About this role
This is NTNU NTNU is a broad-based university with a technical-scientific profile and a focus in professional education. The university is located in three cities with headquarters in Trondheim. At NTNU, 9,000 employees and 43,000 students work to create knowledge for a better world. You will find more information about working at NTNU and the application process here. Video: https://youtu.be/Xt-yHCN5QS0 About the position Are you motivated to take a step towards a doctorate and open up exciting career opportunities? As a PhD Candidate with us, you will work to achieve your doctorate, and at the same time gain valuable experience that qualifies you for a further career in higher education and research, in and outside academia. We invite applications for a PhD position funded by NTNU and associated with the Norwegian Maritime AI Center (MAI). The position contributes to Use Case 12 (UC12): Arctic Maritime Operations and addresses a key challenge for maritime AI: supporting safe, reliable, and timely operational decisions in ice‑affected waters under high uncertainty. The PhD will focus on the Marginal Ice Zone (MIZ), where sea ice responds rapidly to wind, waves, and currents, and where existing ice charts and satellite products are often insufficient for short‑term operational planning. The project will develop AI‑enabled and physics‑informed forecasting and decision‑support approaches by combining heterogeneous observations with physics‑based simulation tools, including operationally adapted configurations of the SAMS (Simulation of Arctic Marine Systems) framework. Your immediate leader will be a professor. About the project The Marginal Ice Zone represents one of the most complex and operationally challenging environments in Arctic maritime operations. In the MIZ, wave–ice interaction, ice breakup, and subsequent compaction can rapidly alter navigability. Storm events may lead to fast shifts in the ice edge and sudden extension of the MIZ, requiring timely decisions under significant uncertainty. While satellite observations and ice charts are essential sources of information, their temporal resolution and predictive capability are often insufficient in the MIZ. This motivates the development of short‑term forecasting and scenario‑based tools that explicitly account for fast ice dynamics and uncertainty relevant for operational planning. The PhD addresses Arctic ice navigation as a system‑level challenge, integrating heterogeneous information from onboard sensors such as marine radar and cameras, satellite Earth‑observation products, ice charts, and metocean forecasts. The objective is to produce coherent, continuously updated representations of ice conditions that support short‑term forecasting, nowcasting, and scenario exploration for route planning and operational decision‑making. Physics‑based simulation plays a central role in this research project by enabling propagation of ice conditions in time and exploration of physically plausible scenarios when observations are sparse or delayed. In this project, the SAMS framework will be used in an operationally oriented configuration, focusing on computationally efficient simulation of MIZ processes such as wave‑induced ice breakup and ice‑edge evolution. These simulations will both directly inform forecasting and be used to support AI model training, validation, and interpretability, providing a physically grounded backbone for hybrid AI–physics decision‑support concepts. AI methods will be applied to fuse heterogeneous data sources, learn fast surrogate representations of physics‑based simulations, and quantify uncertainty relevant for operational decisions. The project leverages MAI foundations for AI‑ready data, hybrid modelling, and trusted AI, while tailoring these capabilities to Arctic MIZ conditions. The research will be guided by operationally relevant questions, such as how storms and wave forcing affect short‑term MIZ evolution; under what conditions wave–ice interaction leads to rapid ice breakup or MIZ extension; and how hybrid AI–physics approaches can support dynamic route planning with quantified uncertainty. Emphasis will be placed on time horizons from minutes to days, which are most relevant for maritime operations. Expected outcomes include hybrid AI–physics workflows for MIZ forecasting, AI‑ready datasets derived from observations and simulations, prototype forecasting and scenario‑evaluation components, and contributions to decision‑support concepts compatible with S‑100‑based maritime information products. The work will result in scientific publications and demonstrators aligned with MAI objectives. The PhD will be conducted in close collaboration between NTNU and the Norwegian Meteorological Institute (MET), with active involvement of interested MAI’s user partners such as Equinor and the Norwegian Coastal Administration (NCA). This ensures close alignment between research outcomes, operational needs, and regulatory frameworks. We seek a motivated candidate with a background in engineering, ocean technology, computer science, data science, geophysics, or related discipline, and with a strong interest in AI, modelling, and Arctic maritime operations. Experience with numerical modelling, geospatial data, or machine learning is an advantage. An interest in system‑level thinking and integration of models, data, and AI methods is particularly valued. The appointment will be carried out in accordance with the principles of the State Employees Act and applicable export control regulations governing the transfer of knowledge, technology, and services. Candidates whose background is assessed to be in conflict with these regulations cannot be employed. Duties of the position Complete the doctoral education until obtaining a doctorate Carry out research of good quality within the framework described above, including development of models, datasets, and prototype solutions Academic publications and popular science disse