ML-TOMCAT: machine-learning-based satellite-corrected global stratospheric ozone profile data set from a chemical transport model

Dhomse, Sandip S.; Arosio, Carlo; Feng, Wuhu; Rozanov, Alexei; Weber, Mark; Chipperfield, Martyn P.

doi:https://doi.org/10.5194/essd-13-5711-2021

Articles | Volume 13, issue 12

https://doi.org/10.5194/essd-13-5711-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-13-5711-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 12

Data description paper

|

10 Dec 2021

Data description paper |

| 10 Dec 2021

ML-TOMCAT: machine-learning-based satellite-corrected global stratospheric ozone profile data set from a chemical transport model

Sandip S. Dhomse, Carlo Arosio, Wuhu Feng, Alexei Rozanov, Mark Weber, and Martyn P. Chipperfield

Supplement

https://doi.org/10.5194/essd-13-5711-2021-supplement

Data sets

ML-TOMCAT V1.0: Machine-Learning-Based Satellite-Corrected Global Stratospheric Ozone Profile Dataset Dhomse S. Sandip, Chipperfield M. P., Wuhu Feng, Carlo Arosio, Mark Weber, and Alexei Rozanov https://doi.org/10.5281/zenodo.5651194

BSVerticalOzone database (v1.0) Birgit Hassler, Stefanie Kremser, Greg Bodeker, Jared Lewis, Kage Nesbit, Sean Davis, Martyn Chipperfield,Sandip Dhomse, and Martin Dameris https://doi.org/10.5281/zenodo.1217184

Download

Article (3414 KB)
Full-text XML

Short summary

High-quality long-term ozone profile data sets are key to estimating short- and long-term ozone variability. Almost all the satellite (and chemical model) data sets show some kind of bias with respect to each other. This is because of differences in measurement methodologies as well as simplified processes in the models. We use satellite data sets and chemical model output to generate 42 years of ozone profile data sets using a random-forest machine-learning algorithm that is named ML-TOMCAT.