Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation

This study presents a novel approach to predicting ship speed based on real-time voyage observation data, aiming to enhance maritime safety and operational efficiency. Observational data from a 20,000-ton bulk carrier, including variables such as latitude, longitude, GPS orientation, wind direction,...

Full description

Saved in:
Bibliographic Details
Main Authors: Weidong Gan, Dianguang Ma, Yu Duan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/6/1011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167380699774976
author Weidong Gan
Dianguang Ma
Yu Duan
author_facet Weidong Gan
Dianguang Ma
Yu Duan
author_sort Weidong Gan
collection DOAJ
description This study presents a novel approach to predicting ship speed based on real-time voyage observation data, aiming to enhance maritime safety and operational efficiency. Observational data from a 20,000-ton bulk carrier, including variables such as latitude, longitude, GPS orientation, wind direction, wind speed, and main engine parameters, were collected and preprocessed to mitigate noise and handle missing values. Six machine learning models—the Backpropagation (BP) Neural Network, Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), XGBoost, and LightGBM—were employed to develop predictive models. Among these, the LightGBM model demonstrated the highest prediction accuracy, achieving a Root Mean Squared Error (RMSE) of 0.188, Mean Absolute Error (MAE) of 0.149, and a coefficient of determination (R<sup>2</sup>) of 0.978. The results highlight the potential of the LightGBM model in optimizing ship navigation and improving maritime operational efficiency. These findings offer a reliable foundation for further advancements in predictive maritime technologies and route optimization.
format Article
id doaj-art-587de14bb53c44dfaf71750bc3d242c8
institution OA Journals
issn 2077-1312
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-587de14bb53c44dfaf71750bc3d242c82025-08-20T02:21:13ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-01136101110.3390/jmse13061011Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard ObservationWeidong Gan0Dianguang Ma1Yu Duan2Tianjin Research Institute for Water Transport Engineering, Ministry of Transport, Tianjin 300456, ChinaTianjin Research Institute for Water Transport Engineering, Ministry of Transport, Tianjin 300456, ChinaTianjin Research Institute for Water Transport Engineering, Ministry of Transport, Tianjin 300456, ChinaThis study presents a novel approach to predicting ship speed based on real-time voyage observation data, aiming to enhance maritime safety and operational efficiency. Observational data from a 20,000-ton bulk carrier, including variables such as latitude, longitude, GPS orientation, wind direction, wind speed, and main engine parameters, were collected and preprocessed to mitigate noise and handle missing values. Six machine learning models—the Backpropagation (BP) Neural Network, Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), XGBoost, and LightGBM—were employed to develop predictive models. Among these, the LightGBM model demonstrated the highest prediction accuracy, achieving a Root Mean Squared Error (RMSE) of 0.188, Mean Absolute Error (MAE) of 0.149, and a coefficient of determination (R<sup>2</sup>) of 0.978. The results highlight the potential of the LightGBM model in optimizing ship navigation and improving maritime operational efficiency. These findings offer a reliable foundation for further advancements in predictive maritime technologies and route optimization.https://www.mdpi.com/2077-1312/13/6/1011ship speed predictionshipboard observationmachine learningmaritime efficiency
spellingShingle Weidong Gan
Dianguang Ma
Yu Duan
Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
Journal of Marine Science and Engineering
ship speed prediction
shipboard observation
machine learning
maritime efficiency
title Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
title_full Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
title_fullStr Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
title_full_unstemmed Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
title_short Comparisons of Machine Learning Methods in Ship Speed Prediction Based on Shipboard Observation
title_sort comparisons of machine learning methods in ship speed prediction based on shipboard observation
topic ship speed prediction
shipboard observation
machine learning
maritime efficiency
url https://www.mdpi.com/2077-1312/13/6/1011
work_keys_str_mv AT weidonggan comparisonsofmachinelearningmethodsinshipspeedpredictionbasedonshipboardobservation
AT dianguangma comparisonsofmachinelearningmethodsinshipspeedpredictionbasedonshipboardobservation
AT yuduan comparisonsofmachinelearningmethodsinshipspeedpredictionbasedonshipboardobservation