Over the next seven years, the simulation experts working at the Department for Integrated Sensor Systems at Danube University Krems will together with Toyota conduct research on methods to replace or significantly reduce rare earths for magnets as key components of electric motors by using simulation and artificial intelligence. The new CD-Laboratory receives funding from the Christian Doppler Research Association and the Federal Ministry for Digitalization and Economic Development (BMDW).

The CD-Laboratory's goal is to develop new strategies for designing magnets used in electric motors to power e-mobility in order to prevent supply bottlenecks of rare-earth elements. To optimize the magnets, artificial intelligence is utilized to run simulation models on supercomputers.

High-performance magnets play a key role in green technologies such as electro mobility. However, the growing demand for electric vehicles will lead to a shortage of rare earths such as neodymium, and heavy rare earth elements such as terbium and dysprosium. They are essential components for high-temperature permanent magnets such as those installed in e-cars.

Project Overview



Duration 01/09/2020 - 31/08/2027
Funding Private (Stiftungen, Vereine etc.)
Christian Doppler Forschungsgesellschaft Logo BMDW Toyota

Department for Integrated Sensor Systems

Center for Modelling and Simulation

Principle investigator for the project (University for Continuing Education Krems) Univ.-Doz.Dipl.-Ing.Dr. Thomas Schrefl


  1. Kovacs A.; Exl, L.; Kornell, A.; Fischbacher, J.; Hovorka, M.; Gusenbauer, M.; Breth, L.; Oezelt, H.; Praetorius, D.; Suess, D.; Schrefl, T: Magnetostatics and Micromagnetics with Physics Informed Neural Networks: Journal of Magnetism and Magnetic Materials 2022, 548, 168951. https://doi.org/10.1016/j.jmmm.2021.168951.
  2. Heistracher, P.; Abert, C.; Bruckner, F.; Schrefl, T.; Suess, D. Proposal for a Micromagnetic Standard Problem: Domain Wall Pinning at Phase Boundaries. Journal of Magnetism and Magnetic Materials 2022, 548, 168875.https://doi.org/10.1016/j.jmmm.2021.168875.
  3. Oezelt, H.; Qu, L.; Kovacs, A.; Fischbacher, J.; Gusenbauer, M.; Beigelbeck, R.; Praetorius, D.; Yano, M.; Shoji, T.; Kato, A.; Chantrell, R.; Winklhofer, M.; Zimanyi, G. T.; Schrefl, T. Full-Spin-Wave-Scaled Stochastic Micromagnetism for Mesh-Independent Simulations of Ferromagnetic Resonance and Reversal. npj Comput Mater 2022, 8 (1), 1–9. https://doi.org/10.1038/s41524-022-00719-5.
  4. Schaffer, S.; Mauser, N. J.; Schrefl, T.; Suess, D.; Exl, L. Machine Learning Methods for the Prediction of Micromagnetic Magnetization Dynamics. IEEE Transactions on Magnetics 2022, 58 (2), 1–6. https://doi.org/10.1109/TMAG.2021.3095251, https://arxiv.org/abs/2103.09079  
  5. Kovacs, A.; Exl, L.; Kornell, A.; Fischbacher, J.; Hovorka, M.; Gusenbauer, M.; Breth, L.; Oezelt, H.; Yano, M.; Sakuma, N.; Kinoshita, A.; Shoji, T.; Kato, A.; Schrefl, T. Conditional Physics Informed Neural Networks. Communications in Nonlinear Science and Numerical Simulation 2022, 104, 106041. https://doi.org/10.1016/j.cnsns.2021.106041, https://arxiv.org/abs/2104.02741  
  6. Exl, L.; Mauser, N. J.; Schaffer, S.; Schrefl, T.; Suess, D. Prediction of Magnetization Dynamics in a Reduced Dimensional Feature Space Setting Utilizing a Low-Rank Kernel Method. Journal of Computational Physics 2021, 444, 110586, https://doi.org/10.1016/j.jcp.2021.110586, https://arxiv.org/abs/2008.05986 
  7. Exl, L.; Suess, D.; Schrefl, T. Micromagnetism.  In Handbook of Magnetism and Magnetic Materials; Coey, M., Parkin, S., Eds.; Springer International Publishing: Cham, 2020; pp 1–44. https://doi.org/10.1007/978-3-030-63101-7_7-1.
  8. Kovacs, A.; Exl, L.; Kornell, A.; Fischbache,r J.; Hovorka, M.; Gusenbauer, M.; Breth, L.; Oezelt, H.; Yano, M.; Sakuma, N.; Kinoshita, A.; Shoji, T.; Kato, A.; Schrefl, T. Exploring the Hysteresis Properties of Nanocrystalline Permanent Magnets Using Deep Learning,https://arxiv.org/abs/2203.16676
  9. Kornell, A., Exl, L, Breth, L., Fischbacher, J., Kovacs, A., Oezelt, H., Gusenbauer, M., Yano, M., Sakuma, N., Kinoshita, A., Shoji, T., Kato, A., Mauser, N. J., Schrefl, T. Description of collective magnetization processes with machine learning models. https://arxiv.org/abs/2205.03708 

Selected talks at international conferences

Markus Gusenbauer, Machine Learning for Relating Structure and Coercivity of Permanent Magnets, June 9, 2021, The 26th International Workshop on Rare Earth and Future Permanent Magnets and Their Application, Online

Thomas Schrefl, Physics informed neural networks for computational magnetism, January 11, 2022, Joint MMM-Intermag conference, New Orleans, Online.

Back to top