TheMeCat
Scientific Data
Abstract: Data-driven materials discovery to accelerate the development of new catalysts for the green transition shows great promise, but requires machine-interpretable experimental data. For this purpose, we…
Prof. Patrick Rinke
Prof. Dr. Patrick Rinke
Technical University of Munich
Lehrstuhl für KI-basierte Materialforschung (Prof. Rinke)
Postal address
James-Franck-Str. 1
85748 Garching b. München
- Phone: +49 (89) 289-54321
- Room: 5101.EG.093
- Homepage
- E-mail: patrick.rinke@tum.de
Research
The Chair of AI-based Materials Science is developing electronic structure and machine learning methods and applies them to pertinent problems in material science, surface science, physics, chemistry and the nano sciences.The electronic structure gives us an atomistic view on matter that is important for many applications.
Examples are materials for clean energy production, light-emitting devices (LEDs) or information and communication technologies (ICT). Perturbing the electronic structure, as done in spectroscopy, reveals more information about matter.
We develop and use theoretical spectroscopy methods to probe the properties of molecules, molecules on surfaces, nanostructures, as well as semiconductors and their surfaces. We also investigate data as new resource in materials science. We participate in the development of a large scale materials database and study the potential of database driven materials science.
188 Publications
An interpretable molecular descriptor for machine learning predictions in atmospheric science
Journal of Chemical Physics
Abstract: The study of aerosol formation and chemistry using machine learning is limited by the lack of molecular descriptors suited to atmospheric compounds. Interpretable models are particularly affected…
Predicting temperature-dependent optoelectronic properties of semiconductor defects with equivariant neural networks
npj Computational Materials
Abstract: The presence of defects strongly influences semiconductor behavior. However, predicting the electronic properties of defective materials at finite temperatures remains computationally expensive even…
Traffic-Emitted Amines Promote New Particle Formation at Roadsides
American Chemical Society Environmental Science and Technology Air
Abstract: New particle formation (NPF) is a major source of atmospheric aerosol particles, significantly influencing particle number concentrations in urban environments. High condensation and coagulation sinks…
Precision benchmarks for solids
Computational Materials Science
Abstract: The GW approximation within many-body perturbation theory is the state of the art for computing quasiparticle energies in solids. Typically, Kohn–Sham (KS) eigenvalues and eigenfunctions, obtained…
Predicting intersystem crossing rate constants of alkoxy-radical pairs with structure-based descriptors and machine learning
Physical Chemistry Chemical Physics
Abstract: Peroxy radicals (RO2) are ubiquitous intermediates in many oxidation processes, especially in the atmospheric gas phase. The recombination reaction of two peroxy radicals (RO2 + R′O2) has been…
Leveraging active learning-enhanced machine-learned interatomic potential for efficient infrared spectra prediction
npj Computational Materials
Abstract: Infrared (IR) spectroscopy is a pivotal analytical tool as it provides real-time molecular insight into material structures and enables the observation of reaction intermediates in situ. However,…
SP-LCC — a dataset on the structure and properties of lignin-carbohydrate complexes from hardwood
Scientific Data
Abstract: Lignin-carbohydrate complexes (LCCs) are bioproducts with high potential as alternatives for petrochemicals. However, the complex structure and the lack of protocols for high-yield production limit…
Enhancing Lignin-Carbohydrate Complexes Production and Properties With Machine Learning
ChemSusChem
Abstract: Lignin-carbohydrate complexes (LCCs) present a unique opportunity for harnessing the synergy between lignin and carbohydrates for high-value product development. However, producing LCCs in high yields…
Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion
npj Computational Materials
Abstract: Transforming CO2 into methanol represents a crucial step towards closing the carbon cycle, with thermoreduction technology nearing industrial application. However, obtaining high methanol yields and…
Summer term 2026
| Title | Dates | Duration | Type | Lecturer (assistant) |
|---|---|---|---|---|
| Academic Writing Skills: Scientific Publications |
|
2 | SE | |
| Atomistic Machine Learning |
|
2 | VO | |
| Computer Tutorial to Atomistic Machine Learning |
|
2 | UE | |
| Current Topics in AI-Based Materials Science |
|
2 | SE | |
| Mentoring in the Bachelor’s Program Physics |
|
0.2 | KO | |
| PREP: Practical Research Experience Program, Chair of AI-based Materials Science |
|
10 | FO | |
| Seminar of the Atomistic Modeling Center |
|
2 | SE | |
| Summer School Atomistic Modeling Center |
|
1 | WS |
Winter term 2026/2027
| Title | Dates | Duration | Type | Lecturer (assistant) |
|---|---|---|---|---|
| Computer Tutorial to Introduction to Machine Learning for Materials Science |
|
2 | UE | |
| Current Topics in AI-Based Materials Science |
|
2 | SE | |
| Introduction to Machine Learning for Materials Science |
|
2 | VO | |
| Machine Learning for Material Science and Engineering |
|
2 | SE | |
| Seminar of the Atomistic Modeling Center |
|
2 | SE |