Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers

TL;DR

This paper introduces a transformer-based approach for the KM3NeT/ORCA neutrino telescope that incorporates physics-informed attention masks, improving neutrino reconstruction and classification by leveraging detector and physics knowledge.

Contribution

It presents a novel transformer model with physics-inspired attention masks that enhance reconstruction and classification in neutrino detection, especially during configuration transfer.

Findings

Transformers outperform traditional models in neutrino reconstruction.

Physics-informed attention masks improve model understanding of detector and physics.

Effective fine-tuning between different detector configurations was demonstrated.

Abstract

The current KM3NeT/ORCA neutrino telescope, still under construction, has not yet reached its full potential in neutrino reconstruction capability. When training any deep learning model, no explicit information about the physics or the detector is provided, thus they remain unknown to the model. This study leverages the strengths of transformers by incorporating attention masks inspired by the physics and detector design, making the model understand both the telescope design and the neutrino physics measured on it. The study also shows the efficacy of transformers on retaining valuable information between detectors when doing fine-tuning from one configurations to another.