Bayesian approach to heterogeneous data fusion of imperfect fission yields for augmented evaluations

We demonstrate that Bayesian machine learning can be used to treat the vast amount of experimental fission data which are noisy, incomplete, discrepant, and correlated. As an example, two-dimensional cumulative yields (CFY) neutron-induced $^{238}$U evaluated with energy dependencies uncertainty qualifications. For independent (IFY) very few data, heterogeneous fusion CFY IFY is employed interpolate dependence. This work shows facilitate further utilization imperfect raw nuclear data.