EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting the future with magnons: Forecasting chaotic time series with reservoir computing

Zeling Xiong, Christopher Heins, Thibaut Devolder, Fabian Kammerbauer, Mathias Kläui, Jürgen Fassbender, Helmut Schultheiss, Katrin Schultheiss

Physical Review Applied · 17.04.2026 · 25 (4)

DOI: 10.1103/ffz7-p6vc ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review Applied, online erschienen am 17.04.2026. Verfasst von Zeling Xiong und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU Research and Innovation Programme Horizon Europe.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forecasting complex, chaotic signals is a central challenge across science and technology, with implications ranging from secure communications to climate modeling. Here we demonstrate that magnons, the collective spin excitations in magnetically ordered materials, can serve as an efficient physical reservoir for predicting such dynamics. Using a magnetic vortex-state microdisk as a magnon-scattering reservoir, we show that intrinsic nonlinear interactions transform a simple microwave input into a high-dimensional spectral output suitable for time-series predictions. Trained on the Mackey-Glass benchmark, which generates a cyclic yet aperiodic time series, the system achieves accurate and reliable predictions that rival other state-of-the-art physical reservoirs. We further identify key design principles: spectral resolution governs the tradeoff between dimensionality and accuracy, while combining multiple device geometries systematically improves performance. These results establish magnonics as a promising platform for unconventional computing, offering a path toward scalable and CMOS-compatible hardware for real-time prediction tasks.

Förderung

  • EU Research and Innovation Programme Horizon Europe

Zitieren

APA

Xiong, Z., Heins, C., Devolder, T., Kammerbauer, F., Kläui, M., Fassbender, J., Schultheiss, H., & Schultheiss, K. (2026). Predicting the future with magnons: Forecasting chaotic time series with reservoir computing. Physical Review Applied, 25(4). https://doi.org/10.1103/ffz7-p6vc

Vancouver

Xiong Z, Heins C, Devolder T, Kammerbauer F, Kläui M, Fassbender J, et al. Predicting the future with magnons: Forecasting chaotic time series with reservoir computing. Physical Review Applied. 2026;25(4). doi:10.1103/ffz7-p6vc

BibTeX
@article{Xiong2026,
  author = {Xiong, Zeling and Heins, Christopher and Devolder, Thibaut and Kammerbauer, Fabian and Kläui, Mathias and Fassbender, Jürgen and Schultheiss, Helmut and Schultheiss, Katrin},
  title = {Predicting the future with magnons: Forecasting chaotic time series with reservoir computing},
  journal = {Physical Review Applied},
  year = {2026},
  volume = {25},
  number = {4},
  doi = {10.1103/ffz7-p6vc}
}
Kostenlos starten →