paper-with-me

홈 › Papers

Towards fully differentiable neural ocean model with Veros

2025-11-21 · Etienne Meunier, Said Ouala, Hugo Frezat, Julien Le Sommer, Ronan Fablet arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.17427

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NeuralOGCM: Differentiable Ocean Modeling with Learnable Physics

2025-12-12 · Hao Wu, Yuan Gao, Fan Xu, Fan Zhang 외 arxiv

High-precision scientific simulation faces a long-standing trade-off between computational efficiency and physical fidelity. To address this challenge, we propose NeuralOGCM, an ocean modeling framework that fuses differ…

Computational Efficiency

KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting

2026-06-06 · Qinghui Chen, Zekai Zhang, Hailong Liu, Jinglin Zhang 외 arxiv

Accurate oceanic forecasting is critical for climate monitoring and disaster early warning. However, ocean spatiotemporal forecasting encounters the double challenges of modeling complex dynamical systems and ensuring co…

Computational Efficiency

Learning Generalized Quasi-Geostrophic Models Using Deep Neural Numerical Models

2019-11-20 · Redouane Lguensat, Julien Le Sommer, Sammy Metref, Emmanuel Cosme 외

We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems. We propose to use machine learning automatic differentiation libraries to develop hybrid numerical models that com…

Adjoint-based online learning of two-layer quasi-geostrophic baroclinic turbulence

2024-11-21 · Fei Er Yan, Hugo Frezat, Julien Le Sommer, Julian Mak 외

For reasons of computational constraint, most global ocean circulation models used for Earth System Modeling still rely on parameterizations of sub-grid processes, and limitations in these parameterizations affect the mo…

AxiomOcean: Forecasting the Three-Dimensional Structure of the Upper Ocean

2026-05-11 · Sensen Wu, Yifan Chen, Guantao Pu, Xiaoyao Sun 외 arxiv

Short-term ocean forecast skill depends strongly on the three-dimensional ocean structure of the upper ocean, which governs stratification, subsurface heat storage, and the response of the ocean to atmospheric forcing. H…