Discovering Neutrinos Through Data Analytics
Astrophysical experiments produce Big Data which need efficient and effective data analytics. In this paper we present a general data analysis process which has been successfully applied to data from IceCube, a cubic kilometer neutrino detector located at the geographic South Pole.
The goal of the analysis is to separate neutrinos from atmospheric muons within the data to determine the muon neutrino energy spectrum. The presented process covers straight cuts, variable selection, classification, and unfolding. A major challenge in the separation is the unbalanced dataset. The expected signal to background ratio in the initial data (trigger level) is roughly 1:\(10^6\). The overall process was embedded in a multi-fold cross-validation to control its performance. A subsequent regularized unfolding yields the sought after neutrino energy spectrum.
KeywordsNeutrinos IceCube Machine learning Random forest Feature selection Cross-validation Signal and background separation
Unable to display preview. Download preview PDF.
- 2.Ruhe, T., Morik, K., Rhode, W.: Application of RapidMiner in Neutrino Astronomy. In: Hofmann, M., Klinkenber, R. (eds.) RapidMiner: Data Mining Use Cases and Business Analytics Applications. CRC Press Book (2013)Google Scholar
- 3.Aartsen, M.G., et al.: Development of a general analysis and unfolding scheme and its application to measure the energy spectrum of atmospheric neutrinos with IceCube. The European Physical Journal C 3, 75–116 (2015)Google Scholar
- 4.Abbasi, R., et al.: Measurement of the atmospheric neutrino energy spectrum from 100 GeV to 400 TeV with IceCube. Phys. Rev. D 83(1), 012001(19) (2011)Google Scholar
- 5.Mierswa, I., Klinkenberg, R., Fischer, S., Ritthoff, O.: A Flexible Platform for Knowledge Discovery Experiments: YALE - Yet Another Learning Environment (2000)Google Scholar