Spatiotemporal continuous estimates of PM2.5 concentrations in China, 2000-2016: A machine learning method with inputs from satellites, chemical transport model, and ground observations.

Ambient exposure to fine particulate matter (PM2.5) is known to harm public health in China. Satellite remote sensing measurements of aerosol optical depth (AOD) were statistically associated with in-situ observations after 2013 to predict PM2.5 concentrations nationwide, while the lack of surface monitoring data before 2013 have created difficulties in historical PM2.5 exposure estimates. Hindcast approaches using statistical models or chemical transport models (CTMs) were developed to overcome this limitation, while those approaches still suffer from incomplete daily coverage due to missing AOD data or limited accuracy due to uncertainties of CTMs. Here we developed a new machine learning (ML) model with high-dimensional expansion (HD-expansion) of numerous predictors (including AOD and other satellite covariates, meteorological variables and CTM simulations). Through comprehensive characterization of the nonlinear effects of, and interactions among different predictors, the HD-expansion parameterized the association between PM2.5 and AOD as a nonlinear function of space and time covariates (e.g., planetary boundary layer height and relative humidity). In this way, the PM2.5-AOD association can vary spatiotemporally. We trained the model with data from 2013 to 2016 and evaluated its performance using annually-iterated cross-validation, which iteratively held out the in-situ observations for a whole calendar year (as testing data) to examine the predictions from a model trained by the rest of the observations. Our estimates were found to be in good agreement with in-situ observations, with correlation coefficients (R2) of 0.61, 0.68, and 0.75 for daily, monthly and annual averages, respectively. To interpolate the missing predictions due to incomplete AOD data, we incorporated a generalized additive model into the ML model. The two-stage estimates of PM2.5 sacrificed the prediction accuracy on a daily timescale (R2 = 0.55), but achieved complete spatiotemporal coverage and improved the accuracy of monthly (R2 = 0.71) and annual (R2 = 0.77) averages. The model was then used to predict daily PM2.5 concentrations during 2000-2016 across China and estimate long-term trends in PM2.5 for the period. We found that population-weighted concentrations of PM2.5 significantly increased, by 2.10 (95% confidence interval (CI): 1.74, 2.46) μg/m3/year during 2000-2007, and rapidly decreased by 4.51 (3.12, 5.90) μg/m3/year during 2013-2016. In this study, we produced AOD-based estimates of historical PM2.5 with complete spatiotemporal coverage, which were evidenced as accurate, particularly in middle and long term. The products could support large-scale epidemiological studies and risk assessments of ambient PM2.5 in China and can be accessed via the website (http://www.meicmodel.org/dataset-phd.html).

[1]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[2]  Qingyang Xiao,et al.  MAIAC-based long-term spatiotemporal trends of PM2.5 in Beijing, China. , 2018, The Science of the total environment.

[3]  中华人民共和国国务院人口普查办公室,et al.  中国2010年人口普查分县资料 = Tabulation on the 2010 population census of the People's Republic of China by county , 2012 .

[4]  Kebin He,et al.  Estimating long-term PM2.5 concentrations in China using satellite-based aerosol optical depth and a chemical transport model , 2015 .

[5]  Alexis K.H. Lau,et al.  High-resolution satellite remote sensing of provincial PM2.5 trends in China from 2001 to 2015 , 2018 .

[6]  K. He,et al.  Air quality improvements and health benefits from China’s clean air action since 2013 , 2017 .

[7]  R. Martin,et al.  Fifteen-year global time series of satellite-derived fine particulate matter. , 2014, Environmental science & technology.

[8]  Bin Zou,et al.  Satellite Based Mapping of Ground PM2.5 Concentration Using Generalized Additive Modeling , 2016, Remote. Sens..

[9]  Michael Brauer,et al.  Addressing Global Mortality from Ambient PM2.5. , 2015, Environmental science & technology.

[10]  Kebin He,et al.  Policy: Cleaning China's air , 2012, Nature.

[11]  J. H. Belle,et al.  Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach. , 2017, Environmental science & technology.

[12]  Miaomiao Liu,et al.  Visibility-Based PM2.5 Concentrations in China: 1957-1964 and 1973-2014. , 2017, Environmental science & technology.

[13]  Xin Fang,et al.  Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network , 2015, Environmental Science and Pollution Research.

[14]  Yuan Xu,et al.  Improvements in the operation of SO2 scrubbers in China's coal power plants. , 2011, Environmental science & technology.

[15]  M. Brauer,et al.  Use of Satellite Observations for Long-Term Exposure Assessment of Global Concentrations of Fine Particulate Matter , 2014, Environmental health perspectives.

[16]  Jun Wang,et al.  Intercomparison between satellite‐derived aerosol optical thickness and PM2.5 mass: Implications for air quality studies , 2003 .

[17]  Jing He,et al.  Impact of diurnal variability and meteorological factors on the PM2.5 - AOD relationship: Implications for PM2.5 remote sensing. , 2017, Environmental pollution.

[18]  Yang Liu,et al.  Calibrating MODIS aerosol optical depth for predicting daily PM2.5 concentrations via statistical downscaling , 2014, Journal of Exposure Science and Environmental Epidemiology.

[19]  Zhang Ying,et al.  Using support vector regression to predict PM10 and PM2.5 , 2014 .

