Rios Huguet, ArnauMorales De León, David2025-09-122025-09-122025-01https://hdl.handle.net/2445/223132Treballs Finals de Grau de Física, Facultat de Física, Universitat de Barcelona, Curs: 2025, Tutor: Arnau Rios HuguetThe 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 predictions6 p.application/pdfengcc-by-nc-nd (c) Morales, 2025http://creativecommons.org/licenses/by-nc-nd/3.0/es/Xarxes neuronals convolucionalsModel de la gota líquidaTreballs de fi de grauConvolutional neural networksLiquid drop modelBachelor's thesesinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/openAccess