Monthly and Quarterly Sea Surface Temperature Prediction Based on Gated Recurrent Unit Neural Network

The sea surface temperature (SST) is an important parameter of the energy balance on the Earth’s surface. SST prediction is crucial to marine production, marine protection, and climate prediction. However, the current SST prediction model still has low precision and poor stability. In this study, a medium and long-term SST prediction model is designed on the basis of the gated recurrent unit (GRU) neural network algorithm. This model captures the SST time regularity by using the GRU layer and outputs the predicted results through the fully connected layer. The Bohai Sea, which is characterized by a large annual temperature difference, is selected as the study area, and the SSTs on different time scales (monthly and quarterly) are used to verify the practicability and stability of the model. The results show that the designed SST prediction model can efficiently fit the results of the real sea surface temperature, and the correlation coefficient is above 0.98. Regardless of whether monthly or quarterly data are used, the proposed network model performs better than long short-term memory in terms of stability and accuracy when the length of the prediction increases. The root mean square error and mean absolute error of the predicted SST are mostly within 0–2.5 °C.

[1]  David G. DeWitt,et al.  Predictive Skill of AGCM Seasonal Climate Forecasts Subject to Different SST Prediction Methodologies , 2008 .

[2]  Junyu Dong,et al.  Prediction of Sea Surface Temperature Using Long Short-Term Memory , 2017, IEEE Geoscience and Remote Sensing Letters.

[3]  Cristóbal López,et al.  Forecasting the SST Space‐time variability of the Alboran Sea with genetic algorithms , 2000 .

[4]  M. Balmaseda,et al.  Tropical Atlantic SST Prediction with Coupled Ocean–Atmosphere GCMs , 2006 .

[5]  Yan Xue,et al.  Forecasts of tropical Pacific SST and sea level using a Markov model , 2000 .

[6]  M. C. Deo,et al.  Prediction of daily sea surface temperature using efficient neural networks , 2017, Ocean Dynamics.

[7]  G. Zhong,et al.  A Multi-Channel LSTM Model for Sea Surface Temperature Prediction , 2021 .

[8]  William W. Hsieh,et al.  Forecasts of Tropical Pacific Sea Surface Temperatures by Neural Networks and Support Vector Regression , 2009 .

[9]  E. García‐Górriz,et al.  Prediction of sea surface temperatures in the western Mediterranean Sea by neural networks using satellite observations , 2007 .

[10]  Jie Zhang,et al.  Sea Surface Temperature Characteristics and Trends in China Offshore Seas from 1982 to 2017 , 2019, Journal of Coastal Research.

[11]  Marouan Bouali,et al.  Temporal trends in sea surface temperature gradients in the South Atlantic Ocean , 2017 .

[12]  Makarand Deo,et al.  Prediction of Sea Surface Temperature by Combining Numerical and Neural Techniques , 2016 .

[13]  Enrique López Droguett,et al.  Prediction of sea surface temperature in the tropical Atlantic by support vector machines , 2013, Comput. Stat. Data Anal..

[14]  Chuli Hu,et al.  Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach , 2019, Remote Sensing of Environment.

[15]  Fathi M. Salem,et al.  Gate-variants of Gated Recurrent Unit (GRU) neural networks , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[16]  Marcos José Santana,et al.  Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure , 2015, Neural Computing and Applications.

[17]  Rajib Rana,et al.  Gated Recurrent Unit (GRU) for Emotion Classification from Noisy Speech , 2016, ArXiv.

[18]  Dae-Il Kim,et al.  Effects of temperature, salinity and irradiance on the growth of the harmful red tide dinoflagellate Cochlodinium polykrikoides Margalef (Dinophyceae) , 2004 .

[19]  Corey J. A. Bradshaw,et al.  Remote sensing of Southern Ocean sea surface temperature: implications for marine biophysical models , 2003 .

[20]  Timothy D. Herbert,et al.  Tropical Ocean Temperatures Over the Past 3.5 Million Years , 2010, Science.

[21]  Carol Anne Clayson,et al.  Seasonal Prediction of Sea Surface Temperature Anomalies Using a Suite of 13 Coupled Atmosphere–Ocean Models , 2006 .

[22]  H. U. Solanki,et al.  Signature analysis of satellite derived SSHa, SST and chlorophyll concentration and their linkage with marine fishery resources , 2015 .

[23]  Lei Zhang,et al.  Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions , 2015 .

[24]  Junyu Dong,et al.  A CFCC-LSTM Model for Sea Surface Temperature Prediction , 2018, IEEE Geoscience and Remote Sensing Letters.

[25]  Smith,et al.  Satellite measurements of sea surface temperature through clouds , 2000, Science.

[26]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[27]  Shuai‐Lei Yao,et al.  Distinct global warming rates tied to multiple ocean surface temperature changes , 2017 .

[28]  Abien Fred Agarap.  A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data , 2017, ICMLC.