Spatiotemporal patterns of PM 10 concentrations over China during 2005-2016: A satellite-based estimation using the random forests approach.

Background: Few studies have estimated historical exposures to PM ₁₀ at a national scale in China using satellite-based aerosol optical depth (AOD). Also, long-term trends have not been investigated.
Objectives: In this study, daily concentrations of PM ₁₀ over China during the past 12 years were estimated with the most recent ground monitoring data, AOD, land use information, weather data and a machine learning approach.
Methods: Daily measurements of PM ₁₀ during 2014-2016 were collected from 1479 sites in China. Two types of Moderate Resolution Imaging Spectroradiometer (MODIS) AOD data, land use information, and weather data were downloaded and merged. A random forests model (non-parametric machine learning algorithms) and two traditional regression models were developed and their predictive abilities were compared. The best model was applied to estimate daily concentrations of PM ₁₀ across China during 2005-2016 at 0.1⁰ (≈10 km).
Results: Cross-validation showed our random forests model explained 78% of daily variability of PM ₁₀ [root mean squared prediction error (RMSE) = 31.5 μg/m ³ ]. When aggregated into monthly and annual averages, the models captured 82% (RMSE = 19.3 μg/m ³ ) and 81% (RMSE = 14.4 μg/m ³ ) of the variability. The random forests model showed much higher predictive ability and lower bias than the other two regression models. Based on the predictions of random forests model, around one-third of China experienced with PM ₁₀ pollution exceeding Grade Ⅱ National Ambient Air Quality Standard (>70 μg/m ³ ) in China during the past 12 years. The highest levels of estimated PM ₁₀ were present in the Taklamakan Desert of Xinjiang and Beijing-Tianjin metropolitan region, while the lowest were observed in Tibet, Yunnan and Hainan. Overall, the PM ₁₀ level in China peaked in 2006 and 2007, and declined since 2008.
Conclusions: This is the first study to estimate historical PM ₁₀ pollution using satellite-based AOD data in China with random forests model. The results can be applied to investigate the long-term health effects of PM ₁₀ in China.
(Copyright © 2018 Elsevier Ltd. All rights reserved.)