JWSS - Journal of Water and Soil Science

Nowadays, greater recognition of drought and introducing its monitoring systems, particularly for the short-term periods, and adding predictability to these systems, could lead to presentation of more effective strategies for the management of water resources allocation. In this research, it is tried to present appropriate models to predict drought in city of Semnan, Iran, using time series, adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (MLP and RBF). For these modeling processes, average monthly meteorological parameters of rainfall, temperature, minimum temperature, maximum temperature, relative humidity, minimum relative humidity, maximum relative humidity and SPI drought index were used during the period 1966 to 2013. The results showed that among the many developed models, the ANFIS model, with input data of average rainfall, maximum temperature, SPI and its last-month value, 10 rules and Gaussian membership function, showed appropriate performance at each stage of training and testing. The values of RMSE, MAE and R at training stage were 0.777, 0.593 and 0.4, respectively, and at testing stage were 0.837, 0.644 and 0.362, respectively. Then, the input parameters of this model were predicted for the next 12 months using ARIMA model, and SPI values were predicted for the next 12 months. The ANN and time series methods with low difference in error values were ranked next, respectively. The input parameters SPI and temperature had better performance and rainfall parameter had weaker performance.

Nowadays, water resource management has been shifted from the construction of new water supply systems to the management and the optimal utilization of the existing ones. In this study, the reservoir operating rules of Doroodzan dam reservoir, located in Fars province, were determined using different methods and the most efficient model was selected. For this purpose, a monthly nonlinear multi-objective optimization model was designed using the monthly data of a fifteen-year period (2002-2017). Objective functions were considered as minimizing water scarcity index in municipal, industrial, environmental and agricultural sectors. In order to determine the operating rule curves of reservoir, in addition to the nonlinear multi-objective optimization model, the methods of ordinary least-squares regression (OLS), fuzzy inference system and adaptive network fuzzy inference system (ANFIS) were used. Also, the reliability, resiliency, vulnerability and sustainability criteria were used to compare the different methods of reservoir performance rules. The results showed that ANFIS model had the higher sustainability criterion (0.26) due to its greater reliability (0.7) and resilience (0.42), as well as its lower vulnerability (0.13), thereby showing the best performance. Therefore, ANFIS model could be effectively used for the creation of Doroodzan reservoir operation rules.