\newpage \section{Introduction} \label{sec:intro} The global shipping industry transports over \SI{80}{\percent} of world trade by volume \cite{UNCTAD2022}. Despite advances in hull design and propulsion, a substantial fraction of fuel burn is attributable to sub‑optimal speed choices driven by inaccurate speed forecasts \cite{Mitsui2019}. Conventional approaches—e.g., the Holtrop–Mennen method \cite{Holtrop1972} or the ITTC‑1998 friction line \cite{ITTC1998}—rely on static ship parameters and simplified sea‑state corrections. Such models neglect the complex, nonlinear interaction among wind, waves, currents, and ship trim.
\subsection{Future Work} \begin{enumerate} \item Extension to **fuel‑consumption** prediction via a joint multi‑task network. \item Incorporation of **ship‑maneuvering** dynamics for autonomous docking. \item Open‑source **benchmark suite** for maritime speed prediction (datasets, evaluation scripts). \end{enumerate} marvelocity pdf
\subsection{Machine‑Learning Approaches} Bai et al. \cite{Bai2021} employed deep neural networks to predict fuel consumption from AIS and weather data, achieving a 5 \% error reduction. Chen and Li \cite{Chen2022} introduced a physics‑informed neural network (PINN) to enforce momentum balance, yet their dataset (≈ 200 k samples) limits generalisation. Such models neglect the complex, nonlinear interaction among