A full-coverage daily XCO₂ dataset in China from 2015 to 2020 based on DSC-DF-LGB

Abstract. Carbon dioxide (CO₂), as a major greenhouse gas, is one of the important causes of global warming. In recent years, the atmospheric CO₂ concentration in China has been increasing year by year. Satellite observation is the main means of obtaining atmospheric CO₂ concentration. However, the current onboard sensors used for measuring atmospheric CO₂ have a narrow observation range and cannot obtain spatiotemporal continuous atmospheric CO₂ concentrations. Therefore, this paper proposes a daily full-coverage XCO₂ dataset generation method based on the DSC-DF-LGB (Deep Separable Convolutional Neural Network and Deep Forest concatenated with LightGBM) model to obtain the spatiotemporal distribution of atmospheric CO₂ in China. The DSC-DF-LGB model was established to train the mapping relationship between OCO-2 XCO₂ retrieval and related variables (reanalysis XCO₂, vegetation parameters, human factors, elevation, and meteorological parameters). The model was used to generate a daily 0.1° full-coverage XCO₂ dataset for China from 2015 to 2020. The cross validation (CV) result indicates that the model has strong performance in estimating XCO₂, with R² and RMSE of 0.9633 and 0.9761 ppm. The TCCON independent site validation result indicates that the estimated XCO₂ has high consistency with in-situ measurements, with R² and RMSE of 0.8786 and 1.5452 ppm. The full-coverage and high-resolution XCO₂ dataset can provide data support for research on carbon sources and sinks. The dataset is available at https://zenodo.org/doi/10.5281/zenodo.12696674 (Huang, 2024).