Learning nuclear cross sections across the chart of nuclides with graph neural networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915580192227328 |
|---|---|
| author | Choi, Hongjun Mitra, Sinjini Brodksy, Jason Glatt, Ruben Holmbeck, Erika Liu, Shusen Schunck, Nicolas Sieverding, Andre Wendt, Kyle |
| author_facet | Choi, Hongjun Mitra, Sinjini Brodksy, Jason Glatt, Ruben Holmbeck, Erika Liu, Shusen Schunck, Nicolas Sieverding, Andre Wendt, Kyle |
| contents | In this work, we explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime. Our approach follows a two-stage learning framework. First, we apply representation learning to encode cross section data into a latent space using either variational autoencoders (VAEs) or implicit neural representations (INRs). Then, we train graph neural networks (GNNs) on the resulting embeddings to predict missing values across the nuclear chart by leveraging the topological structure of neighboring isotopes. We demonstrate accurate cross section predictions within a 9x9 block of missing nuclei. We also find that the optimal GNN training strategy depends on the type of latent representation used, with VAE embeddings performing best under end-to-end optimization in the original space, while INR embeddings achieve better results when the GNN is trained only in the latent space. Furthermore, using clustering algorithms, we map groups of latent vectors into regions of the nuclear chart and show that VAEs and INRs can discover some of the neutron magic numbers. These findings suggest that deep-learning models based on the representation encoding of cross sections combined with graph neural networks holds significant potential in augmenting nuclear theory models, e.g., by providing reliable estimates of covariances of cross sections, including cross-material covariances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning nuclear cross sections across the chart of nuclides with graph neural networks Choi, Hongjun Mitra, Sinjini Brodksy, Jason Glatt, Ruben Holmbeck, Erika Liu, Shusen Schunck, Nicolas Sieverding, Andre Wendt, Kyle Nuclear Theory In this work, we explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime. Our approach follows a two-stage learning framework. First, we apply representation learning to encode cross section data into a latent space using either variational autoencoders (VAEs) or implicit neural representations (INRs). Then, we train graph neural networks (GNNs) on the resulting embeddings to predict missing values across the nuclear chart by leveraging the topological structure of neighboring isotopes. We demonstrate accurate cross section predictions within a 9x9 block of missing nuclei. We also find that the optimal GNN training strategy depends on the type of latent representation used, with VAE embeddings performing best under end-to-end optimization in the original space, while INR embeddings achieve better results when the GNN is trained only in the latent space. Furthermore, using clustering algorithms, we map groups of latent vectors into regions of the nuclear chart and show that VAEs and INRs can discover some of the neutron magic numbers. These findings suggest that deep-learning models based on the representation encoding of cross sections combined with graph neural networks holds significant potential in augmenting nuclear theory models, e.g., by providing reliable estimates of covariances of cross sections, including cross-material covariances. |
| title | Learning nuclear cross sections across the chart of nuclides with graph neural networks |
| topic | Nuclear Theory |
| url | https://arxiv.org/abs/2404.02332 |