Physically Interpretable Machine Learning for nuclear masses

Abstract

We present a novel approach to modeling the ground state mass of atomic nuclei based directly on a probabilistic neural network constrained by relevant physics. Our Physically Interpretable Machine Learning (PIML) approach incorporates knowledge of physics by using a physically motivated feature space in addition to a soft physics constraint that is implemented as a penalty to the loss function. We train our PIML model on a random set of $\sim$20\% of the Atomic Mass Evaluation (AME) and predict the remaining $\sim$80\%. The success of our methodology is exhibited by the unprecedented ${\sigma }_{\text{RMS}}\sim 186$ keV match to data for the training set and ${\sigma }_{\text{RMS}}\sim 316$ keV for the entire AME with $Z\ge 20$. We show that our general methodology can be interpreted using feature importance.

arXiv comment5 pages, 3 figures, comments welcome

References in corpus (25)

• Adam: A Method for Stochastic Optimization
• Nuclear ground-state masses and deformations: FRDM(2012)
• The impact of individual nuclear properties on $r$-process nucleosynthesis
• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Bayesian approach to model-based extrapolation of nuclear observables
• Quantifying Correlated Truncation Errors in Effective Field Theory
• Neutron drip line in the Ca region from Bayesian model averaging
• Quantified limits of the nuclear landscape
• Modeling Kilonova Light Curves: Dependence on Nuclear Inputs
• Statistical Hauser-Feshbach theory with width fluctuation correction including direct reaction channels for neutron induced reaction at low energies
• Generation of fragment angular momentum in fission
• Deep Crustal Heating in a Multicomponent Accreted Neutron Star Crust
• Deep learning: Extrapolation tool for ab initio nuclear theory
• Nuclear masses learned from a probabilistic neural network
• Extrapolation of nuclear structure observables with artificial neural networks
• Propagation of Statistical Uncertainties of Skyrme Mass Models to Simulations of $r$-Process Nucleosynthesis
• Quantifying Uncertainties on Fission Fragment Mass Yields With Mixture Density Networks
• Machine learning-based inversion of nuclear responses
• How good are the Garvey-Kelson predictions of nuclear masses?
• Extrapolating from neural network models: a cautionary tale
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• Neutrino Pair Emission from Hot Nuclei During Stellar Collapse
• Machine-learning approach to finite-size effects in systems with strongly interacting fermions
• Calibration of Energy Density Functionals with Deformed Nuclei

Cited by in corpus (12)

• Nuclear mass predictions using machine learning models
• Nuclear mass predictions based on convolutional neural network
• Kolmogorov-Arnold networks in nuclear binding energy prediction
• Building Surrogate Models of Nuclear Density Functional Theory with Gaussian Processesand Autoencoders
• Discovering Nuclear Models from Symbolic Machine Learning
• Quantifying uncertainty in machine learning on nuclear binding energy
• Investigating the effects of precise mass measurements of Ru and Pd isotopes on machine learning mass modeling
• Bayesian model mixing with multi-reference energy density functional
• Nuclear data activities for medium mass and heavy nuclei at Los Alamos
• Implication of odd-even staggering in the charge radii of calcium isotopes
• A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC
• Product units in gated recurrent units improve nuclear-mass prediction