Machine learning with spatial interpolation techniques for constructing 2-dimensional ozone concentrations in Southern California during the COVID-19 shutdown.

In this study, we combine machine learning and geospatial interpolations to create a two-dimensional high-resolution ozone concentration fields over the South Coast Air Basin for the entire year of 2020. Three spatial interpolation methods (bicubic, IDW, and ordinary kriging) were employed. The predicted ozone concentration fields were constructed using 15 building sites, and random forest regression was employed to test predictability of 2020 data based on input data from past years. Spatially interpolated ozone concentrations were evaluated at twelve sites that were independent of the actual spatial interpolations to find the most suitable method for SoCAB. Ordinary kriging interpolation had the best performance overall for 2020: concentrations were overestimated for Anaheim, Compton, LA North Main Street, LAX, Rubidoux, and San Gabriel sites and underestimated for Banning, Glendora, Lake Elsinore, and Mira Loma sites. The model performance improved from the West to the East, exhibiting better predictions for inland sites. The model is best at interpolating ozone concentrations inside the sampling region (bounded by the building sites), with R2 ranging from 0.56 to 0.85 for those sites, as prediction deficiencies occurred at the periphery of the sampling region, with the lowest R2 of 0.39 for Winchester. All the interpolation methods poorly predicted and underestimated ozone concentrations in Crestline during summer (up to 19 ppb). Poor performance for Crestline indicates that the site has a distribution air pollution levels independent from all other sites. Therefore, historical data from coastal and inland sites should not be used to predict ozone in Crestline using data-driven spatial interpolation approaches. The study demonstrates the utility of machine learning and geospatial techniques for evaluating air pollution levels during anomalous periods.

Societal shifts due to COVID-19 reveal large-scale complexities and feedbacks between atmospheric chemistry and climate change.

The COVID-19 global pandemic and associated government lockdowns dramatically altered human activity, providing a window into how changes in individual behavior, enacted en masse, impact atmospheric composition. The resulting reductions in anthropogenic activity represent an unprecedented event that yields a glimpse into a future where emissions to the atmosphere are reduced. Furthermore, the abrupt reduction in emissions during the lockdown periods led to clearly observable changes in atmospheric composition, which provide direct insight into feedbacks between the Earth system and human activity. While air pollutants and greenhouse gases share many common anthropogenic sources, there is a sharp difference in the response of their atmospheric concentrations to COVID-19 emissions changes, due in large part to their different lifetimes. Here, we discuss several key takeaways from modeling and observational studies. First, despite dramatic declines in mobility and associated vehicular emissions, the atmospheric growth rates of greenhouse gases were not slowed, in part due to decreased ocean uptake of CO2 and a likely increase in CH4 lifetime from reduced NO x emissions. Second, the response of O3 to decreased NO x emissions showed significant spatial and temporal variability, due to differing chemical regimes around the world. Finally, the overall response of atmospheric composition to emissions changes is heavily modulated by factors including carbon-cycle feedbacks to CH4 and CO2, background pollutant levels, the timing and location of emissions changes, and climate feedbacks on air quality, such as wildfires and the ozone climate penalty.