China has set a goal to achieve carbon neutrality by 2060, and satellite remote sensing allows for acquiring large-range and high-resolution carbon dioxide (CO2) data, which can aid in achieving this goal. However, satellite-derived column-averaged dry-air mole fraction of CO2 (XCO2) products often suffer from substantial spatial gaps due to the impacts of narrow swath and clouds. Here, this paper generates daily full-coverage XCO2 data at a high spatial resolution of 0.1° over China during 2015–2020, by fusing satellite observations and reanalysis data in a deep neural network (DNN) framework. Specifically, DNN constructs the relationships between Orbiting Carbon Observatory-2 satellite XCO2 retrievals, Copernicus Atmosphere Monitoring Service (CAMS) XCO2 reanalysis data, and environmental factors. Then, daily full-coverage XCO2 data can be generated based on CAMS XCO2 and environmental factors. Results show that a satisfactory performance is reported in multiform validations, with RMSE and R2 of 0.99 ppm and 0.963 in terms of the sample-based cross-validation, respectively. The independent in-situ validation also indicates high consistency (R2 = 0.866 and RMSE = 1.71 ppm) between XCO2 estimates and ground measurements. Based on the generated dataset, spatial and seasonal distributions of XCO2 across China are investigated, and a growth rate of 2.71 ppm/yr is found from 2015 to 2020. This paper generates long time series of full-coverage XCO2 data, which helps promote our understanding of carbon cycling. The dataset is available from https://doi.org/10.5281/zenodo.7793917.
Read full abstract