Information on the properties of mixtures is a key prerequisite for the design and optimization of chemical engineering processes. However, experimental data are often scarce, which is why predictive models are used in many cases. In addition to classical methods, machine learning (ML) approaches are increasingly being applied, but their development and training likewise require suitable experimental data.

My work focuses on how nuclear magnetic resonance (NMR) spectroscopy can be used to determine the properties of mixtures. One of the aims is to integrate data from NMR measurements into ML-based predictive models in order to gain new insights into mixture behavior while also improving the accuracy of these models.

Lecture Support

• Thermodynamics I (WS 2024/25)

   

Office Hours

By arrangement.