A Neural-based Bio-regionalization of the Mediterranean Sea using Satellite and Argo-Float Records.

Abstract

We present a partitioning of the Mediterranean Sea into regions having well defined characteristics with respect to sea-surface temperature and surface chlorophyll-a concentration observed by satellite and by the Argo mixed-layer depth. This regionalization was performed using an innovative classification based on neural networks, the so-called 2S-SOM. Its major advantage is to consider the specificity of the variables by adding specific weights to each of them, which facilitates the classification and consequently highlights the regional correlations. The 2S-SOM provided a well differentiated regionalization of the Mediterranean Sea waters into seven bioregions governed by specific physical and biogeochemical processes.