Improved global daily nitrogen dioxide concentrations from 2005 to 2023 derived using a deep learning approach

Mu, Jiangshan; Tao, Chenliang; Zhang, Yuqiang; Liu, Zhou; Zhang, Yingnan; Zhao, Na; Luo, Bin; Zhou, Qionghui; Zhang, Qingzhu; Zhang, Hongliang; Xue, Likun

doi:10.5194/essd-18-2999-2026

Articles | Volume 18, issue 5

https://doi.org/10.5194/essd-18-2999-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-18-2999-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 5

Data description article

|

05 May 2026

Data description article |

| 05 May 2026

Improved global daily nitrogen dioxide concentrations from 2005 to 2023 derived using a deep learning approach

Jiangshan Mu, Chenliang Tao, Yuqiang Zhang, Zhou Liu, Yingnan Zhang, Na Zhao, Bin Luo, Qionghui Zhou, Qingzhu Zhang, Hongliang Zhang, and Likun Xue

Supplement

https://doi.org/10.5194/essd-18-2999-2026-supplement

Data sets

GlobalNO2_AIT: 0.1° Annual Resolution Global Ground-level NO2 Dataset Jiangshan Mu and Chenliang Tao https://doi.org/10.5281/zenodo.13842191

Download

Article (3620 KB)
Full-text XML

Short summary

Nitrogen dioxide is a common air pollutant that varies strongly across space and time, yet consistent global information has been limited. We developed a new global dataset that describes daily nitrogen dioxide levels from 2005 to 2023 by combining satellite observations, weather data, and ground measurements using artificial intelligence. The dataset reveals long-term changes and regional patterns and provides a reliable resource for future air quality research.