Hydrograph Estimation based on Various Components of Rainfall Using Adaptive Neuro-Fuzzy Inference System in Kasilian Watershed

Flood hydrograph preparation and estimation are considered a comprehensive information for soil and water managers and planners. While it is not simply possible preparing it for all watersheds. Therfore suitable flood hydrograph estimation and modeling seems to be necessary using available rainfall data. The study area is located in Kasilian representative watershed in Mazandaran province comprising 66.75km2 in area. For the accomplished present study, 15 characteristics of hyetograph as independent variables and 8 characteristics of hydrograph as dependent variables were considered for 60 storms from 1975 to 2009. For estimation flood hydrograph, adaptive neuro-fuzzy inference system with two methods i.e. grid partitioning and subtractive clustering was used. Factor analysis was used to select the input variables. Due to inappropriate precision of estimated models, in order to select the input variables for estimation flood hydrograph in addition factor analysis the variance inflation factor also was used for selecting variables that have minimal multicollinearity. The results showed that the selection of input variables using the variance inflation factor improves the results to factor analysis. The ANFIS results showed that subtractive clustering was found to be superior to grid partitioning.