Signal-background discrimination with convolutional neural networks in the Panda X-Ⅲ experiment using MC simulation
|
摘要
The Panda X-Ⅲ experiment will search for neutrinoless double beta decay of136 Xe with high pressure gaseous time projection chambers at the China Jin-Ping underground Laboratory. The tracking feature of gaseous detectors helps suppress the background level, resulting in the improvement of the detection sensitivity. We study a method based on the convolutional neural networks to discriminate double beta decay signals against the background from high energy gammas generated by214 Bi and208 Tl decays based on detailed Monte Carlo simulation. Using the 2-dimensional projections of recorded tracks on two planes, the method successfully suppresses the background level by a factor larger than 100 with a high signal efficiency. An improvement of 62%on the efficiency ratio of ?_s/(?_b)～1/2 is achieved in comparison with the baseline in the Panda X-Ⅲ conceptual design report.
The Panda X-Ⅲ experiment will search for neutrinoless double beta decay of136 Xe with high pressure gaseous time projection chambers at the China Jin-Ping underground Laboratory. The tracking feature of gaseous detectors helps suppress the background level, resulting in the improvement of the detection sensitivity. We study a method based on the convolutional neural networks to discriminate double beta decay signals against the background from high energy gammas generated by214 Bi and208 Tl decays based on detailed Monte Carlo simulation. Using the 2-dimensional projections of recorded tracks on two planes, the method successfully suppresses the background level by a factor larger than 100 with a high signal efficiency. An improvement of 62%on the efficiency ratio of ?_s/(?_b)～1/2 is achieved in comparison with the baseline in the Panda X-Ⅲ conceptual design report.
The Panda X-Ⅲ experiment will search for neutrinoless double beta decay of136 Xe with high pressure gaseous time projection chambers at the China Jin-Ping underground Laboratory. The tracking feature of gaseous detectors helps suppress the background level, resulting in the improvement of the detection sensitivity. We study a method based on the convolutional neural networks to discriminate double beta decay signals against the background from high energy gammas generated by214 Bi and208 Tl decays based on detailed Monte Carlo simulation. Using the 2-dimensional projections of recorded tracks on two planes, the method successfully suppresses the background level by a factor larger than 100 with a high signal efficiency. An improvement of 62%on the efficiency ratio of ?_s/(?_b)～1/2 is achieved in comparison with the baseline in the Panda X-Ⅲ conceptual design report.
引文
1 F.T.Avignone,S.R.Elliott,and J.Engel,Rev.Mod.Phys.80,481(2008),ar Xiv:0708.1033.
2 A.Gando,et al.(Kam LAND-Zen collaboration),Phys.Rev.Lett.117,082503(2016).
3 J.B.Albert,et al.(EXO-200 collaboration),Nature 510,229(2014),ar Xiv:1402.6956.
4 V.′Alvarez,F.I.G.M.Borges,S.C′arcel,J.M.Carmona,J.Castel,J.M.Catal′a,S.Cebri′an,A.Cervera,D.Chan,C.A.N.Conde,T.Dafni,T.H.V.T.Dias,J.D′?az,M.Egorov,R.Esteve,P.Evtoukhovitch,L.M.P.Fernandes,P.Ferrario,A.L.Ferreira,E.Ferrer-Ribas,E.D.C.Freitas,V.M.Gehman,A.Gil,I.Giomataris,A.Goldschmidt,H.G′omez,J.J.G′omez-Cadenas,K.Gonz′alez,D.Gonz′alez-D′?az,R.M.Guti′errez,J.Hauptman,J.A.H.Morata,D.C.Herrera,V.Herrero,F.J.Iguaz,I.G.Irastorza,V.Kalinnikov,D.Kiang,L.Labarga,I.Liubarsky,J.A.M.Lopes,D.Lorca,M.Losada,G.Luz′on,A.Mar′?,J.Mart′?n-Albo,A.Mart′?nez,T.Miller,A.Moiseenko,F.Monrabal,C.M.B.Monteiro,J.M.Monz′o,F.J.Mora,L.M.Moutinho,J.M.Vidal,H.N.Luz,G.Navarro,M.Nebot,D.Nygren,C.A.B.Oliveira,R.Palma,J.P′erez,J.L.P.Aparicio,J.Renner,L.Ripoll,A.Rodr′?guez,J.Rodr′?guez,F.P.Santos,J.M.F.Santos,L.Segui,L.Serra,D.Shuman,C.Sofka,M.Sorel,J.F.Toledo,A.Tom′as,J.Torrent,Z.Tsamalaidze,D.V′azquez,E.Velicheva,J.F.C.A.Veloso,J.A.Villar,R.C.Webb,T.Weber,J.White,and N.Yahlali,J.Inst.7,T06001(2012),ar Xiv:1202.0721.
5 X.Chen,et al.(Panda X-III collaboration),Sci.China-Phys.Mech.Astron.60,061011(2017),ar Xiv:1610.08883.
6 S.Cebri′an,T.Dafni,H.G′omez,D.C.Herrera,F.J.Iguaz,I.G.Irastorza,G.Luz′on,L.Segui,and A.Tom′as,J.Phys.G-Nucl.Part.Phys.40 ,125203(2013),ar Xiv:1306.3067.
7 P.Ferrario,et al.(The NEXT collaboration),J.High Energy Phys.01,104(2016).
8 P.Baldi,K.Bauer,C.Eng,P.Sadowski,and D.Whiteson,Phys.Rev.D 93,094034(2016),ar Xiv:1603.09349.
9 J.Barnard,E.N.Dawe,M.J.Dolan,and N.Rajcic,Phys.Rev.D 95,014018(2017),ar Xiv:1609.00607.
10 A.Aurisano,A.Radovic,D.Rocco,A.Himmel,M.D.Messier,E.Niner,G.Pawloski,F.Psihas,A.Sousa,and P.Vahle,J.Inst.11,P09001(2016),ar Xiv:1604.01444.
