Machine Learning in Coastal Engineering

Dear Colleagues,

Background: As an extension of standard physics-driven techniques applied in coastal engineering, from physical to numerical modelling, AI is a promising data-driven approach that enables a swift yet reliable analysis of several coastal engineering problems, from gap-filling in wave time series data to the estimation of flooding and overtopping volumes. By leveraging extensive datasets generated from the aforementioned physics-driven modelling techniques, it becomes feasible to apply AI tools, namely machine learning—including artificial neural networks and Bayesian networks—to a myriad of case studies related to coastal protection, wave climatology, and marine renewable energy, among others.

Aim and scope: This SI seeks to showcase original research articles, comprehensive reviews, and insightful case studies that explore the diverse applications of ML in coastal engineering, including but not limited to wave field modelling, sea level variation analysis, and morphological change predictions.

History: While traditional numerical and empirical models have proven effective, they increasingly face challenges related to complexity and computational demands. ML not only matches or surpasses traditional methods in predictive accuracy but also provides significant computational efficiency, facilitating real-time decision-making.

Cutting-edge research: The focus will be on advanced machine learning techniques (e.g., data-driven models with supervised, unsupervised, or semi-supervised learning) applied to coastal engineering problems.

The kind of paper we are looking for: We are looking for multidisciplinary papers that address topics related to coastal engineering—such as wave field prediction, sea level variations, morphological changes, sediment transport, coastal erosion, and marine renewable energy—through the application of state-of-the-art machine learning techniques, including artificial neural networks (ANNs), support vector machines (SVMs), Bayesian networks (BNs), and decision trees (DTs), among others.

Machine learning (ML) applied to coastal engineering problems holds immense potential to enhance the understanding and modelling of complex coastal processes. While traditional numerical and empirical models have proven effective, they increasingly face challenges related to complexity and computational demands. ML not only matches or surpasses traditional methods in predictive accuracy but also provides significant computational efficiency, facilitating real-time decision-making. Despite its promise, ML faces challenges such as data quality, model interpretability, algorithm selection, and generalization. Its success heavily depends on the availability of high-quality representative datasets, which remain a limiting factor. Future research must focus on improving ML robustness, accuracy, and applicability by addressing data limitations, optimizing algorithms for specific problems, and refining training and validation techniques to fully harness its transformative potential. On these grounds, this Special Issue seeks to showcase original research articles, comprehensive reviews, and insightful case studies that explore diverse applications of ML in coastal engineering, including but not limited to wave field modelling, sea level variation analysis, and morphological change predictions.

Prof. Dr. Paulo Jorge Rosa-Santos
Dr. Victor Ramos
Dr. Daniel Clemente
Guest Editors

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 100 words) can be sent to the Editorial Office for announcement on this website.

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 monthly 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.

• wave field prediction
• sea level variations
• morphological changes
• supervised and unsupervised learning
• machine learning
• coastal engineering
• data-driven models
• artificial neural networks (ANNs)
• support vector machines (SVMs)
• Bayesian networks (BNs)
• decision trees (DTs)
• wave prediction
• water level fluctuation
• morphology change
• sediment transport
• coastal erosion
• model validation
• multidisciplinary studies