In Autumn 2020, DOAJ will be relaunching with a new website with updated functionality, improved search, and a simplified application form. More information is available on our blog. Our API is also changing.

Hide this message

Improved 1&thinsp;km resolution PM<sub>2.5</sub> estimates across China using enhanced space–time extremely randomized trees

Atmospheric Chemistry and Physics. 2020;20:3273-3289 DOI 10.5194/acp-20-3273-2020

 

Journal Homepage

Journal Title: Atmospheric Chemistry and Physics

ISSN: 1680-7316 (Print); 1680-7324 (Online)

Publisher: Copernicus Publications

Society/Institution: European Geosciences Union (EGU)

LCC Subject Category: Science: Physics | Science: Chemistry

Country of publisher: Germany

Language of fulltext: English

Full-text formats available: PDF, XML

 

AUTHORS


J. Wei (State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing, China)

J. Wei (Department of Atmospheric and Oceanic Science, Earth System Science Interdisciplinary Center, University of Maryland, College Park, MD, USA)

Z. Li (Department of Atmospheric and Oceanic Science, Earth System Science Interdisciplinary Center, University of Maryland, College Park, MD, USA)

M. Cribb (Department of Atmospheric and Oceanic Science, Earth System Science Interdisciplinary Center, University of Maryland, College Park, MD, USA)

W. Huang (State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing, China)

W. Xue (State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing, China)

L. Sun (College of Geomatics, Shandong University of Science and Technology, Qingdao, China)

J. Guo (State Key Laboratory of Severe Weather, Chinese Academy of Meteorological Sciences, Beijing, China)

Y. Peng (Ministry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing, China)

J. Li (Department of Atmospheric and Oceanic Sciences, School of Physics, Peking University, Beijing, China)

A. Lyapustin (Laboratory for Atmospheres, NASA Goddard Space Flight Center, Greenbelt, Maryland, USA)

L. Liu (College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, China)

H. Wu (State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing, China)

Y. Song (Faculty of Architecture, The University of Hong Kong, Hong Kong SAR, China)

EDITORIAL INFORMATION

Peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 16 weeks

 

Abstract | Full Text

<p>Fine particulate matter with aerodynamic diameters <span class="inline-formula">≤2.5</span>&thinsp;<span class="inline-formula">µ</span>m (PM<span class="inline-formula"><sub>2.5</sub></span>) has adverse effects on human health and the atmospheric environment. The estimation of surface PM<span class="inline-formula"><sub>2.5</sub></span> concentrations has made intensive use of satellite-derived aerosol products. However, it has been a great challenge to obtain high-quality and high-resolution PM<span class="inline-formula"><sub>2.5</sub></span> data from both ground and satellite observations, which is essential to monitor air pollution over small-scale areas such as metropolitan regions. Here, the space–time extremely randomized trees (STET) model was enhanced by integrating updated spatiotemporal information and additional auxiliary data to improve the spatial resolution and overall accuracy of PM<span class="inline-formula"><sub>2.5</sub></span> estimates across China. To this end, the newly released Moderate Resolution Imaging Spectroradiometer Multi-Angle Implementation of Atmospheric Correction AOD product, along with meteorological, topographical and land-use data and pollution emissions, was input to the STET model, and daily 1&thinsp;km PM<span class="inline-formula"><sub>2.5</sub></span> maps for 2018 covering mainland China were produced. The STET model performed well, with a high out-of-sample (out-of-station) cross-validation coefficient of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) of 0.89 (0.88), a low root-mean-square error of 10.33 (10.93)&thinsp;<span class="inline-formula">µ</span>g&thinsp;m<span class="inline-formula"><sup>−3</sup></span>, a small mean absolute error of 6.69 (7.15)&thinsp;<span class="inline-formula">µ</span>g&thinsp;m<span class="inline-formula"><sup>−3</sup></span> and a small mean relative error of 21.28&thinsp;% (23.69&thinsp;%). In particular, the model captured well the PM<span class="inline-formula"><sub>2.5</sub></span> concentrations at both regional and individual site scales. The North China Plain, the Sichuan Basin and Xinjiang Province always featured high PM<span class="inline-formula"><sub>2.5</sub></span> pollution levels, especially in winter. The STET model outperformed most models presented in previous related studies, with a strong predictive power (e.g., monthly <span class="inline-formula"><i>R</i><sup>2</sup>=0.80</span>), which can be used to estimate historical PM<span class="inline-formula"><sub>2.5</sub></span> records. More importantly, this study provides a new approach for obtaining high-resolution and high-quality PM<span class="inline-formula"><sub>2.5</sub></span> dataset across mainland China (i.e., ChinaHighPM<span class="inline-formula"><sub>2.5</sub></span>), important for air pollution studies focused on urban areas.</p>