This work is dedicated to a new model that reconstructs the surface ocean partial pressure of carbon dioxide (pCO₂) over the global ocean on a monthly 1°×1° grid. The model is based on a feed-forward neural network and represents the nonlinear relationships between pCO₂ and the ocean drivers. Reconstructed pCO₂ has a satisfying accuracy compared to independent observational data and shows a good agreement in seasonal and interannual variability with three existing mapping methods.