Full-coverage and fine-scale spatiotemporal retrieval of XCO2 in China based on OCO-2 satellite observations
Abstract
Accurate monitoring of atmospheric CO 2 is crucial for understanding climate change, but satellite observations from missions like OCO-2 have significant spatial and temporal gaps. This study addresses this challenge by developing a high-resolution, full-coverage dataset for a key emission region. We generated a 1km monthly column-averaged CO 2 (XCO 2 ) dataset for China from 2015 to 2021 using a comprehensive set of predictors, including meteorological,vegetation, and anthropogenic activity-related data. We compared four machine learning models (Random Forest, AdaBoost, ANN, and CNN) and selected the best-performing AdaBoost model, validated using 10-fold cross-validation and independent ground-based TCCON data. The AdaBoost model demonstrated superior performance (CV R 2 = 0.85), and the final product showed high accuracy against TCCON measurements (Overall R 2 = 0.93, RMSE = 1.19 ppm), demonstrating competitive or improved accuracy compared with existing products where directly comparable. The reconstructed dataset reveals significant spatiotemporal heterogeneity, with high XCO 2 concentrations in China's major industrial and urban agglomerations, a robust seasonal cycle, and a consistent upward trend. Feature importance analysis confirmed that anthropogenic emissions, meteorological conditions, and biospheric activity are the primary drivers of XCO 2 distribution. This study provides a reliable, high-resolution XCO 2 dataset that is valuable for monitoring China's carbon dynamics, verifying emission inventories, and informing climate mitigation policies.
Related
- From Plant Detection to Satellite Mapping: A Multi-Scale AI Toolkit for Ragweed Surveillance under Climate Change
- Explicit temporal inductive biases for video moment retrieval via multi-scale Gaussian priors
- MSANet: a multi-scale spatiotemporal adaptive network for EEG-based driver fatigue recognition
- Harmonizing Repeated Multi-Platform Optical and LiDAR Observations for Continental-Scale Terrestrial Carbon Cycle Data Assimilation.
- GEO-BERT: A Retrieval augmented LLM Framework for Intelligent Dataset Retrieval from the Gene Expression Omnibus
BibTeX
@article{yang2026fullcoverage,
title = {{Full-coverage and fine-scale spatiotemporal retrieval of XCO2 in China based on OCO-2 satellite observations}},
author = {Yuanyuan Yang and Qianqian Chen and Zhou Shi and Rui Lu and Xiangrui Xu},
journal = {Ecological Informatics},
year = {2026},
month = sep,
doi = {10.1016/j.ecoinf.2026.103921},
url = {https://hal.inrae.fr/hal-05747408v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Full-coverage and fine-scale spatiotemporal retrieval of XCO2 in China based on OCO-2 satellite observations
AU - Yuanyuan Yang
AU - Qianqian Chen
AU - Zhou Shi
AU - Rui Lu
AU - Xiangrui Xu
PY - 2026
DA - 2026/09/11
JO - Ecological Informatics
DO - 10.1016/j.ecoinf.2026.103921
UR - https://hal.inrae.fr/hal-05747408v1
AB - Accurate monitoring of atmospheric CO 2 is crucial for understanding climate change, but satellite observations from missions like OCO-2 have significant spatial and temporal gaps. This study addresses this challenge by developing a high-resolution, full-coverage dataset for a key emission region. We generated a 1km monthly column-averaged CO 2 (XCO 2 ) dataset for China from 2015 to 2021 using a comprehensive set of predictors, including meteorological,vegetation, and anthropogenic activity-related data. We compared four machine learning models (Random Forest, AdaBoost, ANN, and CNN) and selected the best-performing AdaBoost model, validated using 10-fold cross-validation and independent ground-based TCCON data. The AdaBoost model demonstrated superior performance (CV R 2 = 0.85), and the final product showed high accuracy against TCCON measurements (Overall R 2 = 0.93, RMSE = 1.19 ppm), demonstrating competitive or improved accuracy compared with existing products where directly comparable. The reconstructed dataset reveals significant spatiotemporal heterogeneity, with high XCO 2 concentrations in China's major industrial and urban agglomerations, a robust seasonal cycle, and a consistent upward trend. Feature importance analysis confirmed that anthropogenic emissions, meteorological conditions, and biospheric activity are the primary drivers of XCO 2 distribution. This study provides a reliable, high-resolution XCO 2 dataset that is valuable for monitoring China's carbon dynamics, verifying emission inventories, and informing climate mitigation policies.
SN - 1574-9541
ER -