Pouria Nakhaei

Floods pose a significant threat to urban areas due to their high population densities and extensive infrastructure, a vulnerability exacerbated by climate change, rapid urbanization, and the proliferation of impermeable surfaces. While traditional flood prediction efforts have focused on maximum inundation depths, dynamic flood inundation mapping has gained prominence for its ability to provide detailed insights into flood timing, duration, and progression, which are critical for effective emergency response, infrastructure planning, and resilience-building. The integration of high-resolution Digital Elevation Models (DEMs) has improved modeling accuracy by capturing intricate urban topographies, but this advancement has introduced substantial computational challenges, particularly for large-scale, fine-resolution simulations using physics-based hydrodynamic models. Convolutional neural networks (CNNs), particularly U-Net, have shown promise in flood prediction due to their ability to handle complex segmentation tasks and varying input sizes; however, scaling these models to handle large datasets with meter-scale resolutions remains computationally intensive. Addressing this challenge, this study develops a novel approach to predict dynamic flood maps for a large urban area at 10-meter resolution (~10⁶ cells) by dividing the area into smaller tiles for U-Net training, leveraging a comprehensive rainstorm-inundation database (200 cases) created through 2D hydrodynamic simulations, and integrating results into a surrogate model. This innovative framework delivers accurate and rapid predictions of flood dynamics, including spatial extent, depth, and temporal evolution, providing essential tools for urban flood risk management and mitigation strategies. For training, validation, and testing of the U-Net model, 160, 30, and 20 cases were used, respectively. The RMSE, CSI, and POD metrics were used to evaluate the model's performance on the validation and test datasets. The results show high performance for validation with RMSE, CSI, and POD values of 0.015, 0.92, and 0.74, respectively, and for testing with values of 0.017, 0.90, and 0.81, respectively.

Predicting monthly streamflow is essential for hydrological analysis and water resource management. Recent advancements in deep learning, particularly long short-term memory (LSTM) and recurrent neural networks (RNN), exhibit extraordinary efficacy in streamflow forecasting. This study employs RNN and LSTM to construct data-driven streamflow forecasting models. Sensitivity analysis, utilizing the analysis of variance (ANOVA) method, also is crucial for model refinement and identification of critical variables. This study covers monthly streamflow data from 1979 to 2014, employing five distinct model structures to ascertain the most optimal configuration. Application of the models to the Zarrine River basin in northwest Iran, a major sub-basin of Lake Urmia, demonstrates the superior accuracy of the RNN algorithm over LSTM. At the outlet of the basin, quantitative evaluations demonstrate that the RNN model outperforms the LSTM model across all model structures. The S3 model, characterized by its inclusion of all input variable values and a four-month delay, exhibits notably exceptional performance in this aspect. The accuracy measures applicable in this particular context were RMSE (22.8), R² (0.84), and NSE (0.8). This study highlights the Zarrine River’s substantial impact on variations in Lake Urmia’s water level. Furthermore, the ANOVA method demonstrates exceptional performance in discerning the relevance of input factors. ANOVA underscores the key role of station streamflow, upstream station streamflow, and maximum temperature in influencing the model’s output. Notably, the RNN model, surpassing LSTM and traditional artificial neural network (ANN) models, excels in accurately mimicking rainfall–runoff processes. This emphasizes the potential of RNN networks to filter redundant information, distinguishing them as valuable tools in monthly streamflow forecasting.

Precise forecasting of streamflow is crucial for the proper supervision of water resources. The purpose of the present investigation is to predict successive-station streamflow using the Gated Recurrent Unit (GRU) model and to quantify the impact of input information (i.e., precipitation) uncertainty on the GRU model’s prediction using the Generalized Likelihood Uncertainty Estimation (GLUE) computation. The Zarrineh River basin in Lake Urmia, Iran, was nominated as the case study due to the importance of the location and its significant contribution to the lake inflow. Four stations in the basin were considered to predict successive-station streamflow from upstream to downstream. The GRU model yielded highly accurate streamflow prediction in all stations. The future precipitation data generated under the Representative Concentration Pathway (RCP) scenarios were used to estimate the effect of precipitation input uncertainty on streamflow prediction. The p-factor (inside the uncertainty interval) and r-factor (width of the uncertainty interval) indices were used to evaluate the streamflow prediction uncertainty. GLUE predicted reliable uncertainty ranges for all the stations from 0.47 to 0.57 for the r-factor and 61.6% to 89.3% for the p-factor.