In an effort to improve tools for effective flood risk assessment, we applied machine learning algorithms to predict flood-prone areas in Amol city (Iran), a site with recent floods (2017–2018). An ensemble approach was then implemented to predict hazard probabilities using the best machine learning algorithms (boosted regression tree, multivariate adaptive regression spline, generalized linear model, and generalized additive model) based on a receiver operator characteristic-area under the curve assessment. The algorithms were all trained and tested on 92 randomly selected points, information from a flood inundation survey, and geospatial predictor variables (precipitation, land use, elevation, slope percent, curve number, distance to river, distance to channel, and depth to groundwater). The ensemble model had 0.925 and 0.892 accuracy for training and testing data, respectively. We then created a vulnerability map from data on building density, building age, population density, and socio-economic conditions and assessed risk as a product of hazard and vulnerability. The results indicated that distance to channel, land use, and runoff generation were the most important factors associated with flood hazard, while population density and building density were the most important factors determining vulnerability. Areas of highest and lowest flood risks were identified, leading to recommendations on where to implement flood risk reduction measures to guide flood governance in Amol city.

Floods are the most common natural disaster globally and lead to severe damage, especially in urban environments. This study evaluated the efficiency of a self-organizing map neural network (SOMN) algorithm for urban flood hazard mapping in the case of Amol city, Iran. First, a flood inventory database was prepared using field survey data covering 118 flooded points. A 70:30 data ratio was applied for training and validation purposes. Six factors (elevation, slope percent, distance from river, distance from channel, curve number, and precipitation) were selected as predictor variables. After building the model, the odds ratio skill score (ORSS), efficiency (E), true skill statistic (TSS), and the area under the receiver operating characteristic curve (AUC-ROC) were used as evaluation metrics to scrutinize the goodness-of-fit and predictive performance of the model. The results indicated that the SOMN model performed excellently in modeling flood hazard in both the training (AUC = 0.946, E = 0.849, TSS = 0.716, ORSS = 0.954) and validation (AUC = 0.924, E = 0.857, TSS = 0.714, ORSS = 0.945) steps. The model identified around 23% of the Amol city area as being in high or very high flood risk classes that need to be carefully managed. Overall, the results demonstrate that the SOMN model can be used for flood hazard mapping in urban environments and can provide valuable insights about flood risk management.

Variations in rainfall characteristics play a key role in available water resources for a country. In this study, spatial and temporal variations in rainfall in Iran were determined using the daily rainfall concentration index (DRCI) and monthly rainfall percentage index (MRPI), based on 30-year (1987–2016) daily precipitation records from 80 meteorological stations throughout Iran. The results showed that MRPI differed between locations within Iran, with increasing or decreasing trends observed in different areas. The highest significant decreasing trend in MRPI (3–7% per decade) was found for March rainfall in western Iran, and the highest increasing trend in MRPI (3–7% per decade) for November rainfall in eastern and southern Iran. The DRCI values obtained varied from 0.57 to 0.71, indicating moderate and high rainfall concentrations, with the highest DRCI values in coastal zones of Iran near the Caspian Sea and the Persian Gulf. Trend analysis showed increasing trends in DRCI values at 80% of meteorological stations, and these trends were significant at 37% of those stations.

In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models.

Accurate modeling and prediction of suspended sediment load (SSL) in rivers have an important role in environmental science and design of engineering structures and are vital for watershed management. Since different parameters such as rainfall, temperature, and discharge with the different lag times have significant effects on the SSL, quantifying and understanding nonlinear interactions of the sediment dynamics has always been a challenge. In this study, three soft computing models (multilayer perceptron (MLP), adaptive neuro-fuzzy system (ANFIS), and radial basis function neural network (RBFNN)) were used to predict daily SSL. Four optimization algorithms (sine–cosine algorithm (SCA), particle swarm optimization (PSO), firefly algorithm (FFA), and bat algorithm (BA)) were used to improve the capability of SSL prediction of the models. Data from gauging stations at the mouth of the Kasilian and Talar rivers in northern Iran were used in the analysis. The selection of input combinations for the models was based on principal component analysis (PCA). Uncertainty in sequential uncertainty fitting (SUFI-2) and performance indicators were used to assess the potential of models. Taylor diagrams were used to visualize the match between model output and observed values. Assessment of daily SSL predictions for Talar station revealed that ANFIS-SCA yielded the best results (RMSE (root mean square error): 934.2 ton/day, MAE (mean absolute error): 912.2 ton/day, NSE (Nash–Sutcliffe efficiency): 0.93, PBIAS: 0.12). ANFIS-SCA also yielded the best results for Kasilian station (RMSE: 1412.10 ton/day, MAE: 1403.4 ton/day, NSE: 0.92, PBIAS: 0.14). The Taylor diagram confirmed that ANFIS-SCA achieved the best match between observed and predicted values for various hydraulic and hydrological parameters at both Talar and Kasilian stations. Further, the models were tested in Eagel Creek Basin, Indiana state, USA. The results indicated that the ANFIS-SCA model reduced RMSE by 15% and 21% compared to the MLP-SCA and RBFNN-SCA models in the training phase. Comparing models performance indicated that the ANFIS-SCA model could decrease MAE error compared to ANFIS-BA, ANFIS-PSO, ANFIS-FFA, and ANFIS models by 18%, 32%, 37%, and 49% in the training phase, respectively. The results indicated that the integration of optimization algorithms and soft computing models can improve the ability of models for predicting SSL. Additionally, the hybridization of soft computing models with optimization algorithms can decrease the uncertainty of models.