Johannes Margraf
Margraf holds a chair at Bayreuth and studies machine learning for reaction networks and molecular and material properties. The chair is named Physical Chemistry V: Theory and Machine Learning. The lab develops models that use physical structure to reduce the amount of training data required. It cites size extensivity and long-range interactions as properties that can be built into a model. The group also studies wavefunction and density-functional methods and their combination with learning. Its goal is accurate chemical simulation across larger systems and searches for functional molecules.
- Now at
- University of Bayreuth
- Works
- 199
- Citations
- 7,532
- h-index
- 46
Publication numbers from OpenAlex, as of 14 October 2026.
Timeline
-
As of October 2026
Theory and machine learning
Margraf holds a chair at Bayreuth and studies machine learning for reaction networks and molecular and material properties. The chair is named Physical Chemistry V: Theory and Machine Learning.
-
As of October 2026
Data-efficient chemical models
The lab develops models that use physical structure to reduce the amount of training data required. The models can incorporate size extensivity and long-range interactions.
-
As of October 2026
Electronic structure and simulation
The group also studies wavefunction and density-functional methods and their combination with learning. Its goal is accurate chemical simulation across larger systems and searches for functional molecules.
Sources and credits
Photo: ellis.eu; Johannes Margraf profile photograph; creator not stated. License: Not stated by source. Source: ellis.eu. Cropped to a square and resized. Ask us to remove or replace this photo.