Related papers: Validating neural-network refinements of nuclear m…

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is…

The equation of state of dense matter determines the structure of neutron stars, their typical radii, and maximum masses. Recent improvements in theoretical modeling of nuclear forces from the low-energy effective field theory of QCD has…

Neural networks have become popular in many fields of science since they serve as promising, reliable and powerful tools. In this work, we study the effect of data augmentation on the predictive power of neural network models for nuclear…

Nuclear data is critical for many modern applications from stockpile stewardship to cutting edge scientific research. Central to these pursuits is a robust pipeline for nuclear modeling as well as data assimilation and dissemination. We…

We perform a joint analysis of current data from cosmology and laboratory experiments to constrain the neutrino mass parameters in the framework of bayesian statistics, also accounting for uncertainties in nuclear modeling, relevant for…

Artificial neural networks (ANNs) are powerful machine learning methods used in many modern applications such as facial recognition, machine translation, and cancer diagnostics. A common issue with ANNs is that they usually have millions or…

In astrophysical simulations, nuclear reacting flows pose computational challenges due to the stiffness of reaction networks. We introduce neural network-based surrogate models using the DeePODE framework to enhance simulation efficiency…

Neural-network-based machine learning interatomic potentials have emerged as powerful tools for predicting atomic energies and forces, enabling accurate and efficient simulations in atomistic modeling. A key limitation of traditional deep…

Neutrinos are perhaps the most elusive known particles in the universe. We know they have some nonzero mass, but unlike all other particles, the absolute scale remains unknown. In addition, their fundamental nature is uncertain; they can…

For the retrieval of large-scale vegetation biophysical parameters, the inversion of radiative transfer models (RTMs) is the most commonly used approach. In recent years, Artificial Neural Network (ANN)-based methods have become the…

Nuclear reactors provide intense sources of electron antineutrinos, characterized by few-MeV energy E and unoscillated spectral shape Phi(E). High-statistics observations of reactor neutrino oscillations over medium-baseline distances L ~…

Machine learning approaches to nuclear mass prediction have achieved remarkable accuracy, but typically rely on existing theoretical baselines or hand-crafted physics features. Here we demonstrate that these prerequisites can be supplanted…

Deep learning based image denoising methods have been extensively investigated. In this paper, attention mechanism enhanced kernel prediction networks (AME-KPNs) are proposed for burst image denoising, in which, nearly cost-free attention…

The existing nuclear masses formula and nuclear masses model has undoubtedly achieved very good results, but it is still not satisfactory for some nuclear masses. Although there are many studies in Odd-Even staggering (OES) of nuclear…

Modern nuclear data evaluation increasingly requires not only accurate scattering calculations, but also efficient methods for uncertainty quantification and parameter optimization, tasks that benefit from differentiable solvers amenable to…

The evidence for non-vanishing neutrino masses from solar and atmospheric neutrinos provides the first solid hint towards physics beyond the standard model. A full reconstruction of the neutrino spectrum may well provide a key to the…

Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesian inference provides a principled way to regularize neural…

Nuclear astrophysics is that branch of astrophysics which helps understanding some of the many facets of the Universe through the knowledge of the microcosm of the atomic nucleus. In the last decades much advance has been made in nuclear…

Signal-background classification is a central problem in High-Energy Physics (HEP), that plays a major role for the discovery of new fundamental particles. A recent method -- the Parametric Neural Network (pNN) -- leverages multiple signal…

We study methods for reconstructing Bayesian uncertainties on dynamical mass estimates of galaxy clusters using convolutional neural networks (CNNs). We discuss the statistical background of approximate Bayesian neural networks and…