XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models
Carbon dioxide (CO<sub>2</sub>) is a key driver of global climate change. Since the Industrial Revolution, the rapid rise in atmospheric CO<sub>2</sub> levels has significantly intensified global warming and climate-related issues. To accurately and promptly monitor changes i...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/48 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549009580195840 |
|---|---|
| author | Ruizhi Chen Zhongting Wang Chunyan Zhou Ruijie Zhang Huizhen Xie Huayou Li |
| author_facet | Ruizhi Chen Zhongting Wang Chunyan Zhou Ruijie Zhang Huizhen Xie Huayou Li |
| author_sort | Ruizhi Chen |
| collection | DOAJ |
| description | Carbon dioxide (CO<sub>2</sub>) is a key driver of global climate change. Since the Industrial Revolution, the rapid rise in atmospheric CO<sub>2</sub> levels has significantly intensified global warming and climate-related issues. To accurately and promptly monitor changes in CO<sub>2</sub> concentrations and to support the development of climate policies, this study proposes a method based on random forest models to generate a continuous monthly dataset of CO<sub>2</sub> column concentration (XCO<sub>2</sub>) across the entire Chinese region from 2004 to 2023. The study integrates XCO<sub>2</sub> satellite observations from SCIAMACHY, GOSAT, OCO-2, and GF-5B, alongside nighttime light remote sensing data, meteorological parameters, vegetation indices, and CO<sub>2</sub> profile data. Using the random forest algorithm, a complex relationship model was established between XCO<sub>2</sub> concentrations and various environmental variables. The goal of this model is to provide XCO<sub>2</sub> estimates with enhanced spatial coverage and accuracy. The XCO<sub>2</sub> concentrations predicted by the model show a high level of consistency with satellite observations, achieving a correlation coefficient (R-value) of 0.9959 and a root mean square error (RMSE) of 1.1631 ppm. This indicates that the model offers strong predictive accuracy and generalization ability. Additionally, ground-based validation further confirmed the model’s effectiveness, with a correlation coefficient (R-value) of 0.956 when compared with TCCON site observation data. |
| format | Article |
| id | doaj-art-9d3691a85cc54d5c844cd43d93a16fe0 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-9d3691a85cc54d5c844cd43d93a16fe02025-01-10T13:20:03ZengMDPI AGRemote Sensing2072-42922024-12-011714810.3390/rs17010048XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest ModelsRuizhi Chen0Zhongting Wang1Chunyan Zhou2Ruijie Zhang3Huizhen Xie4Huayou Li5Chinese Research Academy of Environmental Sciences, Beijing 100012, ChinaSatellite Application Center for Ecology and Environment, Ministry of Ecology and Environment, Beijing 100094, ChinaSatellite Application Center for Ecology and Environment, Ministry of Ecology and Environment, Beijing 100094, ChinaChinese Research Academy of Environmental Sciences, Beijing 100012, ChinaSatellite Application Center for Ecology and Environment, Ministry of Ecology and Environment, Beijing 100094, ChinaSatellite Application Center for Ecology and Environment, Ministry of Ecology and Environment, Beijing 100094, ChinaCarbon dioxide (CO<sub>2</sub>) is a key driver of global climate change. Since the Industrial Revolution, the rapid rise in atmospheric CO<sub>2</sub> levels has significantly intensified global warming and climate-related issues. To accurately and promptly monitor changes in CO<sub>2</sub> concentrations and to support the development of climate policies, this study proposes a method based on random forest models to generate a continuous monthly dataset of CO<sub>2</sub> column concentration (XCO<sub>2</sub>) across the entire Chinese region from 2004 to 2023. The study integrates XCO<sub>2</sub> satellite observations from SCIAMACHY, GOSAT, OCO-2, and GF-5B, alongside nighttime light remote sensing data, meteorological parameters, vegetation indices, and CO<sub>2</sub> profile data. Using the random forest algorithm, a complex relationship model was established between XCO<sub>2</sub> concentrations and various environmental variables. The goal of this model is to provide XCO<sub>2</sub> estimates with enhanced spatial coverage and accuracy. The XCO<sub>2</sub> concentrations predicted by the model show a high level of consistency with satellite observations, achieving a correlation coefficient (R-value) of 0.9959 and a root mean square error (RMSE) of 1.1631 ppm. This indicates that the model offers strong predictive accuracy and generalization ability. Additionally, ground-based validation further confirmed the model’s effectiveness, with a correlation coefficient (R-value) of 0.956 when compared with TCCON site observation data.https://www.mdpi.com/2072-4292/17/1/48carbon dioxiderandom forestatmospheric remote sensingChinese regionGF-5B |
| spellingShingle | Ruizhi Chen Zhongting Wang Chunyan Zhou Ruijie Zhang Huizhen Xie Huayou Li XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models Remote Sensing carbon dioxide random forest atmospheric remote sensing Chinese region GF-5B |
| title | XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models |
| title_full | XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models |
| title_fullStr | XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models |
| title_full_unstemmed | XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models |
| title_short | XCO<sub>2</sub> Data Full-Coverage Mapping in China Based on Random Forest Models |
| title_sort | xco sub 2 sub data full coverage mapping in china based on random forest models |
| topic | carbon dioxide random forest atmospheric remote sensing Chinese region GF-5B |
| url | https://www.mdpi.com/2072-4292/17/1/48 |
| work_keys_str_mv | AT ruizhichen xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels AT zhongtingwang xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels AT chunyanzhou xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels AT ruijiezhang xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels AT huizhenxie xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels AT huayouli xcosub2subdatafullcoveragemappinginchinabasedonrandomforestmodels |