NuGNN applies a heterogeneous graph neural network to surrogate-solve a 690-isotope nuclear reaction network, achieving few-percent errors and reproducing final abundances where fully connected and Res-U-Net models fail.
Boehnlein et al., Colloquium: Machine learning in nuclear physics.Reviews of Modern Physics94(3), 031003 (2022)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
First NQS variational Monte Carlo calculation of excited states in A=4 nuclei and hypernuclei, reproducing benchmarks and providing the first ab initio M1 transition strength for ^{4}_ΛH consistent with weak-coupling limit at 1.3% suppression.
MR-SCDFT augments standard multireference DFT by using stochastic fields to create reference configurations and a projection-selection step, yielding lower ground-state energies, smaller proton radii, and softer bands than conventional MR-CDFT for 20Ne, 24Mg, and 28Si.
A physics-guided neural network maps density functional theory potential energy landscapes to interacting boson model parameters for rare-earth nuclei, yielding spectra that reflect structural evolution.
PINN framework reconstructs 3D magnetic fields to 10^{-4} simulated accuracy and 10^{-3} experimental accuracy by enforcing divergence-free and curl-free conditions.
Convolutional neural networks classify 12C+12C TPC events at 90-97% accuracy and reconstruct vertices.
citing papers explorer
-
NuGNN: a Graph Neural Network for Nuclear Reaction Network Equations
NuGNN applies a heterogeneous graph neural network to surrogate-solve a 690-isotope nuclear reaction network, achieving few-percent errors and reproducing final abundances where fully connected and Res-U-Net models fail.
-
Neural-network excited states of $A=4$ nuclei and hypernuclei
First NQS variational Monte Carlo calculation of excited states in A=4 nuclei and hypernuclei, reproducing benchmarks and providing the first ab initio M1 transition strength for ^{4}_ΛH consistent with weak-coupling limit at 1.3% suppression.
-
Multireference Covariant Density Functional Theory with Stochastic Basis
MR-SCDFT augments standard multireference DFT by using stochastic fields to create reference configurations and a projection-selection step, yielding lower ground-state energies, smaller proton radii, and softer bands than conventional MR-CDFT for 20Ne, 24Mg, and 28Si.
-
Microscopic derivation of the interacting boson model parameters with machine learning
A physics-guided neural network maps density functional theory potential energy landscapes to interacting boson model parameters for rare-earth nuclei, yielding spectra that reflect structural evolution.
-
3D Magnetic Field Reconstruction and Mapping with Physics-Informed Neural Networks
PINN framework reconstructs 3D magnetic fields to 10^{-4} simulated accuracy and 10^{-3} experimental accuracy by enforcing divergence-free and curl-free conditions.
-
Machine Learning methods for event classification and vertex reconstruction of the 12C + 12C reaction with the MATE-TPC
Convolutional neural networks classify 12C+12C TPC events at 90-97% accuracy and reconstruct vertices.