Ship efficiency forecast based on sensors data collection: improving numerical models through data analytics

Andrea Coraddu, Luca Oneto, Francesco Baldi, Davide Anguita

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

30 Citations (Scopus)


In this paper authors investigate the problem of predicting the fuel consumption of a vessel in real scenario based on data measured by the onboard automation systems. The goal is achieved by exploiting three different approaches: White, Black and Gray Box Models. White Box Models (WBM) are based on the knowledge of the physical underling processes. Black Box Models (BBMs) build upon statistical inference procedures based on the historical data collection. Author proposal is a Gray Box Model (GBM) which is able to exploit both mechanistic knowledge of the underlying physical principles and available measurements. Results on real world data shows that the BBM is able to remarkably improve a state-of-the-art WBM, while the GBM is able to encapsulate the a-priory knowledge of the WBM into the BBM so to achieve the same performance of the latter but requiring less historical data.

Original languageEnglish
Title of host publicationMTS/IEEE OCEANS 2015 - Genova
Subtitle of host publicationDiscovering Sustainable Ocean Energy for a New World
Place of PublicationPiscataway, NJ
Number of pages10
ISBN (Electronic)9781479987368
Publication statusPublished - 17 Sept 2015
EventMTS/IEEE OCEANS 2015 - Genova - Genova, Italy
Duration: 18 May 201521 May 2015


ConferenceMTS/IEEE OCEANS 2015 - Genova


  • fuel Consumption
  • gray box model
  • machine learning
  • naval propulsion plant
  • ship efficiency


Dive into the research topics of 'Ship efficiency forecast based on sensors data collection: improving numerical models through data analytics'. Together they form a unique fingerprint.

Cite this