Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach
We present global predictions of the ground state mass of atomic nuclei based on a novel Machine Learning algorithm. We combine precision nuclear experimental measurements together with theoretical predictions of unmeasured nuclei. This hybrid data set is used to train a probabilistic neural network...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1198572/full |
| _version_ | 1797777461140783104 |
|---|---|
| author | Matthew Mumpower Mengke Li Mengke Li Trevor M. Sprouse Bradley S. Meyer Amy E. Lovell Arvind T. Mohan |
| author_facet | Matthew Mumpower Mengke Li Mengke Li Trevor M. Sprouse Bradley S. Meyer Amy E. Lovell Arvind T. Mohan |
| author_sort | Matthew Mumpower |
| collection | DOAJ |
| description | We present global predictions of the ground state mass of atomic nuclei based on a novel Machine Learning algorithm. We combine precision nuclear experimental measurements together with theoretical predictions of unmeasured nuclei. This hybrid data set is used to train a probabilistic neural network. In addition to training on this data, a physics-based loss function is employed to help refine the solutions. The resultant Bayesian averaged predictions have excellent performance compared to the testing set and come with well-quantified uncertainties which are critical for contemporary scientific applications. We assess extrapolations of the model’s predictions and estimate the growth of uncertainties in the region far from measurements. |
| first_indexed | 2024-03-12T23:04:16Z |
| format | Article |
| id | doaj.art-fc20d87549574d008a07b0609d00e9e2 |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-03-12T23:04:16Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-fc20d87549574d008a07b0609d00e9e22023-07-19T07:35:34ZengFrontiers Media S.A.Frontiers in Physics2296-424X2023-07-011110.3389/fphy.2023.11985721198572Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approachMatthew Mumpower0Mengke Li1Mengke Li2Trevor M. Sprouse3Bradley S. Meyer4Amy E. Lovell5Arvind T. Mohan6Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, United StatesTheoretical Division, Los Alamos National Laboratory, Los Alamos, NM, United StatesDepartment of Physics and Astronomy, Clemson University, Clemson, SC, United StatesTheoretical Division, Los Alamos National Laboratory, Los Alamos, NM, United StatesDepartment of Physics and Astronomy, Clemson University, Clemson, SC, United StatesTheoretical Division, Los Alamos National Laboratory, Los Alamos, NM, United StatesComputational Division, Los Alamos National Laboratory, Los Alamos, NM, United StatesWe present global predictions of the ground state mass of atomic nuclei based on a novel Machine Learning algorithm. We combine precision nuclear experimental measurements together with theoretical predictions of unmeasured nuclei. This hybrid data set is used to train a probabilistic neural network. In addition to training on this data, a physics-based loss function is employed to help refine the solutions. The resultant Bayesian averaged predictions have excellent performance compared to the testing set and come with well-quantified uncertainties which are critical for contemporary scientific applications. We assess extrapolations of the model’s predictions and estimate the growth of uncertainties in the region far from measurements.https://www.frontiersin.org/articles/10.3389/fphy.2023.1198572/fullatomic nucleiBayesian averagingbinding energies and massesMachine Learning-MLnuclear physicscomputational physics |
| spellingShingle | Matthew Mumpower Mengke Li Mengke Li Trevor M. Sprouse Bradley S. Meyer Amy E. Lovell Arvind T. Mohan Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach Frontiers in Physics atomic nuclei Bayesian averaging binding energies and masses Machine Learning-ML nuclear physics computational physics |
| title | Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach |
| title_full | Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach |
| title_fullStr | Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach |
| title_full_unstemmed | Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach |
| title_short | Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach |
| title_sort | bayesian averaging for ground state masses of atomic nuclei in a machine learning approach |
| topic | atomic nuclei Bayesian averaging binding energies and masses Machine Learning-ML nuclear physics computational physics |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2023.1198572/full |
| work_keys_str_mv | AT matthewmumpower bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT mengkeli bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT mengkeli bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT trevormsprouse bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT bradleysmeyer bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT amyelovell bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach AT arvindtmohan bayesianaveragingforgroundstatemassesofatomicnucleiinamachinelearningapproach |