Accurate estimation of significant wave height with Support Vector Regression algorithms and marine radar images

Abstract

Significant wave height (Hs) is a basic parameter in wave characterization, important for different problems in marine activities such as the design and management of vessels, marine structures, and wave energy converters. Hs is usually estimated using in-situ sensors, mainly buoys, that record time series of wave elevation information. In this paper we propose a method for Hs estimation based on a Support Vector Regression algorithm over non-coherent X-band marine radar images. Results for three different platforms (Fino 1, Ekofisk and Glas Dowr) at different locations of the North Sea and South Africa are presented, showing that the SVR obtains a better result than the existing standard method in Hs prediction, within different sea states observed at each location.