Real-Time Estimation of Near Surface Air Temperature over Greece Using Machine Learning Methods and LSA SAF Satellite Products

The air temperature near the earth’s surface is one of the most important meteorological and climatological parameters. Yet, accurate and timely readings are not available in significant parts of the world. The development and the first validation of a methodology for the estimation of Near Surface Air Temperature (NSAT) is presented here. Machine learning and satellite products are in the core of the developed model. Land Surface Analysis Satellite Application Facility (LSA SAF) products related to earth's surface radiation, temperature and humidity budgets, albedo and land cover along with static topography parameters and weather stations measurements are used in the analysis. A series of experiments showed that the Random Forest regression with 20 se-lected satellite and topography predictors was the optimum selection for the estimation of NSAT. The Mean Absolute Error (MAE) of the NSAT estimation model is 0.96 °C while the Mean Biased Error (MBE) is -0.01 °C and the R2 is 0.976. Limited seasonality is present in the efficiency of the model, while an increase of errors was noted during the first morning and afternoon hours. The topography influence in the model efficiency is rather limited. Cloud-free conditions are associ-ated to only marginally smaller errors, supporting the applicability of the model under both cloud-free and cloudy conditions.