[RIBF ULIC MiniWS037] [Rearranged schedule] Combining Nuclear Theory and Machine Learning for fundamental studies and applications

Asia/Tokyo
RIBF 2F Room 203 for 29th Nov and Room 201 for 30th (RIKEN Wako Campus)

RIBF 2F Room 203 for 29th Nov and Room 201 for 30th

RIKEN Wako Campus

Sota Yoshida (Utunomiya University)
Description

In recent years, remarkable progress has been made in combining machine learning with nuclear models. Some of these studies have a significant impact on physics at RIBF: The density functional theory and machine learning have been combined to predict the mass and lifetime of r-process elements, and the nuclear optical model and machine learning are combined to predict neutron-nucleus scattering. Thus, the combination of machine learning and nuclear modeling has great potential.
This mini-workshop will bring together the researchers to discuss how ML can predict physical quantities (mass, lifetime, and/or (n,γ) cross-section) related to the r-process more accurately and what experiments should be proposed to improve the prediction accuracy. We will also explore new opportunities for collaboration.

Registration
Registration
Contact (Masaaki Kimura)
  • Tuesday, November 29
    • 1
      opening
      Speaker: Masaaki Kimura (RIKEN Nishina Center)
    • 2
      Shell model + ML (temporary)
      Speaker: Noritaka Shimizu (Center for Nuclear Study, University of Tokyo)
    • 3
      Uncertainty evaluation of GDR peak energy and new parameter set
      Speaker: Tsunenori Inakura (Tokyo Tech)
    • 4
      Nuclear mass predictions with machine learning reaching the accuracy required by r-process studies
      Speaker: Dr Haozhao Liang (The University of Tokyo)
    • Discussion & Buffer
  • Wednesday, November 30
    • 5
      Assessing transfer entropy from biochemical data
      Speaker: Prof. Yoshiyuki Kabashima
    • 6
      Machine learning assisted density functional theory for electronic systems
      Speaker: Ryosuke Akashi
    • 7
      Uncertainty evaluation of neutron cross section using T6
      Speaker: Tsunenori Inakura (Tokyo Tech)
    • 8
      ML for Fission products
      Speaker: Futoshi Minato (Japan Atomic Energy Agency)
    • 9
      Learning from what we had disposed and an accelerator to “Machine Learning + nuclear physics”
      Speaker: Sota Yoshida (The university of Tokyo)
    • Discussion & Buffer