Dataset for Paper "Satellite-derived estimates of surface ozone by LESO: Extended application and performance evaluation"

The surface ozone concentrations were estimated based on the satellite measurements and the meteorological data using the LEarning Surface Ozone (LESO) framework. The LESO estimation framework comprises a Deep Forest (DF21) machine-learning algorithm.

The inputs are the OMPS Nadir-Mapper total ozone columns and the ERA5 reanalysis data (incl. temperature (t), O3 mixing ratio (o3), relative humidity (r), cloud cover, U-/V- wind components (u/v), cloud cover (cc), and rain water content (crwc) at 200 hPa, 500 hPa, 700 hPa, 900 hPa, and 1000 hPa, respectively).