To main content

A comprehensive review of data processing for ship performance analysis

Abstract

Reliable ship performance analysis can help prevent misguided navigation decisions and enable a more accurate estimation of fuel consumption. Supporting decarbonisation goals and following increasingly stringent maritime regulations will depend on these capabilities. While analysis tools and data collection have come a long way, the processing and managing of ship performance data is still continuously challenged by its complexity and inherent imperfections. Despite its importance, there is still little systematic research on how to process data confined to this field. This paper presents a comprehensive review of methodologies aimed at addressing data-related challenges in ship performance analysis. Based on literature published between 2014 and 2024, the authors identified major data sources such as AIS, onboard sensors, and noon reports, and we examined common quality issues. Subsequently, key processing techniques, including data synchronisation, missing value imputation, data cleaning, and uncertainty management, are evaluated in terms of their applications, effectiveness, and limitations. This review also highlights a significant gap due to the lack of a consistent unified processing pipeline. Resolving these challenges requires not only improved methodologies but also collective efforts to establish benchmark datasets and best practices. These research efforts are critical to enabling reliable data-driven decisions and sustainable ship operations.
Read the publication

Category

Academic literature review

Language

English

Author(s)

Affiliation

  • SINTEF Ocean / Skip og havkonstruksjoner
  • Norwegian University of Science and Technology
  • Nanyang Technological University

Year

2025

Published in

Applied Ocean Research

ISSN

0141-1187

Volume

162

Page(s)

1 - 21

View this publication at Norwegian Research Information Repository