A Machine Learning Method for Estimating Atmospheric Trace Gas Concentration Baselines: Training Data

Training data for estimating atmospheric trace gas concentration baselines. InTEM flags were generated as described in Manning et al. (2021). Meteorological data were extracted from the ECWMF ERA5 global reanalysis, presented in Hersbach et al. (2020),via the ARCO-ERA5 dataset. Variables were extracted around nine AGAGE atmospheric monitoring stations to match data from Prinn et al. (2025). Manning et al. (2021). Evidence of a recent decline in UK emissions of hydrofluorocarbons determined by the InTEM inverse model and atmospheric measurements. Atmospheric Chemistry and Physics, 21, 12739–12755. https://doi.org/10.5194/acp-21-12739-2021 Herbach et al. (2020). The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146, 1999-2049. https://doi.org/10.1002/QJ.3803 Prinn et al. (2025). The dataset of in-situ measurements of chemically and radiatively important atmospheric gases from the Advanced Global Atmospheric Gas Experiment (AGAGE) and affiliated stations (Version 20250123), [Data set], NASA Langley Research Center (LaRC) Data Host Facility (DHF). https://doi.org/10.60718/0FXA-QF43