Document Type


Publication Date



Neural networks require a large quantity of training spectra and detector responses in order to learn to solve the inverse problem of neutron spectrum unfolding. In addition, due to the under-determined nature of unfolding, non-physical spectra which would not be encountered in usage should not be included in the training set. While physically realistic training spectra are commonly determined experimentally or generated through Monte Carlo simulation, this can become prohibitively expensive when considering the quantity of spectra needed to effectively train an unfolding network. In this paper, we present three algorithms for the generation of large quantities of realistic and physically motivated neutron energy spectra. Using an IAEA compendium of 251 spectra, we compare the unfolding performance of neural networks trained on spectra from these algorithms, when unfolding real-world spectra, to two baselines. We also investigate general methods for evaluating the performance of and optimizing feature engineering algorithms.


© 2023 by the authors. Licensee MDPI, Basel, Switzerland.

This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Please fully attribute the citation below, including DOI in any re-use.

Funding note: This material is based upon work supported in part by the Department of Energy National Nuclear Security Administration through the Nuclear Science and Security Consortium under Award Numbers DE-NA0003180 and DE-NA0003996. This material has been approved for release by LLNL under document number LLNL-JRNL-842794.

Source Publication

Journal of Nuclear Engineering