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

2005/11/30 by S. Athanassopoulos, E. Mavrommatis, Athanassopoulos, S. +5
Computer Science · Physics and Astronomy · #Computational Physics and Python Applications #FOS: Physical sciences #High-Energy Particle Collisions Research #Nuclear Theory (nucl-th) #Nuclear physics research studies

paper · pdf · doi:10.48550/arxiv.nucl-th/0511088

openalex publication_date 2005/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A neural-network model is developed to reproduce the differences between experimental nuclear mass-excess values and the theoretical values given by the Finite Range Droplet Model. The results point to the existence of subtle regularities of nuclear structure not yet contained in the best microscopic/phenomenological models of atomic masses. Combining the FRDM and the neural-network model, we create a hybrid model with improved predictive performance on nuclear-mass systematics and related quantities.

Related

• Predicting nuclear masses with product-unit networks
• Nuclear mass predictions based on convolutional neural network
• Robust extrapolation using physics-related activation functions in neural networks for nuclear masses
• Nuclear Mass Predictions Using a Neural Network with Additive Gaussian Process Regression-Optimized Activation Functions
• Validation and extrapolation of atomic mass with physics-informed fully connected neural network