{"ID":2838708,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17427","arxiv_id":"2511.17427","title":"Towards fully differentiable neural ocean model with Veros","abstract":"We present a differentiable extension of the VEROS ocean model, enabling automatic differentiation through its dynamical core. We describe the key modifications required to make the model fully compatible with JAX autodifferentiation framework and evaluate the numerical consistency of the resulting implementation. Two illustrative applications are then demonstrated: (i) the correction of an initial ocean state through gradient-based optimization, and (ii) the calibration of unknown physical parameters directly from model observations. These examples highlight how differentiable programming can facilitate end-to-end learning and parameter tuning in ocean modeling. Our implementation is available online.","short_abstract":"We present a differentiable extension of the VEROS ocean model, enabling automatic differentiation through its dynamical core. We describe the key modifications required to make the model fully compatible with JAX autodifferentiation framework and evaluate the numerical consistency of the resulting implementation. Two...","url_abs":"https://arxiv.org/abs/2511.17427","url_pdf":"https://arxiv.org/pdf/2511.17427v1","authors":"[\"Etienne Meunier\",\"Said Ouala\",\"Hugo Frezat\",\"Julien Le Sommer\",\"Ronan Fablet\"]","published":"2025-11-21T17:24:00Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}