Machine learning for naval architecture, ocean and marine engineering

• Published in: Journal of marine science and technology Vol. 28; no. 1; pp. 1 - 26
• Main Author: PANDA, J P
• Format: Journal Article
• Language: English
• Published: Tokyo Springer Japan 01.03.2023; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Automotive Engineering; Damage detection; Data mining; Datasets; Engineering; Engineering Design; Engineering Fluid Dynamics; Information processing; Learning algorithms; Machine learning; Marine engineering; Marine environment; Mathematical models; Mechanical Engineering; Naval architecture; Naval engineering; Neural networks; Numerical analysis; Ocean; Offshore; Offshore Engineering; Offshore platforms; Optimization; Physics; Regression analysis; Review Article; Shipbuilding; Support vector machines; Wave height; Wind damage; Wind loads; Work platforms; Naval architecture; Marine engineering; Ocean engineering; Artificial intelligence; Data driven modeling; Machine learning
• ISSN: 0948-4280; 1437-8213
• DOI: 10.1007/s00773-022-00914-5

Machine learning (ML)-based techniques have found significant impact in many fields of engineering and sciences, where data-sets are available from experiments and high-fidelity numerical simulations. Those data-sets are generally utilised in a machine learning model to extract information about the underlying physics and derive functional relationships mapping input variables to target quantities of interest. Commonplace machine learning algorithms utilised in scientific machine learning (SciML) include neural networks, support vector machines, regression trees, random forests, etc. The focus of this article is to review the applications of ML in naval architecture, ocean and marine engineering problems; and identify priority directions of research. We discuss the applications of machine learning algorithms for different problems such as wave height prediction, calculation of wind loads on ships, damage detection of offshore platforms, calculation of ship-added resistance and various other applications in coastal and marine environments. The details of the data-sets including the source of data-sets utilised in the ML model development are included. The features used as the inputs to the ML models are presented in detail and finally, the methods employed in optimisation of the ML models were also discussed. Based on this comprehensive analysis, we point out future directions of research that may be fruitful for the application of ML to ocean and marine engineering problems.