Bridging Theory and Data: Correcting Nuclear Mass Models with Interpretable Machine Learning

TL;DR

This paper introduces the Kolmogorov-Arnold Network (KAN) to improve nuclear mass predictions, significantly reducing errors and providing interpretability to identify key physical factors affecting model residuals.

Contribution

It presents a novel hybrid model combining KAN with existing nuclear mass models, enhancing accuracy and interpretability in small-sample, high-complexity nuclear physics problems.

Findings

Prediction error reduced from 0.3 MeV to 0.16 MeV

Proton number identified as most influential factor

Model generalizes across five different mass models

Abstract

Nuclear mass prediction is one of the core issues in nuclear physics research, yet it faces the challenge of small-sample datasets with high complexity. This study introduces the Kolmogorov-Arnold Network (KAN) into the refinement of nuclear mass models, proposing an efficient and interpretable solution. By constructing the KAN-WS4 hybrid model, the prediction accuracy is significantly improved (the root mean square error is reduced from 0.3 MeV to 0.16 MeV). Furthermore, leveraging the intrinsic interpretability of KAN, feature importance analysis reveals that the proton number is the most critical factor influencing residuals, indicating potential systematic biases in proton-related terms within existing theoretical models. The method's generality is demonstrated across five mass models. This study shows that KAN provides a novel approach to small-sample, high-complexity scientific problems. Its interpretability facilitates the data-driven discovery of physical laws, promising broad applicability to key nuclear physics issues.