Estimation of Ataturk Dam Evaporation Amount Using Fuzzy Logic Method

Abstract

Accurate prediction of evaporation is important for various purposes such as dam structure design, operation, and the development and management of water resources. Determining water evaporation from the reservoir volume is an important parameter for reservoir operation studies, based on hydrological and meteorological data. In this study, daily average relative humidity, air temperature, wind speed, and sunshine duration parameters were used for evaporation estimation. In the study, daily evaporation estimation was performed using the methods of Multiple Linear Regression (MLR), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Fuzzy Logic - Simple Membership Functions and Fuzzy Rule Generation Technique (Fuzzy -SMRGT). As the study area, the Atatürk Dam, located between the provinces of Adıyaman and Şanlıurfa, has been chosen. In the study, the model results were evaluated according to statistical criteria such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Coefficient of Determination. When evaluating the model results, it was determined that the MLR, ANFIS and Fuzzy-SMRGT models yielded similar results in daily evaporation estimation and that the Fuzzy Logic (ANFIS and Fuzzy SMRGT) models were applicable.