Application of meta-heuristic algorithms to estimate daily evaporation rate

Accurate estimation of daily evaporation is very important in the sustainable management of water resources. Therefore, the purpose of this study is to investigate the application of the artificial neural network model with the meta-heuristic algorithm of wavelet and firefly to estimate daily ET۰. To achieve this goal, two combined W-ANN and FA-ANN models were investigated for daily estimation of ET۰ in two Mediterranean climates in the west of Iran as a case study. Daily climatic parameters including maximum and minimum temperature (T max and T min), sunshine duration (n), relative humidity (RH), wind speed (U), and evaporation ET۰ were collected from two weather stations from ۲۰۱۲-۲۰۲۲ and during Four combined scenarios were investigated. which were used from ۲۰۱۲ to ۲۰۱۹ for model training and from ۲۰۲۲ to ۲۰۱۹ for model testing. To compare and evaluate the models, statistical indicators of the correlation coefficient, root mean square error, mean absolute value of error, normalized root mean square error, and Nash Sutcliffe coefficient were used. The results showed that all the investigated models have better performance in combined input scenarios. The results of the evaluation criteria showed that the W-ANN hybrid model has the highest daily estimation accuracy.

کلیدواژه ها:

Evaporation ، Artificial neural network ، Firefly ، wavelet