Predictability of the Loop Current Variation and Eddy Shedding Process in the Gulf of Mexico Using an Artificial Neural Network Approach

AbstractA novel approach based on an artificial neural network was used to forecast sea surface height (SSH) in the Gulf of Mexico (GoM) in order to predict Loop Current variation and its eddy shedding process. The empirical orthogonal function analysis method was applied to decompose long-term satellite-observed SSH into spatial patterns (EOFs) and time-dependent principal components (PCs). The nonlinear autoregressive network was then developed to predict major PCs of the GoM SSH in the future. The prediction of SSH in the GoM was constructed by multiplying the EOFs and predicted PCs. Model sensitivity experiments were conducted to determine the optimal number of PCs. Validations against independent satellite observations indicate that the neural network–based model can reliably predict Loop Current variations and its eddy shedding process for a 4-week period. In some cases, an accurate forecast for 5–6 weeks is possible.

[1]  George Z. Forristall,et al.  SS: Metocean: A Statistical Hindcast and Forecast Model for the Loop Current , 2010 .

[2]  Lie-Yauw Oey,et al.  Bred-ensemble ocean forecast of loop current and rings , 2007 .

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

[4]  R. He,et al.  Cloud-free sea surface temperature and colour reconstruction for the Gulf of Mexico: 2003–2009 , 2012 .

[5]  R. Vautard,et al.  Model intercomparison in the Mediterranean: MEDMEX simulations of the seasonal cycle , 2002 .

[6]  William W. Hsieh,et al.  Nonlinear principal component analysis by neural networks , 2001 .

[7]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[8]  Ibrahim Hoteit,et al.  State estimates and forecasts of the loop current in the Gulf of Mexico using the MITgcm and its adjoint , 2013 .

[9]  Robert R. Leben,et al.  Altimeter‐Derived Loop Current Metrics , 2013 .

[10]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[11]  William W. Hsieh,et al.  Nonlinear Principal Component Analysis , 2009 .

[12]  Fanghua Xu,et al.  Hindcasts and forecasts of Loop Current and eddies in the Gulf of Mexico using local ensemble transform Kalman filter and optimum-interpolation assimilation schemes , 2013 .

[13]  D. Chelton,et al.  Global observations of nonlinear mesoscale eddies , 2011 .

[14]  Yizhen Li,et al.  Seasonal variability of Kuroshio intrusion northeast of Taiwan Island as revealed by self-organizing map , 2014, Chinese Journal of Oceanology and Limnology.

[15]  Robert H. Weisberg,et al.  Patterns of upper layer circulation variability in the South China Sea from satellite altimetry usin , 2008 .

[16]  Laurent Bertino,et al.  High-resolution ensemble forecasting for the Gulf of Mexico eddies and fronts , 2009 .

[17]  A. H. Murphy,et al.  Skill Scores Based on the Mean Square Error and Their Relationships to the Correlation Coefficient , 1988 .

[18]  Milton S. Boyd,et al.  Designing a neural network for forecasting financial and economic time series , 1996, Neurocomputing.

[19]  Hyun-chul Lee,et al.  Loop Current, Rings and Related Circulation in the Gulf of Mexico: A Review of Numerical Models and Future Challenges , 2013 .

[20]  William W. Hsieh,et al.  Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography. , 1998 .

[21]  N. Bindoff,et al.  A Statistically Efficient Mapping Technique for Four-Dimensional Ocean Temperature Data , 2000 .

[22]  Damia Gomis,et al.  Applications of EOF Analysis to the Spatial Estimation of Circulation Features in the Ocean Sampled by High-Resolution CTD Soundings , 1998 .

[23]  James N. K. Liu,et al.  An Artificial Neural Network with Chaotic Oscillator for Wind Shear Alerting , 2012 .

[24]  E. Uhlhorn,et al.  Loop Current Response to Hurricanes Isidore and Lili , 2008 .

[25]  V. Kourafalou,et al.  Simulating the dynamics and intensification of cyclonic Loop Current Frontal Eddies in the Gulf of Mexico , 2012 .

[26]  Ruoying He,et al.  Spatial and temporal variability of SST and ocean color in the Gulf of Maine based on cloud-free SST and chlorophyll reconstructions in 2003–2012 , 2014 .

