Nuclear mass systematics by complementing the Finite Range Droplet Model with neural networks

Athanassopoulos, S.; Mavrommatis, E.; Gernoth, K. A.; Clark, John W.

doi:10.12681/hnps.2250

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, as we have done elsewhere [14][15][16], we limit ourselves to highlight the main features of the approach. Before we do so, however, we note that the idea of using artificial neural networks in nuclear physics-mainly to estimate unknown properties of exotic nuclei of relevance to astrophysics-started in the early 90s with the work of Clark and collaborators [37][38][39][40] and continues up to this day [41][42][43][44][45] with more sophisticated applications.…”

Section: Formalism a Bayesian Neural Networkmentioning

confidence: 99%

Refining mass formulas for astrophysical applications: A Bayesian neural network approach

Utama

Piekarewicz

2017

Phys. Rev. C

View full text Add to dashboard Cite

Background: Exotic nuclei, particularly those near the driplines, are at the core of one of the fundamental questions driving nuclear structure and astrophysics today: what are the limits of nuclear binding? Exotic nuclei play a critical role in both informing theoretical models as well as in our understanding of the origin of the heavy elements.Purpose: To refine existing mass models through the training of an artificial neural network that will mitigate the large model discrepancies far away from stability. Methods:The basic paradigm of our two-pronged approach is an existing mass model that captures as much as possible of the underlying physics followed by the implementation of a Bayesian Neural Network (BNN) refinement to account for the missing physics. Bayesian inference is employed to determine the parameters of the neural network so that model predictions may be accompanied by theoretical uncertainties.Results: Despite the undeniable quality of the mass models adopted in this work, we observe a significant improvement (of about 40%) after the BNN refinement is implemented. Indeed, in the specific case of the Duflo-Zuker mass formula, we find that the rms deviation relative to experiment is reduced from σrms = 0.503 MeV to σrms = 0.286 MeV. These newly refined mass tables are used to map the neutron drip lines (or rather "dripbands") and to study a few critical r-process nuclei. Conclusions:The BNN approach is highly successful in refining the predictions of existing mass models. In particular, the large discrepancy displayed by the original "bare" models in regions where experimental data is unavailable is considerably quenched after the BNN refinement. This lends credence to our approach and has motivated us to publish refined mass tables that we trust will be helpful for future astrophysical applications.

show abstract

Section: Formalism a Bayesian Neural Networkmentioning

confidence: 99%

Refining mass formulas for astrophysical applications: A Bayesian neural network approach

Utama

Piekarewicz

2017

Phys. Rev. C

View full text Add to dashboard Cite

show abstract

“…The use ANNs in nuclear physics is mainly to estimate unknown properties of revelant exotic nuclei to astrophysics and began in the early 90s with the work of Clark and collaborators [33][34][35][36]. It continues to this day [37][38][39][40][41] with more sophisticated applications.…”

Section: A Bnn Modelmentioning

confidence: 99%

Uncertainties of nuclear level density estimated using Bayesian neural networks*

Wang 王,

Cui 崔,

Tian 田

et al. 2024

Chinese Phys. C

View full text Add to dashboard Cite

Nuclear level density (NLD) is a critical parameter for understanding nuclear reactions and the structure of atomic nuclei, yet accurate estimation of NLD is challenging due to limitations inherent in both experimental measurements and theoretical models. This paper presents a sophisticated approach using Bayesian Neural Networks (BNN) to analyse NLD across a wide range of models. It uniquely incorporates the assessment of model uncertainties. The application of BNN has demonstrated remarkable success in accurately predicting NLD values when compared to recent experimental data, confirming the effectiveness of our methodology. The reliability and predictive power of the BNN approach not only validates its current application, but also encourages its integration into future analyses of nuclear reaction cross sections.

show abstract

“…In recent years, several authors have tried to reduce the discrepancy between theory and experiment by supplementing various mass models with neural networks (NNs) [15][16][17][18][19][20], where the NN learns the behaviour of the residuals. NNs are excellent interpolators [21], but they should be used with great care for extrapolation.…”

Section: Introductionmentioning

confidence: 99%

A New Mass Model for Nuclear Astrophysics: Crossing 200 keV Accuracy

Shelley

Pastore

2021

Universe

View full text Add to dashboard Cite

By using a machine learning algorithm, we present an improved nuclear mass table with a root mean square deviation of less than 200 keV. The model is equipped with statistical error bars in order to compare with available experimental data. We use the resulting model to predict the composition of the outer crust of a neutron star. By means of simple Monte Carlo methods, we propagate the statistical uncertainties of the mass model to the equation of state of the system.

show abstract

Nuclear mass systematics by complementing the Finite Range Droplet Model with neural networks

Cited by 4 publications

References 4 publications

Refining mass formulas for astrophysical applications: A Bayesian neural network approach

Refining mass formulas for astrophysical applications: A Bayesian neural network approach

Uncertainties of nuclear level density estimated using Bayesian neural networks*

A New Mass Model for Nuclear Astrophysics: Crossing 200 keV Accuracy

Contact Info

Product

Resources

About