[2F10-13] Fission Nuclear Data

3:00 PM - 3:15 PM JST(6:00 AM - 6:15 AM UTC)

[2F11] Development of Fission Nuclear Data Using Machine Learning(2) Fission Product Yield Prediction and Evaluation Using Machine Learning

*JINGDE CHEN¹, Yuta Mukobara¹, Satoshi Chiba², Naoki Yamano¹, Tatsuya Katabuchi¹, chikako isizuka¹ (1. Tokyo Institute of Technology, 2. NAT)

Keywords:

Fission Products Yield,Physics-Informed Bayesian Neural Network,Information Criterion,Watanabe-Akaike Information Criterion

Recently, it has been discovered that linear interpolation of evaluated the energy dependence of fission product yields is not appropriate for important fission products from fission reactions. Therefore, this study aims to construct a machine learning model using Bayesian Neural Networks (BNN) to accurately predict fission yields for energies and fission products where experimental data do not exist. In this presentation, we will report on the results of verifying the validity of incorporating theoretical calculations and insights from nuclear physics into the machine learning model, using cross-validation and widely applicable information criteria (WAIC), in addition to evaluated and experimental values.