Advertisement

Journal of Marine Science and Technology

, Volume 15, Issue 2, pp 160–175 | Cite as

A new approach for deriving temperature and salinity fields in the Indian Ocean using artificial neural networks

  • Prasad Kumar Bhaskaran
  • Ravindran Rajesh Kumar
  • Rahul Barman
  • Ravichandran Muthalagu
Original Article

Abstract

This work reports a new methodology for deriving monthly averages of temperature (T) and salinity (S) fields for the Indian Ocean based on the use of an artificial neural network (ANN). Investigation and analysis were performed for this region with two distinct datasets: (1) monthly climatological data for T and S fields (in 1° × 1° grid boxes) at standard depth levels of the World Ocean Atlas 1994 (WOA94), and; (2) heterogeneous randomly distributed in situ ARGO, ocean station data (OSD) and profiling (PFL) floats. A further numerical experiment was conducted with these two distinct datasets to train the neural network model. Nonlinear regression mapping utilizing a multilayer perceptron (MLP) is employed to tackle nonlinearity in the data. This study reveals that a feed-forward type of network with a resilient backpropagation algorithm is best suited for deriving T and S fields; this is demonstrated by independently using WOA94 and in situ data, which thus tests the robustness of the ANN model. The suppleness of the T and S fields derived from the ANN model provides the freedom to generate a new grid at any desired level with a high degree of accuracy. Comprehensive training, testing and validation exercises were performed to demonstrate the robustness of the model and the consistency of the derived fields. The study points out that the parameters derived from the ANN model using scattered, inhomogeneous in situ data show very good agreement with state-of-the-art WOA climatological data. Using this approach, improvements in ocean climatology can be expected to occur in a synergistic manner with in situ observations. Our investigation of the Indian Ocean reveals that this approach can be extended to model global oceans.

