This paper advances machine learning (ML)-based streamflow prediction by strategically selecting rainfall events, introducing a new loss function, and addressing rainfall forecast uncertainties. Focusing on the Iowa River Basin, we applied the stochastic storm transposition (SST) method to create realistic rainfall events, which were input into a hydrological model to generate corresponding streamflow data for training and testing deterministic and probabilistic ML models. Long short-term memory (LSTM) networks were employed to predict streamflow up to 12 h ahead. An active learning approach was used to identify the most informative rainfall events, reducing data generation effort. Additionally, we introduced a novel asymmetric peak loss function to improve peak streamflow prediction accuracy. Incorporating rainfall forecast uncertainties, our probabilistic LSTM model provided uncertainty quantification for streamflow predictions. Performance evaluation using different metrics improved the accuracy and reliability of our models. These contributions enhance flood forecasting and decision-making while significantly reducing computational time and costs.
Floods are among the most destructive natural hazards, with damages expected to intensify under climate change and socio-economic pressures. Effective reservoir operation remains a critical yet challenging strategy for mitigating downstream impacts, as operators must navigate nonlinear system dynamics, uncertain inflow forecasts, and trade-offs between competing objectives. This study proposes a novel end-to-end data-driven framework that integrates process-based hydraulic simulations, a Transformer-based surrogate model for flood damage prediction, and reinforcement learning (RL) for reservoir gate operation optimization. The framework is demonstrated using the Coralville Reservoir (Iowa, USA) and two major historical flood events (2008 and 2013). Hydraulic and impact simulations with HEC-RAS and HEC-FIA were used to generate training data, enabling the development of a Transformer model that accurately predicts time-varying flood damages. This surrogate is coupled with a Transformer-enhanced Deep Q-Network (DQN) to derive adaptive gate operation strategies. Results show that the RL-derived optimal policy reduces both peak and time-integrated damages compared to expert and zero-opening benchmarks, while maintaining smooth and feasible operations. Comparative analysis with a genetic algorithm (GA) highlights the robustness of the RL framework, particularly its ability to generalize across uncertain inflows and varying initial storage conditions. Importantly, the adaptive RL policy trained on perturbed synthetic inflows transferred effectively to the hydrologically distinct 2013 event, and fine-tuning achieved near-identical performance to the event-specific optimal policy. These findings highlight the capability of the proposed framework to provide adaptive, transferable, and computationally efficient tools for flood-resilient reservoir operation.
Floods are one of the most destructive natural disasters. They can have significant consequences such as loss of life and property. For preparedness and effective mitigation, engineers develop methods to predict floods before they occur. In this study, I investigated the performance of the Iowa Flood Center's flood forecasting method in mountainous regions in Turkey. I showed that the method could provide accurate flood forecasts in mountainous areas with a humid temperate climate.In addition to flood forecasting, flood mitigation is also significant to prevent catastrophic impacts of floods. An emerging approach for flood mitigation is to build multiple small reservoirs that are distributed across the landscape. This practice distributes flood mitigation benefits to a greater area. There are two basic ways of managing reservoirs: passive control and active control. In passive control, the pipe from which the water is released remains entirely open all the time. In active control, one can adjust the amount of water to be released from the reservoir by changing the pipe's opening size. In this thesis, I explored the flood mitigation benefits of distributed small reservoirs. My results showed that the distribution of passive reservoirs across the landscape significantly affects their ability to reduce high flows. Additionally, I compared active and passive control strategies. I demonstrated that active control could increase the efficiency of a system of small reservoirs. However, when reservoir capacity is insufficient, active control does not improve flood mitigation.