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.
Similar content being viewed by others
References
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, DC
Aysal TC, Barner KE (2006) Hybrid polynomial filters for Gaussian and non-Gaussian noise environments. IEEE Trans Signal Process 54(12):4644–4661
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-08145
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
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York, pp 364–369
Boyer T, Levitus S (1994) Quality control of oxygen, temperature and salinity data (NOAA Tech Rep 81). NODC, Washington, DC, pp 65
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 75
Hinton GE (1992) How neural networks learn from experience. Sci Am 9:144–151
Knutti R, Stocker TF, Joos F, Plattner GK (2003) Probabilistic climate change projections using neural networks. Climate Dyn 21:257–272
Kriebel SKT, Brauer W, Eifler W (1998) Coastal upwelling prediction with a mixture of neural networks. IEEE Trans Geosci Remote Sens 36(5):1508–1518
Levitus S (1982) Climatological atlas of the world ocean (NOAA/ERL GFDL Prof Paper 13). US Government Printing Office, Washington, DC, pp 173
Levitus S, Boyer TP (1994) World ocean atlas, vol 4: temperature. NOAA Atlas NESDIS. US Government Printing Office, Washington, DC, pp 117
Levitus S, Gelfeld R (1992) NODC inventory of physical oceanographic profiles (Key to Oceanographic Records Documentation no. 18). NODC, Washington, DC
Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Maths 2(2):164–168
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
Marquardt DW (1963) An algorithm for the least-squares estimation of nonlinear parameters. SIAM J Appl Maths 11(2):431–441
Navone HD, Ceccatto HA (1994) Predicting Indian monsoon rainfall: a neural network approach. Clim Dyn 10(6):305–312
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
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 1993
Riedmiller M (1994) Advanced supervised learning in multi-layer perceptron––from back-propagation to adaptive learning algorithms. Int J Comput Stand Interfaces 16:265–278
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 318–362
Silverman D, Dracup J (2000) Artificial neural networks and long range precipitation prediction in California. J Appl Meteorol 31(1):57–66
Simon H (1998) Neural networks—a comprehensive foundation, 2nd edn. Prentice-Hall, Upper Saddle River, NJ
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):2242–2264
Wang W, Van Gelden PHAJM, Vrijling JK, Ma J (2006) Forecasting daily streamflow using hybrid ANN models. J Hydrol 324:383–399
Wei Y, Kwok FC, George DC, Charles SM (2003) Inverse algorithm for tsunami forecasts. J Waterway Port Coast Ocean Eng 129(2):60–69
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Bhaskaran, P.K., Rajesh Kumar, R., Barman, R. et al. A new approach for deriving temperature and salinity fields in the Indian Ocean using artificial neural networks. J Mar Sci Technol 15, 160–175 (2010). https://doi.org/10.1007/s00773-009-0081-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00773-009-0081-2