Abstract
Nitrogen dioxide (NO2) is an important air pollutant with negative health effects and a precursor of ozone and particulate matter responsible for photo-chemical smog and wintertime air pollution. To evaluate human exposure to NO2 for public health assessment, maps of near-surface NO2 concentrations at a high resolution of 100 m are desirable. In this study, we report hourly maps of gridded near-surface NO2 concentrations that are produced using an extreme gradient-boosted tree ensemble for an Alpine domain (Switzerland and northern Italy) spanning two years, from June 2018 to May 2020. To estimate the NO2 distribution at ground level, we used satellite observations of NO2 vertical column density, land use data, meteorological fields and topographical information to train models with in situ NO2 ground measurements. The best model with this approach captured up to 59% of hourly NO2 variation for 40 test stations in the domain with a mean absolute error of 7.69μg/m3, performing especially well for urban regions with dense sampling. We present the first hourly maps of NO2 concentrations that reveal previously unresolved spatio-temporal variations. Local interpretations of the machine learning model demonstrate that TROPOMI NO2 satellite observations make a strong contribution to the information content of the near-surface NO2 maps besides their relatively coarse resolution (3.5 × 5.5 km2) and the fact that they are only available once a day under cloud-free conditions. The COVID-19 pandemic lockdown presents a case study that offers new insights into the importance of satellite data that can partially re-mediate statistical models' unsusceptibility to unusual events (like changes due to political intervention) with regard to model training.
Highlights
Nitrogen oxides (NOx = NO + NO2) have a range of impacts on air quality either directly or as precursors of ozone (O3) and particulate matter (PM) (Faustini et al, 2014; Beelen et al, 2014)
Such a sampling bias is unavoidable due to the design of air quality monitoring networks, which primarily target highly polluted and densely populated areas where higher sampling is necessary owing to the high spatial variability in NO2 concentrations
By combining multiple covariates in various categories, we demonstrated a machine learning approach based on the XGboost method to generate near-surface NO2 concentration maps spatially at 100 m and temporally at hourly resolution for a domain covering northern Italy and Switzerland
Summary
The European Union (EU) and the World Health Organization (WHO) set the limits of ambient concentration of NO2 at an annual mean of 40μg/m3 This limit is frequently exceeded in many European countries and worldwide resulting in health impacts and damage to ecosystems (Brunekreef and Holgate, 2002; Bouwman et al, 2002; EEA, 2020a) the annual means of NO2 in European countries are decreasing (EEA, 2020a), studies have reported that there is a lack of evidence for a safe annual exposure threshold regarding the association between air pollution and mortality even at cities with lower annual NO2 concentrations (Acha kulwisut et al, 2019; Khomenko et al, 2021). The temporal resolution of these produced maps ranged from daily to yearly depending on their spatial coverage. These previous studies have shown the feasibility of bridging the spatial and temporal gaps between in situ measurements of near-surface NO2 concentration (temporally dense, spatially sparse) and satellite observations from space (temporally sparse, spatially dense). No previous studies have reported hourly maps of near-surface NO2 concentrations at 100 m spatial resolution at regional scale
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
