Title: Forecasting daily pan evaporation using hybrid model of wavelet transform and support vector machines

Authors: Leeladhar Pammar; Paresh Chandra Deka

Addresses: Department of Applied Mechanics and Hydraulics, National Institute of Technology Karnataka, Surathkal, Mangalore, 575025, India ' Department of Applied Mechanics and Hydraulics, National Institute of Technology Karnataka, Surathkal, Mangalore, 575025, India

Abstract: Providing accurate and reliable estimation of evaporation has been of a great importance and has become obvious in many water resources applications such as management of hydrologic, hydraulic and agricultural systems. Researchers are finding reliable method of forecasting of pan evaporation. It is also important because of its key role in the part of development and management of water resources in varied climatic regions. The study includes exploring hybrid model wavelet and support vector machine in daily pan evaporation forecasting for the data recorded near 'Bajpe' of Dakshina Kannada District, of Karnataka State, India. The conjunction method is compared with the single support vector machine. Gamma test and the parameter optimisation are necessary for accurate results and validation, in view of that parameter optimisation with grid search is employed. The root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (CC) statistics are used for comparison of results obtained, which shows that the hybrid method could increase the forecast accuracy and perform better than the single support vector machine.

Keywords: support vector machines; SVM; wavelet transformation; grid search; gamma test; regression; pan evaporation; forecasting accuracy; hybrid modelling; evaporation estimation; water resources; water management; India; hydrology.

DOI: 10.1504/IJHST.2015.071354

International Journal of Hydrology Science and Technology, 2015 Vol.5 No.3, pp.274 - 294

Received: 19 Dec 2014
Accepted: 24 Jun 2015
Published online: 21 Aug 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article