PM2.5 has been considered as a crucial issue in densely populated cities because of its adverse effects on human health. As a way to mitigate this problem on city scale, urban forest is recently suggested as a solution due to its potential to absorb and adhere PM2.5. However, limited observations in the forest prevent a full understanding in the role of forest on urban PM2.5 concentration. In this paper, we present an application of deep learning using satellite data to clarify the role of forest with respect to the PM2.5 concentration mitigation in the city. Based on PM2.5 data collected from the ground-based observation stations, two PM2.5 prediction models are constructed through the deep learning approach. Satellite-derived aerosol optical depth from the GOCI and MODIS are used as the main predictors of two models. Both models predict spatial distribution throughout Seoul, Korea (R2 of 0.61 and 0.78). Particularly, the western parts of Seoul tend to have higher PM2.5 concentrations than the other parts, whereas mid-outskirts have noticeably low concentrations. A comparison of spatial distributions of PM2.5 between observations and predictions show that the existing observation network only reflects 15%–60% of entire characteristics of Seoul. Utilizing city-wide PM2.5 estimations, a comparison of estimated PM2.5 between urban and forest regions has been performed. The results show that the estimated PM2.5 concentrations in the forest regions are less than those in urban regions by up to 16.4 μg m−3. In contrast to urban regions, the average of PM2.5 concentrations in the forest regions is likely below the daily mean WHO PM2.5 outdoor standard. Our study suggests that urban forest could be a potential way to improve urban air quality with a specific focus on PM2.5. In addition, the deep learning approach used in this study can be applied to other cities where obtaining observation measurements is difficult.
|Publication status||Published - 2021 Mar|
Bibliographical noteFunding Information:
This study was carried out with the support of the “R&D Program for Forest Science Technology (Project No. 2019156A00-2021-0101 )” provided by the Korea Forest Service ( Korea Forestry Promotion Institute ) and the Creative-Pioneering Researchers Program of Seoul National University. GOCI data were provided through “Technology Development for Practical Applications of Multi-Satellite Data to Maritime Issues” project of the Ministry of Ocean and Fisheries.
This study was carried out with the support of the ?R&D Program for Forest Science Technology (Project No. 2019156A00-2021-0101)? provided by the Korea Forest Service (Korea Forestry Promotion Institute) and the Creative-Pioneering Researchers Program of Seoul National University. GOCI data were provided through ?Technology Development for Practical Applications of Multi-Satellite Data to Maritime Issues? project of the Ministry of Ocean and Fisheries.
© 2021 Elsevier B.V.
All Science Journal Classification (ASJC) codes
- Geography, Planning and Development
- Environmental Science (miscellaneous)
- Urban Studies
- Atmospheric Science