Estimating Daily Dew Point Temperature Based on Local and Cross-Station Meteorological Data Using CatBoost Algorithm

Accurate estimation of dew point temperature (Tdew) plays a very important role in the fields of water resource management, agricultural engineering, climatology and energy utilization. However, there are few studies on the applicability of local Tdew algorithms at regional scales. This study evaluated the performance of a new machine learning algorithm, i.e., gradient boosting on decision trees with categorical features support (CatBoost) to estimate daily Tdew using limited local and cross-station meteorological data. The random forests (RF) algorithm was also assessed for comparison. Daily meteorological data from 2016 to 2019, including maximum, minimum and average temperature (Tmax, Tmin and Tmean), maximum, minimum and average relative humidity (RHmax, RHmin and RHmean), maximum, minimum and average global solar radiation (Rsmax, Rsmin and Rsmean) from three weather stations in Hunan of China were used to evaluate the CatBoost and RF algorithms. The results showed that both algorithms achieved satisfactory estimation accuracy at the target stations (on average RMSE = 1.020 degrees C, R2 = 0.969, MAE = 0.718 degrees C and NRMSE = 0.087) in the absence of complete meteorological parameters (with only temperature data as input). The CatBoost algorithm (on average RMSE = 1.900 degrees C and R2 = 0.835) was better than the RF algorithm (on average RMSE = 2.214 degrees C and R2 = 0.828). The accuracy and stability of the CatBoost and RF algorithms were positively correlated with the number of input parameters, and the three-parameter algorithms achieved higher estimation accuracy than the two-parameter algorithms. The developed methodology is helpful to predict Tdew at regional scale.