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.

[1]  Graham W. Taylor,et al.  Prediction of flow duration curves for ungauged basins , 2017 .

[2]  Ataur Rahman,et al.  Application of artificial neural networks in regional flood frequency analysis: a case study for Australia , 2014, Stochastic Environmental Research and Risk Assessment.

[3]  Hossein Bonakdari,et al.  Design criteria for sediment transport in sewers based on self-cleansing concept , 2014 .

[4]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[5]  Bradley A. Miller,et al.  Spatial distribution of historical wetland classes on the Des Moines Lobe, Iowa , 2009, Wetlands.

[6]  J. Prior.  Landforms of Iowa , 1991 .

[7]  Mehdi Rahmati,et al.  Reliable and accurate point-based prediction of cumulative infiltration using soil readily available characteristics: A comparison between GMDH, ANN, and MLR , 2017 .

[8]  Bahram Gharabaghi,et al.  Reservoir water level forecasting using group method of data handling , 2018, Acta Geophysica.

[9]  Hui Zhang,et al.  Integration of dynamic rainfall data with environmental factors to forecast debris flow using an improved GMDH model , 2013, Comput. Geosci..

[10]  Hossein Bonakdari,et al.  Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design , 2017, Appl. Math. Comput..

[11]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[12]  Zaher Mundher Yaseen,et al.  Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model , 2017 .

[13]  Bahram Gharabaghi,et al.  Closure to “An integrated framework of extreme learning machines for predicting scour at pile groups in clear water condition” by: I. Ebtehaj, H. Bonakdari, F. Moradi, B. Gharabaghi, Z. Sheikh Khozani , 2019, Coastal Engineering.

[14]  Stanley J. Farlow,et al.  Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[15]  Bahram Gharabaghi,et al.  An integrated framework of Extreme Learning Machines for predicting scour at pile groups in clear water condition , 2018 .

[16]  Mohammad Najafzadeh,et al.  Evaluation of neuro-fuzzy GMDH-based particle swarm optimization to predict longitudinal dispersion coefficient in rivers , 2016, Environmental Earth Sciences.

[17]  A. Parsaie,et al.  Physical and numerical modeling of performance of detention dams , 2017 .

[18]  J. McDonnell,et al.  A decade of Predictions in Ungauged Basins (PUB)—a review , 2013 .

[19]  Paulin Coulibaly,et al.  Streamflow Prediction in Ungauged Basins: Review of Regionalization Methods , 2013 .

[20]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[21]  Kuk-Hyun Ahn,et al.  Regional flood frequency analysis using spatial proximity and basin characteristics: Quantile regression vs. parameter regression technique , 2016 .

[22]  Ataur Rahman,et al.  Regional flood frequency analysis in eastern Australia: Bayesian GLS regression-based methods within fixed region and ROI framework – Quantile Regression vs. Parameter Regression Technique , 2012 .

[23]  Amir Hossein Zaji,et al.  Prediction of scour depth around bridge piers using self-adaptive extreme learning machine , 2017 .

[24]  Bahram Gharabaghi,et al.  Stable alluvial channel design using evolutionary neural networks , 2018, Journal of Hydrology.

[25]  Wolfgang Wagner,et al.  Initial soil moisture effects on flash flood generation – A comparison between basins of contrasting hydro-climatic conditions , 2016 .

[26]  Xin Yan,et al.  Linear regression , 2012 .

[27]  Bahram Gharabaghi,et al.  Entropy-based neural networks model for flow duration curves at ungauged sites , 2015 .

[28]  G. Blöschl,et al.  Flood frequency regionalisation—spatial proximity vs. catchment attributes , 2005 .