Skip to main content
SpringerLink
Log in

CoCluster-DAGCN: a dynamic aggregate graph convolution network by a co-attention LSTM cluster for ocean temperature predictions

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Considering that ocean temperature data contain much irrelevant noise if a traditional method is used to obtain a temperature prediction, it will be difficult to encode the spatiotemporal relationship effectively, and the prediction accuracy will be poor. Therefore, we propose a dynamic graph convolution framework of collaborative attention LSTM clustering (CoCluster-DAGCN) for ocean temperature prediction. The framework first uses a coattention LSTM to remove irrelevant and redundant information and performs pruning and clustering to simplify the graph topology. Second, a multiscale graph convolutional network is used to capture further the multiscale spatiotemporal semantics of the ocean temperature data. A dynamic aggregation strategy constructs a stable spatiotemporal relationship and performs local and global-local context modeling. Additionally, the topological structure generated by the clustering of the LSTM coattention module provides maps of different scales for the dynamic aggregation graph convolution module. Finally, the experimental results show that on ARGO and SST-9 baseline data, our proposed CoCluster-DAGCN ocean temperature prediction framework achieves better performance; namely, the MAE and RMSE values of the SST-9 data are 0.3961 and 0.4316, respectively, and the MAE and RMSE values of the ARGO data are 0.2133 and 0.2811, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Algorithm 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Aa A, Yz A, Mz B (2021) Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks[J]. Inf Sci 577:852–870

    Article  MathSciNet  Google Scholar 

  2. Ai B, Wen Z, Jiang Y, Gao S, Lv G (2019) Sea surface temperature inversion model for infrared remote sensing images based on deep neural network. Infrared Phys Technol 99(2019):231–239

    Article  Google Scholar 

  3. Ali A, Zhu Y, Chen Q, et al (2019) Leveraging Spatio-temporal patterns for predicting citywide traffic crowd flows using deep hybrid neural networks[C]// 2019 IEEE 25th international conference on parallel and distributed systems (ICPADS). IEEE

  4. Ali A, Zhu Y, Zakarya M (2021) A data aggregation-based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing[J]. Multimed Tools Appl:1–33

  5. Ali A, Zhu Y, Zakarya M (2022) Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction[J]. Neural Netw 145:233–247

    Article  Google Scholar 

  6. Aparna SG, D'Souza S, Arjun NB (2018) Prediction of daily sea surface temperature using artificial neural networks. Int J Remote Sens 39(12):4214–4231

  7. Baptista M, Sankararaman S, de Medeiros IP, Nascimento C Jr, Prendinger H, Henriques EMP (2018) Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling. Comput Indust Eng 115(2018):41–53

    Article  Google Scholar 

  8. Chen C , Wang G , Peng C , et al. (2020) Exploring rich and efficient spatial temporal interactions for real time video salient object detection[J]

  9. Fu A, Patil K R, Iiyama M (2020) Region Proposal and Regression Network for Fishing Spots Detection from Sea Temperature[C]//Global Oceans 2020: Singapore–US gulf coast. IEEE: 1–4

  10. He Q, Cheng Z, Song W, Hao Z, Yanling D, Liotta A, Perra C (2020) Improved particle swarm optimization for sea surface temperature prediction. Energ 13, 6:1369

    Google Scholar 

  11. Jin D, Huo L (2018) Influence of tropical Atlantic Sea surface temperature anomalies on the east Asian summer monsoon[J]. Q J R Meteorol Soc 144(714):1490–1500

    Article  Google Scholar 

  12. Kalpesh P, Deo MC, Ravichandran M (2016) Prediction of sea surface temperature by combining numerical and neural techniques. J Atmos Ocean Technol 33(8):1715–1726

    Article  Google Scholar 

  13. Kim YJ, Kim HC, Han D et al (2020) Prediction of monthly Arctic Sea ice concentrations using satellite and reanalysis data based on convolutional neural networks[J]. Cryosphere 14(3):1083–1104

    Article  Google Scholar 

  14. Kug J-S, Kang I-S, Lee J-Y, Jhun J-G (2004) A statistical approach to Indian Ocean Sea surface temperature prediction using a dynamical ENSO prediction. Geophys Res Lett 31:9

    Article  Google Scholar 

  15. Lee DE, Chapman D, Henderson N, Chen C, Cane MA (2016) Multilevel vector autoregressive prediction of sea surface temperature in the north tropical Atlantic Ocean and the Caribbean Sea. Climate Dyn 47 1(2016):95–106

    Article  Google Scholar 

  16. Li Y, Yang R, Yang C, et al (2017) Leveraging LSTM for rapid intensifications prediction of tropical cyclones[J]. ISPRS annals of photogrammetry, Remote Sens Spat Inf Sci, 4

  17. Lin Y, Zhong G. (2021) A Multi-Channel LSTM model for sea surface temperature prediction. In Journal of physics: conference series, Vol. 1880. IOP Publishing, 012029

