Using Machine Learning to Make Computationally Inexpensive Projections of 21st Century Stratospheric Column Ozone Changes in the Tropics

Stratospheric ozone projections in the tropics, modelled using the UKESM1 Earth system model, are explored under different Shared Socioeconomic Pathways (SSPs). Consistent with other studies, it is found that stratospheric column ozone does not return to 1980s values by the end of the 21st century under any SSP scenario as increased ozone mixing ratios in the upper stratosphere are offset by continued ozone decreases in the lower stratosphere. Stratospheric column ozone is projected to be largest under SSP scenarios with the smallest change in radiative forcing, and smallest for SSP scenarios with larger radiative forcing, consistent with an increased Brewer-Dobson circulation at high greenhouse gas loadings. This study explores the use of machine learning (ML) techniques to make accurate, computationally inexpensive projections of tropical stratospheric column ozone. Four ML techniques are investigated: Ridge regression, Lasso regression, Random forests and extra trees. While under many future emissions scenarios all four techniques make reasonable projections, the non-linear methods (Random forests and extra trees) make remarkably accurate projections which fall within the ensemble spread of UKESM1 simulations for each SSP, with the exception of the final decades of the SSP5-8.5 scenario. However, this accuracy can only be achieved when the ML methods are trained on sufficient data, including both historical and future simulations. When trained only on historical data, the projections made using models based on ML techniques fail to accurately predict ozone changes. When sufficiently trained, models of tropical stratospheric column ozone have the potential to make accurate, computationally inexpensive projections, reducing the computational burden placed on fully coupled chemistry-climate and Earth system models and allowing for the exploration of stratospheric column ozone recovery under a much broader range of future scenarios.