Marine Environment Numerical Simulation and Artificial Intelligence

Dear Colleagues,

The marine environment underpins the sustainability, safety, and efficiency of human activities in marine and coastal areas. Understanding its complex interactions is not only critical to preventing structural failures that could lead to catastrophic economic losses and environmental disasters, but also essential to advancing sustainable ocean development in line with global climate and energy goals. Accurate numerical simulation therefore becomes an indispensable tool for predicting ocean states, assessing risks, and designing resilient marine infrastructure. However, conventional numerical models face long-standing challenges: sparse in-situ observations limit model initialization and validation, subgrid-scale processes rely on semi-empirical parameterizations with substantial uncertainties, and high-fidelity simulations demand prohibitive computational resources.

Artificial intelligence, particularly deep learning, brings revolutionary improvements to marine numerical simulation and the observational systems that feed it, effectively addressing the pain points of traditional methods such as high observation costs, data sparsity, and inaccurate physical parameterizations. In terms of observation, AI can reconstruct missing data and filter out noise, supplying richer inputs for model forcing and assimilation. In simulation, deep learning‑based surrogate models compress traditional computation from hours to milliseconds, enabling real-time forecasting and rapid uncertainty quantification, while also learning to improve subgrid parameterization schemes directly from high-resolution data. Data assimilation—the fusion of models and observations—is dramatically accelerated by AI-based emulators and learned error covariances. Furthermore, physics‑guided AI and hybrid modeling ensure that prediction results obey physical conservation laws while maintaining the flexibility of data‑driven approaches, offering a new paradigm that combines the robustness of first principles with the pattern‑recognition power of neural networks.

This Special Issue aims to present and disseminate the most recent advances related to the marine environment, focusing on marine environmental observation, numerical simulation of marine environment, structural resilience under extreme marine events, and artificial intelligence prediction. We consider contributions addressing theoretical and experimental, and numerical studies on marine environmental observation and data reconstruction; numerical simulation of marine environments and fluid–structure–seabed interactions; structural resilience under extreme marine events, including failure mechanisms, risk assessment, and resilient design; and artificial intelligence prediction methods—such as physics-informed machine learning, deep learning-based surrogate models, and AI-enhanced data assimilation—to advance the understanding and forecasting of marine environments.

Prof. Dr. Zhifeng Wang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Marine Science and Engineering is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• ocean environmental observations
• artificial intelligence
• numerical simulation
• physical modelling experiment
• fluid-structure interaction
• marine environment
• marine environmental design parameters