Modeling of stage-discharge using back propagation ANN-, ANFIS-, and WANN-based computing techniques

The development of the stage-discharge relationship is a fundamental issue in hydrological modeling. Due to complexity relationship, discharge prediction plays an essential role planning and water resource management. present study was conducted model at Gaula Barrage site Uttarakhand state India. evaluated adaptive neuro-fuzzy inference system (ANFIS)-, artificial neural network (ANN)-, wavelet-based (WANN)-based models estimate discharge. daily data 12 years (2007–2018) were used train test models. gamma identify best for prediction. input having stage with 1-day lag 1- 2-day lags current-day as output In case ANN models, back propagation algorithm hyperbolic tangent sigmoid activation function used. WANN Haar, trous-based wavelet function. ANFIS triangular, psig, generalized bell, Gaussian membership functions qualitatively quantitatively using correlation coefficient, root means square error, Willmott index, efficiency coefficient. It found that performed better than ANN- WANN-based Barrage.