Towards fully differentiable neural ocean model with Veros
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909916385509376 |
|---|---|
| author | Meunier, Etienne Ouala, Said Frezat, Hugo Sommer, Julien Le Fablet, Ronan |
| author_facet | Meunier, Etienne Ouala, Said Frezat, Hugo Sommer, Julien Le Fablet, Ronan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17427 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards fully differentiable neural ocean model with Veros Meunier, Etienne Ouala, Said Frezat, Hugo Sommer, Julien Le Fablet, Ronan Machine Learning 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. |
| title | Towards fully differentiable neural ocean model with Veros |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.17427 |