Gongbo Chen1, Yichao Wang2, Shanshan Li1, Wei Cao3, Hongyan Ren3, Luke D Knibbs4, Michael J Abramson1, Yuming Guo5. 1. Department of Epidemiology and Preventive Medicine, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia. 2. Murdoch Children's Research Institute, Parkville, Victoria, Australia, Department of Paediatrics, University of Melbourne, Parkville, Victoria, Australia. 3. Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China. 4. Department of Epidemiology and Biostatistics, School of Public Health, The University of Queensland, Brisbane, Australia. 5. Department of Epidemiology and Preventive Medicine, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia. Electronic address: yuming.guo@monash.edu.
Abstract
BACKGROUND: Few studies have estimated historical exposures to PM10 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 PM10 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 PM10 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 PM10 across China during 2005-2016 at 0.1⁰ (≈10 km). RESULTS: Cross-validation showed our random forests model explained 78% of daily variability of PM10 [root mean squared prediction error (RMSE) = 31.5 μg/m3]. When aggregated into monthly and annual averages, the models captured 82% (RMSE = 19.3 μg/m3) and 81% (RMSE = 14.4 μg/m3) 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 PM10 pollution exceeding Grade Ⅱ National Ambient Air Quality Standard (>70 μg/m3) in China during the past 12 years. The highest levels of estimated PM10 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 PM10 level in China peaked in 2006 and 2007, and declined since 2008. CONCLUSIONS: This is the first study to estimate historical PM10 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 PM10 in China.
BACKGROUND: Few studies have estimated historical exposures to PM10 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 PM10 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 PM10 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 PM10 across China during 2005-2016 at 0.1⁰ (≈10 km). RESULTS: Cross-validation showed our random forests model explained 78% of daily variability of PM10 [root mean squared prediction error (RMSE) = 31.5 μg/m3]. When aggregated into monthly and annual averages, the models captured 82% (RMSE = 19.3 μg/m3) and 81% (RMSE = 14.4 μg/m3) 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 PM10 pollution exceeding Grade Ⅱ National Ambient Air Quality Standard (>70 μg/m3) in China during the past 12 years. The highest levels of estimated PM10 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 PM10 level in China peaked in 2006 and 2007, and declined since 2008. CONCLUSIONS: This is the first study to estimate historical PM10 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 PM10 in China.
Authors: Mona Elbarbary; Trenton Honda; Geoffrey Morgan; Yuming Guo; Yanfei Guo; Paul Kowal; Joel Negin Journal: Int J Environ Res Public Health Date: 2020-05-05 Impact factor: 3.390
Authors: Wenxuan Xu; Yongzhong Tian; Yongxue Liu; Bingxue Zhao; Yongchao Liu; Xueqian Zhang Journal: Int J Environ Res Public Health Date: 2019-08-07 Impact factor: 3.390
Authors: Luke Conibear; Carly L Reddington; Ben J Silver; Ying Chen; Christoph Knote; Stephen R Arnold; Dominick V Spracklen Journal: Geohealth Date: 2021-05-01