(W-0050) Postdoctoral Scientist | Research Scientist at MaxPlanckInstitut fr Meteorologie
20146 Hamburg, , Germany -
Full Time


Start Date

Immediate

Expiry Date

13 Nov, 25

Salary

0.0

Posted On

13 Aug, 25

Experience

0 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

Good communication skills

Industry

Information Technology/IT

Description

THE POSITION

We are now inviting internal applications for the following position:
Postdoctoral Scientist | Research Scentist (W-0050 | all genders)
The role involves developing and applying machine learning methods to simulate hydrological and biogeochemical variables in permafrost regions in the Arctic, with the aim of closing the scaling gap between landscape and process scales. A key aspect of the role involves scientific coordination with project partners engaged in local and remote sensing observations.
The successful candidate will contribute to the project Q-ARCTIC, entitled ‘Quantify disturbance impacts on feedbacks between Arctic permafrost and global climate’ (

www.q

  • arctic.net), which is funded by the European Research Council (ERC). This research will be conducted in close collaboration with the Max Planck Institute for Biogeochemistry in Jena, Germany and b.geos GmbH in Korneuburg, Austria.

ABOUT US

The Max Planck Institute for Meteorology (MPI-M) is a multidisciplinary center for climate and Earth system research located in Hamburg, Germany. It is one of the premier climate science research institutes in the world. Located in the heart of one of Europe’s most livable and vibrant cities, it provides a highly international and interdisciplinary environment to conduct scientific research as well as access to state-of-the-art scientific facilities. You can also have a virtual tour to our campus
.

Responsibilities
  • To develop data-driven model based on machine learning (ML) and artificial intelligence (AI) methods to simulate hydrological and biogeochemical variables in permafrost regions in the Arctic;
  • use local and remote-sensing observations to train the model;
  • integrate data-driven model into the ICON framework;
  • disseminate the results through high quality peer-reviewed publications and presentations at conferences.
Loading...