Development of a support-vector-machine-based model for daily pan evaporation estimation

摘要

Evaporation estimation is an important issue in water resources management. In this article, a four-season model with optimalninput combination is proposed to estimate the daily evaporation. First, the model based on support vector machine (SVM)ncoupled with an input determination process is used to determine the optimal combination of input variables. Second, ancomparison of the SVM-based model with the model based on back-propagation network (BPN) is made to demonstrate thensuperiority of the SVM-based model. In addition, season data are used to construct the SVM-based four-season model to furthernimprove the daily evaporation estimation. An application is conducted to demonstrate the performance of the proposed model.nResults show that the SVM-based model can select the optimal input combination with physical mechanism. The SVM-basednmodel is more appropriate than the BPN-based model because of its higher accuracy, robustness and efficiency. Moreover, thenimprovement due to the use of the four-season model increases from 3.22% to 15.30% for RMSE and from 4.84% to 91.16% fornCE, respectively. In conclusion, the SVM-based model coupled with the proposed input determination process should be used tonselect input variables. The proposed four-season SVM-based model with optimal input combination is recommended as annalternative to the existing models. The proposed modelling technique is expected to be useful to improve the daily evaporationnestimation. Copyright © 2012 John Wiley & Sons, Ltd.