Metraipolis › archive › dc_19e1aebd2c73
OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation — arXiv:2608.16070
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16070
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:06:55.293Z
- SHA-256 of the archived text
633f078c049ea5cf2479755d82bca0c5dcf891299f4df0bd4fedf4df716a25fe- Stable URL of this page
https://metraipolis.com/documento/dc_19e1aebd2c73
How to cite
OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation — arXiv:2608.16070 — arXiv (en), https://arxiv.org/abs/2608.16070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19e1aebd2c73 (Metraipolis archive dc_19e1aebd2c73, sha256 633f078c049ea5cf2479755d82bca0c5dcf891299f4df0bd4fedf4df716a25fe)
BibTeX
@misc{dc19e1aebd2c73,
title = {OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation — arXiv:2608.16070},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16070},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19e1aebd2c73; sha256 633f078c049ea5cf2479755d82bca0c5dcf891299f4df0bd4fedf4df716a25fe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable global ocean forecasting is critical for climate monitoring, marine navigation, and extreme event early warning. Physics-based ocean forecasting models impose prohibitive computational costs, while existing deep learning approaches predominantly rely on structured-grid architectures, incurring unnecessary computation on masked land cells and enforcing uniform resolution across dynamically heterogeneous ocean regions regardless of local flow complexity. Here we present OceanLight, an efficient global ocean forecasting framework innovatively combining geometry-adaptive unstructured mesh tokenization with a graph neural network (GNN) backbone. OceanLight achieves pointwise forecast accuracy and kinetic energy spectral fidelity exceeding both operational numerical analyses and state-of-the-art AI-based models, while surpassing all AI-based ocean models in geostrophic balance consistency. Furthermore, OceanLight demonstrates reliable mesoscale eddy representation, capturing coherent ocean structures beyond pointwise statistical optimization. These capabilities are delivered with a 62% reduction in GPU memory consumption and 70\% reduction in FLOPs relative to structured-grid baselines. Our unstructured mesh representation establishes a generalizable paradigm for scalable data-driven oceanography. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16070 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:14.073Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).