metaheuristic algorithms

Estimating the available water plays a vital role in planning water resources projects. The first step in assessing water availability is to calculate runoff in catchments. Moreover, it is necessary to study the effects of climate change on water components such as runoff since climate change directly affects the hydrological components and water resources. In this study, the status of the inflow to Tashk-Bakhtegan lakes as one of the most important lakes in the country was investigated. Because generation of runoff is a complex concept due to its nonlinear and multidimensional nature, various theoretical and physical models have been developed to predict runoff. The high dependence of these physical models on numerous parameters and maps, practically challenfged their efficiency in basins with limited observations. On the other hand, models based on artificial neural networks and fuzzy inference systems are considered applied tools that can help hydrologists in such circumstances. In this study, FFBPNN and ANFIS models and their combination with PSO and GA metaheuristic algorithms have been investigated in evaluating the runoff in historical conditions and under RCP and SSP climate change scenarios.  The obtained results showed that the FFBPNN and ANFIS models combined with the PSO algorithm (ANFIS_PSO) using precipitation, minimum temperature, and maximum temperature as inputs had better performance compared to other models with different inputs. The values of the correlation coefficient, root mean square error (m3/s), Nash-Sutcliffe coefficient and Kling Gupta were respectively 0.99, 2.07, 0.99 and 0.98 in the training period and 0.94, 3.61, 0.91 and 0.88 in the test period and 0.98, 94. 2, 0.97 and 0.98 in the training period and 0.93, 3.87, 0.85 and 0.88 in the test period. The results of this study can be used in investigating the effects of the above mentioned scenarios on important basins of the country and consequently in planning and managing water resources in the context of climate change.