A new preprint led by Pavel Perezhogin introduces a more systematic approach to reducing biases in coarse-resolution ocean models, where key processes like mesoscale eddies are often unresolved. Rather than relying on ad hoc tuning, the study frames parameter adjustment as a calibration problem using Ensemble Kalman Inversion (EKI), applied to a neural network–based parameterization. This method significantly improves model performance — cutting errors in key ocean features and their variability by about half—while remaining robust to the noisy, chaotic nature of ocean dynamics. The results point to a practical pathway for enhancing the accuracy of global ocean simulations.