One Ph.D. position (supervision by Professor Westermann) is available at our chair in the area of deep learning for weather prediction.
Research in this project includes the development of techniques for learning weather phenomena from the past, i.e., recorded weather data at the European and German weather centres, and to use learned representations to improve on the predictability of future weather events. We will start by exploring simple regression models and how internal representations for weather phenomena can be integrated into such models. In a second step, it will be explored how forecast simulations, routinely performed at the weather centres, can be embedded into such models.
If you are interested in applying, you should have a strong background in computer science, including the fields of deep learning and programming, have experience implementing C/C++ algorithms, and you should be excited to work on state-of-the-art research in the field. Good English skills are also a plus.