Use of Gene Expression Programming in regionalization of flow duration curve

Abstract In this paper, a recently introduced artificial intelligence technique known as Gene Expression Programming (GEP) has been employed to perform symbolic regression for developing a parametric scheme of flow duration curve (FDC) regionalization, to relate selected FDC characteristics to catchment characteristics. Stream flow records of selected catchments located in the Auckland Region of New Zealand were used. FDCs of the selected catchments were normalised by dividing the ordinates by their median value. Input for the symbolic regression analysis using GEP was (a) selected characteristics of normalised FDCs; and (b) 26 catchment characteristics related to climate, morphology, soil properties and land cover properties obtained using the observed data and GIS analysis. Our study showed that application of this artificial intelligence technique expedites the selection of a set of the most relevant independent variables out of a large set, because these are automatically selected through the GEP process. Values of the FDC characteristics obtained from the developed relationships have high correlations with the observed values.

[1]  Rafael G. Quimpo,et al.  Regionalized Flow Duration for Philippines , 1983 .

[2]  A. Gustard,et al.  Low Flow Estimation in the United Kingdom , 1992 .

[3]  Andrea Rinaldo,et al.  Basin‐scale soil moisture dynamics and the probabilistic characterization of carrier hydrologic flows: Slow, leaching‐prone components of the hydrologic response , 2007 .

[5]  Ranvir Singh,et al.  Regional Flow-Duration Models for Large Number of Ungauged Himalayan Catchments for Planning Microhydro Projects , 2001 .

[6]  V. Smakhtin,et al.  Continuous daily hydrograph simulation using duration curves of a precipitation index , 2000 .

[7]  Attilio Castellarin,et al.  Regional flow-duration curves: reliability for ungauged basins , 2004 .

[8]  Pao-Shan Yu,et al.  Uncertainty Analysis of Regional Flow Duration Curves , 2002 .

[9]  Karen Croker,et al.  Flow duration curve estimation in ephemeral catchments in Portugal , 2003 .

[10]  Nilgun B. Harmancioglu.  Integrated Approach to Environmental Data Management Systems , 1997 .

[11]  Peter R. Waylen,et al.  A stochastic model of flow duration curves , 1993 .

[12]  A. Rinaldo,et al.  Probabilistic characterization of base flows in river basins: Roles of soil, vegetation, and geomorphology , 2007 .

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

[14]  Croker,et al.  A river network based hydrological model for predicting natural and influenced flow statistics at ungauged sites: Micro LOW FLOWS , 2000, The Science of the total environment.

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

[16]  P. Claps,et al.  Probabilistic Flow Duration Curves for use in Environmental Planning and Management , 1997 .

[17]  Ioannis A. Niadas,et al.  Probabilistic Flow Duration Curves for Small Hydro Plant Design and Performance Evaluation , 2008 .

[18]  A. Gustard,et al.  A region of influence approach to predicting flow duration curves within ungauged catchments , 2002 .

[19]  Andrea Rinaldo,et al.  Ecohydrological model of flow duration curves and annual minima , 2008 .

[20]  Junaid A. Patel.  Evaluation of low flow estimation techniques for ungauged catchments , 2007 .

[21]  Alberto Viglione,et al.  An approach to estimate nonparametric flow duration curves in ungauged basins , 2009 .

[22]  Y. Mohamoud,et al.  Prediction of daily flow duration curves and streamflow for ungauged catchments using regional flow duration curves , 2008 .

[23]  Denis A. Hughes,et al.  Regionalization of daily flow characteristics in part of the Eastern Cape, South Africa , 1997 .

[24]  Maria Mimikou,et al.  Regionalization of flow duration characteristics , 1985 .

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

[26]  Richard M. Vogel,et al.  Closure of "Regional Flow-Duration Curves for Ungauged Sites in Massachusetts" , 1990 .

[27]  Andrea Rinaldo,et al.  Resilience of river flow regimes , 2013, Proceedings of the National Academy of Sciences.

[28]  Attilio Castellarin,et al.  Geostatistical prediction of flow-duration curves , 2013 .

[29]  A. Rinaldo,et al.  Signatures of large‐scale soil moisture dynamics on streamflow statistics across U.S. climate regimes , 2007 .

[30]  C. Cunnane,et al.  LOW-FLOW PREDICTION FOR UNGAUGED RIVER CATCHMENTS IN IRELAND , 2009 .

[31]  R. Abrahart,et al.  Use of Gene Expression Programming for Multimodel Combination of Rainfall-Runoff Models , 2012 .

[32]  Marco Franchini,et al.  Regional analysis of flow duration curves for a limestone region , 1996 .

[33]  R. Woods,et al.  Freshwaters of New Zealand , 2004 .

[34]  Vito Iacobellis.  Probabilistic model for the estimation of T year flow duration curves , 2008 .

[35]  Taha B. M. J. Ouarda,et al.  Improved methods for daily streamflow estimates at ungauged sites , 2012 .

[36]  Richard M. Vogel,et al.  A stochastic index flow model of flow duration curves , 2004 .

[37]  J. McDonnell,et al.  On the need for catchment classification , 2004 .

[38]  Attilio Castellarin,et al.  Predicting annual and long-term flow-duration curves in ungauged basins , 2007 .