Physics-Informed Machine Learning for Offshore Renewable Energy

Dear Colleagues,

The integration of machine learning (ML) techniques into offshore renewable energy (ORE) systems (i.e., wind, wave, and tidal) has the potential to revolutionize the industry by enhancing the accuracy of forecasting, supporting wind turbine and wind farm modelling, optimizing the control performance of wave energy converters (WECs), enhancing farm-level energy production, and supporting the integration of renewable energy into the grid. ML-based research has indeed experienced exponential growth in ORE in recent years. However, in order to fully leverage the benefits of ML in ORE systems, it is crucial to incorporate physical principles and domain knowledge into ML models. Therefore, this Special Issue aims connect researchers and practitioners in order to explore the intersection of physics and ML in ORE research and applications.

The scope of this Special Issue includes, but is not limited to, the following:

1. Development of physics-informed machine learning (PIML) models, training procedures, and algorithms, and their applications in wind, wave, and tidal energies.
2. Method implementations and improvements related to physics-informed neural networks (PINNs), operator learning (e.g., DeepONet), and other frameworks within the scope of scientific machine learning (Sci-ML).
3. The integration of domain knowledge into ML algorithms for the design, control and monitoring of wind turbines, tidal turbines, and WECs, as well as their structural load evaluation and mitigation, and performance optimization.
4. The application of PIML for wind/wave/tidal resource assessment, flow modelling, and farm-level control.
5. The integration of different datasets or physical constraints for ML-based prediction. The data can include various sources of datasets, e.g., meteorological data, wave buoy data, wind turbine SCADA data, and CFD simulation data. The physical constraints can include analytical relations, boundary conditions, causality, etc.
6. The incorporation of structural modelling, flow modelling, or atmospheric dynamics into ML frameworks, for device-scale, farm-scale, and meso-scale applications.
7. Uncertainty quantification and sensitivity analysis in physics-informed ML models for wind, tidal, and wave energy applications.
8. Transfer learning techniques for leveraging physics knowledge in ML applications for ORE.
9. Case studies and future concepts of ORE systems, including wind (both fixed-bottom and floating wind turbines), tidal, and various prototypes of WECs.
10. Benchmarking and comparison of physics-informed ML models against traditional approaches.

Dr. Mingwei Ge
Dr. Jincheng Zhang
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. Energies 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.

• machine learning
• offshore renewable energy
• wind turbine
• wave energy converters
• tidal turbine
• physics-informed machine learning
• modelling
• control
• forecasting