A Spatio-Temporal Attention Graph Convolutional Networks for Sea Surface Temperature Prediction.

Desheng Chen; Jiabao Wen; Caiyun Lv

doi:10.9781/ijimai.2023.02.011

Authors

Desheng Chen Tianjin University
Jiabao Wen Tianjin University
Caiyun Lv Tianjin University

DOI:

https://doi.org/10.9781/ijimai.2023.02.011

Keywords:

Forecasting, Gated Recurrent Unit, Graph Convolution Network (GCN), Sea Surface Temperature

Abstract

Sea surface temperature (SST) is an important index to detect ocean changes, predict SST anomalies, and prevent natural disasters caused by abnormal changes, dynamic variation of which have a profound impact on the whole marine ecosystem and the dynamic changes of climate. In order to better capture the dynamic changes of ocean temperature, it’s vitally essential to predict the SST in the future. A new spatio-temporal attention graph convolutional network (STAGCN) for SST prediction was proposed in this paper which can capture spatial dependence and temporal correlation in the way of integrating gated recurrent unit (GRU) model with graph convolutional network (GCN) and introduced attention mechanism. The STAGCN model adopts the GCN model to learn the topological structure between ocean location points for extracting the spatial characteristics from the ocean position nodes network. Besides, capturing temporal correlation by learning dynamic variation of SST time series data, a GRU model is introduced into the STAGCN model to deal with the prediction problem about long time series, the input of which is the SST data with spatial characteristics. To capture the significance of SST information at different times and increase the accuracy of SST forecast, the attention mechanism was used to obtain the spatial and temporal characteristics globally. In this study, the proposed STAGCN model was trained and tested on the East China Sea. Experiments with different prediction lengths show that the model can capture the spatio-temporal correlation of regional-scale sea surface temperature series and almost uniformly outperforms other classical models under different sea areas and different prediction levels, in which the root mean square error is reduced by about 0.2 compared with the LSTM model.

Downloads

Download data is not yet available.

References

A. J. Constable, Melbourne-Thomas, “Climate change and southern ocean ecosystems i: how changes in physical habitats directly affect marine biota,” Global change biology, vol. 20, pp. 3004–3025, 1 2014.

M. Sumner, K. J. Michael, C. Bradshaw, M. A. Hindell, “Remote sensing of southern ocean sea surface temperature: implications for marine biophysical models,” Remote Sensing of Environment, vol. 84, no. 2, pp. 161–173, 2003.

J. Yang, J. Wen, Y. Wang, B. Jiang, H. Wang, H. Song, “Fog-based marine environmental information monitoring toward ocean of things,” IEEE Internet of Things Journal, vol. 7, no. 5, pp. 4238–4247, 2020.

M. Bouali, O. T. Sato, P. S. Polito, “Temporal trends in sea surface temperature gradients in the south atlantic ocean,” Remote Sensing of Environment, vol. 194, pp. 100–114, 2017.

M. A. Cane, A. Kaplan, D. Pozdnyakov, S. E. Zebiak, “Twentieth-century sea surface temperature trends,” Science, vol. 275, no. 5302, pp. 957–960, 1997.

G. A. Meehl, “Development of global coupled ocean- atmosphere general circulation models,” Climate Dynamics, vol. 5, no. 1, pp. 19–33, 1990.

S. L. Castro, G. A. Wick, M. Steele, “Validation of satellite sea surface temperature analyses in the beaufort sea using uptempo buoys,” Remote Sensing of Environment, vol. 187, pp. 458–475, 2016.

R. Salles, P. Mattos, A. Iorgulescu, E. Bezerra, L. Lima, E. Ogasawara, “Evaluating temporal aggregation for predicting the sea surface temperature of the atlantic ocean,” Ecological Informatics, vol. 36, pp. 94–105, 2016.

C. Xiao, N. Chen, C. Hu, K. Wang, Z. Chen, “Short and mid-term sea surface temperature prediction using time-series satellite data and lstmadaboost combination approach,” Remote Sensing of Environment, vol. 233, p. 111358, 2019.

N. Chen, K. Wang, C. Xiao, J. Gong, “A heterogeneous sensor web node meta-model for the management of a flood monitoring system,” Environmental Modelling Software, vol. 54, no. apr., pp. 222–237, 2014.

