Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods

The satellite remote sensing of Aerosol Optical Depth (AOD) products is crucial in environmental monitoring and atmospheric pollution research. However, data gaps in AOD products from satellites like Fengyun significantly hinder continuous, seamless environmental monitoring capabilities, posing chal...

Full description

Saved in:
Bibliographic Details
Main Authors: Huifang Wang, Min Wang, Pan Jiang, Fanshu Ma, Yanhu Gao, Xinchen Gu, Qingzu Luan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/6/655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467565255950336
author Huifang Wang
Min Wang
Pan Jiang
Fanshu Ma
Yanhu Gao
Xinchen Gu
Qingzu Luan
author_facet Huifang Wang
Min Wang
Pan Jiang
Fanshu Ma
Yanhu Gao
Xinchen Gu
Qingzu Luan
author_sort Huifang Wang
collection DOAJ
description The satellite remote sensing of Aerosol Optical Depth (AOD) products is crucial in environmental monitoring and atmospheric pollution research. However, data gaps in AOD products from satellites like Fengyun significantly hinder continuous, seamless environmental monitoring capabilities, posing challenges for the long-term analysis of atmospheric pollution trends, responses to sudden ecological events, and disaster management. This study aims to develop a high-precision method to fill spatial AOD missing values and generate daily full-coverage AOD products for the Beijing–Tianjin–Hebei region in 2021 by integrating multi-dimensional data, including meteorological models, multi-source remote sensing, surface conditions, and nighttime light parameters, and applying machine learning methods. A comparison of five machine learning models showed that the random forest model performed optimally in AOD inversion, achieving a root mean square error (RMSE) of 0.11 and a coefficient of determination (R<sup>2</sup>) of 0.93. Seasonal evaluation further indicated that the model’s simulation was best in winter. Variable importance analysis identified relative humidity (RH) as the most critical factor influencing model results. The reconstructed full-coverage AOD product exhibited a spatial distribution trend of significantly higher values in the southern plain areas compared to mountainous regions, consistent with the actual aerosol distribution patterns in the Beijing–Tianjin–Hebei area. Moreover, the product demonstrated overall smoothness and high accuracy. This research lays the foundation for establishing a long-term, 1 km resolution, daily spatially continuous AOD product for the Beijing–Tianjin–Hebei region and beyond, providing more robust data support for addressing regional and larger-scale environmental challenges.
format Article
id doaj-art-01d4fd567e484321a9e5607bcbe71ca5
institution Kabale University
issn 2073-4433
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-01d4fd567e484321a9e5607bcbe71ca52025-08-20T03:26:10ZengMDPI AGAtmosphere2073-44332025-05-0116665510.3390/atmos16060655Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning MethodsHuifang Wang0Min Wang1Pan Jiang2Fanshu Ma3Yanhu Gao4Xinchen Gu5Qingzu Luan6Beijng Municipal Climate Center, Beijing 100089, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Economics and Management, Southwest University of Science and Technology, Mianyang 621010, ChinaBeijng Municipal Climate Center, Beijing 100089, ChinaBeijng Municipal Climate Center, Beijing 100089, ChinaSchool of Architectural Engineering, Tianjin University, Tianjin 300072, ChinaBeijng Municipal Climate Center, Beijing 100089, ChinaThe satellite remote sensing of Aerosol Optical Depth (AOD) products is crucial in environmental monitoring and atmospheric pollution research. However, data gaps in AOD products from satellites like Fengyun significantly hinder continuous, seamless environmental monitoring capabilities, posing challenges for the long-term analysis of atmospheric pollution trends, responses to sudden ecological events, and disaster management. This study aims to develop a high-precision method to fill spatial AOD missing values and generate daily full-coverage AOD products for the Beijing–Tianjin–Hebei region in 2021 by integrating multi-dimensional data, including meteorological models, multi-source remote sensing, surface conditions, and nighttime light parameters, and applying machine learning methods. A comparison of five machine learning models showed that the random forest model performed optimally in AOD inversion, achieving a root mean square error (RMSE) of 0.11 and a coefficient of determination (R<sup>2</sup>) of 0.93. Seasonal evaluation further indicated that the model’s simulation was best in winter. Variable importance analysis identified relative humidity (RH) as the most critical factor influencing model results. The reconstructed full-coverage AOD product exhibited a spatial distribution trend of significantly higher values in the southern plain areas compared to mountainous regions, consistent with the actual aerosol distribution patterns in the Beijing–Tianjin–Hebei area. Moreover, the product demonstrated overall smoothness and high accuracy. This research lays the foundation for establishing a long-term, 1 km resolution, daily spatially continuous AOD product for the Beijing–Tianjin–Hebei region and beyond, providing more robust data support for addressing regional and larger-scale environmental challenges.https://www.mdpi.com/2073-4433/16/6/655FY-3D/4AAODHi-8AHIModisHGALSSmachine learning algorithms
spellingShingle Huifang Wang
Min Wang
Pan Jiang
Fanshu Ma
Yanhu Gao
Xinchen Gu
Qingzu Luan
Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
Atmosphere
FY-3D/4A
AODHi-8
AHI
Modis
HGALSS
machine learning algorithms
title Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
title_full Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
title_fullStr Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
title_full_unstemmed Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
title_short Research on Time Series Interpolation and Reconstruction of Multi-Source Remote Sensing AOD Product Data Using Machine Learning Methods
title_sort research on time series interpolation and reconstruction of multi source remote sensing aod product data using machine learning methods
topic FY-3D/4A
AODHi-8
AHI
Modis
HGALSS
machine learning algorithms
url https://www.mdpi.com/2073-4433/16/6/655
work_keys_str_mv AT huifangwang researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT minwang researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT panjiang researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT fanshuma researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT yanhugao researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT xinchengu researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods
AT qingzuluan researchontimeseriesinterpolationandreconstructionofmultisourceremotesensingaodproductdatausingmachinelearningmethods