A surface ocean pCO2 product with improved representation of interannual variability using a vision transformer-based model

The ocean plays a crucial role in regulating the global carbon cycle and mitigating climate change, with the spatial distribution and temporal variations of ocean surface partial pressure of CO2 (spCO2) directly determining the air-sea CO2 flux. However, constructing a high-resolution global spCO2 dataset that is able to resolve interannual and decadal variability remains a challenge due to the spatial sparsity and temporal discontinuity of observational data. To address this, this study presents an approach based on the Vision Transformer (ViT) model, combining high-quality observational data from the CO2 Atlas (SOCAT) with global ocean biogeochemical models to reconstruct a global monthly spCO2 dataset (SJTU-AViT) at 1° resolution from 1982 to 2023. The approach employs the self-attention mechanism of the ViT model to enhance the modeling of the spatial and temporal variations of spCO2, as well incorporates physical-biogeochemical constrains from the derivative of spCO2 with respect to key controlling factors as additional features. Evaluations demonstrate that the new data product (SJTU-AViT) effectively captures spCO2 variability at both global and regional scales, showing good consistency with SOCAT observations, long-term ocean station data, and global atmospheric CO2 trend. The reconstructed spCO2 exhibits well ability to replicate the spCO2 anomalies during El Niño-Southern Oscillation (ENSO) events, particularly in the eastern Pacific Ocean, where it shows a correlation of 0.81 with the Niño 3.4 index and demonstrates high consistency with cruise data. Based on the SJTU-AViT dataset, the estimated global air-sea CO₂ flux patterns are consistent with known regional features such as strong uptake in the Southern Ocean and outgassing in the tropical Pacific. Overall, this study introduces a new global spCO₂ data product and a reconstruction method based on an Artificial Intelligence model, which substantially improves the representation of interannual and decadal variability, enhances physical consistency with key controlling factors, and accurately captures oceanic responses to climate modes such as ENSO. The resulting 42-year dataset provides a valuable resource for advancing understanding of the ocean carbon cycle and global carbon budget assessments. This dataset offers valuable data support for future ocean carbon cycle research, climate change assessment, and global carbon budget estimation.