From $\alpha$ decay to cluster decay: an extreme case of transfer learning

TL;DR

This paper demonstrates how transfer learning with deep neural networks improves the prediction of nuclear decay half-lives, especially in data-sparse scenarios, by leveraging physically informed pretraining and systematic regularization.

Contribution

It introduces a transfer learning approach that pretrains neural networks on alpha decay data to enhance cluster decay predictions with limited data.

Findings

Transfer learning stabilizes optimization in small data regimes.

Pretraining on alpha decay improves cluster decay prediction accuracy.

Models achieve reliable predictions across a range of parent nuclei.

Abstract

When training data are limited, data-driven models are especially vulnerable to optimization-related fluctuations from random initialization and to sampling-induced bias from insufficient training data. We address both challenges with transfer learning (TL): deep neural networks (DNNs) are first pretrained on $\alpha$ decay half-lives and then fine-tuned on a small cluster decay dataset. The pretraining stage provides a physically informed initialization that stabilizes optimization, while transferred global decay systematics regularize the fit and reduce sensitivity to training set composition. Despite extreme data sparsity, the resulting models accurately predict cluster decay half-lives for parent nuclei from $^{221}$Fr to $^{242}$Cm. We further quantify how initialization and sample selection affect predictive accuracy and robustness, demonstrating that TL enables stable and reliable learning in the small-sample regime.