“…to ascertain the relationship between the input and output variables. The physical-based and black box models include conventional regression models [9], artificial neural networks (ANN) [14,20,30,31], feedforward neural networks (FNN) [22,32], general regression neural networks (GRNNs) [33,34], deep belief neural network (DBNN) [35], support vector machines (SVMs) [16,18,[36][37][38], gene expression programming (GEP) [39,40], adaptive neural fuzzy inference system (ANFIS) [41], Fourier analysis [7], hybrid models (e.g., combined wavelet) [23,42,43], fuzzy regression [44], fuzzy cognitive map learning method [45], epidemiology-based forecasting framework [46], temporal disaggregation [47], harmonic analysis [48], and wavelet de-noising [49].…”