Saved in:
Bibliographic Details
Main Authors: Holmberg, Daniel, Clementi, Emanuela, Epicoco, Italo, Roos, Teemu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.23900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909667314106368
author Holmberg, Daniel
Clementi, Emanuela
Epicoco, Italo
Roos, Teemu
author_facet Holmberg, Daniel
Clementi, Emanuela
Epicoco, Italo
Roos, Teemu
contents Accurate ocean forecasting systems are essential for understanding marine dynamics, which play a crucial role in sectors such as shipping, aquaculture, environmental monitoring, and coastal risk management. Traditional numerical solvers, while effective, are computationally expensive and time-consuming. Recent advancements in machine learning have revolutionized weather forecasting, offering fast and energy-efficient alternatives. Building on these advancements, we introduce SeaCast, a neural network designed for high-resolution regional ocean forecasting. SeaCast employs a graph-based framework to effectively handle the complex geometry of ocean grids and integrates external forcing data tailored to the regional ocean context. Our approach is validated through experiments at a high horizontal resolution using the operational numerical forecasting system of the Mediterranean Sea, along with both numerical and data-driven atmospheric forcings. Results demonstrate that SeaCast consistently outperforms the operational model in forecast skill, marking a significant advancement in regional ocean prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accurate Mediterranean Sea forecasting via graph-based deep learning
Holmberg, Daniel
Clementi, Emanuela
Epicoco, Italo
Roos, Teemu
Atmospheric and Oceanic Physics
Accurate ocean forecasting systems are essential for understanding marine dynamics, which play a crucial role in sectors such as shipping, aquaculture, environmental monitoring, and coastal risk management. Traditional numerical solvers, while effective, are computationally expensive and time-consuming. Recent advancements in machine learning have revolutionized weather forecasting, offering fast and energy-efficient alternatives. Building on these advancements, we introduce SeaCast, a neural network designed for high-resolution regional ocean forecasting. SeaCast employs a graph-based framework to effectively handle the complex geometry of ocean grids and integrates external forcing data tailored to the regional ocean context. Our approach is validated through experiments at a high horizontal resolution using the operational numerical forecasting system of the Mediterranean Sea, along with both numerical and data-driven atmospheric forcings. Results demonstrate that SeaCast consistently outperforms the operational model in forecast skill, marking a significant advancement in regional ocean prediction.
title Accurate Mediterranean Sea forecasting via graph-based deep learning
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2506.23900