Estimation of fine particulate matter in an arid area from visibility based on machine learning

BACKGROUND: The absence of air pollution monitoring networks makes it difficult to assess historical fine particulate matter (PM(2.5)) exposures for countries in the areas, such as Kuwait, which are severe impacted by desert dust and anthropogenic pollution. OBJECTIVE: We constructed an ensemble machine learning model to predict daily PM(2.5) concentrations for regions lack of PM(2.5) observations. METHODS: The model was constructed based on daily PM(2.5), visibility, and other meteorological data collected at two sites in Kuwait. Then, our model was applied to predict the daily level of PM(2.5) concentrations for eight airports located in Kuwait and Iraq from 2013–2020. RESULTS: As compared to traditional statistic models, the proposed machine learning methods improved the accuracy in using visibility to predict daily PM(2.5) concentrations with a cross-validation R(2) of 0.68. The predicted level of daily PM(2.5) concentrations were consistent with previous measurements. The predicted average yearly PM(2.5) concentration for the eight stations is 50.65 μg/m(3). For all stations, the monthly average PM(2.5) concentrations reached their maximum in July and their minimum in November. SIGNIFICANCE: These findings make it possible to retrospectively estimate daily PM(2.5) exposures using the large-scale databases of historical visibility in regions with few particulate matter monitoring stations.