Estimating Daily Pan Evaporation Data using Adaptive Neuro Fuzzy Inference System: Case Study within Van Local Station-Turkey

Abstract

The aim of this study is to model the evaporation data, which is one of the important parameters of the hydrological cycle, by using the Adaptive Neuro Fuzzy Inference System (ANFIS). Four different models were designed starting from one input up to four inputs used average daily temperature (ºC), average daily relative humidity (%), average daily current pressure (hPa) and average daily wind speed (m/s) as inputs parameters. Total daily pan evaporation (mm) was selected as output parameter. The normalized daily data of the Van Local Station between 2013 - 2017 was used for training of the model. Data for 2018 were used for testing purposes. Also, two stations in different cities were selected for comparison in order to determine whether the models prepared using data from Van Local Station can be used in other stations. For this purpose, a station from Konya province with climatic characteristics similar to Van province and a station from Kocaeli province with different climatic characteristics were selected. In all models, similar results between Van Local Station and the station selected from Konya were observed, while the results between Van Local Station and the station selected from Kocaeli were observed as relatively low compared to the previous comparison. The fourth model, which was designed using four input parameters, achieved the lowest error values at all stations and Kocaeli station got the best R2 value at this model.