GlobalHighXCO₂: Global Daily Seamless 10 km XCO₂ Dataset Over Land (2003–Present)

GlobalHighXCO2 is part of a series of long-term, seamless, global, high-resolution, and high-quality datasets of air pollutants over land (i.e., GlobalHighAirPollutants, GHAP). It is generated from big data sources (e.g., ground-based measurements, satellite remote sensing products, atmospheric reanalysis, and model simulations) using artificial intelligence, taking into account the spatiotemporal heterogeneity of air pollution. Here is the big data-derived gapless (spatial coverage = 100%) daily 10 km (i.e., D10K) global column-averaged dry-air mole fraction of carbon dioxide (XCO2) dataset over land from 2003 to the present. This dataset exhibits high quality, with a cross-validation coefficient of determination (CV-R²) of 0.99 and a root-mean-square error (RMSE) of 0.97 ppb on a daily basis. If you use the GlobalHighXCO2 dataset in your scientific research, please cite the following reference (Qu et al., ESSD, 2026): Qu, Y., Shi, X., Fan, Y., Wang, Z., and Wei, J. Reconstructing two-decade daily high-resolution seamless global land XCO2 records using a hybrid Transformer–BiLSTM model. Earth System Science Data, 2026, 18, 4279–4301. https://doi.org/10.5194/essd-18-4279-2026