Operator Guidance Informed by AI-Augmented Simulations

2023/07/17 by Samuel J. Edwards, Michael Levine, Edwards, Samuel J. +1
Earth and Planetary Sciences · Engineering · #68T07 #Applications (stat.AP) #Artificial Intelligence (cs.AI) #Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Computer and information sciences #FOS: Physical sciences #J.2 #Machine Learning (cs.LG) #Maritime Navigation and Safety #Oceanographic and Atmospheric Processes #Ship Hydrodynamics and Maneuverability

paper · pdf · doi:10.48550/arxiv.2307.08810

openalex publication_date 2023/07/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper will present a multi-fidelity, data-adaptive approach with a Long Short-Term Memory (LSTM) neural network to estimate ship response statistics in bimodal, bidirectional seas. The study will employ a fast low-fidelity, volume-based tool SimpleCode and a higher-fidelity tool known as the Large Amplitude Motion Program (LAMP). SimpleCode and LAMP data were generated by common bi-modal, bi-directional sea conditions in the North Atlantic as training data. After training an LSTM network with LAMP ship motion response data, a sample route was traversed and randomly sampled historical weather was input into SimpleCode and the LSTM network, and compared against the higher fidelity results.

Related

• Data-Driven Extreme Response Estimation
• Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states
• Response Component Analysis for Sea State Estimation Using Artificial Neural Networks and Vessel Response Spectral Data
• Data-driven, non-linear ship response prediction based on time series of irregular, long-crested sea states amidships
• Short-term ship roll motion prediction using the encoder–decoder Bi-LSTM with teacher forcing