  18. Lin Z, Mao F, Guo J, Wang W, Pan Z, Shen H, Zhu B, Wang Z (2019) Estimation of spatiotemporal PM1. 0 distributions in China by combining PM2. 5 observations with satellite aerosol optical depth. Sci Total Environ 658(2019):1256–1264

    Google Scholar 

  19. Lins ID, Araujo M, das Chagas MM et al (2013) Prediction of sea surface temperature in the tropical Atlantic by support vector machines. Computat Stat Data Anal 61:187–198

  20. Liu J, Zhang T, Han G, Yu G (2018) TD-LSTM: temporal dependence-based LSTM networks for marine temperature prediction. Sens 18, 11:3797

    Article  Google Scholar 

  21. Patil K, Deo MC (2017) Prediction of daily sea surface temperature using efficient neural networks. Ocean Dyn 67, 3-4(2017):357–368

    Article  Google Scholar 

  22. Qiao B, Wu Z, Tang Z et al (2021) Sea surface temperature prediction approach based on 3D CNN and LSTiM with attention mechanism. 2021 23rd lnternational Conference on Advanced Communication Technology (lCACT), pp 342–347

  23. Li Q-J, Zhao Y, Liao H-L et al (2017) Effective forecast of Northeast Pacific Sea surface temperature based on a complementary ensemble empirical mode decomposition–support vector machine method. Atmos Ocean Sci Lett 10(3):261–267

  24. Sithara S, Pramada SK, Thampi SG (2020) Sea level prediction using climatic variables: a comparative study of SVM and hybrid wavelet SVM approaches[J]. Acta Geophys 68(6):1779–1790

    Article  Google Scholar 

  25. Tao Y, He Q, Yao Y (2019) Solution for a time-series AR model based on robust TLS estimation. Geomatics, Nat Hazards Risk 10(1):1–779

    Article  Google Scholar 

  26. Usharani B (2022) ILF-LSTM: enhanced loss function in LSTM to predict the sea surface temperature[J]. Soft Computing 27(18):13129–13141

  27. Wu Aiming, William W Hsieh, and Benyang Tang. 2006. Neural network forecasts of the tropical Pacific Sea surface temperatures. Neural Netw 19, 2 (2006), 145–154.

  28. Wu Z, Jiang C, Conde M, Deng B, Chen J (2019) Hybrid improved empirical mode decomposition and BP neural network model for the prediction of sea surface temperature. Ocean Sci 15, 2:349–360

    Article  Google Scholar 

  29. Xiao C, Chen N, Hu C et al (2019) Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach[J]. Remote Sens Environ 233:111358

    Article  Google Scholar 

  30. Xiao C, Chen N, Hu C et al (2019) Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach[J]. Remote Sens Environ 233(2019):1–18

  31. Xu L, Li Y, Yu J, Li Q, Shi S (2020) Prediction of sea surface temperature using a multiscale deep combination neural network. Remote Sens Lett 11, 7:611–619

    Article  Google Scholar 

  32. Yang Y, Dong J, Sun X, Lima E, Quanquan M, Wang X (2017) A CFCC-LSTM model for sea surface temperature prediction. IEEE Geosci Remote Sens Lett 15, 2:207–211

    Google Scholar 

  33. Yu X, Shi S, Xu L, Liu Y, Miao Q, Sun M (2020) A novel method for sea surface temperature prediction based on deep learning[J]. Math Probl Eng 2020(1):362–369

  34. Zhang Q, Wang H, Dong J et al (2017) Prediction of sea surface temperature using long short-term memory[J]. IEEE Geosci Remote Sens Lett 14(10):1745–1749

    Article  Google Scholar 

  35. Zhang K, Geng X, Yan XH (2020) Prediction of 3-D Ocean temperature by multilayer convolutional LSTM[J]. IEEE Geosci Remote Sens Lett 17(8):1303–1307

Download references

Acknowledgments

This study was funded by the key R&D project of the Shandong Provincial Department of Science and Technology (2017GGX201004) and the Key Science and Technology Project of Qingdao Huanghai University (2019KJ01) (2019KJ02).

Author information

Authors and Affiliations

  1. Qingdao Huanghai University, Qingdao, 266427, China

    Yujie Chen, Peixue Liu, Fuzhen Qin & Shumei Liu

Authors
  1. Yujie Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peixue Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fuzhen Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shumei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yujie Chen.

Ethics declarations

Conflict of interest

The authors have no relevant conflicts of interest to disclose.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Y., Liu, P., Qin, F. et al. CoCluster-DAGCN: a dynamic aggregate graph convolution network by a co-attention LSTM cluster for ocean temperature predictions. Multimed Tools Appl 83, 40791–40809 (2024). https://doi.org/10.1007/s11042-023-15768-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15768-1

Keywords

Search

Navigation