Identifying Surface Sulphur Dioxide (SO) Monitoring Gaps in Saint John, Canada with Land Use Regression and Hot Spot Mapping

Authors

Tsz Kin Siu, Department of Earth and Environmental Sciences, Dalhousie University, 6287 Alumni Cres, Halifax, Nova Scotia B3H 4R2, Canada.
Christopher S. Greene, Department of Earth and Environmental Sciences, Dalhousie University, 6287 Alumni Cres, Halifax, Nova Scotia B3H 4R2, Canada.
Kelvin C. Fong, Department of Earth and Environmental Sciences, Dalhousie University, 6287 Alumni Cres, Halifax, Nova Scotia B3H 4R2, Canada.

Document Type

Journal Article

Publication Date

7-15-2025

Journal

Atmospheric environment (Oxford, England : 1994)

Volume

353

DOI

10.1016/j.atmosenv.2025.121238

Keywords

Air Pollution; Land Use Regression; Machine Learning; Satellite Remote Sensing; Spatial Analysis; Sulphur Dioxide

Abstract

Saint John experiences ambient sulphur dioxide (SO) pollution due to a high density of industrial activities. Despite recent reduction in SO emissions, over 90% of the provincial exceedances of air pollutants were related to SO or total reduced sulphur (TRS), and over 70% among which occurred in Saint John. Pinpointing intra-urban SO hot spots is important for revealing the neighborhoods exposed to high health risk. However, this is challenging due to limited spatial coverage of monitoring. To fill the monitoring gap, we developed two-stage gradient boosting models combining a classifier that discerned between SO-free and SO-polluted days and a regressor that estimated daily SO levels based on remote sensing data. With a 10-fold cross-validation, the classifier achieved 83% accuracy and the regressors attained R of 0.46 and 0.44 for daily mean and maximum SO respectively. Based on model outputs, we conducted spatial hot spot analysis and found high SO levels spread to northeast, northwest, and southeast Saint John, where SO monitoring was absent. Several existing monitoring sites in west Saint John coincided with the hot spots, where SO was not regularly measured. Besides the spatiotemporal lags of nearby monitored SO, wind-related variables such as wind speed and direction had high importance in predicting surface SO, which might suggest potential impacts to remote unmonitored communities from the transport of SO. In summary, our findings suggest that certain unmonitored areas in Saint John may experience high SO levels. Expansion of monitoring efforts would help inform where and when mitigation should be taken to minimize SO-related health impacts.

APA Citation

Siu, Tsz Kin; Greene, Christopher S.; and Fong, Kelvin C., "Identifying Surface Sulphur Dioxide (SO) Monitoring Gaps in Saint John, Canada with Land Use Regression and Hot Spot Mapping" (2025). GW Authored Works. Paper 7587.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/7587

Department

Environmental and Occupational Health