The Institute of Atmospheric Physics researches the physics and chemistry of the global atmosphere from the ground up to an altitude of 120 kilometres.
What to expect
The Earth System Model Evaluation and Analysis department develops innovative methods for evaluating and analysing Earth system models using machine learning (ML) and space-based Earth observation data to improve actionable climate science and technology assessments in aeronautics, space, transport and energy research. The evaluation of Earth system models and the reduction of long-standing systematic errors in Earth system models through ML are essential prerequisites for reliable 21st century climate projections used in climate policy guidelines. The department works closely with the National Center for Atmospheric Research (NCAR), Boulder, CO, USA and the National Oceanic and Atmospheric Administration (NOAA) Geophysical Fluid Dynamics Laboratory (GFDL) in Princeton, USA. In this position, you will develop ML-based parameterisations and submodules to improve Earth system models and ML-based analysis tools for Earth system data.
Your tasks
- development and implementation of ML-based parameterisations and submodules for Earth system models (e.g., ICON-XPP, CESM, GFDL), of methods for generating large ensembles, in particular the use of deep learning methods and explainable artificial intelligence
- planning and implementation of climate model simulations
- development and application of machine learning methods to analyse Earth system data and improve understanding and predictability of the Earth system
- development of an associated benchmark for the evaluation of hybrid Earth system models and training data with the ESMValTool
- supervision of master's and doctoral theses
- acquisition of third-party funding including monitoring of funding opportunities
Your profile
- completed university degree in physics, mathematics or a comparable field, e.g. meteorology
- doctorate in the field of Earth system sciences, physics or a comparable field
- specialist knowledge in the field of Earth system modelling, in particular the development of hybrid (ML and physics) Earth system models and ML-based analysis tools
- many years of experience in the evaluation of hybrid Earth system models and in the analysis of model data
- very good programming skills, especially when dealing with very large amounts of data
- very good English language skills
- willingness to travel, including longer stays with the cooperation partners at NCAR or GFDL
Depending on qualification and assignment of tasks, remuneration will be up to pay grade EG 14 TVöD-Bund.
We look forward to getting to know you!
If you have any questions about this position (Vacancy-ID 1369) please contact:
Mierk Schwabe
Tel.: +49 8153 28 4239
