The aim of this study is to select the best model (combination of different lag times) for predicting the standardized precipitation index (SPI) and the standardized precipitation and evapotranspiration index (SPEI) in next time. Monthly precipitation and temperature data from 1960 to 2019 were used. In temperate climates, such as the north of Iran, the correlation coefficient of SPI and SPEI was 0.94, 0.95, and 0.81 at the time scales of 3, 12, and 48 months, respectively. Besides, this correlation coefficient was 0.47, 0.35, and 0.44 in arid and hot climates, such as the southwest of Iran because potential evapotranspiration (PET) depends on temperature more than rainfall. Drought was predicted using the random forest (RF) model and applying 1–12 months lag times for next time. By increasing of time scale, the prediction accuracy of SPI and SPEI will improve. The ability of SPEI is more than SPI for drought prediction, because the overall accuracy (OA) of prediction will increase, and the errors (i.e., overestimate (OE) and underestimate (UE)) will reduce. It is recommended for future studies (1) using wavelet analysis for improving accuracy of predictions and (2) using the Penman–Monteith method if ground-based data are available.

This research uses the multi layer perceptron- artificial neural network (MLP-ANN), radial basis function- ANN (RBF- ANN), least square support vector machines (LSSVM), adaptive neuro-fuzzy inference system (ANFIS), M5 model tree (M5T), gene expression programming (GEP), genetic programming (GP) and Bayesian network (BN) with five type of mother wavelet functions (MWFs: coif4, db10, dmey, fk6 and sym7) and selected the best model by TOPSIS method. The case study is the Navrood watershed in the north of Iran and the considered parameters are daily flow discharge, temperature and precipitation during 1991 to 2018. The derived results show that the best method is the hybrid of M5T model with sym7 wavelet function. The MWFs were decomposed by discrete wavelet transform (DWT). Combination of AI models and MWFs improves the correlation coefficient of MLP, RBF, LSSVM, ANFIS, GP, GEP, M5T and BN by 8.05, 4.6, 8.14, 8.14, 22.97, 7.5, 5.75 and 10% respectively.

No abstract

In this study, five hydrological models, including the soil and water assessment tool (SWAT), identification of unit hydrograph and component flows from rainfall, evapotranspiration, and streamflow (IHACRES), Hydrologiska Byråns Vattenbalansavdelning (HBV), Australian water balance model (AWBM), and Soil Moisture Accounting (SMA), were used to simulate the flow of the Hablehroud River, north-central Iran. All the models were validated based on the root mean square error (RMSE), coefficient of determination (R2), Nash-Sutcliffe model efficiency coefficient (NS), and Kling-Gupta efficiency (KGE). It was found that SWAT, IHACRES, and HBV had satisfactory results in the calibration phase. However, only the SWAT model had good performance in the validation phase and outperformed the other models. It was also observed that peak flows were generally underestimated by the models. The sensitivity analysis results of the model parameters were also evaluated. A hybrid model was developed using gene expression programming (GEP). According to the error measures, the ensemble model had the best performance in both calibration (NS = 0.79) and validation (NS = 0.56). The GEP combination method can combine model outputs from less accurate individual models and produce a superior river flow estimate.

The purpose of this study was to investigate the impact of climate change on the water level and shrinkage of Lake Urmia. To achieve this, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) algorithm was used to select the top 10 general circulation models (GCMs) among 23 CMIP5 GCMs in the baseline period (1951–2005). Based on the K-nearest neighbors (KNN) method, 10 GCMs were combined and their uncertainties were quantified. Also, the future period (2028–2079) data were generated by using the LARS-WG model. According to the results, the temperature increased in all seasons of the future period. Under the RCP4.5 scenario, the precipitation decreases by 10.4 and 27.8% in spring and autumn, respectively, while it increases by 18.2 and 3.4% in summer and winter, respectively. Moreover, the RCP8.5 scenario lowers the precipitation by 11.4, 22.7, and 4.8% in spring, autumn, and winter, respectively, while it rises by 26.5% in summer. Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) were used to calculate the short-, medium- and long-term meteorological droughts of the baseline and future periods. The occurrence number and peaks of droughts increase, while their durations decrease, in the future period. In general, the SPEI has a robust relationship than the SPI with changes in the water level of Lake Urmia.