Modeling of fine structures in the mass distribution of nuclear reaction products and their recognition by machine learning methods

Abstract

The article is devoted to the analysis of manifestations in rare multibody decays of heavy nuclei. Together with physicists from the FLNR JINR, a computer model of the fine structure was developed, which they found on the basis of experiments on with transuranium element Californium. To test the hypothesis that the structure found is a meaningful, and is not a noise artifact, it was proposed to use a deep convolution network as a binary classifier trained on a large sample of model and noise images. Preliminary results of using the developed neuroclassifier show prospects of the proposed approach.