The carbon dioxide fugacity in the global oceans has shown a slow upward trend, over the past 20 years, the carbon dioxide fugacity in global oceans has increased by 6.7%.This conclusion is based on over 160,000 quality-controlled measurements of surface ocean carbon dioxide fugacity from 2000 to 2020, and employing machine learning methods, a satellite-based assessment model for sea-air carbon dioxide fugacity (fCO2) has been developed, aiming to reveal global changes in fCO2 over the past 20 years. This study investigates the factors influencing sea-air carbon dioxide fugacity (fCO₂) by integrating a comprehensive dataset, including satellite data coordinates, fundamental seawater parameters (e.g., salinity and temperature), wind speed, seawater acidity and alkalinity, seawater velocity, geostrophic seawater velocity, surface partial pressure of carbon dioxide in seawater, downward mass flux of carbon dioxide expressed as carbon, concentrations of dissolved inorganic carbon, phosphate, nitrate, silicate, chlorophyll, and dissolved oxygen. A comparative analysis was conducted among various machine learning methods, such as XGBoost, Random Forest, Light Gradient Booster, Feedforward Neural Network, Convolutional Neural Network, and Backpropagation Neural Network. Based on the best performance, the XGBoost algorithm was selected for model construction. The results of independent field validation demonstrate that the model has a low root mean square error (RMSE = 18.08 μatm), mean absolute percentage error (MAPE = 1.1%), and a high coefficient of determination (R² = 0.91). Ultimately, the global distribution of sea-air carbon dioxide fugacity at a resolution of 0.25° × 0.25° from 2000 to 2020 was reconstructed.
Ji L. Y., Wu S. H., Liu K. X., Zhou L. W., Wang J. L. & Cui L., 2025. A global upward trend in ocean-atmosphere carbon dioxide fugacity. ESS Open Archive. Article.
