Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System
Particulate matter less than 2.5 microns in diameter (PM<sub>2.5</sub>) is an air pollutant that has become a major environmental concern for governments around the world. Management and control require air quality monitoring and prediction. However, previous studies did not fully utiliz...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/8/2009 |
| _version_ | 1827743858994184192 |
|---|---|
| author | Dewinta Heriza Chih-Da Wu Muhammad Aldila Syariz Chao-Hung Lin |
| author_facet | Dewinta Heriza Chih-Da Wu Muhammad Aldila Syariz Chao-Hung Lin |
| author_sort | Dewinta Heriza |
| collection | DOAJ |
| description | Particulate matter less than 2.5 microns in diameter (PM<sub>2.5</sub>) is an air pollutant that has become a major environmental concern for governments around the world. Management and control require air quality monitoring and prediction. However, previous studies did not fully utilize the spectral information in multispectral satellite images and land use data in geographic datasets. To alleviate these problems, this study proposes the extraction of land use information not only from geographic inventory but also from satellite images with a machine learning-based classification. In this manner, near up-to-date land use data and spectral information from satellite images can be utilized, and the integration of geographic and remote sensing datasets boosts the accuracy of PM<sub>2.5</sub> concentration modeling. In the experiments, Landsat-8 imagery with a 30-m spatial resolution was used, and cloud-free image generation was performed prior to the land cover classification. The proposed method, which uses predictors from geographic and multispectral satellite datasets in modeling, was compared with an approach which utilizes geographic and remote sensing datasets, respectively. Quantitative assessments showed that the proposed method and the developed model, with a performance of RMSE = 3.06 µg/m<sup>3</sup> and R<sup>2</sup> = 0.85 comparatively outperform the models with a performance of RMSE = 3.14 µg/m<sup>3</sup> and R<sup>2</sup> = 0.68 for remote sensing datasets and a performance of RMSE = 3.47 µg/m<sup>3</sup> and R<sup>2</sup> = 0.79 for geographic datasets. |
| first_indexed | 2024-03-11T04:35:26Z |
| format | Article |
| id | doaj.art-e97abb6d55b2492582fdec20364d8ef5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:35:26Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e97abb6d55b2492582fdec20364d8ef52023-11-17T21:10:44ZengMDPI AGRemote Sensing2072-42922023-04-01158200910.3390/rs15082009Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information SystemDewinta Heriza0Chih-Da Wu1Muhammad Aldila Syariz2Chao-Hung Lin3Department of Geomatics, National Cheng Kung University, Tainan City 70101, TaiwanDepartment of Geomatics, National Cheng Kung University, Tainan City 70101, TaiwanDepartment of Geomatics Engineering, Institut Teknologi Sepuluh Nopember, Surabaya 60111, IndonesiaDepartment of Geomatics, National Cheng Kung University, Tainan City 70101, TaiwanParticulate matter less than 2.5 microns in diameter (PM<sub>2.5</sub>) is an air pollutant that has become a major environmental concern for governments around the world. Management and control require air quality monitoring and prediction. However, previous studies did not fully utilize the spectral information in multispectral satellite images and land use data in geographic datasets. To alleviate these problems, this study proposes the extraction of land use information not only from geographic inventory but also from satellite images with a machine learning-based classification. In this manner, near up-to-date land use data and spectral information from satellite images can be utilized, and the integration of geographic and remote sensing datasets boosts the accuracy of PM<sub>2.5</sub> concentration modeling. In the experiments, Landsat-8 imagery with a 30-m spatial resolution was used, and cloud-free image generation was performed prior to the land cover classification. The proposed method, which uses predictors from geographic and multispectral satellite datasets in modeling, was compared with an approach which utilizes geographic and remote sensing datasets, respectively. Quantitative assessments showed that the proposed method and the developed model, with a performance of RMSE = 3.06 µg/m<sup>3</sup> and R<sup>2</sup> = 0.85 comparatively outperform the models with a performance of RMSE = 3.14 µg/m<sup>3</sup> and R<sup>2</sup> = 0.68 for remote sensing datasets and a performance of RMSE = 3.47 µg/m<sup>3</sup> and R<sup>2</sup> = 0.79 for geographic datasets.https://www.mdpi.com/2072-4292/15/8/2009fine particulate matterland use regressionoptical satellite images |
| spellingShingle | Dewinta Heriza Chih-Da Wu Muhammad Aldila Syariz Chao-Hung Lin Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System Remote Sensing fine particulate matter land use regression optical satellite images |
| title | Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System |
| title_full | Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System |
| title_fullStr | Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System |
| title_full_unstemmed | Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System |
| title_short | Analysis of Spatial–Temporal Variability of PM<sub>2.5</sub> Concentrations Using Optical Satellite Images and Geographic Information System |
| title_sort | analysis of spatial temporal variability of pm sub 2 5 sub concentrations using optical satellite images and geographic information system |
| topic | fine particulate matter land use regression optical satellite images |
| url | https://www.mdpi.com/2072-4292/15/8/2009 |
| work_keys_str_mv | AT dewintaheriza analysisofspatialtemporalvariabilityofpmsub25subconcentrationsusingopticalsatelliteimagesandgeographicinformationsystem AT chihdawu analysisofspatialtemporalvariabilityofpmsub25subconcentrationsusingopticalsatelliteimagesandgeographicinformationsystem AT muhammadaldilasyariz analysisofspatialtemporalvariabilityofpmsub25subconcentrationsusingopticalsatelliteimagesandgeographicinformationsystem AT chaohunglin analysisofspatialtemporalvariabilityofpmsub25subconcentrationsusingopticalsatelliteimagesandgeographicinformationsystem |