Physics-based learning models for ship hydrodynamics

Gabriel D. Weymouth, Dick K.P. Yue

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review


We present the concepts of physics-based learning models (PBLM) and their relevance and application to the field of ship hydrodynamics. The utility of physics-based learning is motivated by contrasting generic learning models for regression predictions, which do not presume any knowledge of the system other than the training data provided with methods such as semi-empirical models, which incorporate physical insights along with data-fitting. PBLM provides a framework wherein intermediate models, which capture (some) physical aspects of the problem, are incorporated into modem generic learning tools to substantially improve the predictions of the latter, minimizing the reliance on costly experimental measurements or high-resolution highfidelity numerical solutions. To illustrate the versatility and efficacy of PBLM, we present three wave-ship interaction problems: 1) at speed waterline profiles; 2) ship motions in head seas; and 3) three-dimensional breaking bow waves. PBLM is shown to be robust and produce error rates at or below the uncertainty in the generated data at a small fraction of the expense of high-resolution numerical predictions.

Original languageEnglish
Title of host publicationSociety of Naval Architects and Marine Engineers - Transactions 2015
PublisherSociety of Naval Architects and Marine Engineers: SNAME
ISBN (Electronic)9780939773954
Publication statusPublished - 2015
Externally publishedYes
EventSNAME 2013 Annual Meeting and Expo and Ship Production Symposium: Where Industry and Technology Meet - Bellevue, United States
Duration: 6 Nov 20138 Nov 2013


ConferenceSNAME 2013 Annual Meeting and Expo and Ship Production Symposium: Where Industry and Technology Meet
Country/TerritoryUnited States


  • CFD
  • Computers in design
  • Hull form hydrodynamics
  • Machine learning
  • Seakeeping


Dive into the research topics of 'Physics-based learning models for ship hydrodynamics'. Together they form a unique fingerprint.

Cite this