Research
Research Interests
- Deep Learning for Spatio-Temporal Forecasting: Spatio-temporal forecasting is a field focused on creating predictive models for systems that evolve across both space and time. The primary goal is to accurately forecast future states by learning from historical data in domains ranging from urban mobility to environmental science. The central challenge lies in simultaneously modeling two key relationships: spatial dependency (how different locations influence each other) and temporal dependency (how past events influence the future). Effective deep learning models must capture the intricate ways that local events propagate through a system, causing cascading effects elsewhere over time.
- EV Charging Infrastructure: My research focuses on advancing the electrification of transport systems using advanced forecasting models. A primary goal is to forecast the status and properties of EV charging infrastructure—such as availability, or queue times—to enhance the efficiency of charging processes. I apply these predictive insights to the challenge of electrifying heavy-duty trucks, aiming to forecast their operational impact and guide the development of a sustainable logistics ecosystem.
CV
Work Experience
since 2023 Research Assistant at Autonomous Intelligent Systems Group, Universität Münster 2022 - 2023 Research Assistant at Institute of Automation and Information Systems, TU Munich Education
2022 M.Sc., Automation Engineering, RWTH Aachen
Publications
2025
V. Hankemeier and M. Schilling, "Tailored Architectures for Time Series Forecasting: Evaluating Deep Learning Models on Gaussian Process-Generated Data," in Proc. Int. Joint Conf. on Neural Networks (IJCNN), 2025, arXiv:2506.08977. https://doi.org/10.48550/arXiv.2506.08977
2024
Y. Shatewakasi, B. Vogel-Heuser, J. Wilch, V. Hankemeier and J. Höfgen, "Towards NLP-driven Online-classification of Industrial Alarm Messages," IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society, Chicago, IL, USA, 2024, pp. 1-8, doi: 10.1109/IECON55916.2024.10905746.
B. Lahrsen, B. Vogel-Heuser, J. Wilch, V. Hankemeier, M. Wander and C. Kögel, "Investigating the Adaptability of Alarm Root-Cause Analysis Methods for Discrete Process Types," 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), Bari, Italy, 2024, pp. 1214-1221, doi: 10.1109/CASE59546.2024.10711498.
B. Vogel-Heuser, A. Fay, B. Rupprecht, F. Kunze, V. Hankemeier, T. Westermann, G. Manca. "Exploring challenges of alarm root-cause analysis across varying production process types" at - Automatisierungstechnik, vol. 72, no. 4, 2024, pp. 369-386. doi: https://doi.org/10.1515/auto-2023-0180
2022
M. Trinh, J. Moon, L. Gründel, V. Hankemeier, S. Storms and C. Brecher, "Development of a Framework for Continual Learning in Industrial Robotics," 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, 2022, pp. 1-8, doi: 10.1109/ETFA52439.2022.9921432.
Student Thesis
If you are a student passionate about delving into the fields of deep supervised learning, and spatio-temporal forecasting for your thesis, I look forward to hearing from you! Feel free to get in touch, and please include your CV, a short motivational message, and your grade transcript when you do.