Various climatic classifications of Germany exist for building calculations, such as the three cooling load zones defined by VDI 2078 for cooling load design, or the twelve test reference year regions used for energy demand calculations. These classifications are based on data analyses dating back over 30 years. Today, the German Weather Service provides extensive datasets online, including test reference years with hourly values accurate to the square kilometer. These data make it possible to develop new, objective regional classifications based on modern methods.

As part of this project, climate parameters (e.g., annual mean temperature, extreme values, number of frost days) will be defined and automatically determined for a large number of locations using a calculation script. Based on this, the locations will be grouped into new climate regions using machine learning methods (clustering). In doing so, various clustering methods will be tested, the number of clusters will be varied, and different time periods (year-round, summer, winter) will be analyzed. The goal is to derive a robust and transparent alternative regional classification for building simulation and building services engineering design.

The scope and specific focus of the thesis can be adapted.

Programming skills (preferably in Python, e.g., using the scikit-learn library) are required to carry out this work. Knowledge of statistics is a plus.

Since our internships and the supervision of student projects are primarily intended to provide practical experience and career guidance, we ask for your understanding that no compensation is provided. However, we would be happy to issue you a formal internship certificate and nominate your student project for the annual academic award presented by the Association for the Promotion of Air Conditioning and Refrigeration Technology (Verein zur Förderung der Luft- und Kältetechnik e.V.).