Related papers: Deep learning on nuclear mass and $\alpha$ decay h…
This study investigates the application of deep learning models-recurrent neural networks, gated recurrent units, and long short-term memory networks-for predicting nuclear binding energies. Utilizing data from the Atomic Mass Evaluation…
A novel machine learning approach is used to provide further insight into atomic nuclei and to detect orderly patterns amidst a vast data of large-scale calculations. The method utilizes a neural network that is trained on ab initio results…
A detailed study of $\alpha$-clusters decay is exhibited by incorporating crucial microscopic nuclear structure information into the estimations of half-life and preformation factor. For the first time, using the k-cross validation…
Machine learning offers a powerful framework for validating and predicting atomic mass. We compare three improved neural network methods for representation and extrapolation for atomic mass prediction. The powerful method, adopting a…
A convolutional neural network (CNN) is employed to investigate nuclear mass. By introducing the masses of neighboring nuclei and the paring effects at the input layer of the network, local features of the target nucleus are extracted to…
Nuclear segmentation is an important step for profiling aberrant regions of histology sections. However, segmentation is a complex problem as a result of variations in nuclear geometry (e.g., size, shape), nuclear type (e.g., epithelial,…
The probability of $\alpha$ particle emission for some recently observed superheavy nuclei (SHN) are investigated. The $\alpha$-decay half lives of SHN are calculated in a quantum tunneling model with density dependent M3Y (DDM3Y) effective…
The semi-empirical macroscopic-microscopic mass formula is further improved by considering some residual corrections. The rms deviation from 2149 known nuclear masses is significantly reduced to 336 keV, even lower than that achieved with…
In the present work, we have predicted the half-lives for the $\beta^{-}$ decay for higher forbidden unique transitions in the mass range of nuclei from A = 40-138. For these transitions, the experimental data for half-lives are not…
We introduce a new method, called CNNAS (convolutional neural networks for atomistic systems), for calculating the total energy of atomic systems which rivals the computational cost of empirical potentials while maintaining the accuracy of…
Current neural networks for predictions of molecular properties use quantum chemistry only as a source of training data. This paper explores models that use quantum chemistry as an integral part of the prediction process. This is done by…
Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory, however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked.…
Theoretical estimates for the lifetimes of several isotopes of heavy elements with Z=102-120 are presented by calculating the quantum mechanical tunneling probability in a WKB framework and using microscopic nucleus-nucleus potential…
A systematic study on the alpha decay half lives of various isotopes of superheavy element \textit{Z} = 121 within the range 290 $\leq$ A $\leq$ 339 is presented for the first time using Coulomb and proximity potential model for deformed…
Recently, experimental researches on the $\alpha$ decay with long lifetime are one of hot topics in the contemporary nuclear physics [e.g. N. Kinoshita {\sl et al.} (2012) and J. W. Beeman {\sl et al.} (2012) ]. In this study, we have…
Machine learning methods and uncertainty quantification have been gaining interest throughout the last several years in low-energy nuclear physics. In particular, Gaussian processes and Bayesian Neural Networks have increasingly been…
Ensemble learning algorithms, the gradient boosting and bagging regressors, are employed to correct the residuals of nuclear mass excess for a diverse set of six nuclear mass models. The weighted average of these corrected residuals reduces…
The zero neutrino mode of the double beta decay in heavy deformed nuclei is investigated in the framework of the pseudo SU(3) model, which has provided an accurate description of collective nuclear structure and predicted half-lives for the…
We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables, including binding and decay energies, and nuclear charge radii. The model is trained using a multi-task approach with…
The model of binding alpha-particles in nuclei is suggested. It is shown good (with the accuracy of 1-2%) description of the experimental binding energies in light and medium nuclear systems. Our preliminary calculations show enhancement of…