Sea State Estimation from Wave-Induced Ship Responses using Machine Learning

Raphaël E. G. Mounet*, Ulrik D. Nielsen

*Corresponding author for this work

Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

Abstract

This study investigates the application of advanced data processing and machine learning techniques for determining the sea state encountered by a ship in a seaway. Measurements of the wave-induced responses on a large ship during transoceanic voyages are processed and utilized to derive estimates of the wave parameters and spectra in the experienced seaway.

The proposed methodology leverages various machine learning techniques, such as LightGBM and Artificial Neural Networks (ANN). The use of reanalysis data from freely-accessible public repositories – like ERA5 from the European Centre for Medium-Range Weather Forecasts (ECMWF) – is evaluated for its adequacy in model training and testing purposes. The preliminary results demonstrate the efficacy of machine learning techniques in enhancing the accuracy and reliability of sea state estimates.

Providing reliable, real-time information about the local wave conditions is crucial for ship operators and onboard decision-support systems, facilitating efficient decisionmaking and enhancing safety and fuel efficiency in maritime operations.
Original languageEnglish
Publication date2025
Number of pages1
Publication statusPublished - 2025
EventThe 25th DNV Nordic Maritime Universities Workshop - Technical University of Denmark, Kgs. Lyngby, Denmark
Duration: 30 Jan 202531 Jan 2025

Workshop

WorkshopThe 25th DNV Nordic Maritime Universities Workshop
LocationTechnical University of Denmark
Country/TerritoryDenmark
CityKgs. Lyngby
Period30/01/202531/01/2025

Fingerprint

Dive into the research topics of 'Sea State Estimation from Wave-Induced Ship Responses using Machine Learning'. Together they form a unique fingerprint.

Cite this