Pena, B; Huang, L; Ahlgren, F; (2020) A Review on Applications of Machine Learning in Shipping Sustainability. In: Proceedings of the SNAME Maritime Convention 2020. (pp. SNAME-SMC-2020-035). Society of Naval Architects and Marine Engineers (SNAME)

Preview

Text ML and ship - conference paper - very final version.pdf - Accepted Version Download (502kB) | Preview

Abstract

The shipping industry faces a significant challenge as it needs to significantly lower the amounts of Green House Gas emissions at the same time as it is expected to meet the rising demand. Traditionally, optimising the fuel consumption for ships is done during the ship design stage and through operating it in a better way, for example, with more energy-efficient machinery, optimising the speed or route. During the last decade, the area of machine learning has evolved significantly, and these methods are applicable in many more fields than before. The field of ship efficiency improvement by using Machine Learning methods is significantly progressing due to the available volumes of data from online measuring, experiments and computations. This amount of data has made machine learning a powerful tool that has been successfully used to extract information and intricate patterns that can be translated into attractive ship energy savings. This article presents an overview of machine learning, current developments, and emerging opportunities for ship efficiency. This article covers the fundamentals of Machine Learning and discusses the methodologies available for ship efficiency optimisation. Besides, this article reveals the potentials of this promising technology and future challenges.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item