Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet

IntroductionMarine forecasts play a crucial role in ensuring safe navigation, efficient offshore operations, coastal management, and research, particularly in regions with challenging conditions like the Arctic Ocean. These forecasts necessitate precise predictions of ocean currents, wind-driven wav...

Full description

Saved in:
Bibliographic Details
Main Authors: Aleksei V. Buinyi, Dias A. Irishev, Edvard E. Nikulin, Aleksandr A. Evdokimov, Polina G. Ilyushina, Natalia A. Sukhikh
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-11-01
Series:Frontiers in Marine Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmars.2024.1456480/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199331316957184
author Aleksei V. Buinyi
Aleksei V. Buinyi
Dias A. Irishev
Edvard E. Nikulin
Aleksandr A. Evdokimov
Polina G. Ilyushina
Natalia A. Sukhikh
Natalia A. Sukhikh
author_facet Aleksei V. Buinyi
Aleksei V. Buinyi
Dias A. Irishev
Edvard E. Nikulin
Aleksandr A. Evdokimov
Polina G. Ilyushina
Natalia A. Sukhikh
Natalia A. Sukhikh
author_sort Aleksei V. Buinyi
collection DOAJ
description IntroductionMarine forecasts play a crucial role in ensuring safe navigation, efficient offshore operations, coastal management, and research, particularly in regions with challenging conditions like the Arctic Ocean. These forecasts necessitate precise predictions of ocean currents, wind-driven waves, and various other oceanic parameters. Although physics-based numerical models are highly accurate, they come with significant computational requirements. Therefore, data-driven approaches, which are less computationally intensive, may present a more effective solution for predicting sea conditions.MethodsThis study introduces a detailed analysis and comparison of three data-driven models: the newly developed convLSTM-based MariNet, FourCastNet, and PhydNet, a physics-informed model designed for video prediction. Through the utilization of metrics such as RMSE, Bias, and Correlation, we illustrate the areas in which our model outperforms well-known prediction models.ResultsOur model demonstrates enhanced accuracy in forecasting ocean dynamics when compared to FourCastNet and PhyDNet. Additionally, our findings reveal that our model demands significantly less training data and computational resources, ultimately resulting in lower carbon emissions.DiscussionThese findings indicate the potential for further exploration of data-driven models as a supplement to physics-based models in operational marine forecasting, as they have the capability to improve prediction accuracy and efficiency, thereby facilitating more responsive and cost-effective forecasting systems.
format Article
id doaj-art-8b58e8d0a7854049b4b24d7d1d59b229
institution OA Journals
issn 2296-7745
language English
publishDate 2024-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Marine Science
spelling doaj-art-8b58e8d0a7854049b4b24d7d1d59b2292025-08-20T02:12:38ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-11-011110.3389/fmars.2024.14564801456480Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNetAleksei V. Buinyi0Aleksei V. Buinyi1Dias A. Irishev2Edvard E. Nikulin3Aleksandr A. Evdokimov4Polina G. Ilyushina5Natalia A. Sukhikh6Natalia A. Sukhikh7Research and Development Department, Marine Information Technologies LLC, Moscow, RussiaDepartment of Hydrometeorological Modeling, Lomonosov Moscow State University Marine Research Center (LMSU MRC), Moscow, RussiaResearch and Development Department, Marine Information Technologies LLC, Moscow, RussiaResearch and Development Department, Marine Information Technologies LLC, Moscow, RussiaDepartment of Hydrometeorological Research, Lomonosov Moscow State University Marine Research Center (LMSU MRC), Moscow, RussiaGeoinformation Technologies Department, Lomonosov Moscow State University Marine Research Center (LMSU MRC), Moscow, RussiaResearch and Development Department, Marine Information Technologies LLC, Moscow, RussiaDepartment of Hydrometeorological Modeling, Lomonosov Moscow State University Marine Research Center (LMSU MRC), Moscow, RussiaIntroductionMarine forecasts play a crucial role in ensuring safe navigation, efficient offshore operations, coastal management, and research, particularly in regions with challenging conditions like the Arctic Ocean. These forecasts necessitate precise predictions of ocean currents, wind-driven waves, and various other oceanic parameters. Although physics-based numerical models are highly accurate, they come with significant computational requirements. Therefore, data-driven approaches, which are less computationally intensive, may present a more effective solution for predicting sea conditions.MethodsThis study introduces a detailed analysis and comparison of three data-driven models: the newly developed convLSTM-based MariNet, FourCastNet, and PhydNet, a physics-informed model designed for video prediction. Through the utilization of metrics such as RMSE, Bias, and Correlation, we illustrate the areas in which our model outperforms well-known prediction models.ResultsOur model demonstrates enhanced accuracy in forecasting ocean dynamics when compared to FourCastNet and PhyDNet. Additionally, our findings reveal that our model demands significantly less training data and computational resources, ultimately resulting in lower carbon emissions.DiscussionThese findings indicate the potential for further exploration of data-driven models as a supplement to physics-based models in operational marine forecasting, as they have the capability to improve prediction accuracy and efficiency, thereby facilitating more responsive and cost-effective forecasting systems.https://www.frontiersin.org/articles/10.3389/fmars.2024.1456480/fullArcticmachine learningocean predictionLSTMshort-term forecast
spellingShingle Aleksei V. Buinyi
Aleksei V. Buinyi
Dias A. Irishev
Edvard E. Nikulin
Aleksandr A. Evdokimov
Polina G. Ilyushina
Natalia A. Sukhikh
Natalia A. Sukhikh
Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
Frontiers in Marine Science
Arctic
machine learning
ocean prediction
LSTM
short-term forecast
title Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
title_full Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
title_fullStr Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
title_full_unstemmed Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
title_short Optimizing data-driven arctic marine forecasting: a comparative analysis of MariNet, FourCastNet, and PhyDNet
title_sort optimizing data driven arctic marine forecasting a comparative analysis of marinet fourcastnet and phydnet
topic Arctic
machine learning
ocean prediction
LSTM
short-term forecast
url https://www.frontiersin.org/articles/10.3389/fmars.2024.1456480/full
work_keys_str_mv AT alekseivbuinyi optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT alekseivbuinyi optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT diasairishev optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT edvardenikulin optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT aleksandraevdokimov optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT polinagilyushina optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT nataliaasukhikh optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet
AT nataliaasukhikh optimizingdatadrivenarcticmarineforecastingacomparativeanalysisofmarinetfourcastnetandphydnet