Quantitative reconstruction of long-term spatiotemporal patterns of high-resolution ground-level NO2 concentrations in mainland China using fusion techniques and a machine learning framework
Environment International · 2025
DOI: 10.1016/j.envint.2025.109672 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environment International, 2025. Verfasst von Zhen Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Resources and Environment Engineering, Wuhan University of Technology, Wuhan 430070, China; State Key Laboratory of Information Engineering…. Hauptthemen laut MEDLINE: Machine Learning, Environmental Monitoring, Air Pollutants, Nitrogen Dioxide. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Nitrogen dioxide (NO2), as a critical trace gas, plays multiple roles in the atmosphere and poses potential threats to human health. However, existing satellite monitoring methods face challenges, including limited satellite mission durations, poor data quality, and low spatial resolution, which hinder the ability to provide long-term, high-precision NO2 information. To address these issues, this study uses the TROPOMI tropospheric NO2 column concentration product as a baseline and employs partition and cumulative distribution function (CDF) techniques to generate a satellite fusion dataset with both long time spans and high consistency. Based on this dataset, a high-performance, high-spatial-resolution long-term surface NO2 estimation model was developed using machine learning algorithms combined with multi-source geographic data. The model successfully estimates daily average near-surface NO2 concentrations (1 km2 resolution) for mainland China from 2014 to 2020. The results show that the proposed fusion method effectively integrates OMI and TROPOMI data, improves the spatial correlation between satellite products by 16.2 % (R = 0.74 → 0.86), significantly enhances the spatial coverage, and thus more accurately characterizes the spatial distribution characteristics of NO2. The surface-level NO2 estimates based on the LGBM model achieved an R2 of 0.85 in ten-fold cross-validation, with corresponding root mean square error (RMSE) and mean absolute error (MAE) of 7.51 µg/m3 and 5.22 µg/m3, respectively, demonstrating good extrapolation ability for temporal variations. The long-time series results accurately reflect the temporal and spatial evolution of NO2 in mainland China, while the high-precision estimates provide detailed pollution exposure information, revealing urban-scale pollution differences and seasonal variations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Resources and Environment Engineering, Wuhan University of Technology, Wuhan 430070, China; State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, 43…
- School of Resources and Environment Engineering, Wuhan University of Technology, Wuhan 430070, China. Electronic address: simondong@whut.edu.cn.
- School of Resources and Environment Engineering, Wuhan University of Technology, Wuhan 430070, China.
- Zhejiang Key Laboratory of Ecological and Environmental Big Data, Ecological and Environmental Monitoring Center of Zhejiang Province, Hangzhou 310012, China.
Zitieren
APA
Li, Z., Dong, H., He, S., & Huang, H. (2025). Quantitative reconstruction of long-term spatiotemporal patterns of high-resolution ground-level NO2 concentrations in mainland China using fusion techniques and a machine learning framework. Environment International. https://doi.org/10.1016/j.envint.2025.109672
Vancouver
Li Z, Dong H, He S, Huang H. Quantitative reconstruction of long-term spatiotemporal patterns of high-resolution ground-level NO2 concentrations in mainland China using fusion techniques and a machine learning framework. Environment International. 2025. doi:10.1016/j.envint.2025.109672
BibTeX
@article{Li2025,
author = {Li, Zhen and Dong, Heng and He, Sicong and Huang, Huan},
title = {Quantitative reconstruction of long-term spatiotemporal patterns of high-resolution ground-level NO2 concentrations in mainland China using fusion techniques and a machine learning framework},
journal = {Environment International},
year = {2025},
doi = {10.1016/j.envint.2025.109672}
}
EUVIMED