Format

Send to

Choose Destination
Environ Pollut. 2018 Nov;242(Pt B):1417-1426. doi: 10.1016/j.envpol.2018.08.029. Epub 2018 Aug 11.

Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of ground-level PM2.5.

Author information

1
School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing, China.
2
Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong. Electronic address: hohungh@sfu.ca.
3
Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong; Research Institute for Sustainable Urban Development, The Hong Kong Polytechnic University, Hong Kong.
4
Department of Geography, State University of New York at Binghamton, Binghamton, NY, United States.
5
School of Architecture, Chinese University of Hong Kong, New Territories, Hong Kong.
6
Research Center for Humanities and Social Sciences, Academia Sinica, Taiwan.
7
Department of Geography, Environment and Geomatics, University of Ottawa, Ottawa, ON, Canada.

Abstract

Fine particulate matter (PM2.5) has been recognized as a key air pollutant that can influence population health risk, especially during extreme cases such as wildfires. Previous studies have applied geospatial techniques such as land use regression to map the ground-level PM2.5, while some recent studies have found that Aerosol Optical Depth (AOD) derived from satellite images and machine learning techniques may be two elements that can improve spatiotemporal prediction. However, there has been a lack of studies evaluating use of different machine learning techniques with AOD datasets for mapping PM2.5, especially in areas with high spatiotemporal variability of PM2.5. In this study, we compared the performance of eight predictive algorithms with the use of multiple remote sensing datasets, including satellite-derived AOD data, for the prediction of ground-level PM2.5 concentration. Based on the results, Cubist, random forest and eXtreme Gradient Boosting were the algorithms with better performance, while Cubist was the best (CV-RMSE = 2.64 μg/m3, CV-R2 = 0.48). Variable importance analysis indicated that the predictors with the highest contributions in modelling were monthly AOD and elevation. In conclusion, appropriate selection of machine learning algorithms can improve ground-level PM2.5 estimation, especially for areas with nonlinear relationships between PM2.5 and predictors caused by complex terrain. Satellite-derived data such as AOD and land surface temperature (LST) can also be substitutes for traditional datasets retrieved from weather stations, especially for areas with sparse and uneven distribution of stations.

PMID:
30142557
DOI:
10.1016/j.envpol.2018.08.029
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center