@article{Ong2025, 
author = {Muk Chen Ong and Guang Yin},
title = {Synergizing machine learning with fluid–structure interaction research: An overview of trends and challenges},
year = {2025},
journal = {Ocean},
volume = {1},
number = {1},
pages = {9470002},
keywords = {fluid–structure interaction (FSI), machine learning (ML), dynamics, prediction, control},
url = {https://www.sciopen.com/article/10.26599/OCEAN.2025.9470002},
doi = {10.26599/OCEAN.2025.9470002},
abstract = {Fluid–structure interaction (FSI) is a ubiquitous physical phenomenon in ocean engineering, which is critical in the design and operations of various marine structures and underwater vehicles. Especially, in a low-carbon society, FSI plays a pivotal role in the development of hydrokinetic energy conversion devices in ocean renewable energy. For FSI problems, strong nonlinear interactions between flow and structures, as well as turbulent flow pose significant challenges for understanding and predicting the dynamics of the FSI system. Facing these challenges and driven by the motivation of harnessing clean energy from ocean currents and waves, modern machine learning (ML) provides a novel and revolutionary solution to reduce the time and cost associated with traditional methodology in understanding the FSI physics, predicting the FSI dynamics and control for the engineering design. This paper focuses on the transformative potential of modern ML techniques in ocean engineering and presents a review of the current state-of-art ML applications in analyzing complex FSI phenomena within this field. Relevant ML algorithms and techniques are highlighted and the challenges of integrating these techniques into FSI problems are discussed.}
}