Simulation model of Reactive Nitrogen Species in an Urban Atmosphere using a Deep Neural Network: RNDv1.0

Gil, Junsu; Lee, Meehye; Kim, Jeonghwan; Lee, Gangwoong; Ahn, Joonyoung; Kim, Cheol-Hee

doi:https://doi.org/10.5194/gmd-16-5251-2023

Articles | Volume 16, issue 17

https://doi.org/10.5194/gmd-16-5251-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Benchmark datasets and machine learning algorithms for Earth...

https://doi.org/10.5194/gmd-16-5251-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 16, issue 17

Model description paper

|

13 Sep 2023

Model description paper |

| 13 Sep 2023

Simulation model of Reactive Nitrogen Species in an Urban Atmosphere using a Deep Neural Network: RNDv1.0

Junsu Gil, Meehye Lee, Jeonghwan Kim, Gangwoong Lee, Joonyoung Ahn, and Cheol-Hee Kim

Supplement

https://doi.org/10.5194/gmd-16-5251-2023-supplement

Data sets

Sample data for RNDv1.0 Junsu Gil https://doi.org/10.5281/zenodo.5540180

Model code and software

RNDv1.0 Junsu Gil https://doi.org/10.5281/zenodo.5540180

Short summary

In this study, the framework for calculating reactive nitrogen species using a deep neural network (RND) was developed. It works through simple Python codes and provides high-accuracy reactive nitrogen oxide data. In the first version (RNDv1.0), the model calculates the nitrous acid (HONO) in urban areas, which has an important role in producing O₃ and fine aerosol.