"Postdoc in Modelling Greenland and Himalaya Precipitation Using Machine Learning"

Job Summary

This project involves applying deep learning techniques to predict precipitation fields over the Greenland Ice Sheet and the Himalaya. For Greenland, it focuses on spatial precipitation distribution on monthly and yearly timescales for various climate states and ice sheet geometries using RACMO model data. For the Himalaya, it targets instantaneous, high-resolution precipitation fields for static topography using WRF model data to downscale to higher resolutions.

Responsibilities

• Choose, develop, and train machine learning techniques to emulate precipitation fields over the Greenland Ice Sheet.
• Run the regional climate model RACMO over Greenland with various ice sheet geometries to create training datasets.
• Use existing WRF simulations for the Himalaya with fixed geometry to develop emulators.
• Assess and expand machine learning methods to ensure realistic and robust results.
• Publish results in peer-reviewed literature and make emulators publicly available.

Qualifications and Requirements

• Hold a PhD in deep learning techniques with an interest in climate science, or a PhD in Meteorology or Climate Science with clear experience in deep learning.
• Possess strong coding skills, including writing and understanding code.
• Ability to work independently and in a team, including with international collaborators.
• Excellent English writing and speaking skills.

What the Employer Offers

• A two-year position with an option to extend for one more year.
• Full-time working week with a gross monthly salary between €3,546 and €5,538 (salary scale 10 under the Collective Labour Agreement for Dutch Universities).
• 8% holiday pay and 8.3% year-end bonus.
• Pension scheme, partially paid parental leave, and flexible employment terms.
• Access to professional development schemes, sports, and cultural activities.