Job opportunity for a mathematics scientist in the "PRECIP-PREDICT" project

Position at the Royal Meteorological Institute of Belgium

The Royal Meteorological Institute of Belgium is hiring a postdoctoral researcher in the context of a project financed by the Belgian Science Policy Office (Belspo). The project title is “Development of innovative dynamical approaches for short-term PRECIPitation PREDICTion based on long-term radar datasets - PRECIP-PREDICT”. The project will cover a period of 4 years, starting in May 2023, and is a collaboration between the RMIB and the VUB in Brussels specialized on the use of Machine Learning techniques. On the side of the RMIB, the postdoctoral researcher will be hired for a period of a bit more than 2 years, depending on the experience. The project is summarized below.


Summary of the project:

Extreme precipitation is one of the most important natural hazards worldwide, both in terms of economic cost and number of people affected. Belgium is no exception, as portrayed by the July 2021 extreme precipitation event which killed 41 people and caused damage worth over 2 billion euros. As shown in a World Weather Attribution study to which RMI contributed, such events are expected to become more likely and more intense in a warmer climate. Therefore, improving the prediction of high-impact precipitation events is a high priority of the meteorological scientific community. The aim of this project is to improve our understanding of the short-term predictability of precipitation using novel techniques from dynamical systems theory and deep learning. Applying these techniques, inspired by new theoretical insights, will allow us to valorize the long-term archive of radar data of the RMI in a new and innovative way to determine the dynamical properties of the observed precipitation. These improvements will finally be used to improve precipitation predictions disseminated through the RMI App, and thus benefit the general public as well as other users of our forecasts, such as hydrological and civil protection services.


Job description

The hired person will work on the application of recent techniques developed in the context of Dynamical Systems Theory to a long-term archive of radar data. These techniques are at the confluence between extreme value theory and dynamical systems. These tools will be used to characterize the radar dataset available and, based on the experience acquired, to propose new strategies to blending multiple forecasts for nowcasting. A strong collaboration with the group of the VUB is expected in order to condense the information present in the dataset based on Machine Learning techniques.


Required competences

  • A PhD degree in Science with a good background in mathematics
  • A good knowledge of English
  • An ability to work within a team and to easily communicate research at the national and international levels
  • An experience in developing and/or using tools of dynamical systems and nonlinear sciences is an asset.



We offer

  • A contract at the level of SW2 of the Federal Belgian Scientific career for a bit more than 2 years.
  • Reimbursement of the local public (and bike) transports.
  • A nice working environment, with the possibility to develop a network in meteorology and climate dynamics.


Gender equality & gender mainstreaming

In February 2022, the RMI adopted a Gender Equality Plan (GEP). This is an action plan to promote gender equality and gender mainstreaming within the RMI, Through this GEP, the RMI commits itself in a formal and/or substantial way to contribute to the realization of gender equality. The RMI is proud to be able to build a professional and scientific environment that is increasingly inclusive and responsive to today's societal challenges.



If you are interested by this position, please send by email a motivation letter and a Curriculum Vitae to Dr Stéphane Vannitsem (, before June 15, 2023, and mentioning in the subject of the email the acronym of the project (PRECIP-PREDICT). Additional information can also be requested to Dr Stéphane Vannitsem (

Cookies enregistrés