Predicting ocean surface currents using numerical weather prediction model and Kohonen neural network: a northern Adriatic study

The paper documents a concept of ocean forecasting system for ocean surface currents based on self-organizing map (SOM) trained by high-resolution numerical weather prediction (NWP) model and high-frequency (HF) radar data. Wind and surface currents data from the northern Adriatic coastal area were used in a 6-month long training phase to obtain SOM patterns. Very high correlation between current and joined current and wind SOM patterns indicated the strong relationship between winds and currents and allowed for creation of a prediction system. Increasing SOM dimensions did not increase reliability of the forecasting system, being limited by the amount of the data used for training and achieving the lowest errors for 4 × 4 SOM matrix. As the HF radars and high-resolution NWP models are strongly expanding in coastal oceans, providing reliable and long-term datasets, the applicability of the proposed SOM-based forecasting system is expected to be high.

[1]  Lutgarde M. C. Buydens,et al.  Self- and Super-organizing Maps in R: The kohonen Package , 2007 .

[2]  Chuanmin Hu,et al.  Tracking the Deepwater Horizon Oil Spill: A Modeling Perspective , 2011 .

[3]  Pierre F. J. Lermusiaux,et al.  Uncertainty estimation and prediction for interdisciplinary ocean dynamics , 2006, J. Comput. Phys..

[4]  Libe Washburn,et al.  High-frequency radar observations of ocean surface currents. , 2013, Annual review of marine science.

[5]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[6]  E. Stanev,et al.  Consistency and complementarity of different coastal ocean observations: A neural network‐based analysis for the German Bight , 2011 .

[7]  Joanna Staneva,et al.  Blending Surface Currents from HF Radar Observations and Numerical Modeling: Tidal Hindcasts and Forecasts , 2015 .

[8]  Georges Voronoi.  Nouvelles applications des paramètres continus à la théorie des formes quadratiques. Deuxième mémoire. Recherches sur les parallélloèdres primitifs. , 1908 .

[9]  Robert H. Weisberg,et al.  Coastal Ocean Observing Systems , 2015 .

[10]  Juan M. Corchado,et al.  A Hybrid CBR Model for Forecasting in Complex Domains , 2002, IBERAMIA.

[11]  J. Faraway,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[12]  Morakot Pilouk,et al.  Spatial data modelling for 3D GIS , 2007 .

[13]  G. S. Miller,et al.  Observation of Ekman Veering at the Bottom of Lake Michigan , 1988 .

[14]  Hrvoje Kalinic,et al.  Sensitivity of Self-Organizing Map surface current patterns to the use of radial vs. Cartesian input vectors measured by high-frequency radars , 2015, Comput. Geosci..

[15]  Tong Zhu,et al.  Research on the hygroscopic properties of aerosols by measurement and modeling during CAREBeijing-2006 , 2009 .

[16]  Guilherme De A. Barreto,et al.  Time Series Prediction with the Self-Organizing Map: A Review , 2007, Perspectives of Neural-Symbolic Integration.

[17]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[18]  Jean-Michel Brankart,et al.  A Reduced-Order Kalman Filter for Data Assimilation in Physical Oceanography , 2007, SIAM Rev..

[19]  N. Banas,et al.  Evaluation of a coastal ocean circulation model for the Columbia River plume in summer 2004 , 2009 .

[20]  Juan M. Corchado,et al.  Hybrid artificial intelligence methods in oceanographic forecast models , 2002, IEEE Trans. Syst. Man Cybern. Part C.

[21]  Juan M. Corchado,et al.  A hybrid case-based model for forecasting , 2001, Appl. Artif. Intell..

[22]  J. Geleyn,et al.  Interpolation of wind, temperature and humidity values from model levels to the height of measurement , 1988 .

[23]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[24]  Martina Tudor,et al.  Use of high-resolution dynamical adaptation in operational suite and research impact studies , 2004 .

[25]  Ruoying He,et al.  Sea Surface Temperature Patterns on the West Florida Shelf Using Growing Hierarchical Self-Organizing Maps , 2006 .

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

[27]  Vladimir M. Krasnopolsky,et al.  Neural network emulations for complex multidimensional geophysical mappings: Applications of neural network techniques to atmospheric and oceanic satellite retrievals and numerical modeling , 2007 .

[28]  Georg Dorffner,et al.  Neural Networks for Time Series Processing , 1996 .

[29]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[30]  Simone Cosoli,et al.  Validation of Surface Current Measurements in the Northern Adriatic Sea from High-Frequency Radars , 2010 .

[31]  B. Grisogono,et al.  Sea/land breeze climatological characteristics along the northern Croatian Adriatic coast , 2007 .

[32]  Martina Tudor,et al.  The case study of bura of 1st and 3rd February 2007 , 2010 .

[33]  Y. Masumoto,et al.  The reversal of the multi‐decadal trends of the equatorial Pacific easterly winds, and the Indonesian Throughflow and Leeuwin Current transports , 2011 .

[34]  Zhengdong Lu,et al.  Fast neural network surrogates for very high dimensional physics-based models in computational oceanography , 2007, Neural Networks.

[35]  David G. Stork,et al.  Pattern Classification , 1973 .

[36]  Stephan D. Howden,et al.  The Integrated Ocean Observing System High-Frequency Radar Network: Status and Local, Regional, and National Applications , 2010 .

[37]  I. Vilibić,et al.  Using Self-Organising Maps to investigate long-term changes in deep Adriatic water patterns , 2011 .

[38]  A. Mazzoldi,et al.  A Real-Time and Offline Quality Control Methodology for SeaSonde High-Frequency Radar Currents , 2012 .

[39]  P. K. Kundu,et al.  Ekman Veering Observed near the Ocean Bottom , 1976 .

[40]  Raúl Medina,et al.  Backtracking drifting objects using surface currents from high-frequency (HF) radar technology , 2012, Ocean Dynamics.

[41]  William J. Emery,et al.  Data Analysis Methods in Physical Oceanography , 1998 .

[42]  Sonia Castanedo,et al.  Application of HF radar currents to oil spill modelling. , 2009, Marine pollution bulletin.

[43]  I. Vilibić,et al.  Surface current patterns in the northern Adriatic extracted from high‐frequency radar data using self‐organizing map analysis , 2011 .

[44]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[45]  D. Crombie,et al.  Doppler Spectrum of Sea Echo at 13.56 Mc./s. , 1955, Nature.

[46]  Chris Chatfield,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[47]  J. Abbot,et al.  Application of artificial neural networks to rainfall forecasting in Queensland, Australia , 2012, Advances in Atmospheric Sciences.

[48]  Travis A. Smith,et al.  The US Navy coupled ocean-wave prediction system , 2014 .

[49]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[50]  S. Cosoli,et al.  Surface circulation in the Gulf of Trieste (northern Adriatic Sea) from radar, model, and ADCP comparisons , 2013 .

[51]  I. Vilibić,et al.  Mapping underwater sound noise and assessing its sources by using a self-organizing maps method. , 2013, The Journal of the Acoustical Society of America.