Please use this identifier to cite or link to this item: https://idr.l1.nitk.ac.in/jspui/handle/123456789/12609
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPammar, L.
dc.contributor.authorDeka, P.C.
dc.date.accessioned2020-03-31T08:41:53Z-
dc.date.available2020-03-31T08:41:53Z-
dc.date.issued2014
dc.identifier.citationInternational Journal of Earth Sciences and Engineering, 2014, Vol.7, 1, pp.195-202en_US
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/12609-
dc.description.abstractWater scarcity globally has lead to severe problems in water management. Understanding the rate of evaporation, from surface water resources is essential for precise management of the water balance. However, evaporation is difficult to measure experimentally due to its nature. Preparing reliable forecasts of evaporation has become an essential element towards efficient water management. The objective of this paper is to predict daily pan evaporation using different kernel functions of Support Vector Machines (SVM's) based regression approach for the meteorological data obtained for the region 'Lake Abaya' which is located in the Great Rift Valley, southern part of Ethiopia. The meteorological parameters considered for study includes daily details of mean-temperature (T), wind speed (W), sunshine hours (Sh), relative humidity (Rh), rainfall (P). Among the kernel functions used for study, the polynomial kernel function proved its credibility by showing improved performance in training and testing periods. The evidence for performance of polynomial kernel function was seen in terms of correlation coefficient (CC) obtained for training and testing is respectively 0.940, 0.956 which is acceptable. 2014 CAFET-INNOVA TECHNICAL SOCIETY.en_US
dc.titlePrediction of daily pan evaporation using support vector machinesen_US
dc.typeArticleen_US
Appears in Collections:1. Journal Articles

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.