Summary: | The pursuit of higher-resolution and more reliable spatial distribution simulation results for air pollutants is important to human health and environmental safety. However, the lack of high-resolution remote sensing retrieval parameters for gaseous pollutants (sulfur dioxide and ozone) limits the simulation effect to a 1 km resolution. To address this issue, we sequentially generated and optimized the spatial distributions of near-surface PM<sub>2.5</sub>, SO<sub>2</sub>, and ozone at a 1 km resolution in China through two approaches. First, we employed spatial sampling, random ID, and parameter convolution methods to jointly optimize a tree-based machine-learning gradient-boosting framework, LightGBM, and improve the performance of spatial air pollutant simulations. Second, we simulated PM<sub>2.5</sub>, used the simulated PM<sub>2.5</sub> result to simulate SO<sub>2</sub>, and then used the simulated SO<sub>2</sub> to simulate ozone. We improved the stability of 1 km-resolution SO<sub>2</sub> and ozone products through the proposed sequence of multiple-pollutant simulations. The cross-validation (CV) of the random sample yielded an R<sup>2</sup> of 0.90 and an RMSE of 9.62 µg∙m<sup>−3</sup> for PM<sub>2.5</sub>, an R<sup>2</sup> of 0.92 and an RMSE of 3.9 µg∙m<sup>−3</sup> for SO<sub>2</sub>, and an R<sup>2</sup> of 0.94 and an RMSE of 5.9 µg∙m<sup>−3</sup> for ozone, which are values better than those in previous related studies. In addition, we tested the reliability of PM<sub>2.5</sub>, SO<sub>2</sub>, and ozone products in China through spatial distribution reliability analysis and parameter importance reliability analysis. The PM<sub>2.5</sub>, SO<sub>2</sub>, and ozone simulation models and multiple-air-pollutant (MuAP) products generated by the two optimization methods proposed in this study are of great value for long-term, large-scale, and regional-scale air pollution monitoring and predictions, as well as population health assessments.
|