Reconstructing annual XCO₂ at a 1 km×1 km spatial resolution across China from 2012 to 2019 based on a spatial...

Long-time-series, high-resolution datasets of the column-averaged dry-air mole fraction of carbon dioxide (XCO₂) have great practical importance for mitigating the greenhouse effect, assessing carbon emissions and implementing a low-carbon cycle. However, the mainstream XCO₂ datasets obtained from satellite observations have coarse spatial resolutions and are inadequate for supporting research applications with different precision requirements. Here, we developed a new spatial machine learning model by fusing spatial information with CatBoost, called SCatBoost, to fill the above gap based on existing global land-mapped 1° XCO₂ data (GLM-XCO₂). The 1-km-spatial-resolution dataset containing XCO₂ values in China from 2012 to 2019 reconstructed by SCatBoost has stronger and more stable predictive power (confirmed with a cross-validation (R² = 0.88 and RSME = 0.20 ppm)) than other traditional models. According to the estimated dataset, the overall national XCO₂ showed an increasing trend, with the annual mean concentration rising from 392.65 ppm to 410.36 ppm. In addition, the spatial distribution of XCO₂ concentrations in China reflects significantly higher concentrations in the eastern coastal areas than in the western inland areas. The contributions of this study can be summarized as follows: (1) It proposes SCatBoost, integrating the advantages of machine learning methods and spatial characteristics with a high prediction accuracy; (2) It presents a dataset of fine-scale and high resolution XCO₂ over China from 2012 to 2019 by the model of SCatBoost; (3) Based on the generated data, we identify the spatiotemporal trends of XCO₂ in the scale of nation and city agglomeration. These long-term and high resolution XCO₂ data help understand the spatiotemporal variations in XCO₂, thereby improving policy decisions and planning about carbon reduction.