Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling
This work addresses the challenge of tuning uncertain parameterizations in ocean simulations for climate researchers, though it is incremental in applying ensemble methods to existing neural surrogate approaches.
The paper tackled the problem of quantifying parametric sensitivities in ocean modeling by developing ensembles of neural surrogates, resulting in improved reliability for forward predictions and sensitivity estimates with epistemic uncertainty.
Accurate simulations of the oceans are crucial in understanding the Earth system. Despite their efficiency, simulations at lower resolutions must rely on various uncertain parameterizations to account for unresolved processes. However, model sensitivity to parameterizations is difficult to quantify, making it challenging to tune these parameterizations to reproduce observations. Deep learning surrogates have shown promise for efficient computation of the parametric sensitivities in the form of partial derivatives, but their reliability is difficult to evaluate without ground truth derivatives. In this work, we leverage large-scale hyperparameter search and ensemble learning to improve both forward predictions, autoregressive rollout, and backward adjoint sensitivity estimation. Particularly, the ensemble method provides epistemic uncertainty of function value predictions and their derivatives, providing improved reliability of the neural surrogates in decision making.