0538109 20240103225215.320210120235959.9 85095722107 000586815000001 10.1080/15361055.2020.1820805 10 s. cav_un_epca*02578671536-1055768 (2020)962-971Taylor & Francis Alfvén eigenmodes generative models neural networks Tokamak cav_un_auth*0398466 Škvára Vít UFP-V Tokamak Tokamak TOK TOK CZ Ústav fyziky plazmatu AV ČR, v. v. i. cav_un_auth*0101207 Šmídl Václav UTIA-B Adaptivní systémy Department of Adaptive Systems AS AS Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0307300 Pevný T. CZ Ceské vysoké ucení technické v Praze cav_un_auth*0257948 Seidl Jakub UFP-V Tokamak Tokamak TOK TOK CZ Ústav fyziky plazmatu AV ČR, v. v. i. cav_un_auth*0325242 Havránek Aleš UFP-V Tokamak Tokamak TOK TOK CZ Ústav fyziky plazmatu AV ČR, v. v. i. cav_un_auth*0395810 Tskhakaya David UFP-V Tokamak Tokamak TOK TOK AT Ústav fyziky plazmatu AV ČR, v. v. i. https://www.tandfonline.com/doi/pdf/10.1080/15361055.2020.1820805?needAccess=true& GA18-21409S GA ČR cav_un_auth*0374053 EF16_019/0000768 GA MŠk CZ cav_un_auth*0372154 633053 EC XE cav_un_auth*0318270 Chirping Alfvén eigenmodes were observed at the COMPASS tokamak. They are believed to be driven by runaway electrons (REs), and as such, they provide a unique opportunity to study the physics of nonlinear interaction between REs and electromagnetic instabilities, including important topics of RE mitigation and losses. On COMPASS, they can be detected from spectrograms of certain magnetic probes. So far, their detection has required much manual effort since they occur rarely. We strive to automate this process using machine learning techniques based on generative neural networks. We present two different models that are trained using a smaller, manually labeled database and a larger unlabeled database from COMPASS experiments. In a number of experiments, we demonstrate that our approach is a viable option for automated detection of rare instabilities in tokamak plasma. WOS BC 10000 10200 10201 2021 6 UTIA-B 10000 10100 10102 UTIA-B BC RVO:61389021 RVO:67985556 http://hdl.handle.net/11104/0315921 cav_un_auth*0369599 Ceské vysoké ucení technické v Praze 1 Article Nuclear Science Technology A NUCLEARSCIENCE&TECHNOLOGY 1.051 0.185 8.7 0.00286 0.364 2100 61 0.749 18.86 1.17 519 Q1 0.963 124 Q4 29.374 22.1 Q3 Q3 0.7 Q2 22.059 2020 Fusion Science and Technology 15361055 19437641 2020-01-01 76 8 85095722107 SCOPUS 000586815000001 WOS cav_un_epca*0257867 Fusion Science and Technology 1536-1055 1943-7641 Roč. 76 č. 8 2020 962 971 Taylor & Francis