EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STEP: extraction of underlying physics with robust machine learning

Karim K Alaa El-Din iD, Alessandro Forte, Muhammad Firmansyah Kasim, Francesco Miniati, Sam M Vinko

Royal Society Open Science · 2024-06 · 11 (6)

DOI: 10.1098/rsos.231374 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Royal Society Open Science, online erschienen am 05.06.2024. Verfasst von Karim K Alaa El-Din und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, University of Oxford, Oxford, UK. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK STFC XFEL Hub, Royal Society, UK EPSRC.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A prevalent class of challenges in modern physics are inverse problems, where physical quantities must be extracted from experimental measurements. End-to-end machine learning approaches to inverse problems typically require constructing sophisticated estimators to achieve the desired accuracy, largely because they need to learn the complex underlying physical model. Here, we discuss an alternative paradigm: by making the physical model auto-differentiable we can construct a neural surrogate to represent the unknown physical quantity sought, while avoiding having to relearn the known physics entirely. We dub this process surrogate training embedded in physics (STEP) and illustrate that it generalizes well and is robust against overfitting and significant noise in the data. We demonstrate how STEP can be applied to perform dynamic kernel deconvolution to analyse resonant inelastic X-ray scattering spectra and show that surprisingly simple estimator architectures suffice to extract the relevant physical information.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencedifferentiable modellingmachine learningphysicsresonant inelastic X-ray scatteringspectroscopy

Autor:innen und Institutionen

  • Department of Physics, University of Oxford, Oxford, UK.
  • Machine Discovery, Oxford OX4 4GP, UK.
  • Central Laser Facility, STFC Rutherford Appleton Laboratory, Didcot, OX11 0QX, UK.

ORCID-Profile: Karim K Alaa El-Din

Förderung

  • UK STFC XFEL Hub
  • Royal Society
  • UK EPSRC

Zitieren

APA

Alaa El-Din, K. K., Forte, A., Kasim, M. F., Miniati, F., & Vinko, S. M. (2024). STEP: extraction of underlying physics with robust machine learning. Royal Society Open Science, 11(6). https://doi.org/10.1098/rsos.231374

Vancouver

Alaa El-Din KK, Forte A, Kasim MF, Miniati F, Vinko SM. STEP: extraction of underlying physics with robust machine learning. Royal Society Open Science. 2024;11(6). doi:10.1098/rsos.231374

BibTeX
@article{AlaaElDin2024,
  author = {Alaa El-Din, Karim K and Forte, Alessandro and Kasim, Muhammad Firmansyah and Miniati, Francesco and Vinko, Sam M},
  title = {STEP: extraction of underlying physics with robust machine learning},
  journal = {Royal Society Open Science},
  year = {2024},
  volume = {11},
  number = {6},
  doi = {10.1098/rsos.231374}
}
Kostenlos starten →