Hydrology Research In Press, Uncorrected Proof © IWA Publishing 2011 | doi:10.2166/nh.2011.101
Modeling river stage–discharge–sediment rating relation using support vector regression
Sharad K. Jain
Indian Institute of Technology, Roorkee-247667, India E-mail: firstname.lastname@example.org
First received 22 October 2010; accepted in revised form 1 June 2011. Available online 27 January 2012
A variety of data driven approaches have been developed in the recent past to capture the properties of hydrological data for improved modeling. These include artificial neural networks (ANNs), fuzzy logic and evolutionary algorithms, amongst others. Of late, kernel-based machine learning approaches have become popular due to their inherent advantages over traditional modeling techniques. In this work, support vector machines (SVMs), a kernel-based learning approach has been investigated for its suitability to model the relationship between the river stage, discharge, and sediment concentration. SVMs are an approximate implementation of the structural risk minimization principle that aims at minimizing a bound on the generalization error of a model. These have been found to be promising in many areas including hydrology. Application of SVMs to regression problems is known as support vector regression (SVR). This paper presents an application of SVR to model river discharge and sediment concentration rating relation. The results obtained using SVR were compared with those from ANNs and it was found that the SVR approach is better when compared with ANNs.
Keywords: artificial neural network; river stage–discharge rating; sediment concentration; support vector regression
Full Text PDF