Reconstructing two-decade daily high-resolution seamless global land XCO2 records using a hybrid Transformer–BiLSTM model

Abstract

Accurate and temporally continuous global observations of atmospheric carbon dioxide (XCO2) are essential for climate monitoring and emission assessment. However, satellite-based XCO2 observations are often spatially incomplete and temporally discontinuous, while existing products typically suffer from coarse spatial resolution, hindering the detection of fine-scale emission changes. Here, we developed a novel spatiotemporal Transformer–BiLSTM deep-learning network that combines the Transformer’s ability to model long-range spatial dependencies through self-attention mechanisms with the BiLSTM’s ability to capture temporal dynamics. The network assimilates multisource data from satellite observations, meteorological reanalysis, and precursor gases to reconstruct a global, daily, and seamless XCO2 dataset over land at 0.1° spatial resolution from 2003 to 2022. Independent validation of the data-fused XCO2 product against Total Carbon Column Observing Network (TCCON) measurements shows excellent agreement, with an R2 of 0.99, an RMSE of 1.10 ppm, and a mean bias of 0.01 ppm. After bias correction, cross-satellite consistency is further enhanced, achieving a sample-based CV-R2 of 0.99 and an RMSE of 0.36 ppm. The dataset provides accurate daily XCO2 estimates over global land surfaces, enabling investigations of spatial heterogeneity and regional-to-local XCO2 enhancement patterns linked to anthropogenic emissions and biomass-burning events. The record reveals a persistent global increase in atmospheric XCO2 over the past two decades, with a mean growth rate of 2.24 ppm yr−1 (p < 0.001). It reliably resolves global XCO2 variability across a wide range of temporal scales, from day-to-day fluctuations to long-term trends. It consistently captures large-scale climate-driven signals, such as ENSO-related interannual variability, and short-lived XCO2 enhancements associated with major wildfire events, demonstrating its capability to represent both persistent and episodic emission signals. This high-resolution, daily global XCO2 (GlobalHighXCO2) product provides a valuable resource for carbon-cycle research, atmospheric model evaluation, and emission monitoring, and is publicly available at https://doi.org/10.5281/zenodo.18220962 (Qu and Wei, 2026).