Physics Informed Bayesian Machine Learning of Sparse and Imperfect Nuclear Data

TL;DR

This paper introduces a physics-informed Bayesian machine learning approach to accurately evaluate fission product yields using sparse, imperfect nuclear data, integrating physical constraints and prior knowledge for improved predictions.

Contribution

The work develops a novel physics-model informed prior within Bayesian machine learning to better utilize limited nuclear data for fission yield evaluation.

Findings

Effective incorporation of physics knowledge improves data exploitation.

Enhanced predictions of fission yields with sparse data.

Demonstrated the approach's potential for nuclear data analysis.

Abstract

The prevailing data-driven machine learning has been plagued by the absence of physics knowledge and the scarcity of data. We implement the physics-model informed prior into Bayesian machine learning to evaluate the energy dependence of independent fission product yields, which are crucial for advanced nuclear energy applications but only sparse and imperfect experimental data are available. The informative prior is the posterior after learning the generated data from fission models. Furthermore, cumulative fission yields are included as a physical constraint via a conversion matrix to provide augmented energy dependence. Our work demonstrated a truly Bayesian machine learning by incorporating comprehensive physics knowledges as a powerful tool to exploit the sparse but expensive nuclear data.