black widow algorithm

The key to social and economic development is water, an essential natural resource. Worldwide, many areas are experiencing water supply and demand mismatches or are under extreme stress due to water shortages. Water resources have been mismanaged or limited due to an increase in demand and limitations in available water supply (Banadkooki et al., 2019). Rainfall and runoff are considered to be the main components of the hydrological cycle. In order to capture the dynamic relationship between rainfall and runoff, engineers need to develop an accurate model (Tikhamarine et al., 2022). Rainfall-runoff modeling is one of the methods of estimating runoff and a suitable tool for studying hydrological processes, evaluating water resources and watershed management (Abrahart and See, 2000). But the complexity and non-linear nature of the rainfall-runoff process and the unknown effect of the factors on each other and finally on the outflow of the basin make modeling more difficult (Moriasi et al., 2007). Therefore, it is necessary to use methods that, in addition to dynamism, have the ability to develop, have a conceptual and user-friendly structure (Shi et al., 2012). The role and importance of the mentioned process in water resources studies has caused this process to be noticed by experts (Guven, 2009). Therefore, several methods such as artificial neural networks, fuzzy and neuro-fuzzy systems, wavelet analysis, genetic algorithm, genetic programming and stochastic differential equations have been developed to model the rainfall-runoff process (Yaseen et al., 2016; Zhang et al., 2019). The development of rainfall-runoff models using different AI models has been conducted several times in the past two decades, but these models still have several shortcomings. These drawbacks are usually related to overfitting, difficulty in initializing the internal parameters related to these models and proposing the proper input-output architecture of the model (Ahmed et al., 2019).