Efficient SST prediction in the Red Sea using hybrid deep learning-based approach

Prediction of Surface Sea Temperature (SST) is of great importance in seasonal forecasts in the region and beyond, mainly due to its significant role in global atmospheric circulation. On the other hand, SST predicting from given multivariate sequences using historical ocean variables is vital to investigate how SST physical phenomena generated. This paper seeks to significantly improve the prediction of Surface Sea Temperature (SST) by combining two machine learning methodologies: short-term memory networks (LSTM) added to Gaussian Process Regression (GPR). We developed a data-driven approach based on deep learning and GPR modeling to improve the prediction of SST levels in the red sea based on meteorological variables, including the hourly wind speed (WS), air temperature at 2m (T2), and relative humidity (RH) variables. The coupled GPR-LSTM model may potentially carry both flexibility and feature extraction capacity, which could describe temporal dependencies in SST time-series and improve the prediction accuracy of SST. It is necessary to indicate that these types of hybrid-based approach architectures have not used before in SST time-series prediction, so it is a new approach to deal with these types of problems. The results demonstrate a significant improvement when this hybrid model is compared to LSTM and the most frequently used ensemble learning models.

[1]  Jonghwa Kim,et al.  Sea Surface Temperature and High Water Temperature Occurrence Prediction Using a Long Short-Term Memory Model , 2020, Remote. Sens..

[2]  O. Knio,et al.  Joint seismic and electromagnetic inversion for reservoir mapping using a deep learning aided feature-oriented approach , 2020 .

[3]  J. Eynard,et al.  Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study , 2020, Energies.

[4]  J. Thepaut,et al.  The ERA5 global reanalysis , 2020, Quarterly Journal of the Royal Meteorological Society.

[5]  Li Wei,et al.  Prediction of Sea Surface Temperature in the South China Sea by Artificial Neural Networks , 2020, IEEE Geoscience and Remote Sensing Letters.

[6]  Hichem Snoussi,et al.  Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea , 2019, J. Electronic Imaging.

[7]  Hichem Snoussi,et al.  An On-Line and Adaptive Method for Detecting Abnormal Events in Videos Using Spatio-Temporal ConvNet , 2019, Applied Sciences.

[8]  Kan-Jian Zhang,et al.  Wind power prediction with missing data using Gaussian process regression and multiple imputation , 2018, Appl. Soft Comput..

[9]  M. Deo,et al.  Basin-Scale Prediction of Sea Surface Temperature with Artificial Neural Networks , 2018, 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO).

[10]  Desire Sidibé,et al.  Machine vision for timber grading singularities detection and applications , 2017, J. Electronic Imaging.

[11]  Nikolay Laptev,et al.  Deep and Confident Prediction for Time Series at Uber , 2017, 2017 IEEE International Conference on Data Mining Workshops (ICDMW).

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

[13]  T. Sullivan.  Introduction to Uncertainty Quantification , 2015 .

[14]  Desire Sidibé,et al.  Multiple features extraction for timber defects detection and classification using SVM , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[15]  Desire Sidibé,et al.  Automatic Detection and Tracking of Animal Sperm Cells in Microscopy Images , 2015, 2015 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[16]  Mohamad Mazen Hittawe,et al.  Applying Non Linear Approach for ECG Denoising and Waves Localization , 2015, 2015 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[17]  Desire Sidibé,et al.  Bag of words representation and SVM classifier for timber knots detection on color images , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[18]  Fabrice Mériaudeau,et al.  A machine vision based approach for timber knots detection , 2015, International Conference on Quality Control by Artificial Vision.

[19]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[20]  Alex Graves.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[21]  C. Donlon,et al.  The Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) system , 2012 .

[22]  C. Donlon,et al.  OSTIA : An operational, high resolution, real time, global sea surface temperature analysis system , 2007, OCEANS 2007 - Europe.

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

[24]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[25]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[26]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[27]  William W. Hsieh,et al.  Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors , 1998 .

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Charles M. Pérez-Espinoza,et al.  Using Multivariate Time Series Data via Long-Short Term Memory Network for Temperature Forecasting , 2020 .

[30]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.