Machine Learning

Machine Learning Applications and Research @ ISD

Welcome to the Machine Learning Research Group at the Institute of Structural Mechanics and Dynamics in Aerospace Engineering. Our group specializes in application and methodological development of machine learning techniques in mechanics.

We are actively engaged in developing physics-informed machine learning models that integrate domain-specific knowledge to enhance the accuracy and interpretability of predictions especially in coupled problems. Additionally, our research extends into the realm of medical image analysis, where we leverage machine learning algorithms to segment and analyze medical images. The obtained insight are leveraged to enhance diagnostic capabilities and are processed to generate input for subsequent simulations.

Collaborating closely with the other research groups, we develop surrogate models that efficiently represent high-fidelity simulations, facilitating accelerated design processes, near real-time predictions, and optimization studies across various disciplines. Our expertise in regression and classification allows us to analyze experimental data and clinical datasets from us and our partners. We leverage this approach to gain deeper insights into model discovery, refinement, and simulation.

For questions, inquiries, or to express interest, please feel free to reach out to us.

Publications

  1. 2025

    1. Mandl, L., Goswami, S., Lambers, L., & Ricken, T. (2025). Separable physics-informed DeepONet: Breaking the curse of dimensionality in physics-informed machine learning. Computer Methods in Applied Mechanics and Engineering, 434, 117586. https://doi.org/10.1016/j.cma.2024.117586
  2. 2024

    1. Arasteh-Khoshbin, O., Seyedpour, S. M., Mandl, L., Lambers, L., & Ricken, T. (2024). Comparing durability and compressive strength predictions of hyperoptimized random forests and artificial neural networks on a small dataset of concrete containing nano SiO2 and RHA. European Journal of Environmental and Civil Engineering, 1–20. https://doi.org/10.1080/19648189.2024.2393881
    2. Tautenhahn, H.-M., Ricken, T., Dahmen, U., Mandl, L., Bütow, L., Gerhäusser, S., Lambers, L., Chen, X., Lehmann, E., Dirsch, O., & König, M. (2024). SimLivA-Modeling ischemia-reperfusion injury in the liver: A first step towards a clinical decision support tool. GAMM-Mitteilungen. https://doi.org/10.1002/gamm.202370003
  3. 2023

    1. Mandl, L., Mielke, A., Seyedpour, S. M., & Ricken, T. (2023). Affine transformations accelerate the training of physics-informed neural networks of a one-dimensional consolidation problem. Scientific Reports, 13(1), Article 1. https://doi.org/10.1038/s41598-023-42141-x
    2. Mandl, L., Mielke, A., Seyedour, S. M., & Ricken, T. (2023). Affine transformations accelerate the training of physics-informed neural networks of a one-dimensional consolidation problem. Scientific Reports, 13(15566), Article 15566. https://doi.org/10.1038/s41598-023-42141-x
  4. 2021

    1. Lambers, L., Mielke, A., & Ricken, T. (2021). Semi-automated Data-driven FE Mesh Generation and Inverse Parameter Identification for a Multiscale and Multiphase Model of Function-Perfusion Processes in the Liver. PAMM, 21(1), Article 1. https://doi.org/10.1002/pamm.202100190
    2. Egli, F. S., Straube, R. C., Mielke, A., & Ricken, T. (2021). Surrogate Modeling of a Nonlinear, Biphasic Model of Articular Cartilage with Artificial Neural Networks. PAMM, 21(1), Article 1. https://doi.org/10.1002/pamm.202100188
    3. Pi Savall, B., Mielke, A., & Ricken, T. (2021). Data-Driven Stress Prediction for Thermoplastic Materials. PAMM, 21(1), Article 1. https://doi.org/10.1002/pamm.202100225
  5. 2019

    1. Mielke, A., & Ricken, T. (2019). Evaluating Artificial Neural Networks and Quantum Computing for Solving Mechanical Boundary Value Problems. In A. Zingoni (Ed.), Advances in Engineering Materials, Structures and Systems: Innovations, Mechanics and Applications (pp. 537–542). CRC Press-Balkema.
    2. Mielke, A., & Ricken, T. (2019). Evaluating Artificial Neural Networks and Quantum Computing for Mechanics. In PAMM (No. 1; Vol. 19, Issue 1, p. e201900470). https://doi.org/10.1002/pamm.201900470

Head of Group

Researchers

This image shows Tim Ricken

Tim Ricken

Univ.-Prof. Dr.-Ing.

Head of Department

To the top of the page