Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data

Accurate retrieval of column-averaged dry-air mole fraction of methane (XCH<sub>4</sub>) in the atmosphere is important for greenhouse gas emission management. Traditional XCH<sub>4</sub> retrieval methods are complex, while machine learning can be used to model nonlinear rel...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenhao Zhang, Yao Li, Bo Li, Tong Li, Zhengyong Wang, Xiufeng Yang, Yongtao Jin, Lili Zhang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/3/279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204130710126592
author Wenhao Zhang
Yao Li
Bo Li
Tong Li
Zhengyong Wang
Xiufeng Yang
Yongtao Jin
Lili Zhang
author_facet Wenhao Zhang
Yao Li
Bo Li
Tong Li
Zhengyong Wang
Xiufeng Yang
Yongtao Jin
Lili Zhang
author_sort Wenhao Zhang
collection DOAJ
description Accurate retrieval of column-averaged dry-air mole fraction of methane (XCH<sub>4</sub>) in the atmosphere is important for greenhouse gas emission management. Traditional XCH<sub>4</sub> retrieval methods are complex, while machine learning can be used to model nonlinear relationships by analyzing large datasets, providing an efficient alternative. This study proposes an XGBoost algorithm-based retrieval method to improve the efficiency of atmospheric XCH<sub>4</sub> retrieval. First, the key wavelengths affecting XCH<sub>4</sub> retrieval were determined using a radiative transfer model. The TROPOspheric Monitoring Instrument (TROPOMI) L1B satellite data, L2 XCH<sub>4</sub> products, and auxiliary data were matched to construct the dataset. The dataset constructed was used to train the XGBoost model and obtain the TRO_XGB_XCH<sub>4</sub> model. Finally, the accuracy of the proposed model was evaluated using various parameter values and validated against XCH<sub>4</sub> products and Total Carbon Column Observing Network (TCCON) ground-based observations. The results showed that the proposed TRO_XGB_XCH<sub>4</sub> model had a tenfold cross-validation accuracy R of 0.978, a ground-based validation R of 0.749, and a temporal extension accuracy R of 0.863. Therefore, the accuracy of the TRO_XGB_XCH<sub>4</sub> retrieval model is comparable to that of the official TROPOMI L2 product.
format Article
id doaj-art-0156c0b247eb4bf8b1b81a4a2de37398
institution OA Journals
issn 2073-4433
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-0156c0b247eb4bf8b1b81a4a2de373982025-08-20T02:11:21ZengMDPI AGAtmosphere2073-44332025-02-0116327910.3390/atmos16030279Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite DataWenhao Zhang0Yao Li1Bo Li2Tong Li3Zhengyong Wang4Xiufeng Yang5Yongtao Jin6Lili Zhang7School of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaSchool of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAccurate retrieval of column-averaged dry-air mole fraction of methane (XCH<sub>4</sub>) in the atmosphere is important for greenhouse gas emission management. Traditional XCH<sub>4</sub> retrieval methods are complex, while machine learning can be used to model nonlinear relationships by analyzing large datasets, providing an efficient alternative. This study proposes an XGBoost algorithm-based retrieval method to improve the efficiency of atmospheric XCH<sub>4</sub> retrieval. First, the key wavelengths affecting XCH<sub>4</sub> retrieval were determined using a radiative transfer model. The TROPOspheric Monitoring Instrument (TROPOMI) L1B satellite data, L2 XCH<sub>4</sub> products, and auxiliary data were matched to construct the dataset. The dataset constructed was used to train the XGBoost model and obtain the TRO_XGB_XCH<sub>4</sub> model. Finally, the accuracy of the proposed model was evaluated using various parameter values and validated against XCH<sub>4</sub> products and Total Carbon Column Observing Network (TCCON) ground-based observations. The results showed that the proposed TRO_XGB_XCH<sub>4</sub> model had a tenfold cross-validation accuracy R of 0.978, a ground-based validation R of 0.749, and a temporal extension accuracy R of 0.863. Therefore, the accuracy of the TRO_XGB_XCH<sub>4</sub> retrieval model is comparable to that of the official TROPOMI L2 product.https://www.mdpi.com/2073-4433/16/3/279XCH<sub>4</sub> retrievalsatellite remote sensingTROPOMIradiative transfer modelXGBoost
spellingShingle Wenhao Zhang
Yao Li
Bo Li
Tong Li
Zhengyong Wang
Xiufeng Yang
Yongtao Jin
Lili Zhang
Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
Atmosphere
XCH<sub>4</sub> retrieval
satellite remote sensing
TROPOMI
radiative transfer model
XGBoost
title Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
title_full Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
title_fullStr Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
title_full_unstemmed Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
title_short Retrieval of Atmospheric XCH<sub>4</sub> via XGBoost Method Based on TROPOMI Satellite Data
title_sort retrieval of atmospheric xch sub 4 sub via xgboost method based on tropomi satellite data
topic XCH<sub>4</sub> retrieval
satellite remote sensing
TROPOMI
radiative transfer model
XGBoost
url https://www.mdpi.com/2073-4433/16/3/279
work_keys_str_mv AT wenhaozhang retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT yaoli retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT boli retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT tongli retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT zhengyongwang retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT xiufengyang retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT yongtaojin retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata
AT lilizhang retrievalofatmosphericxchsub4subviaxgboostmethodbasedontropomisatellitedata