ECMWF – Scientist to work on machine learning for environmental modelling

ECMWF, Reading, UK or Bonn, Germany
Closing date: 1 November 2021

The Scientist will work in the Innovation Platform Team in the Forecast Department at ECMWF and will be responsible for developing new methods to upscale flood and fire forecast model system from catchment to European scale using machine learning techniques. The work will contribute to the H2020 project EIFFEL (rEvealIng the role oF geoss as the deFault digital portal for building climatE change adaptation & mitigation appLications) and will utilize the forecast model systems used in EFFIS and EFAS within the Copernicus Emergency Management System in combination with GEOSS and Copernicus data to improve the operational model output. The Scientist will apply semantic machine-learning tools developed in the project to augment the forecast systems and assess potential improvements on the European scale. Such improvements can for example, involve improving background maps, incorporating processes such as irrigation or land use change, as well as improving the forcing observational data. They will also create impact response surfaces (IRS) over Europe using the model system to assess the sensitivity of the models with and without the augmentation. The IRS will then be used in the project for climate change impact assessment.

The successful applicant will be responsible for the implementing the developed methodology in ECMWF’s IT infrastructure and report the output in deliverables to the project as well as in international scientific journals. They will work closely with other teams in the Forecast Department responsible for the CEMS flood and fire services. They will also attend the EIFFEL workshops and project meetings and interact with the other project partners to contribute to a successful project. This role will also involve interacting with ECMWF’s group on artificial intelligence to assess the wider use of semantic machine learning methods in other parts of ECMWF’s systems.

Main duties and key responsibilities

  • Contributing to augmenting CEMS flood and fire model systems using machine learning methods and the available GEOSS and Copernicus data.
  • Running and evaluating experiments to assess the potential improvement of the models on the local and continental scale
  • Upscaling the results to the continental scale and create impact response surfaces for the hydrologic and fire models
  • Contributing to the project deliverables that ECMWF are in involved in within the EIFFEL project
  • Providing regular feedback to ECMWF on the potential use of the ML tools in ECWMF’s systems
  • Representing ECMWF at external and international meetings and scientific conferences to present the outcome of the research

For more information about the flood and fire models used in CEMS please refer to:

Other information
The successful candidate will be recruited at the A2 grade, according to the scales of the Co-ordinated Organisations and the annual basic salary will be £62,166.00 net of tax (UK) or EUR 75,178.52 net of tax (Germany). This position is assigned to the employment category STF-PS as defined in the Staff Regulations.
Full details of salary scales and allowances are available on the ECMWF website at, including the Centre’s Staff Regulations regarding the terms and conditions of employment.

Starting date: As soon as possible.
Length of contract: Contract of 24 months, with the possibility of extension, subject to funding.

Successful applicants and members of their family forming part of their households will be exempt from immigration restrictions.


By continuing to use the site, you agree to our privacy policy and the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.