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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61389021%3A_____%2F19%3A00522747" target="_blank" >RIV/61389021:_____/19:00522747 - isvavai.cz</a>

Výsledek na webu

<a href="https://iopscience.iop.org/article/10.1088/1748-0221/14/09/C09011/pdf" target="_blank" >https://iopscience.iop.org/article/10.1088/1748-0221/14/09/C09011/pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1748-0221/14/09/C09011" target="_blank" >10.1088/1748-0221/14/09/C09011</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10305 - Fluids and plasma physics (including surface physics)

Projekt

<a href="/cs/project/LM2015045" target="_blank" >LM2015045: COMPASS – Tokamak pro výzkum termonukleární fúze</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Instrumentation

ISSN

1748-0221

e-ISSN

—

Svazek periodika

14

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

8

Strana od-do

C09011

Kód UT WoS článku

000486989800011

EID výsledku v databázi Scopus

2-s2.0-85074284403