Underwater temperature field reconstruction method based on self organizing neural network and empirical orthogonal function

Abstract

The invention relates to an underwater temperature field reconstruction method based on a self organizing neural network and an empirical orthogonal function. A self-organizing characteristic mappinggraph including multidimensional information including an empirical orthogonal function coefficient, position information, time information, sea surface height and sea surface temperature corresponding to a temperature profile is established, an Euclidean distance between known information and a self-organizing characteristic mapping unit is used to determine an optimal matching unit, and the empirical orthogonal function coefficient to inverse is obtained. A sea surface parameter and water body temperature profile characteristic mapping network is established based on a lot of data information, and nonlinear mapping from sea surface parameters to the water body profile can be realized. The underwater temperature field reconstruction method based on the self organizing neural network and the empirical orthogonal function is excellent in performance, high in stability, needless of knowing a power process in the marine site, easy to realize, low in computing complexity, and suitable forobtaining ocean environmental parameters of the key marine site in quasi-real time by using satellite remote sensing data, and only uses correlation among the ocean environmental parameters.

Description

technical field [0001] The invention belongs to the fields of marine physics, marine engineering, underwater acoustic engineering, etc., and relates to an underwater temperature field reconstruction method based on self-organizing neural network and empirical orthogonal function, which is suitable for underwater temperature field reconstruction using satellite remote sensing data . Background technique [0002] Although a variety of underwater temperature field reconstruction methods have been used in engineering practice, such as temperature profile depth-by-depth layer regression methods, empirical function regression methods, etc., the underwater temperature field reconstruction in deep sea complex waters still faces serious challenges. technical challenge. The root cause is that the existing temperature profile reconstruction methods have certain defects in the face of strong nonlinear processes in complex marine environments. The specific analysis is as follows: [00...

AI Technical Summary

Problems solved by technology

Similar to the above method, in sea areas with frequent eddies and strong fronts, there is usually no significant correlation between sea surface remote sensing parameters and empirical orthogonal function coefficients, which will cause significant errors in temperature profile reconstruction

Images