Research Group Patrick Rinke
Patrick Rinke
Prof. Dr.
Core PI
Patrick Rinke
is Professor for AI-based Material Science at TU Munich.
His chair 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.
Team members @MCML
PostDocs
Casper Larsen
Dr.
→ Group Patrick Rinke
AI-based Material Science
Philip Loche
Dr.
→ Group Patrick Rinke
AI-based Material Science
Matthias Stosiek
Dr.
→ Group Patrick Rinke
AI-based Material Science
PhD Students
Nitik Bhatia
→ Group Patrick Rinke
AI-based Material Science
Tatu Linnala
→ Group Patrick Rinke
AI-based Material Science
Abigale Monasterial
→ Group Patrick Rinke
AI-based Material Science
Prajwal Pisal
→ Group Patrick Rinke
AI-based Material Science
Yuhao Zhang
→ Group Patrick Rinke
AI-based Material Science
Recent News @MCML
Publications @MCML
2026
[21]
X. Zhu • P. Rinke • D. A. Egger
Predicting temperature-dependent optoelectronic properties of semiconductor defects with equivariant neural networks.
npj Computational Materials 12.176. May. 2026. DOI
Predicting temperature-dependent optoelectronic properties of semiconductor defects with equivariant neural networks.
npj Computational Materials 12.176. May. 2026. DOI
[20]
Y. Zhang • S. T. John • M. Stosiek • P. Rinke
An Experiment-Aware Bayesian Optimization Workflow for Noisy Mixed-Input Settings.
AI4Mat @ICLR 2026 - Workshop on AI for Accelerated Materials Design at the 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. URL
An Experiment-Aware Bayesian Optimization Workflow for Noisy Mixed-Input Settings.
AI4Mat @ICLR 2026 - Workshop on AI for Accelerated Materials Design at the 14th International Conference on Learning Representations. Rio de Janeiro, Brazil, Apr 23-27, 2026. To be published. Preprint available. URL
[19]
Y. Zhang • T. John • M. Stosiek • P. Rinke
Bayesian Optimization for Mixed-Variable Problems in the Natural Sciences.
Preprint (Apr. 2026). arXiv
Bayesian Optimization for Mixed-Variable Problems in the Natural Sciences.
Preprint (Apr. 2026). arXiv
[18]
G. Budak • C. Riedel • A. Kamra • P. Rinke • C. Back • M. Stosiek • F. Dirnberger
Role of photonic interference in exciton-mediated magneto-optic responses.
Preprint (Mar. 2026). arXiv
Role of photonic interference in exciton-mediated magneto-optic responses.
Preprint (Mar. 2026). arXiv
[17]
L. Lind • H. Sandström • P. Rinke
An interpretable molecular descriptor for machine learning predictions in atmospheric science.
The Journal of Chemical Physics 164.084115. Feb. 2026. DOI
An interpretable molecular descriptor for machine learning predictions in atmospheric science.
The Journal of Chemical Physics 164.084115. Feb. 2026. DOI
[16]
Á. I. Toldy • P. Pisal • O. Krejčí • P. Rinke • A. Santasalo-Aarnio
TheMeCat: Dataset of Thermocatalytic Conversion of CO2 to Methanol.
Scientific Data 13.165. Jan. 2026. DOI
TheMeCat: Dataset of Thermocatalytic Conversion of CO2 to Methanol.
Scientific Data 13.165. Jan. 2026. DOI
2025
[15]
P. Henkel • J. Li • P. Rinke
Design rules for optimizing quaternary mixed-metal chalcohalides.
Physical Review Materials 9.115405. Nov. 2025. DOI
Design rules for optimizing quaternary mixed-metal chalcohalides.
Physical Review Materials 9.115405. Nov. 2025. DOI
[14]
N. Bhatia • P. Rinke • O. Krejci
Leveraging active learning-enhanced machine-learned interatomic potential for efficient infrared spectra prediction.
npj Computational Materials 11.324. Oct. 2025. DOI
Leveraging active learning-enhanced machine-learned interatomic potential for efficient infrared spectra prediction.
npj Computational Materials 11.324. Oct. 2025. DOI
[13]
F. Bortolussi • J. Brean • A. Rowell • D. C. S. Beddows • K. Weinhold • P. Mettke • M. Merkel • T. • A. Kumar • S. Barua • S. Iyer • A. Karppinen • H. Sandström • P. Rinke • A. Wiedensohler • M. Dal Maso • M. P. Rissanen • Z. Shi • R. M. Harrison
Exoloring the role of oxygenated organic molecules in new particle formation events with explainable artificial intelligence.
EAC 2025 - European Aerosol Conference. Lecce, Italy, Aug 31-Sep 05, 2025. URL
Exoloring the role of oxygenated organic molecules in new particle formation events with explainable artificial intelligence.
EAC 2025 - European Aerosol Conference. Lecce, Italy, Aug 31-Sep 05, 2025. URL
[12]
F. Bortolussi • H. Sandström • F. Partovi • J. Mikkilä • P. Rinke • M. Rissanen
Towards atmospheric identification in chemical ionization mass spectrometry with machine learning.
