Full-coverage 1 km daily ambient PM 2.5 and O 3 concentrations of China in 2005–2017 based on a multi-variable random forest model

[摘要] The health risks of fine particulate matter (PM 2.5 ) and ambient ozone(O 3 ) have been widely recognized in recent years. An accurate estimateof PM 2.5 and O 3 exposures is important for supporting health riskanalysis and environmental policy-making. The aim of our study was toconstruct random forest models with high-performance and estimate dailyaverage PM 2.5 concentration and O 3 daily maximum of 8 h averageconcentration (O 3 -8 hmax) of China in 2005–2017 at a spatial resolutionof 1 km  ×  1 km. The model variables included meteorological variables,satellite data, chemical transport model output, geographic variables andsocioeconomic variables. Random forest model based on 10-fold cross-validation was established, and spatial and temporal validations wereperformed to evaluate the model performance. According to our sample-baseddivision method, the daily, monthly and yearly estimations of PM 2.5 from test datasets gave average model-fitting R 2 values of 0.85, 0.88and 0.90, respectively; these R 2 values were 0.77, 0.77 and 0.69 forO 3 -8 hmax, respectively. The meteorological variables and their laggedvalues can significantly affect both PM 2.5 and O 3 -8 hmaxestimations. During 2005–2017, PM 2.5 concentration exhibited an overall downwardtrend, while ambient O 3 concentration experienced an upward trend. Whilst the spatialpatterns of PM 2.5 and O 3 -8 hmax barely changed between 2005 and2017, the temporal trend had spatial characteristics. The dataset isaccessible to the public at https://doi.org/10.5281/zenodo.4009308 (Ma et al., 2021a), and the shared dataset of Chinese Environmental Public Health Tracking (CEPHT, 2022) is available at https://cepht.niehs.cn:8282/developSDS3.html .

[学科分类] 眼科学