An algorithm for the automatic recognition of oceanic features in frontal maps

Abstract

Satellite imagery provides a unique opportunity for oceanic fronts’ identification and the observation of the synoptic variability of the fronts. Top quality interpretative frontal maps are compiled by expert oceanographers from satellite and in situ data aided by numerical models of the ocean’s circulation. To be used for the initialization and data assimilation in numerical models, these frontal maps have to be digitized and vectorized. Here, we present an algorithm that automatically recognizes oceanic structures (fronts, eddies, filaments) in frontal maps formatted as raster images. The algorithm is based on a formalized description of the structure of the frontal zone, the image vectorization, and the detection of significant structural elements based on the classification of these elements. The classification of the structural elements was first developed by analyzing once-a-week satellite-derived sea surface temperature (SST) images for the western North Atlantic from 2010. The structural elements are then recognized based on their invariant spatial characteristics and their positions relative to one another in any new SST image. The algorithm outputs a set of digital arrays that are vector descriptors of all the significant structural elements of the frontal map.