Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223132
Title: Nuclear mass predictions based on convolutional neural networks
Author: Morales De León, David
Director/Tutor: Rios Huguet, Arnau
Keywords: Xarxes neuronals convolucionals
Model de la gota líquida
Treballs de fi de grau
Convolutional neural networks
Liquid drop model
Bachelor's theses
Issue Date: Jan-2025
Abstract: The precise determination of nuclear masses is essential for understanding atomic nuclei and for applications in astrophysics and nuclear energy. Traditional models like the liquid drop model, with a root mean squared error of σ = 3.94 MeV, fail to meet the accuracy of 100 keV required for nuclear astrophysics research. This work introduces a novel approach by implementing a convolutional neural network (CNN) and leveraging the spatial structure of the nuclide chart. Two models, I3 and I4, are trained and tested on the AME2016 database, achieving values of σ = 0.67 MeV and σ = 0.49 MeV, respectively. Extrapolating to the new nuclei of the AME2020 database, they hold values of σ = 0.64 MeV and σ = 0.57 MeV, demonstrating strong generalization capabilities and proving that CNNs constitute a powerful tool for accurate nuclear mass predictions
Note: Treballs Finals de Grau de Física, Facultat de Física, Universitat de Barcelona, Curs: 2025, Tutor: Arnau Rios Huguet
URI: https://hdl.handle.net/2445/223132
Appears in Collections:Treballs Finals de Grau (TFG) - Física

Files in This Item:
File Description SizeFormat 
TFG-Morales-DeLeón-David.pdf2.96 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons