Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm.

Surface ozone (O[Formula: see text]) is primarily formed through complex photo-chemical reactions in the atmosphere, which are non-linearly dependent on precursors. Even though, there have been many recent studies exploring the potential of machine learning (ML) in modeling surface ozone, the inclusion of limited available ozone precursors information has received little attention. The ML algorithm with in-situ NO information and meteorology explains 87% (R[Formula: see text] = 0.87) of the ozone variability over Munich, a German metropolitan area, which is 15% higher than a ML algorithm that considers only meteorology. The ML algorithm trained for the urban measurement station in Munich can also explain the ozone variability of the other three stations in the same city, with R[Formula: see text] = 0.88, 0.91, 0.63. While the same model robustly explains the ozone variability of two other German cities' (Berlin and Hamburg) measurement stations, with R[Formula: see text] ranges from 0.72 to 0.84, giving confidence to use the ML algorithm trained for one location to other locations with sparse ozone measurements. The inclusion of satellite O[Formula: see text] precursors information has little effect on the ML model's performance.

Tropospheric NO2 and O3 Response to COVID-19 Lockdown Restrictions at the National and Urban Scales in Germany.

This study estimates the influence of anthropogenic emission reductions on nitrogen dioxide ( N O 2 ) and ozone ( O 3 ) concentration changes in Germany during the COVID-19 pandemic period using in-situ surface and Sentinel-5 Precursor TROPOspheric Monitoring Instrument (TROPOMI) satellite column measurements and GEOS-Chem model simulations. We show that reductions in anthropogenic emissions in eight German metropolitan areas reduced mean in-situ (& column) N O 2 concentrations by 23 % (& 16 % ) between March 21 and June 30, 2020 after accounting for meteorology, whereas the corresponding mean in-situ O 3 concentration increased by 4 % between March 21 and May 31, 2020, and decreased by 3 % in June 2020, compared to 2019. In the winter and spring, the degree of N O X saturation of ozone production is stronger than in the summer. This implies that future reductions in N O X emissions in these metropolitan areas are likely to increase ozone pollution during winter and spring if appropriate mitigation measures are not implemented. TROPOMI N O 2 concentrations decreased nationwide during the stricter lockdown period after accounting for meteorology with the exception of North-West Germany which can be attributed to enhanced N O X emissions from agricultural soils.