Projects

The doctoral network Artificial Intelligence in Parkinson’s Disease (AIPD) is researching new AI-based methods for the early diagnosis and treatment of Parkinson’s disease. The goal is to develop digital approaches that enable more precise detection of Parkinson's disease – for example, by identifying speech biomarkers – and thereby support more personalized therapies. The project also addresses issues of trustworthiness, ethics, and the regulation of AI solutions.

The integration of recycled materials continues to pose challenges for the manufacturing industry, as the quality of the products depends on the interaction between the materials used and the manufacturing processes. Variations in trace elements and chemical properties affect additive manufacturing processes such as 3D printing. The GEAR-UP project aims to develop digital tools to facilitate the use of recycled materials in metal and plastics processing. Simulation-based approaches and AI methods will be used to establish resource-efficient manufacturing processes. The digital product passport developed in the project ensures the traceability of materials.

The SYNTHIA project team develops new techniques for the responsible generation and use of synthetic patient data. These data, generated using generative methods of artificial intelligence, can help overcome data protection hurdles, improve prediction models for personalized medicine, and emulate control groups in clinical studies. The validated synthetic data will then be made available on a modern IT platform, together with their possible applications.

Today, most crash tests to evaluate vehicle safety are conducted virtually. Documenting the changes to the simulated vehicle models is particularly time-consuming and costly. The SAFECAR-ML project aims to simplify this process. By combining novel methods of artificial intelligence (AI) with technical knowledge from vehicle development, the project partners from research and automotive industry want to standardize the information processing for the documentation of virtual crash tests. New is the combination of semantically processed free text with multimodal engineering data for machine learning.

Technologies such as CCUS (Carbon Capture, Utilisation, and Storage), which capture and store CO₂, are a key component of decarbonization strategies. The project "Eastern Lights" supports the development of a large-scale CCUS cluster in northern Bulgaria to store CO₂ from the cement industry. The construction of a short pipeline is planned to safely transport CO₂ to saline aquifers for storage. The goal is to establish an efficient transport and storage infrastructure that will serve as a long-term model for CO₂ utilization in the region. Fraunhofer SCAI’s software MYNTS supports the planning and optimization of the CO₂ pipeline network.