2 Postdocs In Deep Learning For Earth System Science

Helmholtz-Zentrum Hereon

The Helmholtz-Zentrum Hereon conducts cutting-edge international research for a changing world: Around 1,000 employees contribute to the tackling of climate change, the sustainable use of the world's coastal systems and the resource-compatible enhancement of the quality of life. From fundamental research to practical applications, the interdisciplinary research spectrum covers a unique range.

Institute of Coastal Systems Analysis and Modeling

The Institute for Coastal Systems Analysis and Modeling studies the dynamics of coastal systems as part of the Earth system and develops prediction methods and future scenarios for coastal systems. One focus of our research is the study of coastal ecosystems, which are subject to increasing pressure to change due to climate change, use of coastal environments, and other human drivers.

Reference code: 50117505_2 – 2024/KS 2
Commencement date: as soon as possible
Work location: Geesthacht (bei Hamburg)
Application deadline: June 23nd, 2024

The Model-driven Machine Learning group, lead by David Greenberg at Helmholtz-Zentrum Hereon, seeks two curious and driven postdocs to start as soon as possible. They will work at the absolute forefront of AI for science, with scalable modern methods, interdisciplinary expertise and industrial-scale computation. A solid background in Deep Learning is required, including some published work. Expertise in Earth System Science and numerical simulation is welcome but optional.

Cooperating with Forschungszentrum Jülich, Alfred-Wegener-Institut and Karlsruhe Institute of Technology, we will design, train, test and deploy HClimRep, the first truly climate-capable Earth system foundation model, on observed and simulated climate data. This transformer-based model will be used for simulation, forecasting, superresolution, bias correction and counterfactual exploration. One postdoc will focus on long-term accuracy and the other on stratospheric advection, but both will have considerable freedom to innovate and will participate in designing, training, testing and deploying HClimRep.

The Model-driven Machine Learning group (m-dml.org) combines ML- and physics-based approaches to Earth system modelling, within the Institute for Coastal Research at Helmholtz-Zentrum Hereon in Geesthacht (hereon.de), near Hamburg, Germany. Our work schedule combines remote and in-person interactions. The successful candidates will focus on challenging and impactful research, with minimal administrative or teaching duties. The positions are initially limited to 3 years.

Equal opportunity is an important part of our personnel policy. We would therefore strongly encourage qualified women to apply for the positions.

Your tasks

• develop and train HClimRep on climate data ranging from the oceans to the stratosphere
• evaluate and tune specialized techniques for long-term accuracy and stability (position 1)
• train a self-attention-based module for tracer advection (position 2)
• write, publish and present research in scientific journals and conferences

Your profile

• PhD in mathematics, physics, machine learning, computer science or the geosciences
• can carry out research independently with curiosity, creativity, initiative and persistence
• works well in a small group with diverse skill sets and backgrounds
• learns quickly on the job and from research articles on ML and the geosciences
• solid publication record showing creative ideas and hard work. High-profile journal articles are welcome but not required
• comfortable programming in Python and PyTorch
• can communicate well in spoken and written English

We offer you

• an exciting and varied job in a research centre with more than 1,000 employees from around 60 nations
• a well connected research campus and best networking opportunities
• an excellent technical infrastructure and modern workplace equipment
• 6 weeks holiday per year; company holidays between Christmas and New Year's Day
• very good compatibility of private and professional life through offers of mobile and flexible work
• family-friendly company policy with childcare facilities, e. g. nursery close to the company
• free assistance program for employees (EAP)
• Corporate Benefits
• a varied offer in the canteen on campus

Interested?

Then we are looking forward to receiving your comprehensive application documents (cover letter, CV, transcripts, certificates etc.) indicating the reference number code no. 2024/KS 2 until June 23rd, 2024.