Neural Network Model for Evaporation Prediction in Plain Area of Syrian Coastal Region Depending on Monthly Temperature


Abstract in English

Evaporation forms one of the hydrology cycle elements that it's hard to measure its actual amounts in the field conditions, so it’s estimated by calculations of experimental relations, which depend on climatic elements data. So the research goal is to build a mathematical model to estimate monthly evaporation amount in plain area of Syrian Coast, using Artificial Neural Network (ANN), and depending on dry air temperature, and produce comparison study between the results of network and other models. The mathematical model was built by the (NN-tool box), which is one of the v tools. A multilayer ANN architecture of error Back-propagation algorithm was built. The suitable training algorithms, number of hidden layers, number of neurons in each hidden layer, were determined. The results showed that the ANN (1-9-1) was the best model with MSE of 0.0032 for validation group, using Transfer Function Logsigmoid and Linear in hidden and output layers, respectively. A comparison model for the results obtained from the proposed ANN with EVANOV model by using SIMULINK technique was developed. This indicated that the ANN using temperature only gives results more accurate than EVANOV equation in determining evaporation.

References used

SUDHEER, M.E. et, al. Estimating actual evapotranspiration from limited climatic data using neural computing technique. J. Irri. Drain. Engg. ASCE. 129(3), 2003, 214-218
KESKIN, K.P. TERZI, O. Artificial Neural Network Models of Daily Pan Evaporation. J. Hydrologic Engrg. 11(1), 2006, 65-70
MOGHADDAMNIA, A. et, al. Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. Science Direct U. S. A.Vol.32, 2009, 88-97

Download