Using machine-learning to construct TOMCAT model and occultation measurement-based stratospheric methane (TCOM-CH4) and nitrous oxide (TCOM-N2O) profile data sets

Monitoring the atmospheric concentrations of greenhouse gases (GHGs) is crucial to improve our understanding of their climate impact. However, there are no long-term profile data sets of important GHGs that can be used to gain a better insight into the processes controlling their variations in the atmosphere. In this study, we apply corrections to chemical transport model (CTM) output based on profile measurements from two solar occultation instruments: the HALogen Occultation Experiment (HALOE) and the Atmospheric Chemistry Experiment – Fourier Transform Spectrometer (ACE-FTS). The goal is to construct long-term (1991–2021), gap-free stratospheric profile data sets, hereafter referred to as TCOM, for two important GHGs.

To estimate the corrections that need to be applied to the CTM profiles, we use the extreme gradient boosting (XGBoost) regression model. For methane (TCOM-CH4), we utilize both HALOE and ACE satellite profile measurements from 1992 to 2018 to train the XGBoost model, while profiles from 2019 to 2021 serve as an independent evaluation data set. As there are no nitrous oxide (N2O) profile measurements for earlier years, we derive XGBoost-derived correction terms to construct TCOM-N2O profiles using only ACE-FTS profiles from the 2004–2018 time period, with profiles from 2019–2021 used for the independent evaluation.

Overall, both TCOM-CH4 and TCOM-N2O profiles exhibit excellent agreement with the available satellite-measurement-based data sets. We find that compared to evaluation profiles, biases in TCOM-CH4 and TCOM-N2O are generally less than 10 % and 50 %, respectively, throughout the stratosphere. The daily zonal mean profile data sets, covering altitude (15–60 km) and pressure (300–0.1 hPa) levels, are publicly available via the following links: https://doi.org/10.5281/zenodo.7293740 for TCOM-CH4 (Dhomse, 2022a) and https://doi.org/10.5281/zenodo.7386001 for TCOM-N2O (Dhomse, 2022b).