TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publications
  4. Exploiting the Fourier Neural Operator for faster magnetization model evaluations based on the Fokker-Planck equation
 
Options

Exploiting the Fourier Neural Operator for faster magnetization model evaluations based on the Fokker-Planck equation

Citation Link: https://doi.org/10.15480/882.5070
Publikationstyp
Journal Article
Date Issued
2023-03-19
Sprache
English
Author(s)
Knopp, Tobias  
Albers, Hannes  
Grosser, Mirco  
Möddel, Martin  orcid-logo
Kluth, Tobias  
Institut
Biomedizinische Bildgebung E-5  
TORE-DOI
10.15480/882.5070
TORE-URI
http://hdl.handle.net/11420/15205
Journal
International journal on magnetic particle imaging  
Volume
9
Issue
1, suppl. 1
Start Page
Infinite Science Publishing
Article Number
2303003
Citation
International Journal on Magnetic Particle Imaging 9 (1, supp. 1): 2303003 (2023)
Publisher DOI
10.18416/IJMPI.2023.2303003
Scopus ID
2-s2.0-85151531001
Publisher
Infinite Science Publishing
Accurate modeling of the mean magnetic moment of an ensemble of magnetic particles in dynamic magnetic fields is a challenging task that requires sophisticated differential equation solvers. However, these methods are computationally costly and therefore not practical for long excitation sequences such as those of the Lissajous type. In this paper we propose to accelerate simulations by using a neural network mapping from the input parameter functions that are applied to the original particle simulator directly to the mean magnetic moment output function. The architecture of the neural network is based on the Fourier neural operator, which allows to train mappings between function spaces. Our results show that the particle simulation can be accelerated by a factor of about 200 while the relative error of the neural network simulator remains below 1.5 %.
DDC Class
510: Mathematik
600: Technik
610: Medizin
620: Ingenieurwissenschaften
Funding Organisations
Deutsche Forschungsgemeinschaft (DFG)  
Publication version
publishedVersion
Lizenz
https://creativecommons.org/licenses/by/4.0/
Loading...
Thumbnail Image
Name

597-Article Text-3577-1-10-20230320.pdf

Size

828.12 KB

Format

Adobe PDF

TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback