At Aalto University, curiosity moves across disciplines, roles and communities. We bring people together to ask new questions, challenge familiar
thinking and turn ideas into impact. Our work is rooted in responsibility, courage and collaboration, and in a shared commitment to shaping a more sustainable future. The School of Engineering is inviting applications for a Doctoral Researcher in Physics-Enhanced Machine Learning for Floating Offshore Wind Digital Twins Floating offshore wind turbines will be central to the clean-energy transition, but their behaviour at sea is difficult to predict and monitor. They move in six degrees of freedom under irregular waves and turbulent wind. The mooring lines that keep them in position are located deep underwater, where permanent sensing is costly and difficult to maintain. Operators therefore need digital twins that combine hydrodynamic knowledge with sensor data to estimate quantities that cannot be measured directly. In this full-time, salaried Doctoral Researcher position, you will help develop the next generation of these digital twins: models that capture the wave-driven dynamics of floating turbines, update as new data arrive, detect early signs of degradation, and quantify the uncertainty of their estimates. The position is funded by the Research Council of Finland. It is based at Aalto University's Otaniemi campus in Espoo, Finland, and starts on 28 January 2027 or as agreed. Research environment and duties At the Department of Energy and Mechanical Engineering , our Marine and Arctic Technology research group studies how ships and offshore structures move and are loaded in waves, wind and ice. We combine machine learning and data-driven methods with hydrodynamic theory, numerical simulation and model-scale experiments. In this role, you will help us build digital twins that track the wave-induced motions, mooring loads and structural condition of floating offshore wind turbines in real time using only a small number of sensors. Your work will contribute to safer and more cost-effective floating wind farms, where wave loads and mooring tensions can be monitored continuously, degradation can be detected early, and maintenance can be planned before failures occur. Your work will include: Developing physics-enhanced machine-learning models that learn the coupled hydrodynamic and structural dynamics of floating wind turbines from measured data and update in real time. These methods will build on, among other approaches, Koopman operator theory and dynamic mode decomposition (DMD). Embedding hydrodynamic knowledge into these models so that they remain physically consistent across sea states, including wave excitation, radiation-memory effects, slow-drift motions and mooring-line dynamics. Estimating wave-induced motions and mooring loads that cannot be measured directly. Detecting early mooring-system or structural degradation and distinguishing it from normal changes in waves, wind and turbine operating conditions. Quantifying the uncertainty of these estimates using Bayesian filtering and probabilistic machine learning. Generating and analysing data from: hydrodynamic simulations, including potential-flow methods and, where needed, computational fluid dynamics (CFD) and coupled simulation tools such as OpenFAST Publishing results in leading international journals and presenting them at conferences. You will work closely with researchers in the Marine and Arctic Technology group and with our international academic collaborators. This is an exciting time to join us. Floating offshore wind is scaling up rapidly, and industry guidance increasingly favours indirect monitoring of hard-to-access components, such as mooring lines, using sensors located elsewhere on the structure. Our group has recently shown that digital twins learned directly from measurements can estimate unmeasured responses and loads from only a few sensors, including verification using wave-basin test data. In this role, you will take these methods a step further by embedding hydrodynamics into the learning process and moving from accurate estimation toward reliable, self-updating condition monitoring. What you bring To thrive in this role, you will need: A Master's degree completed by the start of the position. Suitable backgrounds include naval architecture, marine or ocean engineering, offshore engineering, mechanical, civil or aerospace engineering, applied mathematics, physics, computer science, or a related field. A strong foundation in linear algebra and in at least one of the following areas: hydrodynamics or fluid mechanics, structural dynamics, dynamical systems, or signal processing. Good programming skills in Python or a similar language, together with a genuine interest in machine learning. Curiosity, independence, and the ability to communicate clearly and work well in a team. We also value: Knowledge of marine or offshore hydrodynamics, such as wave-structure interaction, potential-flow or boundary-element methods, or computational fluid dynamics (e.g. OpenFOAM or REEF3D). Experience with OpenFAST, MoorDyn or WAMIT, or similar software. Experience with dynamic mode