Coupled 1D–2D hydrodynamic models are widely utilized in flood hazard mapping. Previous studies adopted conceptual hydrological models or 1D hydrodynamic models to evaluate the impact of drainage density on river flow. However, the drainage density affects not only river flow, but also the flooded area and location. Therefore, this work adopts the 1D–2D model SOBEK to investigate the impact of drainage density on river flow. The uncertainty of drainage density in flood hazard mapping is assessed by a designed case and a real case, Yanshuixi Drainage in Tainan, Taiwan. Analytical results indicate that under the same return period rainfall, reduction in tributary drainages in a model (indicating a lower drainage density) results in an underestimate of the flooded area in tributary drainages. This underestimate causes higher peak discharges and total volume of discharges in the drainages, leading to flooding in certain downstream reaches, thereby overestimating the flooded area. The uncertainty of drainage density decreases with increased rainfall. We suggest that modeling flood hazard mapping with low return period rainfalls requires tributary drainages. For extreme rainfall events, a lower drainage density could be selected, but the drainage density of local key areas should be raised.

This study proposes a method for predicting the long-term temporal two-dimensional range and depth of flooding in all grid points by using a convolutional neural network (CNN). The deep learning model was trained using a large rainfall dataset obtained from actual flooding events, and the corresponding raster flood data computed using a physical model. Various rainfall distributions (at different times or over different accumulation periods), the mesh of the simulated area, and the topography of the simulated area were considered when evaluating the performance of two CNNs: a simple CNN and Inception CNN. Neither CNN architecture could converge when the coordinate information was not included in the input data. Adding terrain elevation information to the rainfall data already containing coordinates increased the accuracy of flood prediction. Our findings indicated that in the proposed method, real-time flooding observation data are not required for corrections, and we concluded that the method can be used for long-term flood forecasting. Our model can accurately pinpoint when the water level changes from rising to falling. Once meteorological forecasted rainfall data are obtained, a corresponding long-term forecast of the two-dimensional flooding range and depth can be obtained within seconds.

HIGHLIGHTS. This study presents a stochastic ANN model.Use GA-SA method to calibrate the ANN weights.A large training dataset is accomplished via a non-nomral m

Highlights. A stochastic model for generating a rain field is develop under consideration of correlation of rainfalls in time and space.The rainstorm event cons

This study aims to develop a smart model for the two-dimensional (2D) inundation simulation based on the derived artificial neural network (ANN) model with real-time measurements at the roadside IoT (Internet of Things) sensors; in detail, the flooding zones and associated area can be quantified by combining the inundation-depth estimates at the ungauged locations (defined by the virtual IoT sensor, VIOT) via the corresponding inundation-estimation equations, established using the ANN-derived model with the measurements at the IoT sensors (named SM_EID_VIOT model). Moreover, the resulting inundation-depth estimates at the ungauged locations from the proposed SM_EID_VIOT model can be improved by means of the real-time error-correction approach for the 2D inundation simulation. To demonstrate the reliability of the results from the proposed SM_EID_VIOT model, 1000 simulations of the rainfall-induced flood events within the study area of the Miaoli City of Northern Taiwan are generated as the model-training and validation datasets. Consequently, the proposed SM_EID_VIOT could estimate the inundation depths with an acceptable accuracy at the ungauged locations in time and space based on a low root mean square error (RMSE) of under 0.01 m and a high coefficient of determination (R²) of over 0.8; and it also can delineate the flooding zone to quantify the corresponding area in high reliability in terms of the precision ratio of about 0.7.

This study aims to model a probabilistic-based reliability analysis, named the RA_IWS_Canal model, for calculating the probability of the irrigation water supply exceeding the water demand (i.e., reliability) within a multi-canal irrigation zone due to variations in hydrological and irrigation uncertainty factors. The proposed RA_IWS_Canal model is developed by coupling uncertainty and risk analysis with a logistic regression equation. The Zhudong irrigation zone, located within the Touqian River watershed in northern Taiwan, was selected as the study area, with the inflow from Shanping Weir, water supplies at 15 irrigation canals, and water intakes of two reservoirs (Baoshan and Baoshan II) and a water treatment plant (Yuandon); 1000 simulations of 10-day irrigation water allocations and resulting exceedance probabilities of the water supplies at the 15 canals were achieved using the multivariate Monte Carlo simulation and the uncertainty with the water allocation model (RIBASIM), and employed in the development of the proposed RA_IWS_Canal model. The model development and application results indicate that the uncertainty factors and the inflow from Shanping Weir markedly and positively influence the exceedance probability of the canal-based irrigation water supply to boost the corresponding reliability (about 0.8). The water intake of the Baoshan Reservoir has a lower relationship (by 0.19) than the Yuandon water treatment plant with the reliabilities of the irrigation water supplies at its downstream canals. As a result, the proposed RA_IWS_Canal model can evaluate the effect of not only the canal-based uncertainty factors, but also the regional features on the irrigation water supply reliability. In addition, using the proposed RA_IWS_Canal model, the planned irrigation water demands at various canals within a multi-canal irrigation zone could be accordingly formulated based on acceptable reliability.