Estimating 2-year flood flows using the generalized structure of the Group Method of Data Handling

Abstract

The lack of stream gauging data worldwide has inspired an abundance of methods attempting to predict the complex natural process of streamflow. A set of traditional regression equations have been developed by the U.S. Geological Survey for the state of Iowa. However, several inconsistencies were noted, including irregular region definition and varying input parameters between regions. To overcome the common problems faced in modelling, and to combat the irregularities in the regression equations, a new Group Method of Data Handling (GMDH) algorithm has been proposed using a combination of the classical combinatorial GMDH and multilayer GMDH to predict the 2-year peak flow. Data from 365 stream gauges located in the state of Iowa were used in the model development. The new algorithm was compared to the two classical algorithms and the traditional linear regression equations developed by the U.S. Geological Survey. The new algorithm which requires fewer input parameters without relying on regionalization was found to be the best method. The developed algorithm is based on a more robust hydrologic theory and therefore is a reliable method for predicting the 2-year peak flow for ungauged basins. The two main hypotheses inspired by the past regression equations and suggested in this study were that regionalization is not necessary and that using fewer input parameters to avoid redundancy still produces a robust prediction method. This study has developed a novel and reliable prediction method for peak flow prediction at ungauged basins while advancing insight into the most influential variables governing the magnitude of the flow.