OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements

Accurate prediction of key ocean elements (e.g., chlorophyll-a concentration, sea surface temperature, etc.) is imperative for maintaining marine ecological balance, responding to marine disaster pollution, and promoting the sustainable use of marine resources. Existing spatio-temporal prediction mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Renhao Xiao, Yixiang Chen, Lizhi Miao, Jie Jiang, Donglin Zhang, Zhou Su
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239671084679168
author Renhao Xiao
Yixiang Chen
Lizhi Miao
Jie Jiang
Donglin Zhang
Zhou Su
author_facet Renhao Xiao
Yixiang Chen
Lizhi Miao
Jie Jiang
Donglin Zhang
Zhou Su
author_sort Renhao Xiao
collection DOAJ
description Accurate prediction of key ocean elements (e.g., chlorophyll-a concentration, sea surface temperature, etc.) is imperative for maintaining marine ecological balance, responding to marine disaster pollution, and promoting the sustainable use of marine resources. Existing spatio-temporal prediction models primarily rely on either physical or data-driven approaches. Physical models are constrained by modeling complexity and parameterization errors, while data-driven models lack interpretability and depend on high-quality data. To address these challenges, this study proposes OKG-ConvGRU, a domain knowledge-guided remote sensing prediction framework for ocean elements. This framework integrates knowledge graphs with the ConvGRU network, leveraging prior knowledge from marine science to enhance the prediction performance of ocean elements in remotely sensed images. Firstly, we construct a spatio-temporal knowledge graph for ocean elements (OKG), followed by semantic embedding representation for its spatial and temporal dimensions. Subsequently, a cross-attention-based feature fusion module (CAFM) is designed to efficiently integrate spatio-temporal multimodal features. Finally, these fused features are incorporated into an enhanced ConvGRU network. For multi-step prediction, we adopt a Seq2Seq architecture combined with a multi-step rolling strategy. Prediction experiments for chlorophyll-a concentration in the eastern seas of China validate the effectiveness of the proposed framework. The results show that, compared to baseline models, OKG-ConvGRU exhibits significant advantages in prediction accuracy, long-term stability, data utilization efficiency, and robustness. This study provides a scientific foundation and technical support for the precise monitoring and sustainable development of marine ecological environments.
format Article
id doaj-art-5123eefd0a214098a950bf8d2e8c9c32
institution Kabale University
issn 2072-4292
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-5123eefd0a214098a950bf8d2e8c9c322025-08-20T04:00:54ZengMDPI AGRemote Sensing2072-42922025-08-011715267910.3390/rs17152679OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean ElementsRenhao Xiao0Yixiang Chen1Lizhi Miao2Jie Jiang3Donglin Zhang4Zhou Su5School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaAccurate prediction of key ocean elements (e.g., chlorophyll-a concentration, sea surface temperature, etc.) is imperative for maintaining marine ecological balance, responding to marine disaster pollution, and promoting the sustainable use of marine resources. Existing spatio-temporal prediction models primarily rely on either physical or data-driven approaches. Physical models are constrained by modeling complexity and parameterization errors, while data-driven models lack interpretability and depend on high-quality data. To address these challenges, this study proposes OKG-ConvGRU, a domain knowledge-guided remote sensing prediction framework for ocean elements. This framework integrates knowledge graphs with the ConvGRU network, leveraging prior knowledge from marine science to enhance the prediction performance of ocean elements in remotely sensed images. Firstly, we construct a spatio-temporal knowledge graph for ocean elements (OKG), followed by semantic embedding representation for its spatial and temporal dimensions. Subsequently, a cross-attention-based feature fusion module (CAFM) is designed to efficiently integrate spatio-temporal multimodal features. Finally, these fused features are incorporated into an enhanced ConvGRU network. For multi-step prediction, we adopt a Seq2Seq architecture combined with a multi-step rolling strategy. Prediction experiments for chlorophyll-a concentration in the eastern seas of China validate the effectiveness of the proposed framework. The results show that, compared to baseline models, OKG-ConvGRU exhibits significant advantages in prediction accuracy, long-term stability, data utilization efficiency, and robustness. This study provides a scientific foundation and technical support for the precise monitoring and sustainable development of marine ecological environments.https://www.mdpi.com/2072-4292/17/15/2679ocean elementspatio-temporal predictionConvGRUcross-attentiontime-series remote sensing image
spellingShingle Renhao Xiao
Yixiang Chen
Lizhi Miao
Jie Jiang
Donglin Zhang
Zhou Su
OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
Remote Sensing
ocean element
spatio-temporal prediction
ConvGRU
cross-attention
time-series remote sensing image
title OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
title_full OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
title_fullStr OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
title_full_unstemmed OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
title_short OKG-ConvGRU: A Domain Knowledge-Guided Remote Sensing Prediction Framework for Ocean Elements
title_sort okg convgru a domain knowledge guided remote sensing prediction framework for ocean elements
topic ocean element
spatio-temporal prediction
ConvGRU
cross-attention
time-series remote sensing image
url https://www.mdpi.com/2072-4292/17/15/2679
work_keys_str_mv AT renhaoxiao okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements
AT yixiangchen okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements
AT lizhimiao okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements
AT jiejiang okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements
AT donglinzhang okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements
AT zhousu okgconvgruadomainknowledgeguidedremotesensingpredictionframeworkforoceanelements