A bias-corrected GEMS geostationary satellite product for nitrogen dioxide using machine learning to enforce consistency with the TROPOMI satellite instrument

Oak, Yujin J.; Jacob, Daniel J.; Balasus, Nicholas; Yang, Laura H.; Chong, Heesung; Park, Junsung; Lee, Hanlim; Lee, Gitaek T.; Ha, Eunjo S.; Park, Rokjin J.; Kwon, Hyeong-Ahn; Kim, Jhoon

doi:https://doi.org/10.5194/amt-17-5147-2024

Articles | Volume 17, issue 17

https://doi.org/10.5194/amt-17-5147-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

GEMS: first year in operation (AMT/ACP inter-journal SI)

https://doi.org/10.5194/amt-17-5147-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 17, issue 17

Research article

|

05 Sep 2024

Research article |

| 05 Sep 2024

A bias-corrected GEMS geostationary satellite product for nitrogen dioxide using machine learning to enforce consistency with the TROPOMI satellite instrument

Yujin J. Oak, Daniel J. Jacob, Nicholas Balasus, Laura H. Yang, Heesung Chong, Junsung Park, Hanlim Lee, Gitaek T. Lee, Eunjo S. Ha, Rokjin J. Park, Hyeong-Ahn Kwon, and Jhoon Kim

Data sets

A bias-corrected GEMS geostationary satellite product for nitrogen dioxide using machine learning to enforce consistency with the TROPOMI satellite instrument Yujin Oak https://doi.org/10.7910/DVN/ZQQJRO

Short summary

We present an improved NO₂ product from GEMS by calibrating it to TROPOMI using machine learning and by reprocessing both satellite products to adopt common NO₂ profiles. Our corrected GEMS product combines the high data density of GEMS with the accuracy of TROPOMI, supporting the combined use for analyses of East Asia air quality including emissions and chemistry. This method can be extended to other species and geostationary satellites including TEMPO and Sentinel-4.