As a consequence of technological innovations and the escalating focus on sustainable strategies within marine environments, autonomous ships have garnered heightened interest in recent times [1]. However, these ships face obstacles stemming from unfavorable meteorological circumstances, encompassing powerful gusts of wind and tempestuous ocean waves [2]. Consequently, the acquisition of immediate and accurate assessments of sea conditions assumes a vital role for autonomous ships, functioning as a crucial approach to ensuring their security and reliability [3]. Sea condition denotes the prevailing circumstances of wave dynamics and wind patterns within the expanse of the open ocean, characterized by quantitative metrics such as wave amplitude, temporal frequency, and spectral distribution [4]. A multitude of traditional techniques exist for evaluating sea conditions, yet each is encumbered with certain constraints [5]. Despite the continuous data provision afforded by manual observation, this method is unduly contingent upon the proficiency of the observers and lacks uniformity in its application.