تقدير التبخر اليومي في الساحل السوري باستخدام برمجة التعبير الجيني و نظام الاستدلال العصبي الضبابي التكيفي

Abstract EN

ABSTRACT-The evaporation is one of the basic components of the hydrologic cycle.

It is necessary to accurately estimate it for the development and management of water resources, it affects the amount of runoff, the capacity of surface reservoirs, and the plant's need for water, and it requires knowledge of many climatic variables.

Although, there are many empirical formulas available for evaporation estimate, but their performances are not all satisfactory due to the complicated nature of the evaporation process.

Therefore, the aim of this research is to evaluate the accuracy of Gene Expression Programming (GEP) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for estimating daily evaporation in the Syrian coast, and compare their results with the results of the Ivanov equation.

For this, we built GEP and ANFIS models using available climate data, taken from five climatic stations spread over the studied entire area and located at different heights.

The statistical parameters used to evaluate the accuracy of the models were: Root Mean Squared Error (RMSE) and correlation coefficient (R).

Comparative results showed that GEP is better than ANFIS for estimating pan evaporation.

Both models outperformed the Ivanov equation.

the model which including temperature, relative humidity, solar radiation and elevation is the best for estimating daily evaporation in the Syrian coast, where the values of RMSE and R for the test group in GEP and ANFIS models were respectively (0.55mm / day), R = 0.94, (0.7mm/ day), R = 0.92.