Tackling the muon identification in water Cherenkov detectors problem for the future Southern Wide-field Gamma-ray Observatory by means of machine learning

This paper presents several approaches to deal with the problem of identifying muons in a water Cherenkov detector with a reduced water volume and 4 PMTs. Different perspectives of information representation are used, and new features are engineered using the specific domain knowledge. As results show, these new features, in combination with the convolutional layers, are able to achieve a good performance avoiding overfitting and being able to generalise properly for the test set. The results also prove that the combination of state-of-the-art machine learning analysis techniques and water Cherenkov detectors with low water depth can be used to efficiently identify muons, which may lead to huge investment savings due to the reduction of the amount of water needed at high altitudes. This achievement can be used in further research to be able to discriminate between gamma and hadron-induced showers using muons as discriminant.

Automated summary

This paper presents several approaches to address the problem of identifying muons in a water Cherenkov detector with reduced water volume and 4 PMTs. By utilizing different perspectives of information representation and engineering new features, in combination with convolutional layers, these approaches achieve good performance on the test set without overfitting. The results also demonstrate that state-of-the-art machine learning analysis techniques in low water depth Cherenkov detectors can efficiently identify muons, leading to significant cost savings in high-altitude regions where less water is required.