A method to rapidly estimate extreme ship response events is developed in this paper. The method involves training by a Long Short-Term Memory (LSTM) neural network to correct a lower-fidelity hydrodynamic model to the level of a higher-fidelity simulation. More focus is placed on larger responses by isolating the time-series near peak events identified in the lower-fidelity simulations and training on only the shorter time-series around the large event. The method is tested on the estimation of pitch time-series maxima in Sea State 5 (significant wave height of 4.0 meters and modal period of 15.0 seconds,) generated by a lower-fidelity hydrodynamic solver known as SimpleCode and a higher-fidelity tool known as the Large Amplitude Motion Program (LAMP). The results are also compared with an LSTM trained without special considerations for large events.

Operational guidance is provided in the form of selection of speeds and headings, and is generally based on accessing ship motions response predictions from a pre-computed database or lookup table for a given condition. Operational guidance is an important consideration in the survival of a ship and has been the focus of many International Maritime Organization (IMO) publications, IMO (1995), IMO (2007), IMO (2020). Recommendations for ship-specific operational guidance has been developed and discussed in the interim guidelines of the Second Generation Intact Stability by IMO, IMO (2020). While these guidelines are certainly useful in design and at sea, they are not comprehensive. The ocean environment is random and complex.