Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911329032339456 |
|---|---|
| author | Van Hoomissen, T. Alhuthali, J. Ortiz, A. M. Mariscal, D. A. Dorst, R. S. Eisenbach, S. Zhang, H. Pilgram, J. J. Constantin, C. G. Rovige, L. Niemann, C. Schaeffer, D. B. |
| author_facet | Van Hoomissen, T. Alhuthali, J. Ortiz, A. M. Mariscal, D. A. Dorst, R. S. Eisenbach, S. Zhang, H. Pilgram, J. J. Constantin, C. G. Rovige, L. Niemann, C. Schaeffer, D. B. |
| contents | Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density ($n_e$) and electron temperature ($T_e$). Deep neural networks can provide accurate estimates of $n_e$ and $T_e$ 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 $n_e$ and $T_e$ in both the collective and non-collective scattering regimes. We evaluate errors in $n_e$ and $T_e$ 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 $\lessapprox$ 200 experimentally measured spectra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18173 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra Van Hoomissen, T. Alhuthali, J. Ortiz, A. M. Mariscal, D. A. Dorst, R. S. Eisenbach, S. Zhang, H. Pilgram, J. J. Constantin, C. G. Rovige, L. Niemann, C. Schaeffer, D. B. Plasma Physics Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density ($n_e$) and electron temperature ($T_e$). Deep neural networks can provide accurate estimates of $n_e$ and $T_e$ 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 $n_e$ and $T_e$ in both the collective and non-collective scattering regimes. We evaluate errors in $n_e$ and $T_e$ 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 $\lessapprox$ 200 experimentally measured spectra. |
| title | Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra |
| topic | Plasma Physics |
| url | https://arxiv.org/abs/2512.18173 |