Deep learning is having a profound impact in many fields, especially those that involve some form of image processing. Deep neural networks excel in turning an input image into a set of high-level features. On the other hand, tomography deals with the inverse problem of recreating an image from a number of projections. In plasma diagnostics, tomography aims at reconstructing the cross-section of the plasma from radiation measurements. This reconstruction can be computed with neural networks. However, previous attempts have focused on learning a parametric model of the plasma profile. In this work, we use a deep neural network to produce a full, pixel-by-pixel reconstruction of the plasma profile. For this purpose, we use the overview bolometer system at JET, and we introduce an up-convolutional network that has been trained and tested on a large set of sample tomograms. We show that this network is able to reproduce existing reconstructions with a high level of accuracy, as measured by several metrics.

Deep learning for plasma tomography using the bolometer system at JET / Matos, F.A., Ferreira, D.R., Carvalho, P.J., Abhangi, M., Abreu, P., Aftanas, M., Afzal, M., Aggarwal, K.M., Aho-Mantila, L., Ahonen, E., Aints, M., Airila, M., Albanese, R., Alegre, D., Alessi, E., Aleynikov, P., Alfier, A., Alkseev, A., Allan, P., Almaviva, S., et al.. - In: FUSION ENGINEERING AND DESIGN. - ISSN 0920-3796. - 114:(2017), pp. 18-25. [10.1016/j.fusengdes.2016.11.006]

Deep learning for plasma tomography using the bolometer system at JET

Albanese, R.;Coccorese, V.;De Tommasi, G.;Mattei, M.;Pironti, A.;Quercia, A.;Rubinacci, G.;Villone, F.;
2017

Abstract

Deep learning is having a profound impact in many fields, especially those that involve some form of image processing. Deep neural networks excel in turning an input image into a set of high-level features. On the other hand, tomography deals with the inverse problem of recreating an image from a number of projections. In plasma diagnostics, tomography aims at reconstructing the cross-section of the plasma from radiation measurements. This reconstruction can be computed with neural networks. However, previous attempts have focused on learning a parametric model of the plasma profile. In this work, we use a deep neural network to produce a full, pixel-by-pixel reconstruction of the plasma profile. For this purpose, we use the overview bolometer system at JET, and we introduce an up-convolutional network that has been trained and tested on a large set of sample tomograms. We show that this network is able to reproduce existing reconstructions with a high level of accuracy, as measured by several metrics.
2017
Deep learning for plasma tomography using the bolometer system at JET / Matos, F.A., Ferreira, D.R., Carvalho, P.J., Abhangi, M., Abreu, P., Aftanas, M., Afzal, M., Aggarwal, K.M., Aho-Mantila, L., Ahonen, E., Aints, M., Airila, M., Albanese, R., Alegre, D., Alessi, E., Aleynikov, P., Alfier, A., Alkseev, A., Allan, P., Almaviva, S., et al.. - In: FUSION ENGINEERING AND DESIGN. - ISSN 0920-3796. - 114:(2017), pp. 18-25. [10.1016/j.fusengdes.2016.11.006]
File in questo prodotto:
File Dimensione Formato  
Matos_2017_Deep learning for plasma tomography using the bolometer system at JET.pdf

solo utenti autorizzati

Tipologia: Versione Editoriale (PDF)
Licenza: Accesso privato/ristretto
Dimensione 661.89 kB
Formato Adobe PDF
661.89 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/886241
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 50
  • ???jsp.display-item.citation.isi??? 45
social impact