Prediction of Turbulence Temporal Evolution in PANTA by Long-Short Term Memory Network
-
- AIZAWACARANZA Masaomi
- College of Industrial Technology, Nihon University
-
- SASAKI Makoto
- College of Industrial Technology, Nihon University
-
- MINAGAWA Hiroki
- College of Industrial Technology, Nihon University
-
- NAKAZAWA Yuuki
- College of Industrial Technology, Nihon University
-
- LIU Yoshitatsu
- College of Industrial Technology, Nihon University
-
- JAJIMA Yuki
- College of Industrial Technology, Nihon University
-
- KAWACHI Yuichi
- Interdisciplinary Graduate School of Engineering Sciences, Kyushu University
-
- ARAKAWA Hiroyuki
- Institute of Science and Engineering, Academic Assembly, Shimane University
-
- HARA Kazuyuki
- College of Industrial Technology, Nihon University
Description
<p>Prediction of time evolution of multi-scale turbulence is performed by using Long-short term memory networks. The time series data is obtained by Langmuir probes in a linear magnetized plasma device, PANTA. The simultaneous prediction of high and low frequency components of turbulence is shown to be possible within several tens percent accuracy. The prediction accuracy depends on the initial network, which can be controlled by reducing the learning rate.</p>
Journal
-
- Plasma and Fusion Research
-
Plasma and Fusion Research 17 (0), 1201048-1201048, 2022-05-13
The Japan Society of Plasma Science and Nuclear Fusion Research
- Tweet
Details 詳細情報について
-
- CRID
- 1390573870495235328
-
- ISSN
- 18806821
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- KAKEN
- OpenAIRE
-
- Abstract License Flag
- Disallowed
