Hybrid improved empirical mode decomposition and BP neural network model for the prediction of sea surface temperature

Abstract. Sea surface temperature (SST) is the major factor that affects the ocean–atmosphere interaction, and in turn the accurate prediction of SST is the key to ocean dynamic prediction. In this paper, an SST-predicting method based on empirical mode decomposition (EMD) algorithms and back-propagation neural network (BPNN) is proposed. Two different EMD algorithms have been applied extensively for analyzing time-series SST data and some nonlinear stochastic signals. The ensemble empirical mode decomposition (EEMD) algorithm and complementary ensemble empirical mode decomposition (CEEMD) algorithm are two improved algorithms of EMD, which can effectively handle the mode-mixing problem and decompose the original data into more stationary signals with different frequencies. Each intrinsic mode function (IMF) has been taken as input data to the back-propagation neural network model. The final predicted SST data are obtained by aggregating the predicted data of individual series of IMFs (IMF i ). A case study of the monthly mean SST anomaly (SSTA) in the northeastern region of the North Pacific shows that the proposed hybrid CEEMD-BPNN model is much more accurate than the hybrid EEMD-BPNN model, and the prediction accuracy based on a BP neural network is improved by the CEEMD method. Statistical analysis of the case study demonstrates that applying the proposed hybrid CEEMD-BPNN model is effective for the SST prediction. Highlights include the following: Highlights. An SST-predicting method based on the hybrid EMD algorithms and BP neural network method is proposed in this paper. SST prediction results based on the hybrid EEMD-BPNN and CEEMD-BPNN models are compared and discussed. A case study of SST in the North Pacific shows that the proposed hybrid CEEMD-BPNN model can effectively predict the time-series SST.

[1]  C. Tucker,et al.  The modulated annual cycle: an alternative reference frame for climate anomalies , 2007 .

[2]  Qing Xu,et al.  Analysis of tidal amplitude changes using the EMD method , 2017 .

[3]  R. Pearson,et al.  Gray-box identification of block-oriented nonlinear models , 2000 .

[4]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[5]  Ari Murdimanto,et al.  THREE-WAY ERROR ANALYSIS OF SEA SURFACE TEMPERATURE (SST) BETWEEN HIMAWARI-8, BUOY, AND MUR SST IN SAVU SEA , 2018, International Journal of Remote Sensing and Earth Sciences (IJReSES).

[6]  Ling Tang,et al.  A Novel CEEMD-Based EELM Ensemble Learning Paradigm for Crude Oil Price Forecasting , 2015, Int. J. Inf. Technol. Decis. Mak..

[7]  Yang Han,et al.  A hybrid EMD-AR model for nonlinear and non-stationary wave forecasting , 2016 .

[8]  Norden E. Huang,et al.  A review on Hilbert‐Huang transform: Method and its applications to geophysical studies , 2008 .

[9]  Norden E. Huang,et al.  Complementary Ensemble Empirical Mode Decomposition: a Novel Noise Enhanced Data Analysis Method , 2010, Adv. Data Sci. Adapt. Anal..

[10]  Jie Chen,et al.  Three-Dimensional Temperature Field Change in the South China Sea during Typhoon Kai-Tak (1213) Based on a Fully Coupled Atmosphere–Wave–Ocean Model , 2019, Water.

[11]  James L. Kinter,et al.  Seasonality in Prediction Skill and Predictable Pattern of Tropical Indian Ocean SST , 2015 .

[12]  H J Motulsky,et al.  Fitting curves to data using nonlinear regression: a practical and nonmathematical review , 1987, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[13]  M. C. Deo,et al.  Neural networks for wave forecasting , 2001 .

[14]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[15]  Patrick Heimbach,et al.  Low-Frequency SST and Upper-Ocean Heat Content Variability in the North Atlantic , 2014 .

[16]  Philip A. Wilson,et al.  Adaptive neural network-based backstepping fault tolerant control for underwater vehicles with thruster fault , 2015 .

[17]  T. Sadeghifar,et al.  Coastal Wave Height Prediction using Recurrent Neural Networks (RNNs) in the South Caspian Sea , 2017 .