EAC 2025 - European Aerosol Conference. Lecce, Italy, Aug 31-Sep 05, 2025. URL
Towards atmospheric identification in chemical ionization mass spectrometry with machine learning.
EAC 2025 - European Aerosol Conference. Lecce, Italy, Aug 31-Sep 05, 2025. URL
[11]
P. Pisal • O. Krejci • P. Rinke
Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion.
PSI-K 2025 - 7th PSI-K Conference. Lausanne, Switzerland, Aug 25-28, 2025. DOI
Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion.
PSI-K 2025 - 7th PSI-K Conference. Lausanne, Switzerland, Aug 25-28, 2025. DOI
[10]
N. Bhatia • O. Krejci • S. Botti • P. Rinke • M. A. L. Marques
MACE4IR: A foundation model for molecular infrared spectroscopy.
Preprint (Aug. 2025). arXiv
MACE4IR: A foundation model for molecular infrared spectroscopy.
Preprint (Aug. 2025). arXiv
[9]
J. Brean • F. Bortolussi • A. Rowell • D. C. S. Beddows • K. Weinhold • P. Mettke • M. Merkel • A. Kumar • S. Barua • S. Iyer • A. Karppinen • H. Sandström • P. Rinke • A. Wiedensohler • M. Pöhlker • M. Dal Maso • M. Rissanen • Z. Shi • R. M. Harrison
Traffic-Emitted Amines Promote New Particle Formation at Roadsides.
ACS ES&T Air 2.8. Jul. 2025. DOI
Traffic-Emitted Amines Promote New Particle Formation at Roadsides.
ACS ES&T Air 2.8. Jul. 2025. DOI
[8]
R. R. Valiev • R. T. Nasibullin • H. Sandström • P. Rinke • K. Puolamäki • T. Kurten
Predicting intersystem crossing rate constants of alkoxy-radical pairs with structure-based descriptors and machine learning.
Physical Chemistry Chemical Physics 27.28. Jun. 2025. DOI
Predicting intersystem crossing rate constants of alkoxy-radical pairs with structure-based descriptors and machine learning.
Physical Chemistry Chemical Physics 27.28. Jun. 2025. DOI
[7]
P. Pisal • O. Krejci • P. Rinke
Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion.
npj Computational Materials 11.213. Jun. 2025. DOI
Machine learning accelerated descriptor design for catalyst discovery in CO2 to methanol conversion.
npj Computational Materials 11.213. Jun. 2025. DOI
[6]
J. Baumsteiger • L. Celiberti • P. Rinke • M. Todorović • C. Franchini
Exploring Noncollinear Magnetic Energy Landscapes with Bayesian Optimization.
Digital Discovery 4.6. May. 2025. DOI
Exploring Noncollinear Magnetic Energy Landscapes with Bayesian Optimization.
Digital Discovery 4.6. May. 2025. DOI
[5]
H. Sandström • P. Rinke
Similarity-based analysis of atmospheric organic compounds for machine learning applications.
Geoscientific Model Development 18.9. May. 2025. DOI
Similarity-based analysis of atmospheric organic compounds for machine learning applications.
Geoscientific Model Development 18.9. May. 2025. DOI
[4]
Y. Zhang • M. Vaara • A. Alesafar • D. Bach Nguyen • P. Silva • L. Koskelo • J. Ristolainen • M. Stosiek • J. Löfgren • J. Vapaavuori • P. Rinke
Data-efficient optimization of thermally-activated polymer actuators through machine learning.
Materials and Design 253.113908. May. 2025. DOI
Data-efficient optimization of thermally-activated polymer actuators through machine learning.
Materials and Design 253.113908. May. 2025. DOI
[3]
H. Homm • J. Laakso • P. Rinke
Efficient dataset generation for machine learning halide perovskite alloys.
Physical Review Materials 9.053802. May. 2025. DOI
Efficient dataset generation for machine learning halide perovskite alloys.
Physical Review Materials 9.053802. May. 2025. DOI
[2]
F. Bortolussi • H. Sandström • F. Partovi • J. Mikkilä • P. Rinke • M. Rissanen
Technical note: Towards atmospheric compound identification in chemical ionization mass spectrometry with pesticide standards and machine learning.
Atmospheric Chemistry and Physics 25.1. Jan. 2025. DOI
Technical note: Towards atmospheric compound identification in chemical ionization mass spectrometry with pesticide standards and machine learning.
Atmospheric Chemistry and Physics 25.1. Jan. 2025. DOI
[1]
K. Ghosh • M. Todorović • A. Vehtari • P. Rinke
Active learning of molecular data for task-specific objectives.
The Journal of Chemical Physics 162.014103. Jan. 2025. DOI
Active learning of molecular data for task-specific objectives.
The Journal of Chemical Physics 162.014103. Jan. 2025. DOI
©all images: LMU | TUM
Back to Top
2024-12-27 - Last modified: 2026-04-22