Wave calibration in numerical wave tanks using AI methods

Analytical solutions for numerical wavetanks are limited presently to a simple bathymetry and third order accuracy. Furthermore, tanks are generally characterised using linear transfer functions to relate the wavemaker forcing amplitude to wave elevation at a probe located in the wavetank. This paper reports on a numerical wavetank implemented using the OpenFOAM software package. The aim of the research is to train neural networks to represent non-linear transfer functions mapping a desired wave surface-elevation time-trace at a probe to the wavemaker input required to create it.