Application of gene expression programming to predict daily dew point temperature

•The ability of GEP was investigated to estimate daily dew point temperature.•Three types of scenarios were utilized to develop the different GEP models.•Actual vapor pressure was effective parameter in estimating dew point temperature.•Dew point temperature can be estimated using adjacent station data and GEP. In the present research, gene expression programming (GEP) was used to estimate daily dew point temperature (Tdew) in Tabriz and Urmia which are located in the northwest of Iran, using the recorded data sets for the period of 1998–2012. Accordingly, three types of scenarios namely temperature-based, multiple parameters-based and periodicity-based were considered to develop the GEP models. Various combinations of meteorological parameters including minimum air temperature (Tmin), maximum air temperature (Tmax), mean air temperature (T), actual vapor pressure (ea), relative humidity (RH) and atmospheric pressure (Pa) were used as inputs in the first and second scenarios. Also, root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE) and coefficient of determination (R2) were employed to investigate the models’ accuracy. The results showed that the ea is the most effective parameter in estimating Tdew. In the second part of the present study, Tdew of each station was estimated using meteorological data of the adjacent station. It is found that the meteorological data of the adjacent station can be used to predict Tdew. Moreover, the results of validation stage generally confirmed the outcomes of testing stage.