S. Eisenbach

S. Eisenbach

Auto-generated profile, based on publicly available information

S. Eisenbach

Department of Physics and Astronomy, University of California—Los Angeles 1 , Los Angeles, California 90095

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 October 2024 in Journal of Physics D: Applied Physics
Verified
Journal Article
Closed access
SES Eisenbach
S Eisenbach
DMD A Mariscal
D A Mariscal
RDR S Dorst
R S Dorst
THT Van Hoomissen
T Van Hoomissen
AOA M Ortiz
A M Ortiz
CNChristoph Niemann
Christoph Niemann
With the emergence of high-repetition-rate two-dimensional Thomson scattering (TS) measurements, improving spectral data analysis is a key area of interest. We present a new way to derive the electron temperature and density of laser-driven blast waves in plasmas from their TS spectra with machine learning (ML). This analysis occurs in both the non-collective ( α < 1) and collective ( α > 1) scattering regimes with the goal of autonomously and more accurately determining T e and n e both where spectral data has been collected and to give the ability to predict these attributes in regions where data has not been collected. We introduce three ML models, one trained only on experimental data, one only on synthetic data, and one using transfer learning, and compare their speed and accuracy with the conventional TS inversion algorithms in the open source PlasmaPy python package.

1 January 2026 in Physics of Plasmas
Verified
Journal Article
Open access
THT. Van Hoomissen
T. Van Hoomissen
JAJ. Alhuthali
J. Alhuthali
AOA. M. Ortiz
A. M. Ortiz
DMD. A. Mariscal
D. A. Mariscal
RDR. S. Dorst
R. S. Dorst
DSD. B. Schaeffer
D. B. Schaeffer
Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density (ne) and electron temperature (Te). Deep neural networks can provide accurate estimates of ne and Te when conventional fitting algorithms may fail, such as when TS spectra are dominated by noise, or when fast analysis is required for real-time operation. Although deep neural networks typically require large training sets, transfer learning can improve model performance on a target task with limited data by leveraging pre-trained models from related source tasks, where select hidden layers are further trained using target data. We present five architecturally diverse deep neural networks, pre-trained on synthetic TS data and adapted for experimentally measured TS data, to evaluate the efficacy of transfer learning in estimating ne and Te in both the collective and non-collective scattering regimes. We evaluate errors in ne and Te estimates as a function of training set size for models trained with and without transfer learning, and we observe decreases in model error from transfer learning when the training set contains ≲200 experimentally measured spectra.