K. Patil, M. C. Deo, M. Ravichandran, “Prediction of sea surface temperature by combining numerical and neural techniques,” Journal of Atmospheric and Oceanic Technology, vol. 33, no. 8, pp. 1715–1726, 2016.

Y. Xue, A. LeetmAa, “Forecasts of tropical pacific sst and sea level using a markov model,” Geophysical Research Letters, vol. 27, no. 17, pp. 2701–2704, 2000.

X. Yan, A. Leetmaa, J. Ming, “2000: Enso prediction with markov models: The impact of seal level,” 2013, doi: https://doi.org/10.1175/1520-0442(2000)013%3C0849:EPWMMT%3E2.0.CO;2

D. C. Collins, C. J. C. Reason, F. Tangang, “Predictability of indian ocean sea surface temperature using canonical correlation analysis,” Climate Dynamics, vol. 22, no. 5, pp. 481–497, 2004.

T. Laepple, S. Jewson, “Five year ahead prediction of sea surface temperature in the tropical atlantic: a comparison between ipcc climate models and simple statistical methods,” Physics, 2007, doi: https://doi.org/10.48550/arXiv.physics/0701165

K. Patil, M. C. Deo, S. Ghosh, M. Ravichandran, “Predicting sea surface temperatures in the north indian ocean with nonlinear autoregressive neural networks,” International Journal of Oceanography, 2013 (2013-4-30), vol. 2013, pp. 1–11, 2013.

I. D. Lins, M. Araujo, M. Moura, M. A. Silva, E. L. Droguett, “Prediction of sea surface temperature in the tropical atlantic by support vector machines,” Computational Statistics Data Analysis, vol. 61, pp. 187–198, 2013.

A. Wu, W. W. Hsieh, B. Tang, “Neural network forecasts of the tropical pacific sea surface temperatures,” Neural Networks, vol. 19, no. 2, pp. 145–154, 2006.

S. G. Aparna, S. D’Souza, N. B. Arjun, “Prediction of daily sea surface temperature using artificial neural networks,” International Journal of Remote Sensing, vol. 39, no. 11-12, pp. 4214–4231, 2018.

Q. He, C. Zha, W. Song, Z. Hao, Y. Du, A. Liotta, C. Perra, “Improved particle swarm optimization for sea surface temperature prediction,” Energies, vol. 13, 2020.

J. Xie, J. Zhang, J. Yu, L. Xu, “An adaptive scale sea surface temperature predicting method based on deep learning with attention mechanism,” IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 5, pp. 740–744, 2020.

X. Liu, T. Wilson, P. N. Tan, L. Luo, “Hierarchical lstm framework for long-term sea surface temperature forecasting,” 2020.

J. Liu, T. Zhang, G. Han, Y. Gou, “Td-lstm: Temporal dependence-based lstm networks for marine temperature prediction,” Sensors, vol. 18, 2018.

Park, Kim, Lee, Song, “Temperature prediction using the missing data refinement model based on a long short-term memory neural network,” Atmosphere, vol. 10, no. 11, p. 718, 2019.

S. Hochreiter, J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

R. Dey, F. M. Salemt, “Gate-variants of gated recurrent unit (gru) neural networks,” pp. 1597–1600, 2017.

Z. Qin, W. Hui, J. Dong, G. Zhong, S. Xin, “Prediction of sea surface temperature using long short-term memory,” IEEE Geoence and Remote Sensing Letters, vol. 14, no. 10, pp. 1745–1749, 2017.

Y. Feng, T. Sun, J. Dong, C. Li, “Study on long term sea surface temperature (sst) prediction based on temporal convolutional network (tcn) method,” ACM Turing Award Celebration Conference-China (ACM TURC 2021), pp. 28–32, 2021.

M. Han, Y. Feng, X. Zhao, C. Sun, C. Liu, “A convolutional neural network using surface data to predict subsurface temperatures in the pacific ocean,” IEEE Access, vol. PP, no. 99, pp. 1–1, 2019.

M. Abadi, P. Barham, J. Chen, Z. Chen, X. Zhang, “Tensorflow: A system for large-scale machine learning,” 2016.

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, A. Müller, J. Nothman, G. Louppe, “Scikit-learn: Machine learning in python,” 2012.