Prediction of flow duration curve in ungauged catchments using genetic expression programming

Abstract

A set of multivariate equations have been developed using gene expression programming (GEP) based symbolic regression technique to generate the flow quantiles of flow duration curve (FDC) in the ungauged catchments in the East Coast of Peninsular Malaysia. The equations were derived from four to seven candidate explanatory variables prepared from climatic, geomorphologic, geographic characteristics, soil properties, and land use and land cover information. Support vector machine (SVM) was used to optimize the best combinations for calibration and validation of GEP models from the data available in thirteen gauged catchments in the study area. Seven flow percentiles namely 0.05, 0.10, 0.25, 0.50, 0.75, 0.90, and 0.95 as well as extreme, maximum, minimum and mean annual flows were identified to develop a framework for predicting various flow metrics. Obtained results revealed that nonlinear regression equations developed using GEP can generate FDCs in ungauged catchments of East Coast of Peninsular Malaysia with an efficiency of up to 0.92.