Physical Review Letters · 2019 · 109 citations · 28 references
ComputingComputer ScienceNuclear EngineeringMachine LearningNuclear PhysicsUncertainty QuantificationBayesian InferenceBayesian LearningBayesian ModelingBayesian StatisticsNeural NetworksProbabilistic Machine LearningBayesian EstimationBayesian NetworksBayesian Neural NetworksFission Product AnalysisFission Product YieldsInterpreting Experimental DataNuclear Fission ModelsPosterior Uncertainty Quantification
Fission product yields are key infrastructure data for nuclear applications in many aspects. It is a challenge both experimentally and theoretically to obtain accurate and complete energy-dependent fission yields. We apply the Bayesian neural network (BNN) approach to learn existing fission yields and predict unknowns with uncertainty quantification. We demonstrated that the BNN is particularly useful for evaluations of fission yields when incomplete experimental data are available. The BNN evaluation results are quite satisfactory on distribution positions and energy dependencies of fission yields.
28
Modern Nuclear Data Evaluation with the TALYS Code System
A. J. Koning, D. Rochman · Nuclear Data Sheets · 2012 · 1.2K citations
Improved predictions of reactor antineutrino spectra
Th. A. Mueller, D. Lhuillier, M. Fallot et al. · Physical Review C · 2011 · 1K citations · Full text
U. Brösa, Andreas Müller · Physics Reports · 1990 · 585 citations