Patrick Rinke

Professor Patrick Rinke leads the Chair of AI-based Materials Science at the Technical University of Munich (TUM), within the TUM School of Natural Sciences and Department of Physics. His research group develops advanced electronic structure and machine learning methods to address critical challenges in materials science, surface science, physics, chemistry, and nanoscience.

Professor Rinke's research spans multiple cutting-edge domains including electronic structure theory development, machine learning applications for materials science, data-driven materials discovery, biomaterials engineering, atmospheric science applications, clean energy materials, and hybrid materials systems. His work integrates advanced computational methods with practical applications across diverse scientific fields, particularly focusing on how artificial intelligence can transform traditional materials research.

Analyzing his recent publications reveals strong trends in applying machine learning techniques to materials discovery, with particular emphasis on Bayesian optimization methods, active learning approaches for molecular data, and efficient dataset generation strategies. His research spans from fundamental electronic structure theory to practical applications in biomaterials, atmospheric science, and renewable energy technologies.

Professor Rinke has received several prestigious awards including the August-Wilhelm Scheer visiting professorship (2017), a German Science Foundation research scholarship (2007), the Outstanding Postdoctoral Research Achievement Award from UC Santa Barbara (2009), recognition as an Outstanding Referee for Physical Review journals (2014), and the Institute of Physics Computational Physics Group Thesis Prize (2003).

Professor Rinke actively contributes to the academic community through teaching and supervision. For the Winter term 2025/26, he is teaching courses including Academic Writing Skills, Introduction to Machine Learning for Materials Science, Current Topics in AI-Based Materials Science, and Machine Learning for Natural Sciences. His research group includes several team members working on diverse projects spanning the intersection of AI and materials science.