Estimating Daily Pan Evaporation Using Data Mining Process

Abstract

This study investigates applicability of data mining process in estimation of daily pan evaporation which is one of the fundamental elements in the hydrological cycle. Firstly, the models were developed by using autoregressive modeling frequently preferred in hydrological studies for Lake Eğirdir in the southern part of Turkey and it was shown suitability of the AR(3) model. Hence, the 1-day, 2-day and 3-day previous daily pan evaporation values of Lake Eğirdir were used to develop the other DM models. The correlation coefficient and root mean square error criteria were used for evaluating the accuracy of the developed models. When the results of developed models were compared to observed pan evaporation according to these criteria, it was determined that the AR(3) model is a little more appropriate to estimate of daily pan evaporation. Consequently, it was shown DM models are useful as they are based on only daily pan evaporation data and not included the meteorological parameters.