RIASSUNTO
Maritime Situational Awareness (MSA) is the capability of understanding events, circumstances and activities within and impacting the maritime environment. Nowadays, the vessel positioning sensors provide a vast amount of data that could enhance the maritime knowledge if analysed and modelled. Vessel positioning data is dynamic and continuous on time and space, requiring spatio-temporal data mining techniques to derive knowledge. In this paper, several spatio-temporal data mining techniques are proposed to enhance the MSA, tackling existing challenges such as automatic maritime route extraction and synthetic representation, mapping vessels activities, anomaly detection or position and track prediction. The aim is to provide a more complete and interactive Maritime Situational Picture (MSP) and, hence, to provide more capabilities to operational authorities and policy-makers to support the decision-making process. The proposed approaches are evaluated on diverse areas of interest from the Dover Strait to the Icelandic coast.