Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data

Accurate estimation of ambient PM<sub>2.5</sub> concentrations is crucial for assessing air quality and health risks, particularly in regions with limited ground-based monitoring. Satellite-retrieved data products, such as top-of-atmosphere reflectance (TOAR) and aerosol optical depth (A...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Jawad Hussain, Myeongsu Seong, Behjat Shahid, Heming Bai
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Toxics
Subjects:
Online Access:https://www.mdpi.com/2305-6304/13/5/392
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719751324991488
author Muhammad Jawad Hussain
Myeongsu Seong
Behjat Shahid
Heming Bai
author_facet Muhammad Jawad Hussain
Myeongsu Seong
Behjat Shahid
Heming Bai
author_sort Muhammad Jawad Hussain
collection DOAJ
description Accurate estimation of ambient PM<sub>2.5</sub> concentrations is crucial for assessing air quality and health risks, particularly in regions with limited ground-based monitoring. Satellite-retrieved data products, such as top-of-atmosphere reflectance (TOAR) and aerosol optical depth (AOD), are widely used for PM<sub>2.5</sub> estimation. However, complex atmospheric conditions cause retrieval gaps in TOAR and AOD products, limiting their reliability. This study introduced a spatiotemporal convolutional approach to fill sampling gaps in TOAR and AOD data from the Himawari-8 geostationary satellite over the Yangtze River Delta (YRD) in 2016. Four machine-learning models (random forest, extreme gradient boosting, gradient boosting, and support vector regression) were used to estimate hourly PM<sub>2.5</sub> concentrations by integrating gap-filled and original TOAR and AOD data with meteorological variables. The random forest model trained on gap-filled TOAR data yielded the highest predictive accuracy (R<sup>2</sup> = 0.75, RMSE = 18.30 μg m<sup>−3</sup>). Significant seasonal variations in PM<sub>2.5</sub> estimates were found, with TOAR-based models outperforming AOD-based models. Furthermore, we observed that a substantial portion of the YRD population in non-attainment areas is at risk of cardiovascular disease due to chronic PM<sub>2.5</sub> exposure. This study suggests that TOAR-based models offer more reliable PM<sub>2.5</sub> estimates, enhancing air-quality assessments and public health-risk evaluations.
format Article
id doaj-art-2c70d0b70cc745b480d7d179d8e6d003
institution DOAJ
issn 2305-6304
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Toxics
spelling doaj-art-2c70d0b70cc745b480d7d179d8e6d0032025-08-20T03:12:05ZengMDPI AGToxics2305-63042025-05-0113539210.3390/toxics13050392Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite DataMuhammad Jawad Hussain0Myeongsu Seong1Behjat Shahid2Heming Bai3Research Center for Intelligent Information Technology, Nantong University, Nantong 226019, ChinaDepartment of Mechatronics and Robotics, School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaFaculty of Media and Communication Studies, University of Central Punjab, Lahore 54590, PakistanResearch Center for Intelligent Information Technology, Nantong University, Nantong 226019, ChinaAccurate estimation of ambient PM<sub>2.5</sub> concentrations is crucial for assessing air quality and health risks, particularly in regions with limited ground-based monitoring. Satellite-retrieved data products, such as top-of-atmosphere reflectance (TOAR) and aerosol optical depth (AOD), are widely used for PM<sub>2.5</sub> estimation. However, complex atmospheric conditions cause retrieval gaps in TOAR and AOD products, limiting their reliability. This study introduced a spatiotemporal convolutional approach to fill sampling gaps in TOAR and AOD data from the Himawari-8 geostationary satellite over the Yangtze River Delta (YRD) in 2016. Four machine-learning models (random forest, extreme gradient boosting, gradient boosting, and support vector regression) were used to estimate hourly PM<sub>2.5</sub> concentrations by integrating gap-filled and original TOAR and AOD data with meteorological variables. The random forest model trained on gap-filled TOAR data yielded the highest predictive accuracy (R<sup>2</sup> = 0.75, RMSE = 18.30 μg m<sup>−3</sup>). Significant seasonal variations in PM<sub>2.5</sub> estimates were found, with TOAR-based models outperforming AOD-based models. Furthermore, we observed that a substantial portion of the YRD population in non-attainment areas is at risk of cardiovascular disease due to chronic PM<sub>2.5</sub> exposure. This study suggests that TOAR-based models offer more reliable PM<sub>2.5</sub> estimates, enhancing air-quality assessments and public health-risk evaluations.https://www.mdpi.com/2305-6304/13/5/392PM<sub>2.5</sub>aerosol optical depthtop of atmospheric reflectancecardiovascular diseasesmachine-learning
spellingShingle Muhammad Jawad Hussain
Myeongsu Seong
Behjat Shahid
Heming Bai
Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
Toxics
PM<sub>2.5</sub>
aerosol optical depth
top of atmospheric reflectance
cardiovascular diseases
machine-learning
title Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
title_full Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
title_fullStr Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
title_full_unstemmed Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
title_short Estimating PM<sub>2.5</sub> Exposures and Cardiovascular Disease Risks in the Yangtze River Delta Region Using a Spatiotemporal Convolutional Approach to Fill Gaps in Satellite Data
title_sort estimating pm sub 2 5 sub exposures and cardiovascular disease risks in the yangtze river delta region using a spatiotemporal convolutional approach to fill gaps in satellite data
topic PM<sub>2.5</sub>
aerosol optical depth
top of atmospheric reflectance
cardiovascular diseases
machine-learning
url https://www.mdpi.com/2305-6304/13/5/392
work_keys_str_mv AT muhammadjawadhussain estimatingpmsub25subexposuresandcardiovasculardiseaserisksintheyangtzeriverdeltaregionusingaspatiotemporalconvolutionalapproachtofillgapsinsatellitedata
AT myeongsuseong estimatingpmsub25subexposuresandcardiovasculardiseaserisksintheyangtzeriverdeltaregionusingaspatiotemporalconvolutionalapproachtofillgapsinsatellitedata
AT behjatshahid estimatingpmsub25subexposuresandcardiovasculardiseaserisksintheyangtzeriverdeltaregionusingaspatiotemporalconvolutionalapproachtofillgapsinsatellitedata
AT hemingbai estimatingpmsub25subexposuresandcardiovasculardiseaserisksintheyangtzeriverdeltaregionusingaspatiotemporalconvolutionalapproachtofillgapsinsatellitedata