Reconstruction of Sub-Surface Velocities from Satellite Observations Using Iterative Self-Organizing Maps

TL;DR

This paper introduces a novel method using modified self-organizing maps to accurately reconstruct deep ocean current velocities from satellite surface data without assuming specific water column structures, achieving high-resolution results.

Contribution

The paper presents a new approach that leverages local data correlations and autonomous float data to improve deep ocean velocity reconstruction without prior structural assumptions.

Findings

Root mean squared error of ~2.8cm/s in velocity reconstruction

Direction errors smaller than 30 degrees

Outperforms existing methods by over a factor of two

Abstract

In this letter a new method based on modified self-organizing maps is presented for the reconstruction of deep ocean current velocities from surface information provided by satellites. This method takes advantage of local correlations in the data-space to improve the accuracy of the reconstructed deep velocities. Unlike previous attempts to reconstruct deep velocities from surface data, our method makes no assumptions regarding the structure of the water column, nor the underlying dynamics of the flow field. Using satellite observations of surface velocity, sea-surface height and sea-surface temperature, as well as observations of the deep current velocity from autonomous Argo floats to train the map, we are able to reconstruct realistic high--resolution velocity fields at a depth of 1000m. Validation reveals extremely promising results, with a speed root mean squared error of ~2.8cm/s, a factor more than a factor of two smaller than competing methods, and direction errors consistently smaller than 30 degrees. Finally, we discuss the merits and shortcomings of this methodology and its possible future applications.