High resolution mapping of nitrogen dioxide and particulate matter in Great Britain (2003–2021) with multi-stage data reconstruction and ensemble machine learning methods

Abstract

In this contribution, we applied a multi-stage machine learning (ML) framework to map daily values of nitrogen dioxide (NO₂) and particulate matter (PM₁₀ and PM_2.5) at a 1 km² resolution over Great Britain for the period 2003–2021. The process combined ground monitoring observations, satellite-derived products, climate reanalyses and chemical transport model datasets, and traffic and land-use data. Each feature was harmonized to 1 km resolution and extracted at monitoring sites. Models used single and ensemble-based algorithms featuring random forests (RF), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), as well as lasso and ridge regression. The various stages focused on augmenting PM_2.5 using co-occurring PM₁₀ values, gap-filling aerosol optical depth and columnar NO₂ data obtained from satellite instruments, and finally the training of an ensemble model and the prediction of daily values across the whole geographical domain (2003–2021). Results show a good ensemble model performance, calculated through a ten-fold monitor-based cross-validation procedure, with an average R² of 0.690 (range 0.611–0.792) for NO₂, 0.704 (0.609–0.786) for PM₁₀, and 0.802 (0.746–0.888) for PM_2.5. Reconstructed pollution levels decreased markedly within the study period, with a stronger reduction in the latter eight years. The pollutants exhibited different spatial patterns, while NO₂ rose in close proximity to high-traffic areas, PM demonstrated variation at a larger scale. The resulting 1 km² spatially resolved daily datasets allow for linkage with health data across Great Britain over nearly two decades, thus contributing to extensive, extended, and detailed research on the long-and short-term health effects of air pollution.