Colloquium: Machine learning in nuclear physics
A Boehnlein, M Diefenthaler, N Sato, M Schram… - Reviews of modern …, 2022 - APS
Advances in machine learning methods provide tools that have broad applicability in
scientific research. These techniques are being applied across the diversity of nuclear …
scientific research. These techniques are being applied across the diversity of nuclear …
Precise mass measurements of radioactive nuclides for astrophysics
J Clark, G Savard, M Mumpower… - The European Physical …, 2023 - Springer
Much of astrophysics is fueled by nuclear physics with observables, such as energy output
and elements produced, that are heavily dependent on the masses of the nuclides. A mass …
and elements produced, that are heavily dependent on the masses of the nuclides. A mass …
Local Bayesian Dirichlet mixing of imperfect models
To improve the predictability of complex computational models in the experimentally-
unknown domains, we propose a Bayesian statistical machine learning framework utilizing …
unknown domains, we propose a Bayesian statistical machine learning framework utilizing …
Physically interpretable machine learning for nuclear masses
We present an approach to modeling the ground-state mass of atomic nuclei based directly
on a probabilistic neural network constrained by relevant physics. Our physically …
on a probabilistic neural network constrained by relevant physics. Our physically …
Nuclear mass predictions using machine learning models
The exploration of nuclear mass or binding energy, a fundamental property of atomic nuclei,
remains at the forefront of nuclear physics research due to limitations in experimental …
remains at the forefront of nuclear physics research due to limitations in experimental …
Modeling heavy-ion fusion cross section data via a novel artificial intelligence approach
D Dell'Aquila, B Gnoffo, I Lombardo… - Journal of Physics G …, 2022 - iopscience.iop.org
We perform a comprehensive analysis of complete fusion cross section data with the aim to
derive, in a completely data-driven way, a model suitable to predict the integrated cross …
derive, in a completely data-driven way, a model suitable to predict the integrated cross …
Importance of physical information on the prediction of heavy-ion fusion cross sections with machine learning
In this work, the Light Gradient Boosting Machine (LightGBM), which is a modern decision
tree based machine-learning algorithm, is used to study the fusion cross section (CS) of …
tree based machine-learning algorithm, is used to study the fusion cross section (CS) of …
From complexity to clarity: Kolmogorov-arnold networks in nuclear binding energy prediction
H Liu, J Lei, Z Ren - arXiv preprint arXiv:2407.20737, 2024 - arxiv.org
This study explores the application of Kolmogorov-Arnold Networks (KANs) in predicting
nuclear binding energies, leveraging their ability to decompose complex multi-parameter …
nuclear binding energies, leveraging their ability to decompose complex multi-parameter …
Universal reduced basis for the calibration of covariant energy density functionals
AL Anderson, J Piekarewicz - Physical Review C, 2024 - APS
The reduced basis method is used to construct a “universal” basis of Dirac orbitals that may
be applicable throughout the nuclear chart to calibrate covariant energy density functionals …
be applicable throughout the nuclear chart to calibrate covariant energy density functionals …
Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders
From the lightest Hydrogen isotopes up to the recently synthesized Oganesson (Z= 118), it is
estimated that as many as about 8,000 atomic nuclei could exist in nature. Most of these …
estimated that as many as about 8,000 atomic nuclei could exist in nature. Most of these …