Physics-informed neural networks solve two-flavor neutrino oscillation equations in vacuum and matter with mean squared errors of order 10^{-3} to 10^{-4}, matching analytical results.
Neutrino physics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In the present lectures the following topics are considered: general properties of neutrinos, neutrino mass phenomenology (Dirac and Majorana masses), neutrino masses in the simplest extensions of the standard model (including the seesaw mechanism), neutrino oscillations in vacuum, neutrino oscillations in matter (the MSW effect) in 2- and 3-flavour schemes, implications of CP, T and CPT symmetries for neutrino oscillations, double beta decay, solar neutrino oscillations and the solar neutrino problem, and atmospheric neutrinos. We also give a short overview of the results of the accelerator and reactor neutrino experiments and of future projects. Finally, we discuss how the available experimental data on neutrino masses and lepton mixing can be summarized in the phenomenologically allowed forms of the neutrino mass matrix.
fields
hep-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-Informed Neural Networks for Solving Two-Flavor Neutrino Oscillations in Vacuum and Matter Environments for Atmospheric and Reactor Neutrinos
Physics-informed neural networks solve two-flavor neutrino oscillation equations in vacuum and matter with mean squared errors of order 10^{-3} to 10^{-4}, matching analytical results.