[27]  J. McWilliams,et al.  A New Sea Surface Height–Based Code for Oceanic Mesoscale Eddy Tracking , 2014 .

[28]  Tl Lee.  Neural network prediction of a storm surge , 2006 .

[29]  Alberto Alvarez,et al.  Forecasting the SST space-time variability of the Alboran Sea with genetic algorithms , 1999 .

[30]  M. Yau,et al.  Application of Artificial Neural Networks on North Atlantic Tropical Cyclogenesis Potential Index in Climate Change , 2012 .

[31]  W. Hsieh,et al.  Coupling Neural Networks to Incomplete Dynamical Systems via Variational Data Assimilation , 2001 .

[32]  Ruoying He,et al.  Modeling ocean circulation and biogeochemical variability in the Gulf of Mexico , 2013 .

[33]  J. Beckers,et al.  EOF Calculations and Data Filling from Incomplete Oceanographic Datasets , 2003 .

[34]  Chester J. Koblinsky,et al.  Empirical orthogonal function analysis of global TOPEX/POSEIDON altimeter data and implications for detection of global sea level rise , 1996 .

[35]  Alberto Alvarez,et al.  Performance of satellite-based ocean forecasting (SOFT) systems: A study in the Adriatic Sea , 2003 .

[36]  T. Miles,et al.  Temporal and spatial variability of Chl-a and SST on the South Atlantic Bight: Revisiting with cloud-free reconstructions of MODIS satellite imagery , 2010 .

[37]  Tal Ezer,et al.  Loop Current warming by Hurricane Wilma , 2006 .

[38]  Ruoying He,et al.  Clustering of Loop Current patterns based on the satellite-observed sea surface height and self-organizing map , 2015 .

[39]  Robert R. Leben,et al.  On the Linear Relationship between Loop Current Retreat Latitude and Eddy Separation Period , 2010 .

[40]  Tal Ezer,et al.  An exercise in forecasting loop current and eddy frontal positions in the Gulf of Mexico , 2005 .

[41]  V. Kourafalou,et al.  Influence of frontal cyclone evolution on the 2009 (Ekman) and 2010 (Franklin) Loop Current eddy detachment events , 2014 .

[42]  J. Soares,et al.  An application of neural network technique to correct the dome temperature effects on pyrgeometer measurements , 2006 .

[43]  William W. Hsieh,et al.  Skill Comparisons between Neural Networks and Canonical Correlation Analysis in Predicting the Equatorial Pacific Sea Surface Temperatures , 2000 .

[44]  Michel Rixen,et al.  Results on SSH neural network forecasting in the Mediterranean Sea , 2002, SPIE Remote Sensing.

[45]  A. Semtner.  Modeling Ocean Circulation , 1995, Science.

[46]  William W. Hsieh,et al.  Nonlinear multivariate and time series analysis by neural network methods , 2004 .

[47]  J. Lamkin,et al.  Larval fish assemblages at the Loop Current boundary in the Gulf of Mexico : Larval fish assemblages and oceanic boundaries , 1993 .

[48]  Vladimir M. Krasnopolsky,et al.  The Application of Neural Networks in the Earth System Sciences: Neural Networks Emulations for Complex Multidimensional Mappings , 2013 .

[49]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[50]  Ruoying He,et al.  A cloud‐free, satellite‐derived, sea surface temperature analysis for the West Florida Shelf , 2003 .

[51]  A. Hannachi,et al.  A Primer for EOF Analysis of Climate Data , 2004 .

[52]  R. Leben,et al.  What Do We Know and What Can We Predict About the Timing of Loop Current Eddy Separation , 2006 .

[53]  William W. Hsieh,et al.  Neural network forecasts of the tropical Pacific sea surface temperatures , 2006, Neural Networks.

[54]  Jennifer M. Jolley.  Applying Neural Network Models to Predict Recurrent Maltreatment in Child Welfare Cases with Static and Dynamic Risk Factors , 2012 .

[55]  R. Vautard,et al.  Singular-spectrum analysis: a toolkit for short, noisy chaotic signals , 1992 .

[56]  P. Sammarco,et al.  Expansion of coral communities within the Northern Gulf of Mexico via offshore oil and gas platforms , 2004 .

[57]  Peter Cornillon,et al.  Air–sea interaction over ocean fronts and eddies , 2008 .