A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity

Accurate mid-short term prediction of sea surface salinity (SSS) is essential for operational ocean monitoring, particularly for capturing short-term salinity fluctuations that affect regional ocean dynamics and weather conditions. However, existing models struggle to extract complex spatiotemporal...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangwen Peng, Yingbing Liu, Cong Xiao, Wenying Du, Changjiang Xiao
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2548008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224330148315136
author Guangwen Peng
Yingbing Liu
Cong Xiao
Wenying Du
Changjiang Xiao
author_facet Guangwen Peng
Yingbing Liu
Cong Xiao
Wenying Du
Changjiang Xiao
author_sort Guangwen Peng
collection DOAJ
description Accurate mid-short term prediction of sea surface salinity (SSS) is essential for operational ocean monitoring, particularly for capturing short-term salinity fluctuations that affect regional ocean dynamics and weather conditions. However, existing models struggle to extract complex spatiotemporal dependencies and are often limited to local regions, reducing their global applicability. To address these challenges, we propose a Dynamic Adaptive Graph Convolutional Recurrent Network (DAGCRN) for global SSS prediction. The DAGCRN employs an encoder–decoder architecture, where both the encoder and decoder integrate adaptive graph convolutional recurrent units (AGCRUs) and gated recurrent units (GRUs). AGCRUs dynamically construct topological relationships via graph convolution to model spatial variations, while GRUs capture temporal dependencies. This enables DAGCRN to effectively model the nonlinear and dynamic nature of global SSS variations. We evaluate DAGCRN's performance on the ESA Sea Surface Salinity CCI v3.21 dataset, which provides global gridded SSS observations from February 2010 to September 2020. Forecasting lead times range from 1 to 12 days. DAGCRN consistently outperforms LSTM, BiLSTM, ConvLSTM, and TCN. For 12-day prediction, RMSE is reduced by 36.0%, 24.4%, 13.0%, and 5.5%, respectively, demonstrating its effectiveness in modeling spatiotemporal dependencies for global SSS forecasting.
format Article
id doaj-art-e7d290247a484d3983bcf5c6dd172c5e
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-e7d290247a484d3983bcf5c6dd172c5e2025-08-25T11:31:37ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2548008A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinityGuangwen Peng0Yingbing Liu1Cong Xiao2Wenying Du3Changjiang Xiao4School of Computer Science and Technology, Hainan University, Haikou, Hainan, People's Republic of ChinaSchool of Computer Science and Technology, Hainan University, Haikou, Hainan, People's Republic of ChinaSchool of Computer Science and Technology, Hainan University, Haikou, Hainan, People's Republic of ChinaNational Engineering Research Center of Geographic Information System, China University of Geosciences, Wuhan, People's Republic of ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, People's Republic of ChinaAccurate mid-short term prediction of sea surface salinity (SSS) is essential for operational ocean monitoring, particularly for capturing short-term salinity fluctuations that affect regional ocean dynamics and weather conditions. However, existing models struggle to extract complex spatiotemporal dependencies and are often limited to local regions, reducing their global applicability. To address these challenges, we propose a Dynamic Adaptive Graph Convolutional Recurrent Network (DAGCRN) for global SSS prediction. The DAGCRN employs an encoder–decoder architecture, where both the encoder and decoder integrate adaptive graph convolutional recurrent units (AGCRUs) and gated recurrent units (GRUs). AGCRUs dynamically construct topological relationships via graph convolution to model spatial variations, while GRUs capture temporal dependencies. This enables DAGCRN to effectively model the nonlinear and dynamic nature of global SSS variations. We evaluate DAGCRN's performance on the ESA Sea Surface Salinity CCI v3.21 dataset, which provides global gridded SSS observations from February 2010 to September 2020. Forecasting lead times range from 1 to 12 days. DAGCRN consistently outperforms LSTM, BiLSTM, ConvLSTM, and TCN. For 12-day prediction, RMSE is reduced by 36.0%, 24.4%, 13.0%, and 5.5%, respectively, demonstrating its effectiveness in modeling spatiotemporal dependencies for global SSS forecasting.https://www.tandfonline.com/doi/10.1080/17538947.2025.2548008Sea surface salinitydynamic adaptive graph convolutionglobal mid-short term predictionspatiotemporal prediction
spellingShingle Guangwen Peng
Yingbing Liu
Cong Xiao
Wenying Du
Changjiang Xiao
A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
International Journal of Digital Earth
Sea surface salinity
dynamic adaptive graph convolution
global mid-short term prediction
spatiotemporal prediction
title A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
title_full A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
title_fullStr A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
title_full_unstemmed A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
title_short A dynamic adaptive graph convolutional recurrent network model for efficient mid-short term prediction of global sea surface salinity
title_sort dynamic adaptive graph convolutional recurrent network model for efficient mid short term prediction of global sea surface salinity
topic Sea surface salinity
dynamic adaptive graph convolution
global mid-short term prediction
spatiotemporal prediction
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2548008
work_keys_str_mv AT guangwenpeng adynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT yingbingliu adynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT congxiao adynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT wenyingdu adynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT changjiangxiao adynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT guangwenpeng dynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT yingbingliu dynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT congxiao dynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT wenyingdu dynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity
AT changjiangxiao dynamicadaptivegraphconvolutionalrecurrentnetworkmodelforefficientmidshorttermpredictionofglobalseasurfacesalinity