Enhanced natural releases of mercury in response to the reduction in anthropogenic emissions during the COVID-19 lockdown by explainable machine learning

Abstract

Abstract. The wide spread of the coronavirus (COVID-19) has significantly impacted the global human activities. Compared to numerous studies on conventional air pollutants, atmospheric mercury that has matched sources from both anthropogenic and natural emissions is rarely investigated. At a regional site in eastern China, an intensive measurement was performed, showing obvious decreases in gaseous elemental mercury (GEM) during the COVID-19 lockdown, while it was not as significant as most of the other measured air pollutants. Before the lockdown, when anthropogenic emissions dominated, GEM showed no correlation with temperature and negative correlations with wind speed and the height of the boundary layer. In contrast, GEM showed significant correlation with temperature, while the relationship between GEM and the wind speed/boundary layer disappeared during the lockdown, suggesting the enhanced natural emissions of mercury. By applying a machine learning model and the SHAP (SHapley Additive exPlanations) approach, it was found that the mercury pollution episodes before the lockdown were driven by anthropogenic sources, while they were mainly driven by natural sources during and after the lockdown. Source apportionment results showed that the absolute contribution of natural surface emissions to GEM unexpectedly increased (44 %) during the lockdown. Throughout the whole study period, a significant negative correlation was observed between the absolute contribution of natural and anthropogenic sources to GEM. We conclude that the natural release of mercury could be stimulated to compensate for the significantly reduced anthropogenic GEM via the surface–air exchange in the balance of mercury.

Identifying Driving Factors of Atmospheric N2O5 with Machine Learning

“…Mean absolute SHAP values were used to identify the key factors in the formation and loss of N 2 O 5 using data in both Pre-WO and WO. A larger SHAP value (unit: pptv) indicates a higher contribution of this feature to the variation in N 2 O 5 levels . O 3 had the highest impact on N 2 O 5 concentrations, exhibiting a change of 126 ± 108 pptv in N 2 O 5 levels (Figure b).…”

Global Distribution of Mercury in Foliage Predicted by Machine Learning

“…Machine learning methods have recently been extensively applied to many studies of environmental pollution, such as distribution of soil antibiotic resistance genes, agricultural ammonia emissions, soil Hg concentrations, and atmospheric Hg emissions . The predicted performance of environmental indicators can be substantially improved with the use of abundant covariates and advanced algorithms.…”

“…Machine learning methods have recently been extensively applied to many studies of environmental pollution, 19 such as distribution of soil antibiotic resistance genes, 20 agricultural ammonia emissions, 21 soil Hg concentrations, 22 and atmospheric Hg emissions. 23 The predicted performance of environmental indicators can be substantially improved with the use of abundant covariates and advanced algorithms. This enables us to construct a spatial map of foliar Hg concentrations at a global scale by integrating a comprehensive observation database of foliar Hg concentrations with machine learning algorithms.…”