Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions
The use of statistical models and machine-learning techniques along satellite-derived aerosol optical depth (AOD) is a promising method to estimate ground-level particulate matter with an aerodynamic diameter of ≤2.5 μm (PM<sub>2.5</sub>), mainly in urban areas with low air quality monit...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/16/3102 |
_version_ | 1797522206900617216 |
---|---|
author | Johana M. Carmona Pawan Gupta Diego F. Lozano-García Ana Y. Vanoye Iván Y. Hernández-Paniagua Alberto Mendoza |
author_facet | Johana M. Carmona Pawan Gupta Diego F. Lozano-García Ana Y. Vanoye Iván Y. Hernández-Paniagua Alberto Mendoza |
author_sort | Johana M. Carmona |
collection | DOAJ |
description | The use of statistical models and machine-learning techniques along satellite-derived aerosol optical depth (AOD) is a promising method to estimate ground-level particulate matter with an aerodynamic diameter of ≤2.5 μm (PM<sub>2.5</sub>), mainly in urban areas with low air quality monitor density. Nevertheless, the relationship between AOD and ground-level PM<sub>2.5</sub> varies spatiotemporally and differences related to spatial domains, temporal schemes, and seasonal variations must be assessed. Here, an ensemble multiple linear regression (EMLR) model and an ensemble neural network (ENN) model were developed to estimate PM<sub>2.5</sub> levels in the Monterrey Metropolitan Area (MMA), the second largest urban center in Mexico. Four AOD-SDSs (Scientific Datasets) from MODIS Collection 6 were tested using three spatial domains and two temporal schemes. The best model performance was obtained using AOD at 0.55 µm from MODIS-Aqua at a spatial resolution of 3 km, along meteorological parameters and daily scheme. EMLR yielded a correlation coefficient (<i>R</i>) of ~0.57 and a root mean square error (<i>RMSE</i>) of ~7.00 μg m<sup>−3</sup>. ENN performed better than EMLR, with an <i>R</i> of ~0.78 and <i>RMSE</i> of ~5.43 μg m<sup>−3</sup>. Satellite-derived AOD in combination with meteorology data allowed for the estimation of PM<sub>2.5</sub> distributions in an urban area with low air quality monitor density. |
first_indexed | 2024-03-10T08:25:14Z |
format | Article |
id | doaj.art-3a946d45a2e6453696497dd0b64a2fd3 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T08:25:14Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-3a946d45a2e6453696497dd0b64a2fd32023-11-22T09:31:53ZengMDPI AGRemote Sensing2072-42922021-08-011316310210.3390/rs13163102Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial DistributionsJohana M. Carmona0Pawan Gupta1Diego F. Lozano-García2Ana Y. Vanoye3Iván Y. Hernández-Paniagua4Alberto Mendoza5Escuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Av. Eugenio Garza Sada 2501, Monterrey 64849, MexicoScience and Technology Institute, Universities Space Research Association (USRA), Huntsville, AL 35806, USAEscuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Av. Eugenio Garza Sada 2501, Monterrey 64849, MexicoEscuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Av. Eugenio Garza Sada 2501, Monterrey 64849, MexicoCentro de Ciencias de la Atmósfera, Universidad Nacional Autónoma de México, Circuito Investigación Científica S/N, C.U., Coyoacán, Ciudad de México 04510, MexicoEscuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Av. Eugenio Garza Sada 2501, Monterrey 64849, MexicoThe use of statistical models and machine-learning techniques along satellite-derived aerosol optical depth (AOD) is a promising method to estimate ground-level particulate matter with an aerodynamic diameter of ≤2.5 μm (PM<sub>2.5</sub>), mainly in urban areas with low air quality monitor density. Nevertheless, the relationship between AOD and ground-level PM<sub>2.5</sub> varies spatiotemporally and differences related to spatial domains, temporal schemes, and seasonal variations must be assessed. Here, an ensemble multiple linear regression (EMLR) model and an ensemble neural network (ENN) model were developed to estimate PM<sub>2.5</sub> levels in the Monterrey Metropolitan Area (MMA), the second largest urban center in Mexico. Four AOD-SDSs (Scientific Datasets) from MODIS Collection 6 were tested using three spatial domains and two temporal schemes. The best model performance was obtained using AOD at 0.55 µm from MODIS-Aqua at a spatial resolution of 3 km, along meteorological parameters and daily scheme. EMLR yielded a correlation coefficient (<i>R</i>) of ~0.57 and a root mean square error (<i>RMSE</i>) of ~7.00 μg m<sup>−3</sup>. ENN performed better than EMLR, with an <i>R</i> of ~0.78 and <i>RMSE</i> of ~5.43 μg m<sup>−3</sup>. Satellite-derived AOD in combination with meteorology data allowed for the estimation of PM<sub>2.5</sub> distributions in an urban area with low air quality monitor density.https://www.mdpi.com/2072-4292/13/16/3102air pollutionfine particulate mattersatellite dataneural networksensemble models |
spellingShingle | Johana M. Carmona Pawan Gupta Diego F. Lozano-García Ana Y. Vanoye Iván Y. Hernández-Paniagua Alberto Mendoza Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions Remote Sensing air pollution fine particulate matter satellite data neural networks ensemble models |
title | Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions |
title_full | Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions |
title_fullStr | Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions |
title_full_unstemmed | Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions |
title_short | Evaluation of MODIS Aerosol Optical Depth and Surface Data Using an Ensemble Modeling Approach to Assess PM<sub>2.5</sub> Temporal and Spatial Distributions |
title_sort | evaluation of modis aerosol optical depth and surface data using an ensemble modeling approach to assess pm sub 2 5 sub temporal and spatial distributions |
topic | air pollution fine particulate matter satellite data neural networks ensemble models |
url | https://www.mdpi.com/2072-4292/13/16/3102 |
work_keys_str_mv | AT johanamcarmona evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions AT pawangupta evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions AT diegoflozanogarcia evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions AT anayvanoye evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions AT ivanyhernandezpaniagua evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions AT albertomendoza evaluationofmodisaerosolopticaldepthandsurfacedatausinganensemblemodelingapproachtoassesspmsub25subtemporalandspatialdistributions |