Bayesian Evaluation of Energy Dependent Neutron Induced Fission Yields

From both the fundamental and applied perspectives, fragment mass distributions are important observables of fission. We apply the Bayesian neural network (BNN) approach to learn the existing neutron induced fission yields and predict unknowns with uncertainty quantification. Comparing the predicted results with experimental data, the BNN evaluation results are found to be satisfactory for the distribution positions and energy dependencies of fission yields. Predictions are made for the fragment mass distributions of several actinides, which may be useful for future experiments.