Lakes have an important role in storing water for drinking, producing hydroelectric power, and environmental, agricultural, and industrial uses. In order to optimize the use of lakes, precise prediction of the lake water level (LWL) is a main issue in water resources management. Due to the existence of nonlinear relations, uncertainty, and characteristics of the time series variables, the exact prediction of the lake water level is difficult. In this study the hybrid support vector regression (SVR) and the grey wolf algorithm (GWO) are used to predict lake water level fluctuations. Also, three types of data preprocessing methods, namely Principal component analysis, Random forest, and Relief algorithm were used for finding the best input variables for prediction LWL by the SVR and SVR-GWO models. Before the LWL simulation on monthly time step using the hybrid model, an evolutionary approach based on different monthly lags was conducted for determining the best mask of the input variables. Results showed that based on the random forest method, the best scenario of the inputs was $X_{t-1}, X_{t-2}, X_{t-3}, X_{t-4}$ for the SVR-GWO model. Also, the performance of the SVR-GWO model indicated that it could simulate the LWL with acceptable accuracy (with RMSE = 0.08 m, MAE = 0.06 m, and R² = 0.96).

Evapotranspiration estimation and forecasting is a key step in water management projects, especially in water-scarce countries such as Iran. Seasonal autoregressive integrated moving average (SARIMA), support vector machine (SVM), and group method of data handling (GMDH) models were developed and assessed to find an appropriate model for short and long-term forecasting of monthly reference evapotranspiration in the Guilan Plain, northern Iran. Monthly meteorological data gathered from four weather stations (Anzali, Astara, Manjil, and Rasht) were used to calculate monthly reference evapotranspiration in the period of 1993–2014 using the FAO-56 Penman–Monteith (FAO-PM) equation. The evapotranspiration data from 1993 to 2012 were used to fit SARIMA models and calibrate SVM and GMDH models, and the monthly evapotranspiration rates for the years 2013 and 2014 were forecasted using the calibrated models. The developed models were assessed using RMS error (RMSE), the Pearson correlation coefficient ($R$ ), the Nash–Sutcliffe model efficiency coefficient (NS), and percent bias. Taylor diagrams also were used to compare the accuracy of forecasts produced by the models. For the whole forecasting period (2013–2014), the RMSE of the calibrated SARIMA, SVM, and GMDH models were, respectively, 8.796, 9.830, and $9.547\mathrm{mm}/\mathrm{month}$ for Anzali weather station; 8.136, 9.057, and $7.808\mathrm{mm}/\mathrm{month}$ for Astara weather station; 9.454, 8.947, and $8.876\mathrm{mm}/\mathrm{month}$ for Manjil weather station; and 9.301, 10.509, and $10.138\mathrm{mm}/\mathrm{month}$ for Rasht weather station. In other words, in two weather stations under study (Anzali and Rasht), the best results were obtained from SARIMA; however, for Astara and Manjil weather stations, GMDH generated the best forecasts. Furthermore, at different forecasting horizons (1–24 months), the SARIMA models generally outperformed the SVM and GMDH models.