“…Due to their excellent accuracy, these methods are commonly used by experts in modeling hydrological processes such as linear and multilinear regression (LMR) (Abdulelah Al-Sudani et al, 2019; A. Ahani, Shourian, & Rahimi Rad, 2018), autoregressive models (AR) (Banihabib et al, 2019), genetic algorithm (GA) combination models (Yaghoubi et al, 2019), gene expression programming (GEP) (Das et al, 2019), artificial neural networks (ANNs) (Ghose & Samantaray, 2019;Xu et al, 2009), wavelet transform (WT) (Freire et al, 2019;Honorato et al, 2019;Ravansalar et al, 2017), adaptive neuro-fuzzy inference system (ANFIS) (Chang et al, 2019;Yaseen et al, 2017), bayesian neural network (BNN) (Ren et al, 2018), recurrent neural networks (RNNs) (Tian et al, 2018), support vector regression (SVR) Yu et al, 2020) support vector machine (Ghorbani et al, 2018). Sabzi et al conducted monthly streamflow modeling utilizing ANFIS, the standalone models of ANN and autoregressive integrated moving average (ARIMA), and an integrated ANN-ARIMA model by using snow telemetry data in Elephant Butte reservoir at Mexico city (Zamani Sabzi et al, 2017).…”