Keywords

Temperature Salinity Neural network 

References

  1. 1.
    Antonov JI, Levitus S, Boyer TP, Conkright ME, O’Brien T, Stephens C, Trotsenko B (1998) World ocean atlas 1998, vol 3: temperature of the Indian Ocean. NOAA Atlas NESDIS 29, US Government Printing Office, Washington, DCGoogle Scholar
  2. 2.
    Aysal TC, Barner KE (2006) Hybrid polynomial filters for Gaussian and non-Gaussian noise environments. IEEE Trans Signal Process 54(12):4644–4661Google Scholar
  3. 3.
    Ballabrera J, Mourre B, Garcia-Ladona E, Font J, Kalaroni S (2007) Modeling salinity profiles from temperature using cluster analysis and neural networks derived from Argo data. Geophys Res Abs 9:EGU2007-A-08145Google Scholar
  4. 4.
    Barman R, Prasad Kumar B, Pandey PC, Dube SK (2006) Tsunami travel time prediction using neural networks. Geophys Res Lett 33:L16612. doi: 10.1029/2006GL026688 CrossRefGoogle Scholar
  5. 5.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York, pp 364–369Google Scholar
  6. 6.
    Boyer T, Levitus S (1994) Quality control of oxygen, temperature and salinity data (NOAA Tech Rep 81). NODC, Washington, DC, pp 65Google Scholar
  7. 7.
    Conkright ME, Boyer T, Levitus S (1994) Quality control and processing of historical oceanographic nutrient data (NOAA Tech Rep NESDIS 79). NODC, Washington, DC, pp 75Google Scholar
  8. 8.
    Hinton GE (1992) How neural networks learn from experience. Sci Am 9:144–151CrossRefGoogle Scholar
  9. 9.
    Knutti R, Stocker TF, Joos F, Plattner GK (2003) Probabilistic climate change projections using neural networks. Climate Dyn 21:257–272CrossRefGoogle Scholar
  10. 10.
    Kriebel SKT, Brauer W, Eifler W (1998) Coastal upwelling prediction with a mixture of neural networks. IEEE Trans Geosci Remote Sens 36(5):1508–1518CrossRefGoogle Scholar
  11. 11.
    Levitus S (1982) Climatological atlas of the world ocean (NOAA/ERL GFDL Prof Paper 13). US Government Printing Office, Washington, DC, pp 173Google Scholar
  12. 12.
    Levitus S, Boyer TP (1994) World ocean atlas, vol 4: temperature. NOAA Atlas NESDIS. US Government Printing Office, Washington, DC, pp 117Google Scholar
  13. 13.
    Levitus S, Gelfeld R (1992) NODC inventory of physical oceanographic profiles (Key to Oceanographic Records Documentation no. 18). NODC, Washington, DCGoogle Scholar
  14. 14.
    Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Maths 2(2):164–168Google Scholar
  15. 15.
    Li S, Hsieh WW, Wu A (2005) Hybrid coupled modeling of the tropical Pacific using neural networks. J Geophys Res 110:C09024. doi: 10.1029/2004JC002595 CrossRefGoogle Scholar
  16. 16.
    Marquardt DW (1963) An algorithm for the least-squares estimation of nonlinear parameters. SIAM J Appl Maths 11(2):431–441Google Scholar
  17. 17.
    Navone HD, Ceccatto HA (1994) Predicting Indian monsoon rainfall: a neural network approach. Clim Dyn 10(6):305–312CrossRefGoogle Scholar
  18. 18.
    Prasad Kumar B, Rahul B, Dube SK, Pandey PC, Ravichandran M, Nayak S (2009) Development of a new comprehensive ocean atlas for Indian Ocean utilizing ARGO data. Int J Climatol. doi: 10.1002/joc.1885
  19. 19.
    Reidmiller M, Braun H (1993) A direct adaptive method for faster back-propagation learning—the RPROP algorithm. In: IEEE Int Conf Neural Networks, San Francisco, CA, 28 March–1 April 1993Google Scholar
  20. 20.
    Riedmiller M (1994) Advanced supervised learning in multi-layer perceptron––from back-propagation to adaptive learning algorithms. Int J Comput Stand Interfaces 16:265–278CrossRefGoogle Scholar
  21. 21.
    Rumelhart DE, Hinton G, Williams R (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: foundations. The MIT Press, Cambridge, MA, pp 318–362Google Scholar
  22. 22.
    Silverman D, Dracup J (2000) Artificial neural networks and long range precipitation prediction in California. J Appl Meteorol 31(1):57–66CrossRefGoogle Scholar
  23. 23.
    Simon H (1998) Neural networks—a comprehensive foundation, 2nd edn. Prentice-Hall, Upper Saddle River, NJGoogle Scholar
  24. 24.
    Sun C, Rienecker MM, Rosati A, Harrison M, Wittenberg A, Keppenne CL, Jacob JP, Kovach RM (2007) Comparison and sensitivity of ODASI ocean analyses in the tropical Pacific. Mon Weather Rev 135(6):2242–2264CrossRefGoogle Scholar
  25. 25.
    Wang W, Van Gelden PHAJM, Vrijling JK, Ma J (2006) Forecasting daily streamflow using hybrid ANN models. J Hydrol 324:383–399CrossRefGoogle Scholar
  26. 26.
    Wei Y, Kwok FC, George DC, Charles SM (2003) Inverse algorithm for tsunami forecasts. J Waterway Port Coast Ocean Eng 129(2):60–69Google Scholar

Copyright information

© JASNAOE 2009

Authors and Affiliations

  • Prasad Kumar Bhaskaran
    • 1
  • Ravindran Rajesh Kumar
    • 1
  • Rahul Barman
    • 2
  • Ravichandran Muthalagu
    • 3
  1. 1.Department of Ocean Engineering and Naval ArchitectureIndian Institute of TechnologyKharagpurIndia
  2. 2.Department of Atmospheric SciencesUniversity of Illinois at UrbanaChampaignUSA
  3. 3.Indian National Centre for Ocean Information Services, Ministry of Earth SciencesHyderabadIndia

Personalised recommendations