Iranian Journal of Irrigation and Drainage Iranian Journal of Irrigation and Drainage

Forecasting of river discharge is a important aspect of efficient water resources planning and management. In this study, time series pre and post-processing methods along with support vector machine (SVM) and Gaussian process regression (GPR) kernel based approaches were used to estimate flow discharge of two natural river in the United States with two consecutive hydrometric stations. The first river contained about 2 years of data and in the second river 4 years of daily discharge data was used. Different models were defined based on hydraulic characteristics and the capability of integrated pre and post-processing methods in two states of inter-station and between-stations was investigated. For data pre-processing, the Discrete Wavelet Transform (DWT) method was first used. Then, the high-frequency sub-series were selected and re-decomposed using the Ensemble Empirical Mode Decomposition (EEMD). Finally, sub-series with higher energy were imposed as inputs for kernel-based models. Non-linear neural average (NNA) model was also used for data post-processing. The obtained results from the defined models showed the high accuracy of the integrated methods used in the research in estimating flow discharge. At both stations, the error percentage was reduced by approximately 20 to 25% using the integrated pre-post-processing methods compared to the intelligent kernel based models. It was observed that in the case of river flow prediction based on the station's own data, the RMSE error value of the model decreased from approximately 0.3 to 0.26 and in the case of using the previous station data decreased from 0.44 to 0.33. Due to the high capability and accuracy of the pre-processing methods used in this study, similar studies are recommended in other rivers of the country.

Despite the high capability of field-scale agro-hydrological models to simulate plant growth interactions with water and solute transport in agricultural systems, their application to real conditions of large sugarcane fields in Khuzestan province faces many challenges, including spatial heterogeneity of irrigation scheduling across the field, the difficulty of determining initial and boundary conditions as well as several unknown model parameters, and data–intensiveness of calibration procedure. This work aimed to implement the agro-hydrological modeling under real operational conditions of large fields with surface/subsurface drainage. In this work, a distributed agro-hydrological modeling scheme was developed through the application of a modified version of the SWAP model and an improved variant of the Unified Particle Swarm Optimization (UPSO) algorithm with capability of sub-daily calibration and simulation of controlled drainage. The developed model was applied to a sugarcane field with subsurface drainage with planted sugarcane (CP48-103 cultivar) in Imam Khomeini Sugarcane Agro-industrial company farms, during 2010-07-19 to 2011-12-11 (481 days). The results revealed the reasonable performance of the developed modeling scheme in retrieving the measured soil moisture, groundwater level, subsurface drainage outflow (with an EF of 0.901, 0.827, and 0.877 for calibration dataset; and 0.514, 0.798, and 0.672 for validation dataset, respectively), soil water solute concentration, subsurface drainage outflow salinity (with a NRMSE of 0.039 and 0.096 for calibration dataset; and 0.154 and 0.046 for validation dataset, respectively), Leaf Area Index, cane yield, and sucrose yield (with an EF of 0.995, 0.999, and 0.972, respectively).

Drought is one of the natural and recurring climatic phenomena that has various effects on economic, social
and environmental sectors. Drought, itself, is not a challenge, but it is the beginning of a crisis depending on the
degree of vulnerability and impact it has on various sectors. Therefore, this study has attempted to calculate the
risk of drought for the baseline period using natural risk definition and to estimate the best model for predicting
its rate for future periods affected by different methods under climate change. Accordingly, drought risk was
calculated using the two meteorological drought indices SPEI and eRDI the for years 1983-2015. Then, was
determined the degree of vulnerability for the Afin area using a questionnaire. After estimating the risk during
this time period, with the help of the Markov chain statistical technique, the drought risk characteristics of the
region were obtained. Using the four modeling methods the best drought risk prediction model was determined
and by using the meteorological variables studied from the three climate models of the CORDEX project the
drought risk for the years 2020-2100was predicted. The results of this study showed a decrease in risk for 2020-
2046 and an increase in 2047-2000 based on both RCP4.5 and RCP8.5 compared to the period 1983-1995.