A novel Machine-Learning method for spin classification of neutron resonances

TL;DR

This paper introduces a machine learning approach to automatically classify neutron resonance quantum numbers using resonance energies and widths, improving the efficiency and accuracy of nuclear data analysis.

Contribution

The study develops a novel machine learning classifier trained on simulated data to assign quantum numbers to neutron resonances without relying on detailed transmission measurements.

Findings

Effective classification on simulated data

Successful application to real $^{52}$Cr resonance data

Handles cases with unreliable capture widths

Abstract

The performance of nuclear reactors and other nuclear systems depends on a precise understanding of the neutron interaction cross sections for materials used in these systems. These cross sections exhibit resonant structure whose shape is determined in part by the angular momentum quantum numbers of the resonances. The correct assignment of the quantum numbers of neutron resonances is, therefore, paramount. In this project, we apply machine learning to automate the quantum number assignments using only the resonances' energies and widths and not relying on detailed transmission or capture measurements. The classifier used for quantum number assignment is trained using stochastically generated resonance sequences whose distributions mimic those of real data. We explore the use of several physics-motivated features for training our classifier. These features amount to out-of-distribution tests of a given resonance's widths and resonance-pair spacings. We pay special attention to situations where either capture widths cannot be trusted for classification purposes or where there is insufficient information to classify resonances by the total spin $J$. We demonstrate the efficacy of our classification approach using simulated and actual $^{52}$Cr resonance data.