Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention

Sea surface temperature (SST) prediction has received increasing attention in recent years due to its paramount importance in the various fields of oceanography. Existing studies have shown that neural networks are particularly effective in making accurate SST predictions by efficiently capturing sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Benyun Shi, Conghui Ge, Hongwang Lin, Yanpeng Xu, Qi Tan, Yue Peng, Hailun He
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4126
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152594731302912
author Benyun Shi
Conghui Ge
Hongwang Lin
Yanpeng Xu
Qi Tan
Yue Peng
Hailun He
author_facet Benyun Shi
Conghui Ge
Hongwang Lin
Yanpeng Xu
Qi Tan
Yue Peng
Hailun He
author_sort Benyun Shi
collection DOAJ
description Sea surface temperature (SST) prediction has received increasing attention in recent years due to its paramount importance in the various fields of oceanography. Existing studies have shown that neural networks are particularly effective in making accurate SST predictions by efficiently capturing spatiotemporal dependencies in SST data. Among various models, the ConvLSTM framework is notably prominent. This model skillfully combines convolutional neural networks (CNNs) with recurrent neural networks (RNNs), enabling it to simultaneously capture spatiotemporal dependencies within a single computational framework. To overcome the limitation that CNNs primarily capture local spatial information, in this paper we propose a novel model named DatLSTM that integrates a deformable attention transformer (DAT) module into the ConvLSTM framework, thereby enhancing its ability to process more complex spatial relationships effectively. Specifically, the DAT module adaptively focuses on salient features in space, while ConvLSTM further captures the temporal dependencies of spatial correlations in the SST data. In this way, DatLSTM can adaptively capture complex spatiotemporal dependencies between the preceding and current states within ConvLSTM. To evaluate the performance of the DatLSTM model, we conducted short-term SST forecasts in the Bohai Sea region with forecast lead times ranging from 1 to 10 days and compared its efficacy against several benchmark models, including ConvLSTM, PredRNN, TCTN, and SwinLSTM. Our experimental results show that the proposed model outperforms all of these models in terms of multiple evaluation metrics short-term SST prediction. The proposed model offers a new predictive learning method for improving the accuracy of spatiotemporal predictions in various domains, including meteorology, oceanography, and climate science.
format Article
id doaj-art-b4636340644a4bc6a6f34fb2be4887e7
institution Kabale University
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-b4636340644a4bc6a6f34fb2be4887e72024-11-26T18:19:38ZengMDPI AGRemote Sensing2072-42922024-11-011622412610.3390/rs16224126Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable AttentionBenyun Shi0Conghui Ge1Hongwang Lin2Yanpeng Xu3Qi Tan4Yue Peng5Hailun He6College of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaSea surface temperature (SST) prediction has received increasing attention in recent years due to its paramount importance in the various fields of oceanography. Existing studies have shown that neural networks are particularly effective in making accurate SST predictions by efficiently capturing spatiotemporal dependencies in SST data. Among various models, the ConvLSTM framework is notably prominent. This model skillfully combines convolutional neural networks (CNNs) with recurrent neural networks (RNNs), enabling it to simultaneously capture spatiotemporal dependencies within a single computational framework. To overcome the limitation that CNNs primarily capture local spatial information, in this paper we propose a novel model named DatLSTM that integrates a deformable attention transformer (DAT) module into the ConvLSTM framework, thereby enhancing its ability to process more complex spatial relationships effectively. Specifically, the DAT module adaptively focuses on salient features in space, while ConvLSTM further captures the temporal dependencies of spatial correlations in the SST data. In this way, DatLSTM can adaptively capture complex spatiotemporal dependencies between the preceding and current states within ConvLSTM. To evaluate the performance of the DatLSTM model, we conducted short-term SST forecasts in the Bohai Sea region with forecast lead times ranging from 1 to 10 days and compared its efficacy against several benchmark models, including ConvLSTM, PredRNN, TCTN, and SwinLSTM. Our experimental results show that the proposed model outperforms all of these models in terms of multiple evaluation metrics short-term SST prediction. The proposed model offers a new predictive learning method for improving the accuracy of spatiotemporal predictions in various domains, including meteorology, oceanography, and climate science.https://www.mdpi.com/2072-4292/16/22/4126sea surface temperatureconvolutional LSTMdeformable attentionspatiotemporal predictive learning
spellingShingle Benyun Shi
Conghui Ge
Hongwang Lin
Yanpeng Xu
Qi Tan
Yue Peng
Hailun He
Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
Remote Sensing
sea surface temperature
convolutional LSTM
deformable attention
spatiotemporal predictive learning
title Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
title_full Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
title_fullStr Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
title_full_unstemmed Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
title_short Sea Surface Temperature Prediction Using ConvLSTM-Based Model with Deformable Attention
title_sort sea surface temperature prediction using convlstm based model with deformable attention
topic sea surface temperature
convolutional LSTM
deformable attention
spatiotemporal predictive learning
url https://www.mdpi.com/2072-4292/16/22/4126
work_keys_str_mv AT benyunshi seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT conghuige seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT hongwanglin seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT yanpengxu seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT qitan seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT yuepeng seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention
AT hailunhe seasurfacetemperaturepredictionusingconvlstmbasedmodelwithdeformableattention