GEOMAR Helmholtz Centre for Ocean Research Kiel is a foundation of public law jointly financed by the Federal Republic of Germany (90 %) and the state of Schleswig-Holstein (10 %) and is one of the internationally leading institutions in the field of marine sciences. Currently GEOMAR disposes over an annual budget of approx. 80 million Euro and has approx. 1000 employees.
Project Description
Ocean currents transport enormous amounts of heat and are responsible for the role of the ocean in climate and climate change. An important integral measure of large-scale ocean currents is the Atlantic Meridional Overturning Circulation (AMOC) shaping the temperatures in the rim countries along the Atlantic Ocean. Systematic efforts to measure the AMOC are only available for specific regions and limited periods. On the other hand, there exists a wide range of observations, gathered through ships, moorings, satellites and autonomous robots, which could combined contain substantial information on the AMOC. This proposal aims at training the relation between the large-scale AMOC and regional currents and water masses in the virtual world of a physically-consistent ocean model. We will study the ability of machine learning methods (Convolutional Neural Networks, Spatial Transformer Networks and Recurrent Neural Networks) combined with pattern mining methods to infer regional observations triggering AMOC changes and to get insights explaining this process.
This is a joint research project of GEOMAR and the Department of Computer Science at Kiel University. The PhD student work at the interface between Computer Science, Data Science and Physical Oceanography, but have a research focus on the Computer Science aspects. The overarching research question of the PhD thesis will be to investigate the potential of machine learning and pattern mining (or combinations of both) to infer/predict the degree of influence of regional (small scale) attributes to global large scale attributes within complex global spatio-temporal systems and to identify the corresponding enabling key elements.The project will focus on novel approaches to (1) scalable machine learning applied on complex spatio-temporal systems (convolutional neuronal networks, spatial transformer networks, and recurrent neuronal networks), and (2) spatio-temporal pattern mining.
Qualification
Required:
- Master’s degree (or equivalent) in Computer Sciences or a related field by the beginning of the project, preferably with a focus on neural networks or machine learning and pattern mining in general.
- be able to communicate fluently in spoken and written English
- have experience in software development, preferably in data processing applications, in Python or related programming languages
If the required degree is not completed at the time of application, the degree certificate must be handed in before the above start date of the contract and the application must contain plausible evidence that the degree can be finished before that date.
Desired:
- knowledge in Marine Sciences
- willingness to work in teams of the two research units and the MarDATA school
- experience with neural networks
- experience in data mining
- development of data processing software
The position is available for a funding period of 36 months. The salary depends on qualification and could be up to the class 13 TVöD-Bund of the German tariff for public employees. This is a full-time position. The position cannot be split. Flexible working time models are generally possible. The fixed-term contract shall comply with Section 2 Paragraph 1 of The Act of Academic Fixed-Term Contract (German WissZeitVG).
Please send your application for this post via email in a single pdf-file mentioning the keyword “MarDATA-OceanCurrents” in the subject line. Please send your application not later than July 4th, 2021 to the following email address:bewerbung(at)geomar.de
For further information regarding the position and research units please contact Prof. Dr. Arne Biastoch (abiastoch(at)geomar.de) and Prof. Dr. Matthias Renz (mr(at)informatik.uni-kiel.de).
More details about the position here.