Deep learning mapping of surface MDA8 ozone: The impact of predictor variables on ozone levels over the contiguous United States

The limited number of ozone monitoring stations imposes uncertainty in various applications, calling for ac-curate approaches to capturing ozone values in all regions, particularly those with no in-situ measurements. This study uses deep learning (DL) to accurately estimate daily maximum 8-hr average (MDA8) ozone and examines the spatial contribution of several factors on ozone levels over the contiguous U.S. (CONUS) in 2019. A com-parison between in-situ observations and DL-estimated MDA8 ozone values shows a correlation coefficient (R) of 0.95, an index of agreement (IOA) of 0.97, and a mean absolute bias (MAB) of 2.79 ppb, highlighting the promising performance of the deep convolutional neural network (Deep-CNN) at estimating surface MDA8 ozone. Spatial cross-validation also confirms the high spatial accuracy of the model, which obtains an R of 0.91, and IOA of 0.96 and an MAB of 3.46 ppb when it is trained and tested on separate stations. To interpret the black -box nature of our DL model, we use Shapley additive explanations (SHAP) to generate a spatial feature contribution map (SFCM), the results of which confirm an advanced ability of Deep-CNN to capture the in-teractions between most predictor variables and ozone. For instance, the model shows that solar radiation (SRad) SFCM, with higher values, enhances the formation of ozone, particularly in the south and southwestern CONUS. As SRad triggers ozone precursors to produce ozone via photochemical reactions, it increases ozone concen-trations. The model also shows that humidity, with its low values, increases ozone concentrations in the western mountainous regions. The negative correlation between humidity and ozone levels can be attributed to factors such as higher ozone decomposition resulting from increased levels of humidity and OH radicals. This study is the first to introduce the SFCM to investigate the spatial role of predictor variables on changes in estimated MDA8 ozone levels.

Automated summary

This study utilizes deep learning (DL) to accurately estimate the levels of surface MDA8 ozone in the contiguous U.S. (CONUS) in 2019. The DL model shows promising performance with a correlation coefficient of 0.95, an index of agreement of 0.97, and a mean absolute bias of 2.79 ppb when compared to in-situ observations. Spatial cross-validation confirms the high spatial accuracy of the model, with a correlation coefficient of 0.91, an index of agreement of 0.96, and a mean absolute bias of 3.46 ppb.