Developing an Advanced PM2.5 Exposure Model in Lima, Peru

Remote Sensing

Odón Sánchez¹  Kyle Steenland²  BryanN. Vu²  Qingyang Xiao²  Jianzhao Bi²  Yang Liu²  William Checkley³  NadiaN. Hansel³  GustavoF. Gonzales⁴ 

[1] Carrera Profesional de Ingeniería Ambiental, Universidad Nacional Tecnológica de Lima Sur (UNTELS), cruce Av. Central y Av. Bolivar, Villa El Salvador, Lima 15102, Peru;Department of Environmental Health, Rollins School of Public Health, Emory University, Atlanta, GA 30322, USA;Division of Pulmonary and Critical Care, School of Medicine, Johns Hopkins University, Baltimore, MD 21205, USA;Endocrinology and Reproduction Unit, Research and Development Laboratories (LID), Faculty of Sciences and Philosophy, Universidad Peruana Cayetano Heredia, Lima 15102, Peru;

关键词: PM2.5;    air pollution;    MAIAC AOD;    WRF-chem;    random forest;    machine learning;    remote sensing;    Lima;    Peru;   

DOI  :  10.3390/rs11060641

来源: DOAJ

【 摘 要 】

It is well recognized that exposure to fine particulate matter (PM2.5) affects health adversely, yet few studies from South America have documented such associations due to the sparsity of PM2.5 measurements. Lima’s topography and aging vehicular fleet results in severe air pollution with limited amounts of monitors to effectively quantify PM2.5 levels for epidemiologic studies. We developed an advanced machine learning model to estimate daily PM2.5 concentrations at a 1 km2 spatial resolution in Lima, Peru from 2010 to 2016. We combined aerosol optical depth (AOD), meteorological fields from the European Centre for Medium-Range Weather Forecasts (ECMWF), parameters from the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem), and land use variables to fit a random forest model against ground measurements from 16 monitoring stations. Overall cross-validation R2 (and root mean square prediction error, RMSE) for the random forest model was 0.70 (5.97 μg/m3). Mean PM2.5 for ground measurements was 24.7 μg/m3 while mean estimated PM2.5 was 24.9 μg/m3 in the cross-validation dataset. The mean difference between ground and predicted measurements was −0.09 μg/m3 (Std.Dev. = 5.97 μg/m3), with 94.5% of observations falling within 2 standard deviations of the difference indicating good agreement between ground measurements and predicted estimates. Surface downwards solar radiation, temperature, relative humidity, and AOD were the most important predictors, while percent urbanization, albedo, and cloud fraction were the least important predictors. Comparison of monthly mean measurements between ground and predicted PM2.5 shows good precision and accuracy from our model. Furthermore, mean annual maps of PM2.5 show consistent lower concentrations in the coast and higher concentrations in the mountains, resulting from prevailing coastal winds blown from the Pacific Ocean in the west. Our model allows for construction of long-term historical daily PM2.5 measurements at 1 km2 spatial resolution to support future epidemiological studies.

【 授权许可】

Unknown