Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region

Air pollution and public health issues caused by fine particulate matter (PM<sub>2.5</sub>) are becoming increasingly severe. Although well-established satellite methods exist for retrieving daytime PM<sub>2.5</sub> concentrations, these methods are limited by weak nighttime...

Full description

Saved in:
Bibliographic Details
Main Authors: Tong Li, Bo Li, Zhihua Han, Wenhao Zhang, Xiufeng Yang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10963726/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850281633301659648
author Tong Li
Bo Li
Zhihua Han
Wenhao Zhang
Xiufeng Yang
author_facet Tong Li
Bo Li
Zhihua Han
Wenhao Zhang
Xiufeng Yang
author_sort Tong Li
collection DOAJ
description Air pollution and public health issues caused by fine particulate matter (PM<sub>2.5</sub>) are becoming increasingly severe. Although well-established satellite methods exist for retrieving daytime PM<sub>2.5</sub> concentrations, these methods are limited by weak nighttime light radiation. To resolve these challenges, this study proposed a nighttime PM<sub>2.5</sub> concentration estimation method based on explainable machine learning and low-light data. Owing to the complexity of nighttime light sources, primarily composed of artificial lighting and moonlight, both types of light were considered by simulating lunar irradiance and artificial light radiance. This study utilized nighttime lighting, meteorological, various geospatial auxiliary, simulated nighttime light radiation, and ground-based PM<sub>2.5</sub> monitoring data to construct a dataset with an effective sample size of 24,311. A deep neural network model was trained to estimate nighttime PM<sub>2.5</sub> concentrations. The experimental results show that, after adding the simulated nighttime light radiation, the tenfold cross-validation <italic>R</italic><sup>2</sup> of the model improved from 0.6 to 0.73. In addition, 74&#x0025; of site-based tenfold cross-validation <italic>R</italic><sup>2</sup> values exceeded 0.7, indicating the model's robust spatial adaptability. The model was then used to estimate nighttime PM<sub>2.5</sub> concentrations in the study area for 2021. The Shapley additive explanation model was applied to analyze the effect curves of different predictors on nighttime PM<sub>2.5</sub> to examine the contributions of various factors. This study can serve as a reference for similar research in the future, and the proposed retrieval method offers a broad coverage of nighttime PM<sub>2.5</sub> data, providing a useful supplement to ground station measurements.
format Article
id doaj-art-6257a437bbd6419f9646ce71e4213b49
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-6257a437bbd6419f9646ce71e4213b492025-08-20T01:48:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118110471105910.1109/JSTARS.2025.356013610963726Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei RegionTong Li0https://orcid.org/0009-0001-8728-0513Bo Li1Zhihua Han2Wenhao Zhang3https://orcid.org/0000-0001-8762-1878Xiufeng Yang4School of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang, ChinaAir pollution and public health issues caused by fine particulate matter (PM<sub>2.5</sub>) are becoming increasingly severe. Although well-established satellite methods exist for retrieving daytime PM<sub>2.5</sub> concentrations, these methods are limited by weak nighttime light radiation. To resolve these challenges, this study proposed a nighttime PM<sub>2.5</sub> concentration estimation method based on explainable machine learning and low-light data. Owing to the complexity of nighttime light sources, primarily composed of artificial lighting and moonlight, both types of light were considered by simulating lunar irradiance and artificial light radiance. This study utilized nighttime lighting, meteorological, various geospatial auxiliary, simulated nighttime light radiation, and ground-based PM<sub>2.5</sub> monitoring data to construct a dataset with an effective sample size of 24,311. A deep neural network model was trained to estimate nighttime PM<sub>2.5</sub> concentrations. The experimental results show that, after adding the simulated nighttime light radiation, the tenfold cross-validation <italic>R</italic><sup>2</sup> of the model improved from 0.6 to 0.73. In addition, 74&#x0025; of site-based tenfold cross-validation <italic>R</italic><sup>2</sup> values exceeded 0.7, indicating the model's robust spatial adaptability. The model was then used to estimate nighttime PM<sub>2.5</sub> concentrations in the study area for 2021. The Shapley additive explanation model was applied to analyze the effect curves of different predictors on nighttime PM<sub>2.5</sub> to examine the contributions of various factors. This study can serve as a reference for similar research in the future, and the proposed retrieval method offers a broad coverage of nighttime PM<sub>2.5</sub> data, providing a useful supplement to ground station measurements.https://ieeexplore.ieee.org/document/10963726/Nighttime lighting datanighttime particulate matter (PM<sub xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">2.5</sub>)satellite observationShapley additive explanation (SHAP)
spellingShingle Tong Li
Bo Li
Zhihua Han
Wenhao Zhang
Xiufeng Yang
Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Nighttime lighting data
nighttime particulate matter (PM<sub xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">2.5</sub>)
satellite observation
Shapley additive explanation (SHAP)
title Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
title_full Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
title_fullStr Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
title_full_unstemmed Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
title_short Nighttime PM<sub>2.5</sub> Concentration Estimation Based on NPP-VIIRS and Interpretable Machine Learning: The Case of Beijing&#x2013;Tianjin&#x2013;Hebei Region
title_sort nighttime pm sub 2 5 sub concentration estimation based on npp viirs and interpretable machine learning the case of beijing x2013 tianjin x2013 hebei region
topic Nighttime lighting data
nighttime particulate matter (PM<sub xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">2.5</sub>)
satellite observation
Shapley additive explanation (SHAP)
url https://ieeexplore.ieee.org/document/10963726/
work_keys_str_mv AT tongli nighttimepmsub25subconcentrationestimationbasedonnppviirsandinterpretablemachinelearningthecaseofbeijingx2013tianjinx2013hebeiregion
AT boli nighttimepmsub25subconcentrationestimationbasedonnppviirsandinterpretablemachinelearningthecaseofbeijingx2013tianjinx2013hebeiregion
AT zhihuahan nighttimepmsub25subconcentrationestimationbasedonnppviirsandinterpretablemachinelearningthecaseofbeijingx2013tianjinx2013hebeiregion
AT wenhaozhang nighttimepmsub25subconcentrationestimationbasedonnppviirsandinterpretablemachinelearningthecaseofbeijingx2013tianjinx2013hebeiregion
AT xiufengyang nighttimepmsub25subconcentrationestimationbasedonnppviirsandinterpretablemachinelearningthecaseofbeijingx2013tianjinx2013hebeiregion