Estimating historical PM2.5 exposures for three decades (1987–2016) in Japan using measurements of associated air pollutants and land use regression. (August 2020)

• Record Type: Journal Article
• Authors: Araki, Shin; Shima, Masayuki; Yamamoto, Kouhei
• Is Part Of: Environmental pollution. Volume 263(2020)Supplement Part A
• Publication Date: 2020-08
• Subjects: Air pollution -- Machine learning -- Temporal trend -- Spatial distribution; Pollution -- Periodicals; Pollution -- Environmental aspects -- Periodicals; Environmental Pollution -- Periodicals; Pollution -- Périodiques; Pollution -- Aspect de l'environnement -- Périodiques; Pollution -- Effets physiologiques -- Périodiques; Pollution; Pollution -- Environmental aspects; Periodicals; Electronic journals; 363.73
• DOI: 10.1016/j.envpol.2020.114476
• Languages: English
• ISSNs: 0269-7491

Abstract

Abstract: Accurate estimation of historical PM 2.5 exposures for epidemiological studies is challenging when extensive monitoring data are limited in duration. Here, we develop a national-scale PM 2.5 exposure model for Japan using measurements recorded between 2014 and 2016 to estimate monthly means for 1987 through 2016. Our objective is to obtain accurate PM 2.5 estimates for years prior to implementation of extensive PM 2.5 monitoring, using observations from a limited period. We utilize a neural network to convey the non-linear relationship between the target pollutant and predictors, while incorporating the associated air pollutants. We obtain high R 2 values of 0.76 and 0.73 through spatial and temporal cross validation, respectively. We evaluate estimation accuracy using an independent data set and achieve an R 2 of 0.75. Moreover, monthly variations for 2000–2013 are well reproduced with correlation coefficients of greater than 0.78, obtained through a comparison with observations. We estimate monthly means at 1 × 1 km resolution from 1987 through 2016. The estimates show decreases in the area and population weighted means beginning in the 1990s. We successfully estimate monthly mean PM 2.5 concentrations over three decades with outstanding predictive accuracy. Our findings illustrate that the presented approach achieves accurate long-term historical estimations using observations limited in duration. Graphical abstract: Image 1 Highlights: We built a national-scale PM2.5 exposure model using observations from 2014 to 2016. We used suspended particulate matter, NO2, and SO2 concentrations as predictors. We obtained an R 2 of 0.75 through model validation using an independent data set. The monthly variations were well reproduced for 2000–2013. We achieved accurate historical estimations using observations limited in duration.