decomposition, Koopman operator methods, system identification or operational modal analysis. Experience with Kalman filtering, Bayesian inference, Gaussian processes or uncertainty quantification. Experience with deep learning for time series, such as Transformers or graph neural networks, using PyTorch or JAX. Scientific publications or a strong Master's thesis in a related area. Language requirements: English: Excellent English-language skills are required. Finnish: Finnish-language skills are not required. We know that meaningful work is built by people with different backgrounds, experiences and perspectives. If you recognise yourself in the purpose of this role, we encourage you to apply and tell us what you would bring to our community. What we offer At Aalto, you can expect: The opportunity to work in a growing research team at the intersection of marine hydrodynamics, machine learning and offshore structural dynamics. Work with purpose in a community where research, education, creativity and services support meaningful change. A multidisciplinary environment where collaboration, curiosity and new thinking are part of everyday work. Extensive occupational health-care services. Staff-priced sports-centre services on campus and at other UniSport locations. A workplace at Aalto University's Otaniemi campus, with excellent public transport connections and a wide range of services. If you are selected for this position, you will apply for the right to pursue doctoral studies at Aalto University School of Engineering. Doctoral studies at Aalto University typically take approximately four years. The position will initially be filled with a two-year fixed-term contract, with the possibility of extension based on progress in research and studies and on performance. We support your professional growth with varied training and development opportunities shaped around your interests and aspirations. The expected starting salary for a Doctoral Researcher is approximately EUR 3,000 per month (gross), and it increases as the Doctoral Researcher progresses in research and studies. Work-life balance and well-being in all aspects of life are important to us at Aalto. Curious to make a difference? Please submit your application through our recruitment system by 28 December 2026. If you are already working at Aalto University, please apply through our internal Workday system. If you are a student or visitor at Aalto University, please apply using your personal email address. All applications must include the following materials: Cover letter / motivation letter with your contact information and preferred starting date (maximum 1 page). CV including details of all academic outputs. Contact details of two referees. Description of your Master's thesis project (maximum 1 page). Course transcripts for your Bachelor's and Master's degrees, including grades and a clear explanation of the grading scale. Research statement (maximum 2 pages) answering the question below. Research statement question: How could early degradation of a mooring line, such as a gradual loss of stiffness, be detected in a floating offshore wind turbine using only a few sensors on the tower and platform while wind and wave conditions keep changing? In your statement, outline: the methods you would use the data you would need how you would validate your approach what could cause the approach to fail. We do not expect a complete solution; we want to see how you think. You are welcome to draw on any relevant background, including hydrodynamics, structural dynamics, signal processing or machine learning. All materials should be submitted in English as a single PDF file, compiled in the order specified above. Applications submitted by email will not be accepted. Shortlisted candidates will be invited to interviews and may be asked to complete a short technical task. Aalto University reserves the right to leave the position open, extend the application period, and consider candidates who have not applied during the application period. For more information about the role, please contact: Associate Professor Arttu Polojärvi, arttu.polojarvi@aalto.fi Dr. Mohammad Mahdi Abaei, Academy Research Fellow, mohammad.abaei@aalto.fi For questions related to the application process, please contact HR Advisor Anna-Maija Harju anna-maija.harju@Aalto.fi or hr-eng@aalto.fi About Aalto University Aalto University builds on the legacy of three leading Finnish universities: Helsinki University of Technology, Helsinki School of Economics and the University of Art and Design Helsinki. Since 2010, we have brought science, art, technology and business together in new ways. Today, the Aalto community consists of more than 16,000 students and 5,200 employees, including 446 professors. Half of our teaching and research staff have an international background. Our campus in Espoo is a vibrant cluster of research and innovation with striking architecture, peaceful nature, open spaces for collaboration and a wide range of services, all with excellent public transport connections. Diversity is part of who we are. We work actively to build a community where people can belong, contribute and grow.
