Further exploration of binding energy residuals using machine learning and the development of a composite ensemble model

Abstract

This paper describes the development of the Four Model Tree Ensemble (FMTE). The FMTE is a composite of machine learning models trained on experimental binding energies from the Atomic Mass Evaluation (AME) 2012. The FMTE predicts binding energy values for all nuclei with N > 7 and Z > 7 from AME 2020 with a standard deviation of 76 keV and a mean average deviation of 34 keV. The FMTE model was developed by combining three new models with one prior model. The new models presented here have been trained on binding energy residuals from mass models using four machine learning approaches. The models presented in this work leverage shape parameters along with other physical features. We have determined the preferred machine learning approach for binding energy residuals is the least-squares boosted ensemble of trees. This approach appears to have a superior ability to both interpolate and extrapolate binding energy residuals. A comparison with the masses of isotopes that were not measured previously and a discussion of extrapolations approaching the neutron drip line have been included.

Phys. Rev. C - Accepted 17 June, 2025

References in corpus (19)

• Surface diffuseness correction in global mass formula
• Nuclear masses learned from a probabilistic neural network
• Mass measurements of 99-101In challenge ab initio nuclear theory of the nuclide 100Sn
• Nuclear mass predictions using machine learning models
• Detailed illustration of accuracy of presently used nuclear-mass models
• First application of mass measurement with the Rare-RI Ring reveals the solar r-process abundance trend at A=122 and A=123
• $B\rho$-defined Isochronous Mass Spectrometry and Mass Measurements of ${}^{58}$Ni Fragments
• Summit of the N=40 Island of Inversion: precision mass measurements and ab initio calculations of neutron-rich chromium isotopes
• High-precision mass measurements of neutron deficient silver isotopes probe the robustness of the $N$ = 50 shell closure
• Precise neural network predictions of energies and radii from the no-core shell model
• Nuclear mass predictions based on convolutional neural network
• Investigating nuclear structure near $N=32$ and $N=34$: Precision mass measurements of neutron-rich Ca, Ti and V isotopes
• Precision mass measurements in the zirconium region pin down the mass surface across the neutron midshell at $N=66$
• High-precision mass measurement of ${}^{103}$Sn restores smoothness of the mass surface
• High-precision Penning-trap mass measurements of Cd and In isotopes at JYFLTRAP remove the fluctuations in the two-neutron separation energies
• High Precision Binding Energies from Physics Informed Machine Learning
• Probing the N=104 midshell region for the r process via precision mass spectrometry of neutron-rich rare-earth isotopes with the JYFLTRAP double Penning trap
• Precise Mass Measurements of $A=133$ Isobars with the Canadian Penning Trap: Resolving the $Q_{{\beta }^{-}}$ anomaly at ${}^{133}$Te
• Impact of nuclear mass models on $r$-process nucleosynthesis and heavy element abundances in $r$-process enhanced metal-poor stars