Inferring Surface NO 2 Over Western Europe: A Machine Learning Approach With Uncertainty Quantification
Journal of Geophysical Research: Atmospheres · 28.10.2024 · 129 (20)
DOI: 10.1029/2023jd040676 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Geophysical Research: Atmospheres, online erschienen am 15.10.2024. Verfasst von Wenfu Sun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Belgian Federal Science Policy Office.
Abstract (Originalsprache)
Nitrogen oxides (NO x = NO + NO 2 ) are of great concern due to their impact on human health and the environment. In recent years, machine learning (ML) techniques have been widely used for surface NO 2 estimation with rapid developments in computational power and big data. However, the uncertainties inherent to such retrievals are rarely studied. In this study, a novel ML framework has been developed, enhanced with uncertainty quantification techniques, to estimate surface NO 2 and provide corresponding data‐induced uncertainty. We apply the Boosting Ensemble Conformal Quantile Estimator (BEnCQE) model to infer surface NO 2 concentrations over Western Europe at the daily scale and 1 km spatial resolution from May 2018 to December 2021. High NO 2 mainly appears in urban areas, industrial areas, and roads. The space‐based cross‐validation shows that our model achieves accurate point estimates ( r = 0.8, R 2 = 0.64, root mean square error = 8.08 μg/m 3 ) and reliable prediction intervals (coverage probability, PI‐50%: 51.0%, PI‐90%: 90.5%). Also, the model result agrees with the Copernicus Atmosphere Monitoring Service (CAMS) model. The quantile regression in our model enables us to understand the importance of predictors for different NO 2 level estimations. Additionally, the uncertainty information reveals the extra potential exceedance of the World Health Organization (WHO) 2021 limit in some locations, which is undetectable by only point estimates. Meanwhile, the uncertainty quantification allows assessment of the model's robustness outside existing in‐situ station measurements. It reveals challenges of NO 2 estimation over urban and mountainous areas where NO 2 is highly variable and heterogeneously distributed.
Förderung
- Belgian Federal Science Policy Office
Zitieren
APA
Sun, W., Tack, F., Clarisse, L., Schneider, R., Stavrakou, T., & Roozendael, M. V. (2024). Inferring Surface NO 2 Over Western Europe: A Machine Learning Approach With Uncertainty Quantification. Journal of Geophysical Research: Atmospheres, 129(20). https://doi.org/10.1029/2023jd040676
Vancouver
Sun W, Tack F, Clarisse L, Schneider R, Stavrakou T, Roozendael MV. Inferring Surface NO 2 Over Western Europe: A Machine Learning Approach With Uncertainty Quantification. Journal of Geophysical Research: Atmospheres. 2024;129(20). doi:10.1029/2023jd040676
BibTeX
@article{Sun2024,
author = {Sun, Wenfu and Tack, Frederik and Clarisse, Lieven and Schneider, Rochelle and Stavrakou, Trissevgeni and Roozendael, Michel Van},
title = {Inferring Surface NO 2 Over Western Europe: A Machine Learning Approach With Uncertainty Quantification},
journal = {Journal of Geophysical Research: Atmospheres},
year = {2024},
volume = {129},
number = {20},
doi = {10.1029/2023jd040676}
}
EUVIMED