Research

Modern X-ray free-electron lasers (XFELs) have transformed how scientists study molecular and material structures. Their unique beam properties are crucial for experiments, but optimizing these features, especially advanced ones such as the wavefront shape, is a complex and time-consuming endeavor. Moreover, the lack of near-real-time feedback from experiments to the XFEL machine prevents immediate beam adjustments, resulting in inefficient use of valuable experimental time and limiting XFEL's full scientific potential.

In this project, AI4Ops@XFEL, we propose optimizing X-ray free-electron laser (XFEL) operation through AI-driven real-time feedback, addressing critical challenges in optimizing beam parameters and maximizing data quality. By integrating machine learning into experimental diagnostics, this project aims to unlock AI-based control over XFEL beam properties, building the foundation for significantly enhancing experiment quality.

• Role: PI
• Year(s): 2026-2029 (3 years)
• Volume: about 250k Euro

Drone Ballet ("Drohnenballet") is a joint project by the company Zouber from Kiel and Hamburg University of Technology, funded by the Federal Ministry of Research, Technology, and Space (BMFTR), Germany, as part of UAM-Inno Region SH. We plan to develop a new generation of creative, efficiently plannable drone shows. It focuses on AI-based flight-path planning and dynamic swarm control so that shows can be generated automatically, interactively adapted during performances, and enriched with effects such as morphing between shapes and interactive elements. The technology is also intended as a building block for further urban air mobility applications, for example, in sea rescue, agriculture, or inspection, and offers an emission-free alternative to fireworks.

• Project Webseite: Sourced
• Role: PI
• Year(s): 2026-2028 (3 years)
• Volume: about 290k Euro

• Role: PI
• Year(s): 2026-2027 (2 years)
• Volume: about 33k Euro
• TORE

Distributed, locality-aware process mining and process mining on resource-constrained IoT devices.

• Project Webseite: Sourced
• Role: PI
• Year(s): 2023-2027 (4 years)
• Volume: about 400k Euro
• TORE

The KIMMCO project investigates how biodiversity affects the CO2 storage capacity of phytoplankton, a key factor in marine conservation. Researchers integrate data from sensors, cameras, optical measurements, and satellites, using AI to analyse these inputs and deliver near real-time insights into phytoplankton productivity and composition. The project aims to make large-scale ocean measurements more efficient, accurate, and sustainable by reducing time, ship operations, and the CO2 footprint of marine observation.

• Project website
• Role: Co-PI
• Year(s): 2025-2027 (2.5 years)
• Volume: 325k Euro

Intelligent underwater monitoring systems combining distributed underwater sensor networks with cloud-based digital twins.

• Helmholtz MarData
• Role: Co-PI
• Year(s): 2025-2028 (3 years)
• Volume: 230k Euro

Understanding creates acceptance. This is the premise behind the new CAPTN project X-Ferry. With this research project, the CAPTN initiative is taking another step towards realizing its idea of developing a mobility chain of self-driving, safe and clean vehicles. After the Fjord Area, 5G and Flex projects, which laid the foundation for autonomous shipping in Kiel, the focus is now on explaining the technical processes and communicating with users. Initially, the focus will remain on ships. The new project will research systems that will increase the acceptance of autonomous vehicles.

• Project Webseite: X-Ferry
• Role: Co-PI
• Year(s): 2024-2027 (3 years)
• Volume: 270k Euro

Data-driven prediction and event detection for underwater sensing.

• Project Webseite: INSYST
• Role: PI
• Year(s): 2023-2026 (3 years)
• Volume: 325k Euro