Random Forest-Based Retrieval of XCO<sub>2</sub> Concentration from Satellite-Borne Shortwave Infrared Hyperspectral

Random Forest-Based Retrieval of XCO<sub>2</sub> Concentration from Satellite-Borne Shortwave Infrared Hyperspectral

As carbon dioxide (CO<sub>2</sub>) concentrations continue to rise, climate change, characterized by global warming, presents a significant challenge to global sustainable development. Currently, most global shortwave infrared CO<sub>2</sub> retrievals rely on fully physical...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenhao Zhang, Zhengyong Wang, Tong Li, Bo Li, Yao Li, Zhihua Han
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Atmosphere
Subjects:
carbon dioxide
machine learning
shortwave infrared
TCCON
Online Access:https://www.mdpi.com/2073-4433/16/3/238
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As carbon dioxide (CO<sub>2</sub>) concentrations continue to rise, climate change, characterized by global warming, presents a significant challenge to global sustainable development. Currently, most global shortwave infrared CO<sub>2</sub> retrievals rely on fully physical retrieval algorithms, for which complex calculations are necessary. This paper proposes a method to predict the concentration of column-averaged CO<sub>2</sub> (XCO<sub>2</sub>) from shortwave infrared hyperspectral satellite data, using machine learning to avoid the iterative computations of the physical method. The training dataset is constructed using the Orbiting Carbon Observatory-2 (OCO-2) spectral data, XCO<sub>2</sub> retrievals from OCO-2, surface albedo data, and aerosol optical depth (AOD) measurements for 2019. This study employed a variety of machine learning algorithms, including Random Forest, XGBoost, and LightGBM, for the analysis. The results showed that Random Forest outperforms the other models, achieving a correlation of 0.933 with satellite products, a mean absolute error (MAE) of 0.713 ppm, and a root mean square error (RMSE) of 1.147 ppm. This model was then applied to retrieve CO<sub>2</sub> column concentrations for 2020. The results showed a correlation of 0.760 with Total Carbon Column Observing Network (TCCON) measurements, which is higher than the correlation of 0.739 with satellite product data, verifying the effectiveness of the retrieval method.
ISSN:2073-4433

Similar Items