Artificial Intelligence Research Platform

Data scientists and researchers from diverse fields at HZDR design and train artificial intelligence models using increasingly large and cross-disciplinary datasets. This approach enables them to develop comprehensive solutions and uncover new insights and applications in the research fields of Matter, Energy, and Health.
The newly established HZDR AI Lab, founded in 2024, serves as a central hub for researchers within HZDR, at other Helmholtz centers, research institutions, and industry.

News from the AI Lab

06.06.2025 AI Lab: HAICON25 Pos­ter Prize for Philip Müller for his work on Uncertainties in Large Language Models

20.05.2025 AI Lab: New Course Portfolio on “AI in Administration & Management”

11.12.2024 AI Lab: Helmholtz Publishes AI Usage Recommendations

More news
Foto: Materials of the future thanks to faster simulations, KI@HZDR ©Copyright: Blaurock/HZDR

AI Lab

Our AI Lab is the central hub for AI-related topics at the HZDR.
More
Foto: Icon AI offers ©Copyright: iStock

Industry Collaborations

Our goal is to le­verage our expertise in AI for research, innovation, and collaboration with industry partners.
More
Foto: Icon AI consulting ©Copyright: iStock

Helmholtz AI Consultant Team

We develop and disseminate AI-supported data science solutions to tackle the grand challenges in research and society.
More
Foto: Brain-inspired computing ©Copyright: Blaurock Markenkommunikation/HZDR

Research Field Mat­ter

Particle accelerators, future materials, brain-inspired computing, planetary research
More
Foto: Artificial intelligence supports the search for hard-to-reach mineral resources ©Copyright: HZDR/Blaurock Markenkommunikation

Research Field Energy

Machine learning methods drive the search for raw materials
More
Foto: Cancer irradiation with the highest precision ©Copyright: Blaurock Markenkommunikation/HZDR

Research Field Health

AI algorithms improve the diagnosis and treatment of cancer
More

AI Publications

Journal articles (refereed), Invited lectures

2025

Data management makes machine learning easier

Korten, T.; Hoffmann, H.; Steinbach, P.; Özkan, Ö.

Hydrogen adsorption energy trends in Mo/WXY (X, Y = S, Se, Te) regular and Janus TMD monolayers: A first-principles and machine learning study

Tejaswini, G.; Sudheer, A. E.; Kumar, A.; Perepu, P. K.; Vallinayagam, M.; et al. (10 authors)

Virtual pulse reconstruction diagnostic for single-shot measurement of free electron laser radiation power

Mirian, N. S.; Korten, T.; Steinbach, P.; Vladimir, R.

Combining sequential Gaussian co-simulation and Monte Carlo dropout-based deep learning models for geochemical anomaly detection and uncertainty assessment

Huang, D.; Renguang, Z.; Jian, W.; Tolosana Delgado, R.

Scalable Machine Learning for Electronic Structure Theory

Cangi, A.

  • Invited lecture (Conferences)
    Theoretical Chemistry Colloquium, 21.01.2025, Marburg, Germany

More publications