arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02332nucl-th
收藏

利用图神经网络学习核素图上核反应截面的变化

Learning nuclear cross sections across the chart of nuclides with graph neural networks

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Arizona State University(亚利桑那州立大学)

Hongjun Choi, Sinjini Mitra, Jason Brodksy, Ruben Glatt, Erika Holmbeck, Shusen Liu, Nicolas Schunck, Andre Sieverding, Kyle Wendt

AI总结:

本研究提出两阶段深度学习框架,结合表示学习与图神经网络预测核素图上缺失的核反应截面,并在9x9缺失块中实现准确预测,同时发现中子幻数,为核理论模型提供协方差估计支持。

摘要:

在这项工作中,我们探索使用深度学习技术来学习当添加或移除质子和中子时核反应截面如何变化。作为原理验证,我们聚焦于快能区的中子诱发反应。我们的方法遵循一个两阶段学习框架。首先,我们应用表示学习将截面数据编码到潜在空间中,使用变分自编码器(VAEs)或隐式神经表示(INRs)。然后,我们在得到的嵌入上训练图神经网络(GNNs),通过利用相邻同位素的拓扑结构来预测核素图上的缺失值。我们展示了在9x9块缺失核素内的准确截面预测。我们还发现,最优的GNN训练策略取决于所使用的潜在表示类型,其中VAE嵌入在原始空间中的端到端优化下表现最佳,而INR嵌入在仅于潜在空间训练GNN时取得更好结果。此外,使用聚类算法,我们将潜在向量组映射到核素图的区域,并表明VAEs和INRs能够发现一些中子幻数。这些发现表明,基于截面表示编码的深度学习模型结合图神经网络在增强核理论模型方面具有显著潜力,例如通过提供截面协方差(包括跨材料协方差)的可靠估计。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