Implementation of the Random Forest method for the Imaging Atmospheric Cherenkov Telescope MAGIC

Albert, J.; Aliu, E.; Anderhub, H.; Antoranz, P.; Armada, A.; Asensio, M.; Baixeras, C.; Barrio, J. A.; Bartko, H.; Bastieri, D.; Becker, J.; Bednarek, W.; Berger, K.; Bigongiari, C.; Biland, A.; Bock, R. K.; Bordas, P.; Bosch Ramon, V.; Bretz, T.; Britvitch, I.; Camara, M.; Carmona, E.; Chilingarian, A.; Ciprini, S.; Coarasa, J. A.; Commichau, S.; Contreras, J. L.; Cortina, J.; Costado, M. T.; Curtef, V.; Danielyan, V.; Dazzi, F.; Angelis, A. D.; Delgado, C.; Los, R. d.; Lotto, B. D.; Domingo Santamaria, E.; Dorner, D.; Doro, M.; Errando, M.; Fagiolini, M.; Ferenc, D.; Fernandez, E.; Firpo, R.; Flix, J.; Fonseca, M. V.; Font, L.; Fuchs, M.; Galante, N.; Garcia Lopez, R. J.; Garczarczyk, M.; Gaug, M.; Giller, M.; Goebel, F.; Hakobyan, D.; Hayashida, M.; Hengstebeck, T.; Herrero, A.; Hohne, D.; Hose, J.; Huber, S.; Hsu, C. C.; Jacon, P.; Jogler, T.; Kosyra, R.; Kranich, D.; Kritzer, R.; Laille, A.; Lindfors, E.; Lombardi, S.; Longo, F.; Lopez, J.; Lopez, M.; Lorenz, E.; Majumdar, P.; Maneva, G.; Mannheim, K.; Mariotti, M.; Martinez, M.; Mazin, D.; Merck, C.; Meucci, M.; Meyer, M.; Miranda, J. M.; Mirzoyan, R.; Mizobuchi, S.; Moralejo, A.; Nieto, D.; Nilsson, K.; Ninkovic, J.; Ona Wilhelmi, E.; Otte, N.; Oya, I.; Panniello, M.; Paoletti, Riccardo; Paredes, J. M.; Pasanen, M.; Pascoli, D.; Pauss, F.; Pegna, R.; Persic, M.; Peruzzo, L.; Piccioli, A.; Puchades, N.; Prandini, E.; Raymers, A.; Rhode, W.; Ribo, M.; Rico, J.; Rissi, M.; Robert, A.; Rugamer, S.; Saggion, A.; Saito, T. Y.; Sanchez, A.; Sartori, P.; Scalzotto, V.; Scapin, V.; Schmitt, R.; Schweizer, T.; Shayduk, M.; Shinozaki, K.; Shore, S. N.; Sidro, N.; Sillanpaa, A.; Sobczynska, D.; Spanier, F.; Stamerra, A.; Stark, L. S.; Takalo, L.; Temnikov, P.; Tescaro, D.; Teshima, M.; Torres, D. F.; Turini, N.; Vankov, H.; Venturini, A.; Vitale, V.; Wagner, R. M.; Wibig, T.; Wittek, W.; Zandanel, F.; Zanin, R.; Zapatero, J.

doi:10.1016/j.nima.2007.11.068

The paper describes an application of the tree classification method Random Forest (RF), as used in the analysis of data from the ground-based gamma telescope MAGIC. In such telescopes, cosmic gamma-rays are observed and have to be discriminated against a dominating background of hadronic cosmic-ray particles. We describe the application of RF for this gamma/hadron separation. The RF method often shows superior performance in comparison with traditional semi-empirical techniques. Critical issues of the method and its implementation are discussed. An application of the RF method for estimation of a continuous parameter from related variables, rather than discrete classes, is also discussed. (C) 2008 Published by Elsevier B.V.

J., A., E., A., H., A., P., A., A., A., M., A., et al. (2008). Implementation of the Random Forest method for the Imaging Atmospheric Cherenkov Telescope MAGIC. NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH. SECTION A, ACCELERATORS, SPECTROMETERS, DETECTORS AND ASSOCIATED EQUIPMENT, 588(3), 424-432 [10.1016/j.nima.2007.11.068].