PhD in Predicting and parameterizing sea-ice using deep learning algorithms

at Norwegian Meteorological Institute
Published December 10, 2022
Location Oslo, Norway
Category Deep Learning  
Job Type Scholarship  


About us

Modern meteorology requires management and analysis of enormous amounts of data, and offers great and exciting professional challenges. Since the institute was established in 1866, the Norwegian meteorologists have played a key role in this development.

Norwegian Meteorological Institute is today a leading international environment of expertise in operational meteorology and climatology.

About the position

The Norwegian Meteorological Institute (MET Norway) opens a 3-year position as a PhD student at the Development Centre for Weather Forecasting. The successful candidate will play an important role in developing machine learning based approaches to predict sea-ice on km-scales and below. This data driven approach is planned to be tested as a parameterization for MET Norway’s Arctic short-range weather prediction system and as service of MET Norway and its collaborating partners.

The Development Centre for Weather Forecasting has about 40 research scientists (natural and social sciences) and 10 research meteorologists in Oslo, Tromsø and Bergen. The Centre is dedicated to user-informed, research-driven development of services, and is responsible for MET Norway’s automated value chain for numerical weather forecasting (science to service; open data;; Hereby the Centre has an important role in supporting MET Norway’s responsibility on the delivery of 24/7 operational services. The Centre has extensive national and international collaborations and research projects, and the degree of external funding is very high. Its organization emphasizes flexibility and interdisciplinarity, which is especially important in user and stakeholder engagement.

One of MET Norway’s central goals is to develop reliable and accurate Arctic weather and sea-ice forecasts, as well as warnings for the benefit of maritime operations, business and society. The forecast information which is issued by MET Norway is usually based on numerical models and data-driven approaches. For Arctic forecasts, we have a strong focus on understanding and developing the simulation of the coupled atmosphere - sea-ice systems and, in particular, the representation of sea-ice.


Responsibility / work tasks

We are looking for a PhD student with a background in computational- and/or geo-sciences and an interest in developing approaches based on machine learning to predict sea-ice on km-scales and below. These approaches will then be tested in the MET Norway Ice Service and for parameterizing sea-ice in the operational Arctic numerical weather prediction system AROME-Arctic.

The position is part of a new project, Digital Sea Ice, that has been funded by the Norwegian Research Council and is coordinated by the Norwegian University of Science and Technology (NTNU, Trondheim, and has collaboration with the Jiangsu University of Science and Technology (JUST) and Dalian University of Technology (DLUT). The primary objective is to build a multiscale digital infrastructure that connects sea-ice forecasting models on a regional scale with local and more detailed ice-ice and ice-structure discrete element models. These models are then updated by in-situ and shipboard measurements locally, and regionally by satellite measurements. The PhD student will collaborate with the partners in the Digital Sea Ice project and will be supported by machine learning and sea-ice experts at MET Norway, including working closely with the Ice Service at our Tromsø office to develop the forecast relevance to operational requirements.

The expected impact of the project are novel methods and a digital infrastructure for improved spatial and temporal forecasting and maritime safety decision support in an increasingly dynamic Arctic environment due to climate changes. Such infrastructure will enable more accurate data and information to be produced, thus resulting in better insight on polar Earth systems.

The position is located in Oslo, with some short periods in Tromsø. The working language at MET Norway is Norwegian, however an important part of the expected work will be in English. For all applicants fluency in written and spoken English is required, and for foreign applicants a willingness to learn Norwegian. Training courses will be provided.


  • master degree in computational and/or geophysical sciences
  • experience and documented knowledge in applied mathematics/scientific programming in a Linux environment
  • demonstrated Python programming skills
  • experience with deep neural network applications
  • experience with sea-ice prediction
  • ability to take responsibility, work independently within an interdisciplinary environment
  • good collaborative and interpersonal skills
  • good oral and written communication skills.


  • we can offer a good working environment with professional challenges in a modern, technological environment
  • salary on the governmental salary scales as PHD student, dependent on qualifications and experience, NOK 501.000 - 714.000 pr. year
  • membership in the governmental pension scheme (2% deducted from gross salary)
  • the position is for a period of three years.
  • the student needs to fulfill the conditions for the University Oslo PhD program and will need to apply for admission.

Additional information

We emphasize diversity and therefore encourage all those who are qualified to apply  regardless of age, gender, functional capacity, ethnic background or gaps in the resume. The Government has invited to a joint effort for inclusion and has set a target that 5% of all new employees in the state should have impaired functional capacity or gaps in their resumes. The working conditions will be facilitated for employees with disabilities. Applicants who inform that they have reduced functional capacity will be invited to interview if they are qualified.

If an applicant does not wish to be registered on the public application list, the applicant will need to give a reasonable argued justification. Information about the applicant can still be published. If the wish to not be registered on the public application list is denied, the applicant will be informed prior to the disclosure.

Further information can be obtained from the Director of Development Centre for Weather Forecasting

Dr. Jørn Kristiansen (Tel. +47 46420054; Email

Please attach CV, list of publications and the names of two references.