AI for Fusion Energy Challenge Finale: Multi-Machine Disruption Prediction

Go back to programme

AI for Fusion Energy Challenge Finale: Multi-Machine Disruption Prediction

  • Watch

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    • Watch

      Register

      * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    ITU together with the International Atomic Energy Agency (IAEA) and its partners – Huazhong University of Science and Technology (HUST), MIT Plasma Science and Fusion Centre (PSFC), and Southwestern Institute of Physics (SWIP) – within the IAEA Coordinated Research Project on AI for Fusion launched a challenge which aimed to explore the potential of machine learning in contributing to multi-machine disruption prediction. Participants accessed data from three distinct fusion devices called “tokamaks” (Alcator C-Mod, J-TEXT, and HL-2A) to develop a cross-machine disruption prediction model using ML, with strong generalization capabilities.  

    By participating in this challenge, participants acquired hands-on experience in AI/ML in areas relevant to fusion energy science as well as competing for prizes, recognition, and certificates. This webinar will cover presentation from best teams of this competition and winners will be announced at the end of the session to recognize their outstanding performance.

    Multi-Machine Disruption Prediction Prizes;

    1. isaacOluwafemiOg – Winner (1st place) Prize: 2500 USD – Isaac Oluwafemi Ogunniyi
    2. newbee – Runner-up (2nd place) Prize: 1500 USD – Ning Jia
    3. ludian – Third place (3rd place) Prize: 1000 USD – Dian Lu

    Acknowledgement: This challenge has been carried out with the support and coordination of the ITU, IAEA, HUST, MIT PSFC and SWIP.The realization of this data challenge was made possible thanks to the work of Dr Chengshuo Shen (HUST), Dr Jinxiang Zhu (PSFC), Dr Zheng Wei (HUST), Dr Zhongyu Yang (SWIP), Dr Cristina Rea (PSFC), Diakhere Gueye, Dr Matteo Barbarino (IAEA), and Thomas Basikolo (ITU). 

    More information can be found on: 

    https://aiforgood.itu.int/about-ai-for-good/ai-for-fusion-energy-challenge/ 

    https://zindi.africa/competitions/multi-machine-disruption-prediction-challenge  

    Share this session
    • Watch

      Register

      * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    • Start date
      12 December 2023 at 15:30 CET Geneva | 09:30-10:30 EST, New York | 22:30-23:30 CST, Beijing
    • End date
      12 December 2023 at 16:30 CET Geneva | 09:30-10:30 EST, New York | 22:30-23:30 CST, Beijing
    • Duration
      60 minutes
    • Programme stream
    • UN SDGs
    In partnership with