KIT | KIT-Bibliothek | Impressum | Datenschutz

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

Stirnberg, Roland; Cermak, Jan; Fuchs, Julia; Andersen, Hendrik

The quantification of factors leading to harmfully high levels of particulate matter (PM) remains challenging. This study presents a novel approach using a statistical model that is trained to predict hourly concentrations of particles smaller than 10 μm (PM10) by combining satellite‐borne Aerosol Optical Depth (AOD) with meteorological and land‐use parameters. The model is shown to accurately predict PM10 (overall R2=0.77, RMSE=7.44 μg/m3) for measurement sites in Germany. The capability of satellite observations to map and monitor surface air pollution is assessed by investigating the relationship between AOD and PM10 in the same modelling setup. Sensitivity analyses show that important drivers of modelled PM10 include multi‐day mean wind flow, boundary layer height (BLH), day of year (DOY) and temperature. Different mechanisms associated with elevated PM10 concentrations are identified in winter and summer. In winter, mean predictions of PM10 concentrations >35 μg/m3 occur when BLH is below ~500m. Paired with multi‐day easterly wind flow, mean model predictions surpass 40 μg/m3 of PM10. In summer, PM10 concentrations seemingly are less driven by meteorology, but by emission or chemical particle formation processes, which are not included in the model. ... mehr

Open Access Logo

Verlagsausgabe §
DOI: 10.5445/IR/1000105923
Veröffentlicht am 18.02.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Institut für Meteorologie und Klimaforschung - Atmosphärische Spurenstoffe und Fernerkundung (IMK-ASF)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 02.2020
Sprache Englisch
Identifikator ISSN: 2169-897X, 2169-8996
KITopen-ID: 1000105923
Erschienen in Journal of geophysical research / D
Band 125
Heft 4
Seiten Art.e2019JD031380
Vorab online veröffentlicht am 06.02.2020
Schlagwörter aerosol optical depth; MAIAC; PM10; air quality; drivers of air pollution; machine learning
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page