[20]  Hai Guo,et al.  Trends of ambient fine particles and major chemical components in the Pearl River Delta region: observation at a regional background site in fall and winter. , 2014, The Science of the total environment.

[21]  Yu Zhan,et al.  Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm , 2017 .

[22]  Qiang Zhang,et al.  Associating ambient exposure to fine particles and human fertility rates in China. , 2018, Environmental pollution.

[23]  T. Zhu,et al.  The role of meteorological conditions and pollution control strategies in reducing air pollution in Beijing during APEC 2014 and Victory Parade 2015 , 2017 .

[24]  中华人民共和国国务院人口普查办公室,et al.  中国2000年人口普查资料 = Tabulation on the 2000 population census of the People's Republic of China , 2002 .

[25]  Yang Liu,et al.  Estimating ground-level PM 2.5 concentrations over three megalopolises in China using satellite-derived aerosol optical depth measurements , 2016 .

[26]  Qiang Zhang,et al.  Multi-year downscaling application of two-way coupled WRF v3.4 and CMAQ v5.0.2 over east Asia for regional climate and air quality modeling: model evaluation and aerosol direct effects , 2017 .

[27]  Yang Liu,et al.  Satellite-Based Spatiotemporal Trends in PM2.5 Concentrations: China, 2004–2013 , 2015, Environmental health perspectives.

[28]  Yi Li,et al.  National-Scale Estimates of Ground-Level PM2.5 Concentration in China Using Geographically Weighted Regression Based on 3 km Resolution MODIS AOD , 2016, Remote. Sens..

[29]  Yang Liu,et al.  Estimating ground-level PM2.5 in China using satellite remote sensing. , 2014, Environmental science & technology.

[30]  Dominick V. Spracklen,et al.  Substantial changes in air pollution across China during 2015–2017 , 2018, Environmental Research Letters.

[31]  George Christakos,et al.  Space-time mapping of ground-level PM2.5 and NO2 concentrations in heavily polluted northern China during winter using the Bayesian maximum entropy technique with satellite data , 2017, Air Quality, Atmosphere & Health.

[32]  Itai Kloog,et al.  Low-Concentration PM2.5 and Mortality: Estimating Acute and Chronic Effects in a Population-Based Study , 2015, Environmental health perspectives.

[33]  Yuesi Wang,et al.  Mechanism for the formation of the January 2013 heavy haze pollution episode over central and eastern China , 2013, Science China Earth Sciences.

[34]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[35]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[36]  Matthew L. Thomas,et al.  Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: an analysis of data from the Global Burden of Diseases Study 2015 , 2017, The Lancet.

[37]  Yujie Wang,et al.  Assessing PM2.5 Exposures with High Spatiotemporal Resolution across the Continental United States. , 2016, Environmental science & technology.

[38]  G. Pfister,et al.  Spatiotemporal prediction of fine particulate matter during the 2008 northern California wildfires using machine learning. , 2015, Environmental science & technology.

[39]  Qiang Zhang,et al.  Sulfur dioxide and primary carbonaceous aerosol emissions in China and India, 1996-2010 , 2011 .

[40]  J. Xin,et al.  Mechanism for the formation of the January 2013 heavy haze pollution episode over central and eastern China , 2014 .

[41]  M. Brauer,et al.  Global Estimates of Fine Particulate Matter using a Combined Geophysical-Statistical Method with Information from Satellites, Models, and Monitors. , 2016, Environmental science & technology.

[42]  P. Gupta,et al.  Particulate Matter Air Quality Assessment using Integrated Surface, Satellite, and Meteorological Products , 2009 .

[43]  Zbigniew Klimont,et al.  The last decade of global anthropogenic sulfur dioxide: 2000–2011 emissions , 2013 .

[44]  Armistead G Russell,et al.  Improving the Accuracy of Daily PM2.5 Distributions Derived from the Fusion of Ground-Level Measurements with Aerosol Optical Depth Observations, a Case Study in North China. , 2016, Environmental science & technology.

[45]  Qiang Zhang,et al.  Fusing Observational, Satellite Remote Sensing and Air Quality Model Simulated Data to Estimate Spatiotemporal Variations of PM2.5 Exposure in China , 2017, Remote. Sens..

[46]  Montserrat Fuentes,et al.  Comparison of exposure estimation methods for air pollutants: ambient monitoring data and regional air quality simulation. , 2011, Environmental research.

[47]  Xiya Zhang,et al.  Improving Satellite-Driven PM2.5 Models with VIIRS Nighttime Light Data in the Beijing-Tianjin-Hebei Region, China , 2017, Remote. Sens..

[48]  G. Peters,et al.  The socioeconomic drivers of China’s primary PM2.5 emissions , 2014 .

[49]  Liangpei Zhang,et al.  Estimating Ground‐Level PM2.5 by Fusing Satellite and Station Observations: A Geo‐Intelligent Deep Learning Approach , 2017, 1707.03558.

[50]  G. Powers,et al.  A Description of the Advanced Research WRF Version 3 , 2008 .

[51]  Michael Brauer,et al.  An Integrated Risk Function for Estimating the Global Burden of Disease Attributable to Ambient Fine Particulate Matter Exposure , 2014, Environmental health perspectives.