due to its ability to capture uneven spatial rainfall in the area. Overall, the results indicate that the LSTM model can be a helpful supplementary to physically based models in streamflow simulation of complex urban river systems, by giving fast streamflow predictions with usually acceptable accuracy. Our results can provide helpful information for hydrological engineers in the application of flooding early warning and emergency preparedness in the context of flooding risk management.

Urban pluvial flooding now occurs more frequently than it has in past decades, mainly due to an increasing number of extreme precipitation events occurring in the context of a changing climate. To limit the evolving risks of urban pluvial flooding in a more environmentally friendly manner, the research community has recently paid increasing attention to Nature‐Based Solutions (NBS), which are based on new green technologies. To meet the urgent demand for a comprehensive review of the most recent literature, this review conducts a systematic survey of the literature to characterize various NBS adopted in different regions of the world and to elaborate on the benefits and limitations of such NBS. The review highlights the role of NBS in urban flood risk management under ongoing climate change and rapid urbanization. It shows that NBS could effectively mitigate urban flooding caused by high‐frequency precipitation events, with additional economic, ecological, and social benefits. However, NBS are less effective at helping cope with pluvial flooding caused by extreme precipitation events over a short period of time, while gray infrastructures also have limitations as a mitigation measure against extreme pluvial flooding. We thus recommend identifying flood risk management strategies by evaluating the performance of alternative combinations of NBS with gray infrastructures in preventing pluvial flooding in the cities. Finally, recent advances made in the applications of NBS are presented with suggestions (e.g., long‐term monitoring) to improve urban flood adaptive management.