Deep neural networks for plasma tomography with applications to JET and COMPASS

JET Contributors, Jan Mlynar, T. Ahlgren, L. Aho-Mantila, M. Airila, C. Björkas, A. Lahtinen, K. Nordlund, E. Safi, S. K. Sipila , O. Asunta, M. Groth, A. Hakola, J. Karhunen, S. Koivuranta, T. Kurki-Suonio, B. Lomanowski, J. Lonnroth, A. Salmi, M. I. K. Santala

Research output: Contribution to journalConference articleScientificpeer-review


Convolutional neural networks (CNNs) have found applications in many image processing tasks, such as feature extraction, image classification, and object recognition. It has also been shown that the inverse of CNNs, so-called deconvolutional neural networks, can be used for inverse problems such as plasma tomography. In essence, plasma tomography consists in reconstructing the 2D plasma profile on a poloidal cross-section of a fusion device, based on line-integrated measurements from multiple radiation detectors. Since the reconstruction process is computationally intensive, a deconvolutional neural network trained to produce the same results will yield a significant computational speedup, at the expense of a small error which can be assessed using different metrics. In this work, we discuss the design principles behind such networks, including the use of multiple layers, how they can be stacked, and how their dimensions can be tuned according to the number of detectors and the desired tomographic resolution for a given fusion device. We describe the application of such networks at JET and COMPASS, where at JET we use the bolometer system, and at COMPASS we use the soft X-ray diagnostic based on photodiode arrays.

Original languageEnglish
Article numberC09011
JournalJournal of Instrumentation
Number of pages7
Publication statusPublished - Sep 2019
MoE publication typeA4 Article in conference proceedings
EventEuropean Conference on Plasma Diagnostics (ECPD): ECPD2019 - Lisbon, Portugal
Duration: 6 May 201910 May 2019
Conference number: 3

Fields of Science

  • 114 Physical sciences

Cite this