Regional Ocean Forecasting with Hierarchical Graph Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Holmberg, Daniel, Clementi, Emanuela, Roos, Teemu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909396882161664
author Holmberg, Daniel
Clementi, Emanuela
Roos, Teemu
author_facet Holmberg, Daniel
Clementi, Emanuela
Roos, Teemu
contents Accurate ocean forecasting systems are vital for understanding marine dynamics, which play a crucial role in environmental management and climate adaptation strategies. 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, medium-range 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 spatial resolution using the operational numerical model of the Mediterranean Sea provided by the Copernicus Marine Service, along with both numerical and data-driven atmospheric forcings.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11807
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Regional Ocean Forecasting with Hierarchical Graph Neural Networks
Holmberg, Daniel
Clementi, Emanuela
Roos, Teemu
Atmospheric and Oceanic Physics
Machine Learning
Accurate ocean forecasting systems are vital for understanding marine dynamics, which play a crucial role in environmental management and climate adaptation strategies. 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, medium-range 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 spatial resolution using the operational numerical model of the Mediterranean Sea provided by the Copernicus Marine Service, along with both numerical and data-driven atmospheric forcings.
title Regional Ocean Forecasting with Hierarchical Graph Neural Networks
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2410.11807