ANS is committed to advancing, fostering, and promoting the development and application of nuclear sciences and technologies to benefit society.
Explore the many uses for nuclear science and its impact on energy, the environment, healthcare, food, and more.
Explore membership for yourself or for your organization.
Conference Spotlight
2026 Nuclear Energy Conference & Expo (NECX)
August 24–27, 2026
Dallas, TX|Hilton Anatole
Latest Magazine Issues
Jul 2026
Jan 2026
2026
Latest Journal Issues
Nuclear Science and Engineering
September 2026
Nuclear Technology
August 2026
Fusion Science and Technology
Latest News
In transition: Commercializing fusion power
Commercial fusion power is closer than ever. There are now around 30 U.S. fusion companies, several of which claim to be on track to connect to the grid as early as the 2030s.
Tokamak and laser inertial confinement approaches benefit from decades of research at facilities such as the National Ignition Facility (NIF) at Lawrence Livermore National Laboratory and ITER, with alternative concepts including stellarator, magnetic mirror, and Z-pinch confinement also making notable progress as private and government funding for fusion increases.
R. Moreno, J. Vega, S. Dormido-Canto, A. Pereira, A. Murari, JET Contributors
Fusion Science and Technology | Volume 69 | Number 2 | April 2016 | Pages 485-494
Technical Paper | doi.org/10.13182/FST15-167
Articles are hosted by Taylor and Francis Online.
The Advanced Predictor of Disruptions (APODIS) has been working in the JET real-time network since the beginning of the ITER-like wall (ILW) campaigns. APODIS is a data-driven system based on a multilayer structure of Support Vector Machines (SVM) classifiers. APODIS was trained with JET data corresponding to carbon wall discharges between April 2006 and October 2009, without any retraining in spite of its use with metallic wall discharges. This paper has two main parts. First, APODIS disruption prediction capabilities are evaluated during the ILW run period from July 2013 to October 2014. The results obtained from these experimental campaigns (more than 1059 nondisruptive discharges and 390 nonintentional disruptions) showed 2.46% false alarms and 85.38% success rate. Taking into account that ITER (International Thermonuclear Experimental Reactor) will work with a similar wall to the current ILW at JET, the purpose of the second part of this study is to compare predictors trained with data from JET ILW campaigns. The high computational cost that APODIS training requires and the great performance of SVM have motivated the development of a one-layer SVM predictor. Therefore, an APODIS version and a simpler one-layer predictor have been compared. They have been trained with data between September 2011 and July 2012 (1036 nondisruptive discharges and 201 nonintentional disruptions) and tested with experimental data in the period July 2013 to October 2014 (1051 nondisruptive discharges and 390 nonintentional disruptions). The one-layer predictor shows slightly better results than the APODIS structure.
