Peak flood estimation using gene expression programming

Summary As a case study for the Auckland Region of New Zealand, this paper investigates the potential use of gene-expression programming (GEP) in predicting specific return period events in comparison to the established and widely used Regional Flood Estimation (RFE) method. Initially calibrated to 14 gauged sites, the GEP derived model was further validated to 10 and 100 year flood events with a relative errors of 29% and 18%, respectively. This is compared to the RFE method providing 48% and 44% errors for the same flood events. While the effectiveness of GEP in predicting specific return period events is made apparent, it is argued that the derived equations should be used in conjunction with those existing methodologies rather than as a replacement.

[1]  R. Vogel,et al.  L moment diagrams should replace product moment diagrams , 1993 .

[2]  Khaled Haddad,et al.  Regional Flood Estimation in New South Wales Australia Using Generalized Least Squares Quantile Regression , 2011 .

[3]  Raghavan Srinivasan,et al.  PREDICTION OF TWO‐YEAR PEAK STREAM‐DISCHARGES USING NEURAL NETWORKS 1 , 1997 .

[4]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[5]  Vladan Babovic,et al.  GENETIC PROGRAMMING: A NEW PARADIGM IN RAINFALL RUNOFF MODELING 1 , 2002 .

[6]  Ali Aytek,et al.  An application of artificial intelligence for rainfall-runoff modeling , 2008 .

[7]  John R. Koza,et al.  Genetic programming as a means for programming computers by natural selection , 1994 .

[8]  J. Hosking.  L‐Moments: Analysis and Estimation of Distributions Using Linear Combinations of Order Statistics , 1990 .

[9]  Khaled H. Hamed,et al.  Flood Frequency Analysis , 1999 .

[10]  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 .

[11]  A. Mckerchar,et al.  Maps of flood statistics for regional flood frequency analysis in New Zealand , 1990 .

[12]  Cândida Ferreira,et al.  Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence , 2014, Studies in Computational Intelligence.

[13]  R. Abrahart,et al.  Flood estimation at ungauged sites using artificial neural networks , 2006 .

[14]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[15]  V. Nguyen,et al.  A comparative study of regression based methods in regional flood frequency analysis , 1999 .

[16]  D. Thomas,et al.  Generalization of streamflow characteristics from drainage-basin characteristics , 1970 .

[17]  Aytac Guven,et al.  Estimation of Peak Flood Discharges at Ungauged Sites Across Turkey , 2012, Water Resources Management.

[18]  Jalal Shiri,et al.  Forecasting daily stream flows using artificial intelligence approaches , 2012 .

[19]  Özgür Kisi,et al.  Modeling rainfall-runoff process using soft computing techniques , 2013, Comput. Geosci..

[20]  Hazi Mohammad Azamathulla,et al.  Gene-Expression Programming for the Development of a Stage-Discharge Curve of the Pahang River , 2011 .

[21]  Ton H. Snelder,et al.  MULTISCALE RIVER ENVIRONMENT CLASSIFICATION FOR WATER RESOURCES MANAGEMENT 1 , 2002 .

[22]  A. Tait,et al.  Generating Multiyear Gridded Daily Rainfall over New Zealand , 2005 .

[23]  J. R. Wallis,et al.  Some statistics useful in regional frequency analysis , 1993 .

[24]  Ataur Rahman,et al.  Design flood estimation in ungauged catchments using genetic algorithm-based artificial neural network (GAANN) technique for Australia , 2015, Natural Hazards.

[25]  Muhammad Zaffar Hashmi,et al.  Use of Gene Expression Programming in regionalization of flow duration curve , 2014 .

[26]  Xiaogu Zheng,et al.  Thin plate smoothing spline interpolation of daily rainfall for New Zealand using a climatological rainfall surface , 2006 .

[27]  J. Sansom,et al.  Mesoscale spatial variation of rainfall through a hidden semi‐Markov model of breakpoint data , 2003 .

[28]  Ali Aytek,et al.  New Approach for Stage–Discharge Relationship: Gene-Expression Programming , 2009 .

[29]  Delineating Flood-Flow Regions for the North Island of New Zealand , 2016 .

[30]  A. Mckerchar,et al.  Shifts in flood and low-flow regimes in New Zealand due to interdecadal climate variations , 2003 .

[31]  A. Mckerchar.  Regional flood frequency analysis for small New Zealand basins. I: Mean annual flood estimation , 1991 .

[32]  Özgür Kisi,et al.  River suspended sediment estimation by climatic variables implication: Comparative study among soft computing techniques , 2012, Comput. Geosci..