Identifying low-PM2.5 exposure commuting routes for cyclists through modeling with the random forest algorithm based on low-cost sensor measurements in three Asian cities. (1st February 2022)

• Record Type: Journal Article
• Authors: Wu, Tzong-Gang; Chen, Yan-Da; Chen, Bang-Hua; Harada, Kouji H.; Lee, Kiyoung; Deng, Furong; Rood, Mark J.; Chen, Chu-Chih; Tran, Cong-Thanh; Chien, Kuo-Liong; Wen, Tzai-Hung; Wu, Chang-Fu
• Is Part Of: Environmental pollution. Volume 294(2022)
• Publication Date: 2022-02-01
• Subjects: PM2.5 -- Cyclist -- Routing -- Asian city -- Random forest -- Spatial autocorrelation; 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.2021.118597
• Languages: English
• ISSNs: 0269-7491

Abstract

Abstract: Cyclists can be easily exposed to traffic-related pollutants due to riding on or close to the road during commuting in cities. PM2.5 has been identified as one of the major pollutants emitted by vehicles and associated with cardiopulmonary and respiratory diseases. As routing has been suggested to reduce the exposures for cyclists, in this study, PM2.5 was monitored with low-cost sensors during commuting periods to develop models for identifying low exposure routes in three Asian cities: Taipei, Osaka, and Seoul. The models for mapping the PM2.5 in the cities were developed by employing the random forest algorithm in a two-stage modeling approach. The land use features to explain spatial variation of PM2.5 were obtained from the open-source land use database, OpenStreetMap. The total length of the monitoring routes ranged from 101.36 to 148.22 km and the average PM2.5 ranged from 13.51 to 15.40 μg/m³ among the cities. The two-stage models had the standard k-fold cross-validation (CV) R 2 of 0.93, 0.74, and 0.84 in Taipei, Osaka, and Seoul, respectively. To address spatial autocorrelation, a spatial cross-validation approach applying a distance restriction of 100 m between the model training and testing data was employed. The over-optimistic estimates on the predictions were thus prevented, showing model CV-R 2 of 0.91, 0.67, and 0.78 respectively in Taipei, Osaka, and Seoul. The comparisons between the shortest-distance and lowest-exposure routes showed that the largest percentage of reduced averaged PM2.5 exposure could reach 32.1% with the distance increases by 37.8%. Given the findings in this study, routing behavior should be encouraged. With the daily commuting trips expanded, the cumulative effect may become significant on the chronic exposures over time. Therefore, a route planning tool for reducing the exposures shall be developed and promoted to the public. Graphical abstract: Image 1 Highlights: Cyclists' PM2.5 exposures were monitored in Taipei, Osaka, and Seoul. Random forest land use models are developed for mapping PM2.5 . Spatial k-fold cross-validation is applied, showing model CV-R 2 above 0.67. Alternative routes can reduce the PM2.5 exposure over 30% for cyclist commuters.