[18]  Manoj Kumar,et al.  Observation of plasma shift in SST-1 using optical imaging diagnostics , 2017 .

[19]  Cheng Li,et al.  A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights , 2018, Ocean Engineering.

[20]  Tai-Wen Hsu,et al.  Ensemble Empirical Mode Decomposition on Storm Surge Separation from Sea Level Data , 2011 .

[21]  Ashish Sharma,et al.  Global seasonal precipitation forecasts using improved sea surface temperature predictions , 2017 .

[22]  Shang-Ping Xie,et al.  Intermodel Uncertainty in ENSO Amplitude Change Tied to Pacific Ocean Warming Pattern , 2016 .

[23]  Tsong-Lin Lee.  Back-propagation neural network for long-term tidal predictions , 2004 .

[24]  Makarand Deo,et al.  Neural networks in ocean engineering , 2006 .

[25]  J. Donges,et al.  Hierarchical structures in Northern Hemispheric extratropical winter ocean–atmosphere interactions , 2015, 1506.06634.

[26]  Abdullah Al Mamun,et al.  Regional ocean wave height prediction using sequential learning neural networks , 2017 .

[27]  T. M. Chin,et al.  A long-term record of blended satellite and in situ sea-surface temperature for climate monitoring, modeling and environmental studies , 2016 .

[28]  Xianqing Lv,et al.  Application of the EMD Method to River Tides , 2018 .

[29]  Hojjat Adeli,et al.  A new music-empirical wavelet transform methodology for time-frequency analysis of noisy nonlinear and non-stationary signals , 2015, Digit. Signal Process..

[30]  Tal Ezer,et al.  Accelerated flooding along the U.S. East Coast: On the impact of sea‐level rise, tides, storms, the Gulf Stream, and the North Atlantic Oscillations , 2014 .

[31]  Andrew T. Wittenberg,et al.  Impacts on Ocean Heat from Transient Mesoscale Eddies in a Hierarchy of Climate Models , 2015 .

[32]  Nicholas A. Bond,et al.  Causes and impacts of the 2014 warm anomaly in the NE Pacific , 2015 .

[33]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

[34]  Julien Yvonnet,et al.  Computational homogenization for nonlinear conduction in heterogeneous materials using model reduction , 2008 .

[35]  Jie Chen,et al.  Numerical investigation of Typhoon Kai-tak (1213) using a mesoscale coupled WRF-ROMS model , 2019, Ocean Engineering.

[36]  Yuntao Han,et al.  A hybrid EMD-SVR model for the short-term prediction of significant wave height , 2016 .

[37]  Dong Eun Lee,et al.  Diversity, Nonlinearity, Seasonality, and Memory Effect in ENSO Simulation and Prediction Using Empirical Model Reduction , 2016 .

[38]  S. Suemasa,et al.  A Study on the Fatigue (I) , 1959 .

[39]  Yolanda Villacampa,et al.  Neural network for determining the characteristic points of the bars , 2017 .

[40]  Yooil Kim,et al.  A study on the fatigue damage model for Gaussian wideband process of two peaks by an artificial neural network , 2016 .

[41]  Lei Wu,et al.  Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method , 2016 .

[42]  Thomas M. Smith,et al.  Daily High-Resolution-Blended Analyses for Sea Surface Temperature , 2007 .

[43]  Ryuichi Kawamura,et al.  An estimation of water origins in the vicinity of a tropical cyclone’s center and associated dynamic processes , 2017, Climate Dynamics.

[44]  Zhiping Wen,et al.  Relative importance of tropical SST anomalies in maintaining the Western North Pacific anomalous anticyclone during El Niño to La Niña transition years , 2016, Climate Dynamics.

[45]  Brian J. Soden,et al.  Atmospheric and Oceanic Origins of Tropical Precipitation Variability , 2016 .

[46]  Dominic A. Hudson,et al.  The impact of atmospheric initialisation on seasonal prediction of tropical Pacific SST , 2011 .

[47]  Han Soo Lee.  Estimation of extreme sea levels along the Bangladesh coast due to storm surge and sea level rise using EEMD and EVA , 2013 .