Runoff Modeling using ANN-based Generalized Feed Forward (GFF) and Multi Linear Regression (MLR) Technique for Narmada River Basin, Gujarat

Runoff prediction is one of the most important topics in water resources planning, development and management on a sustainable basis. The Generalized Feed Forward (GFF) Multiple Linear Regression (MLR). This study was undertaken to develop evaluate applicability GFF MLR models by way training testing developed during monsoon period (June September) for Narmada River Basin Chota Udaipur district Gujarat state India. daily data rainfall, runoff, minimum & maximum temperature wind speed were used season. split into two sets: set from 2004 2008 2009 2010 river basin. input pairs applied network selected architecture performed using back propagation algorithm models. A number networks constructed each them trained separately, best based accuracy predictions phase. following statistical indices such as mean squared error (MSE), coefficient efficiency (CE), determination (R2) correlation (r) test performance predicted suspended sediment found be performing It evident that fit very poorly dataset under study. current day’s runoff can simulated (GFF–8).