Quantifying Uncertainties on Fission Fragment Mass Yields With Mixture Density Networks

Abstract

Probabilistic machine learning techniques can learn both complex relations between input features and output quantities of interest as well as take into account stochasticity or uncertainty within a data set. In this initial work, we explore the use of one such probabilistic network, the Mixture Density Network (MDN), to reproduce fission yields and their uncertainties. We study mass yields for the spontaneous fission of ${}^{252}$Cf, exploring the number of training samples needed for converged predictions, how different levels of uncertainty propagate from the training set to the MDN predictions, and how well physical constraints of the yields - such as normalization and symmetry - are upheld by the algorithm. Finally, we test the ability of the MDN to interpolate between and extrapolate beyond samples in the training set using energy-dependent mass yields for the neutron-induced fission on ${}^{235}$U. The MDN provides a reliable way to include and predict uncertainties and is a promising path forward for supplementing sparse sets of nuclear data.

arXiv comment20 pages, 8 figures, submitted to J. Phys. G

References in corpus (12)

• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Bayesian approach to model-based extrapolation of nuclear observables
• Photometric redshift estimation via deep learning
• Neutron drip line in the Ca region from Bayesian model averaging
• Determining Fundamental Properties of Matter Created in Ultrarelativistic Heavy-Ion Collisions
• Fission fragment charge and mass distributions in 239Pu(n,f) in the adiabatic nuclear energy density functional theory
• Bayesian Evaluation of Incomplete Fission Yields
• Description of Induced Nuclear Fission with Skyrme Energy Functionals: I. Static Potential Energy Surfaces and Fission Fragment Properties
• Correlated Prompt Fission Data in Transport Simulations
• A Time Projection Chamber for High Accuracy and Precision Fission Cross Section Measurements
• A Method to Calculate Fission-Fragment Yields $Y(Z,N)$ versus Proton and Neutron Number in the Brownian Shape-Motion Model. Application to calculations of U and Pu charge yields
• Number of Particles in Fission Fragments

Cited by in corpus (12)

• Machine Learning in Nuclear Physics
• Nuclear masses learned from a probabilistic neural network
• Multi-task learning on nuclear masses and separation energies with the kernel ridge regression
• Physically Interpretable Machine Learning for nuclear masses
• Toward emulating nuclear reactions using eigenvector continuation
• Bayesian evaluation of charge yields of fission fragments of 239U
• Horizons: Nuclear Astrophysics in the 2020s and Beyond
• Recent advances in the quantification of uncertainties in reaction theory
• Optimizing multilayer Bayesian neural networks for evaluation of fission yields
• Bayesian Data Fusion of Imperfect Fission Yields for Augmented Evaluations
• Building Surrogate Models of Nuclear Density Functional Theory with Gaussian Processesand Autoencoders
• Shell quenching in nuclear charge radii based on Monte Carlo dropout Bayesian neural network