I. Introduction
Real time estimation of actual and imminent wave fields in the vicinity of ships and floating structures are important for safe and efficient operations. Historically, three main approaches have been cited in the open literatures with varying degrees of accuracies: the use of wave buoys, ship radars (e.g. X-band and K-band radars) / satellite and ship motions. A few publications from the open literature on these topics are given in [1],[2],[3] on wave rider buoys, [4] to [8] on using ship radars and [9] to [13], on hydrodynamic and spectral modeling using ship motions. It is not the intention here to present an exhaustive list and a detailed review on each topic but rather highlight a few papers focused on the machine learning model. In [16] Anagnostopoulos predicted propulsion power using Big Data techniques. Sclavounos and Ma used Support Vector Machine model to forecast the sea state elevations and vessel responses using past time records [17]. A Grey Online Sequential Extreme Learning Machine is implemented to model ship roll predictions by Yin et al. in [18].