Speaker
Description
KM3NeT is a new research infrastructure housing the next generation of neutrino
telescopes in the Mediterranean deep sea. This facility comprises two detectors:
KM3NeT/ARCA and KM3NeT/ORCA, consisting of vertical arranged detection
units, 230 and 115, respectively, each equiped with 18 digital optical modules.
The photomultipliers within each optical module detect Cherenkov light emitted
by charged particles propagating in the seawater. KM3NeT/ARCA is optimized
for the search of astrophysiscal neutrino sources in the range of TeV to PeV;
whereas KM3NeT/ORCA is used to study the neutrino oscillation phenomena in
the GeV energy range.
The current size of the detector limits the reconstruction of neutrino events in the
telescope. This study demonstrates the efficacy of transformer models as large
representation models and their ability to retain valuable information from the
full detector when evaluating data from various smaller KM3NeT/ORCA
configurations. Beginning with models trained on simulations of the complete
KM3NeT/ORCA detector, composed by 115 detection units, fine-tuning on
smaller configurations yields remarkable improvements over models trained from
scratch on these configurations with very limited data. These comparisons across
different setups, as well as the final configuration, also enable an estimation of
the detector sensitivity as it grows in size.
