GlobVision designed and developed a solution for the estimation of near-ground air temperature using computational intelligence methods and the integration of remote sensing data and in-situ measurements.
Machine learning methodologies were exploited to estimate the relationship between in-situ measurements of near surface temperature at meteorological stations and remotely sensed data. Results were obtained by (a) identifying the best combination of input remote sensing parameters to produce the optimum performance in estimating temperature and (b) using multiple spatial and temporal cases involving grouped and single meteorological stations.
Near-ground air temperature is one of the most critical parameters of meteorological models for advanced climate modeling. The approach of using remote sensing data to complement ground information and compensate for (or fill-in) missing data offers significant advantages to meteorologists.
