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

Abstract. 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 global spCO₂ data product that is able to resolve interannual and decadal variability remains a challenge due to the spatial sparsity and temporal discontinuity of observational data. This study presents an approach based on the Vision Transformer (ViT) model, combining high-quality observational data from the CO₂ Atlas (SOCAT) with multiple advanced global ocean biogeochemical models results 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 as incorporates physical-biogeochemical constraints from the derivative of spCO₂ with respect to key controlling factors as additional features. The incorporation of advanced ocean biogeochemical models during the training process allows the ViT-based model to capture more accurate spCO₂ variability in these data-sparse regions. Evaluations demonstrate that the new data product 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 trends. The reconstructed spCO₂ demonstrates strong capability in reproducing 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. This study not only provide a new 42-year data product for advancing understanding of the ocean carbon cycle and global carbon budget assessments, but also introduces a new Transformer-based deep learning framework for Earth system data reconstruction. The data product is publicly accessible at https://doi.org/10.5281/zenodo.15331978 (Zhang et al., 2025) and will be updated regularly.