An online-learned eddy parameterization in a differentiable shallow water model
Ocean general circulation models rely on parameterizations to approximate subgrid-scale processes. While parameterizations are traditionally physics-based, machine learning has recently provided an alternative, data-driven approach for developing parameterizations. However, most machine learning-based parameterizations are learned offline due to the lack of differentiable general circulation models. Here, we train an eddy momentum parameterization represented by a neural network online in an idealized barotropic gyre model. We develop the model as fully differentiable in Julia with the automatic differentiation tool Enzyme. The network weights are trained using a loss function that has the same form as in adjoint-based data assimilation, with synthetic observations generated by a fine-resolution simulation. A range of diagnostics evaluate the performance of the parameterized coarse-resolution model. We find improved energetics, physically realistic dynamics, and numerical stability for multi-decadal roll-outs. Importantly, the online-learned parameterization absorbs artifacts from the numerical discretization, such as the time-stepping scheme used, which is invisible to offline-learned parameterizations. We suggest that this is key to improved numerical stability of machine-learned parameterizations. Our research suggests that online-trained neural network parameterizations can be an effective solution to the subgrid-scale parameterization and model calibration problem.
Authors
- Sri Hari Krishna Narayanan (ORCID: https://orcid.org/0000-0003-0388-5943)
- Michel Schanen (ORCID: https://orcid.org/0000-0002-4164-027X)
- Sarah Williamson (ORCID: https://orcid.org/0000-0002-0583-1546)
- Patrick Heimbach (ORCID: https://orcid.org/0000-0003-3925-6161)
- Chihiro Kodama (ORCID: https://orcid.org/0000-0001-8252-7479)
- Nora Loose (ORCID: https://orcid.org/0000-0002-3684-9634)
- William S. Moses (ORCID: https://orcid.org/0000-0003-2627-0642)
- Valentin Churavy (ORCID: https://orcid.org/0000-0002-9033-165X)
Institutions
- Argonne National Laboratory (US)
- University of Illinois Urbana-Champaign (US)
- Bjerknes Centre for Climate Research (NO)
- University of Oxford (GB)
- Nansen International Environmental and Remote Sensing Center (RU)
- Nansen Environmental and Remote Sensing Center (NO)
- The University of Texas at Austin (US)
- Saarland University (DE)
Publication Details
- Published
- 2026-11-12
- DOI
- https://doi.org/10.22541/essoar.15012107/v1
- Primary Topic
- Oceanographic and Atmospheric Processes
- Type
- preprint