Debris floods, as one of the most significant natural hazards, often threaten the lives and property of many people worldwide. Predicting models are essential for flood warning systems to minimize casualties of debris floods. Since HEC-HMS (Hydrologic Engineering Center’s Hydrological Modelling System) cannot simulate debris flow, this study proposes a new hybrid model that uses artificial intelligence models to overcome HEC-HMS’s insufficiency in reflecting the sediment concentration effect on the debris floods. A sediment concentration is an effective factor for evaluating debris flood peak flows. This led to the proposal of new hybrid models for predicting the debris flood peak flows on the basis of hybridization of the artificial intelligence models (Bayesian Network (BN) and Support Vector Regression–Particle Swarm Optimization (SVR-PSO)) and HEC-HMS. To estimate the sediment concentration of floods by using the proposed artificial intelligence models, we nominated an average basin elevation, an average basin slope, a basin area, the current day rainfall, the antecedent rainfall of the past 3 days, and the streamflow of the previous day the previous day as the effective variables. In the validation stage, the average of the Mean Absolute Relative Error (MARE) of the estimated values were 0.024, 0.038, and 0.024 for the typical floods that occurred in the Navrood, Kasilian, and the Amameh basins in the north of Iran, respectively. Similarly, we obtained values of 0.038, 0.073, and 0.040 for the debris flood events for the three respective locations. After predicting the debris flood peak flows by the proposed hybrid HMS-BN and HMS-SVR-PSO models, the average of the MAREs for all debris flood events was reduced to 0.013 and 0.014, respectively. The comparison of MAREs of the examined hybrid models shows that the HMS-BN model results in higher accuracy than the HMS-SVR-PSO model in the prediction of the debris flood peak flows. Generally, the absolute error of prediction by the proposed hybrid model is reduced to one-third of the HEC-HMS. The prediction of the debris flood peak flows using the proposed hybrid model can be examined in the debris flood warning systems to reduce the potential damages and casualties in similar basins.

Reservoir operation in flood conditions on hourly time scales poses significant difficulties due to the inherent uncertainty of inflow forecasts. Hence, incorporating ensemble flood forecasts into real-time reservoir operation optimization has rarely been investigated to effectively address uncertainties in inflow forecasts for flood control, let alone its added value compared to no-forecast operating scheme in multi-objective reservoir operating system. This research first investigates the potential of sequential Long Short-Term Memory networks to forecast one-day-ahead ensemble inflow floods based on numerical weather prediction data. Next, a new framework has been developed to incorporate ensemble inflow forecasts into multi-objective reservoir operation optimization using grid search-based genetic algorithm. Finally, we implemented our proposed ensemble-based operating method on the Dez dam basin in Iran and compared it with the benchmark no-forecast operating approach. The results revealed that the Long Short-Term Memory model reasonably performed well to propagate uncertainty in short-term ensemble inflow forecasts. In addition, the ensemble-based operating method could reduce release peaks and increase reservoir storage more than that of a deterministic (no-forecast) operating approach. Our findings demonstrated that the applicability of a skillful ensemble-based scheme in reservoir flood control operations could be effective in decreasing flood damage and water shortage.

The quality of precipitation forecasting is critical for more accurate hydrological forecasts, especially flood forecasting. The use of numerical weather prediction (NWP) models has attracted much attention due to their impact on increasing the flood lead time. It is vital to post-process raw precipitation forecasts because of their significant bias when they feed hydrological models. In this research, ensemble precipitation forecasts (EPFs) of three NWP models (National Centers for Environmental Prediction (NCEP), United Kingdom Meteorological Office (UKMO) (Exeter, UK), and Korea Meteorological Administration (KMA) (SEOUL, REPUBLIC OF KOREA)) were investigated for six historical storms leading to heavy floods in the Dez basin, Iran. To post-process EPFs, the raw output of every single NWP model was corrected using regression models. Then, two proposed models, the Group Method of Data Handling (GMDH) deep learning model and the Weighted Average–Weighted Least Square Regression (WA-WLSR) model, were employed to construct a multi-model ensemble (MME) system. The ensemble reservoir inflow was simulated using the HBV hydrological model under the two modeling approaches involving deterministic forecasts (simulation using observed precipitation data as input) and ensemble forecasts (simulation using post-processed EPFs as input). The results demonstrated that both GMDH and WA-WLSR models had a positive impact on improving the forecast skill of the NWP models, but more accurate results were obtained by the WA-WLSR model. Ensemble forecasts outperformed coupled atmospheric–hydrological modeling in comparison with deterministic forecasts to simulate inflow hydrographs. Our proposed approach lends itself to quantifying uncertainty of ensemble forecasts in hydrometeorological the models, making it possible to have more reliable strategies for extreme-weather event management.

In this chapter, the precipitation threshold at which debris floods occur was evaluated experimentally, and the factors that influence debris flood occurrence, including the bed slope, sediment layer thickness, sediment grain size, length of alluvial flow direction, precipitation intensity, and time of debris flood occurrence, were examined. The impacts of these factors on debris flood initiation were investigated through dimensional analysis. Then, a method was developed to estimate the precipitation intensity threshold based on a set of laboratory tests. Furthermore, different methods for determining the precipitation intensity threshold at which debris floods are initiated were assessed and discussed. The results of the experiments showed that the effect of the sediment layer thickness on debris flood occurrence can be ignored. Moreover, by independently evaluating the effect of each factor on debris flood occurrence, it was found that the sediment length and average diameter of sediments are influential to debris flood initiation. The results of this research provide a better understanding of debris flood mechanisms and occurrence thresholds of debris floods and can be employed to prepare a forecasting model.