Using Convolutional Neural Networks for Muon detection in WCD tank

González, B. S.; Conceição, R.; Tomé, B.; Pimenta, M.; Herrera, José Benavente; Guillén, Alberto

doi:10.1088/1742-6596/1603/1/012024

Cited by 8 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the stations with muons constitute roughly a 5% of the total (see Table 1). Therefore, the class ratio must be balanced before training [25]. A random oversampling technique was applied to the training set, creating new samples of stations with muons by randomly repeating those available in the data set.…”

Section: Analysis Strategymentioning

confidence: 99%

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using machine learning techniques

et al. 2021

Self Cite

View full text Add to dashboard Cite

The muon tagging is an essential tool to distinguish between gamma and hadron-induced showers in wide field-of-view gamma-ray observatories. In this work, it is shown that an efficient muon tagging (and counting) can be achieved using a water Cherenkov detector with a reduced water volume and 4 PMTs, provided that the PMT signal spatial and time patterns are interpreted by an analysis based on machine learning (ML). The developed analysis has been tested for different shower and array configurations. The output of the ML analysis, the probability of having a muon in the WCD station, has been used to notably discriminate between gamma and hadron induced showers with $$S/ \sqrt{B} \sim 4$$ S / B ∼ 4 for shower with energies $$E_0 \sim 1\,$$ E 0 ∼ 1 TeV. Finally, for proton-induced showers, an estimator of the number of muons was built by means of the sum of the probabilities of having a muon in the stations. Resolutions about $$20\%$$ 20 % and a negligible bias are obtained for vertical showers with $$N_{\mu } > 10$$ N μ > 10 .

show abstract

Section: Analysis Strategymentioning

confidence: 99%

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using machine learning techniques

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Note that the stations with muons constitute roughly a 5 % of the total (see Table 1). Therefore, the class ratio must be balanced before training [18]. A random oversampling technique was applied to the training set, creating new samples of stations with muons by randomly repeating those available in the data set.…”

Section: Convolutional Neural Network: Design Training and Optimisationmentioning

confidence: 99%

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using Machine Learning techniques

Conceição,

González,

Guillén

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The muon tagging is an essential tool to distinguish between gamma and hadron-induced showers in wide field-of-view gamma-ray experiments. In this work, it is shown that a good muon tagging (and counting) can be achieved using a water Cherenkov detector with a reduced water volume and 4 PMTs, provided that the PMT signal spatial and time patterns are interpreted by an analysis based on Machine Learning. The developed analysis has been tested for different shower and array configurations. The output of the ML analysis, the probability of having a muon in the WCD station, has been used to notably discriminate between gamma and hadron induced showers with S/ √ B ∼ 4 for shower with energies E 0 ∼ 1 TeV.

show abstract

“…Since the subsets are partitioned by separating the EAS, the proportion of stations with muons will remain. For this reason, different preprocessing techniques have been explored in order to balance the classes before the training stage, which is a must if we want to identify any muon [19].…”

Section: Data Curation and Preprocessingmentioning

confidence: 99%

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

González¹,

Conceição²,

Pimenta³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Using Convolutional Neural Networks for Muon detection in WCD tank

Cited by 8 publications

References 4 publications

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using machine learning techniques

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using machine learning techniques

Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using Machine Learning techniques

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

Contact Info

Product

Resources

About