STEP: extraction of underlying physics with robust machine learning
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.
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
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}
}
EUVIMED