Transfer Learning in KM3NeT/ORCA for Neutrino Event Reconstruction

This study explores using transformer models to analyze data from the KM3NeT/ORCA neutrino telescope. Due to the increasing detector’s size, reconstructing neutrino events is challenging. By training models on simulations for the full detector (115 detection units) and fine-tuning them on smaller configurations, significant performance improvements can be achieved compared to models trained from scratch on limited data samples. This approach also helps estimate the detector’s sensitivity as it grows.