Estimation of ocean subsurface thermal structure from surface parameters: A neural network approach

Satellite remote sensing provides diverse and useful ocean surface observations. It is of interest to determine if such surface observations can be used to infer information about the vertical structure of the ocean's interior, like that of temperature profiles. Earlier studies used either sea surface temperature or dynamic height/sea surface height to infer the subsurface temperature profiles. In this study we have used neural network approach to estimate the temperature structure from sea surface temperature, sea surface height, wind stress, net radiation, and net heat flux, available from an Arabian Sea mooring from October 1994 to October 1995, deployed by the Woods Hole Oceanographic Institution. On the average, 50% of the estimations are within an error of ±0.5°C and 90% within ±1.0°C. The average RMS error between the estimated temperature profiles and in situ observations is 0.584°C with a depth‐wise average correlation coefficient of 0.92.

[1]  A. Fischera,et al.  Moored observations of upper-ocean response to the monsoons in the Arabian Sea during 1994 – 1995 , 2002 .

[2]  C. Eriksen,et al.  Moored observations of upper-ocean response to the monsoons in the Arabian Sea during 1994-1995 , 2002 .

[3]  M. Ali,et al.  Detection of Bay of Bengal eddies from TOPEX and in situ observations , 2000 .

[4]  Peter C. Chu,et al.  Determination of Vertical Thermal Structure from Sea Surface Temperature , 2000 .

[5]  Peter C. Chu,et al.  A Geometric Model for the Beaufort/Chukchi Sea Thermohaline Structure , 1999 .

[6]  John C. Kindle,et al.  Atmospheric forcing in the Arabian Sea during 1994–1995: observations and comparisons with climatology and models , 1998 .

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  William J. Emery,et al.  An Automated Neural Network Cloud Classifier for Use over Land and Ocean Surfaces , 1997 .

[9]  A. Fischer,et al.  Arabian Sea mixed layer deepening during the monsoon : observations and dynamics , 1997 .

[10]  P. Chu,et al.  South China Sea warm pool detected in spring from the Navy's Master Oceanographic Observational Data Set (MOODS) , 1997 .

[11]  Peter C. Chu,et al.  A parametric model for the Yellow Sea thermal variability , 1997 .

[12]  C. Eriksen,et al.  Moored instruments weather Arabian Sea monsoons, yield data , 1997 .

[13]  J. L. Mitchell,et al.  Synthetic temperature profiles derived from Geosat altimetry: Comparison with air‐dropped expendable bathythermograph profiles , 1990 .

[14]  Paul C. Fiedler,et al.  Surface manifestations of subsurface thermal structure in the California Current , 1988 .

[15]  B. Simon,et al.  Inference of vertical motion in the Equatorial Indian Ocean using satellite data , 1987 .

[16]  Timothy W. Kao,et al.  The Gulf Stream and its frontal structure: a quantitative representation , 1987 .

[17]  C. Szczechowski,et al.  Potential Oceanographic Applications Of Satellite Altimetry For Inferring Subsurface Thermal Structure , 1983, Proceedings OCEANS '83.

[18]  R. Cheney.  Comparison data for Seasat altimetry in the western North Atlantic , 1982 .

[19]  Carl Wunsch,et al.  On Using Satellite Altimetry to Determine the General Circulation of the Oceans With Application to Geoid Improvement (Paper 80R0631) , 1980 .