Parts | Days | Selection | Search | Updates | Downloads | Help
AKBP: Arbeitskreis Beschleunigerphysik
AKBP 6: Plasma Accelerators, Ions II
AKBP 6.5: Talk
Tuesday, March 10, 2026, 12:15–12:30, SCH/A117
Human-Explainable, Compact, Clustering-based Latents for Fast Proton Energy Spectra Estimation — •Vedhas Pandit1, Jeyhun Rustamov1, Martin Rehwald1, Stefan Assenbaum1, Vidisha Rana1, Hans-Peter Schlenvoigt1, Michael Bussmann1,2, Ulrich Schramm1,3, Thomas Kluge1, and Jeffrey Kelling1,4 — 1Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany — 2Center for Advance Systems Understanding (CASUS), Görlitz, Saxony, Germany — 3Technische Universität Dresden, Faculty of Physics, Dresden, Saxony, Germany — 4Technische Universität Chemnitz, Institute of Physics, Chemnitz, Saxony, Germany
A bottleneck in gaining a deeper understanding of the complex laser-plasma interaction that generates laser-accelerated protons is the lack of robust and near real-time information extraction from high frequency shot-data, due to human intervention required in the process. Here, we present an approach to employ deep learning methods to reduce the need for human input into the analysis of Thomson Parabola Spectrometer (TPS) measurements of proton energy spectra given relatively limited labelled data. Our approach builds on deep feature extraction using general pre-trained autoencoders, self organizing map-based clustering of global image features and the spectra that are available as labels, to effectively reduce the dimension of input and output modalities. Lower dimensional representations then enable a small model to be trained on limited data to estimate proton spectra and to help with spectrometer re-calibrations.
Keywords: proton energy spectrum; thomson parabola spectrometer; self organizing map; interpretable latent representation; variational autoencoder