11 P.T.Komiske,E.M.Metodiev,and M.D.Schwartz,J.High Energy Phys.01,110(2017).
12 C.F.Madrazo,I.H.Cacha,L.L.Iglesias,and J.M.de Lucas,ar Xiv:1708.07034.
13 R.Haake,in 2017 European Physical Society Conference on High Energy Physics(EPS-HEP 2017)Venice,Italy,July 5-12(2017)(Proceeding of Science,New York,2017).
14 H.Luo,M.Luo,K.Wang,T.Xu,and G.Zhu,ar Xiv:1712.03634.
15 J.Renner,et al.(NEXT collaboration),J.Inst.12,T01004(2017),ar Xiv:1609.06202.
16 X.G.Cao,et al.(Panda X-I collaboration),Sci.China-Phys.Mech.Astron.57,1476(2014),ar Xiv:1405.2882.
17 A.Tan,et al.(Panda X-II collaboration),Phys.Rev.D 93,122009(2016).
18 I.G.Irastorza,F.Aznar,J.Castel,S.Cebri′an,T.Dafni,J.Gal′an,J.A.Garcia,J.G.Garza,H.G′omez,D.C.Herrera,F.J.Iguaz,G.Luzon,H.Mirallas,E.Ruiz,L.Segu′?,and A.Tom′as,J.Cosmol.Astropart.Phys.2016,033(2016),ar Xiv:1512.07926.
19 S.Agostinelli,et al.(GEANT4 collaboration),Nucl.Instrum.Methods Phys.Res.Sect.A 506,250(2003).
20 J.Allison,et al.(GEANT4 collaboration),IEEE Trans.Nucl.Sci.53,270(2006).
21 O.A.Ponkratenko,V.I.Tretyak,and Y.G.Zdesenko,Phys.Atom.Nuclei 63,1282(2000).
22 E.Aprile,and T.Doke,Rev.Mod.Phys.82,2053(2010),ar Xiv:0910.4956.
23 A.Krizhevsky,I.Sutskever,and G.E.Hinton,in Advances in Neural Information Processing Systems 25,edited by F.Pereira,C.J.C.Burges,L.Bottou,and K.Q.Weinberger(Neural Information Processing Systems(NIPS),Lake Tahoe,2012).pp.1097-1105.
24 M.D.Zeiler,and R.Fergus,ar Xiv:1311.2901.
25 K.Simonyan,and A.Zisserman,ar Xiv:1409.1556.
26 K.He,and J.Sun,ar Xiv:1412.1710.
27 K.He,X.Zhang,S.Ren,and J.Sun,ar Xiv:1512.03385.
1)http://magboltz.web.cern.ch/magboltz/
2 )https://garfieldpp.web.cern.ch/garfieldpp/
3)https://github.com/keras-team/keras
2 A.Gando,et al.(Kam LAND-Zen collaboration),Phys.Rev.Lett.117,082503(2016).
3 J.B.Albert,et al.(EXO-200 collaboration),Nature 510,229(2014),ar Xiv:1402.6956.
4 V.′Alvarez,F.I.G.M.Borges,S.C′arcel,J.M.Carmona,J.Castel,J.M.Catal′a,S.Cebri′an,A.Cervera,D.Chan,C.A.N.Conde,T.Dafni,T.H.V.T.Dias,J.D′?az,M.Egorov,R.Esteve,P.Evtoukhovitch,L.M.P.Fernandes,P.Ferrario,A.L.Ferreira,E.Ferrer-Ribas,E.D.C.Freitas,V.M.Gehman,A.Gil,I.Giomataris,A.Goldschmidt,H.G′omez,J.J.G′omez-Cadenas,K.Gonz′alez,D.Gonz′alez-D′?az,R.M.Guti′errez,J.Hauptman,J.A.H.Morata,D.C.Herrera,V.Herrero,F.J.Iguaz,I.G.Irastorza,V.Kalinnikov,D.Kiang,L.Labarga,I.Liubarsky,J.A.M.Lopes,D.Lorca,M.Losada,G.Luz′on,A.Mar′?,J.Mart′?n-Albo,A.Mart′?nez,T.Miller,A.Moiseenko,F.Monrabal,C.M.B.Monteiro,J.M.Monz′o,F.J.Mora,L.M.Moutinho,J.M.Vidal,H.N.Luz,G.Navarro,M.Nebot,D.Nygren,C.A.B.Oliveira,R.Palma,J.P′erez,J.L.P.Aparicio,J.Renner,L.Ripoll,A.Rodr′?guez,J.Rodr′?guez,F.P.Santos,J.M.F.Santos,L.Segui,L.Serra,D.Shuman,C.Sofka,M.Sorel,J.F.Toledo,A.Tom′as,J.Torrent,Z.Tsamalaidze,D.V′azquez,E.Velicheva,J.F.C.A.Veloso,J.A.Villar,R.C.Webb,T.Weber,J.White,and N.Yahlali,J.Inst.7,T06001(2012),ar Xiv:1202.0721.
5 X.Chen,et al.(Panda X-III collaboration),Sci.China-Phys.Mech.Astron.60,061011(2017),ar Xiv:1610.08883.
6 S.Cebri′an,T.Dafni,H.G′omez,D.C.Herrera,F.J.Iguaz,I.G.Irastorza,G.Luz′on,L.Segui,and A.Tom′as,J.Phys.G-Nucl.Part.Phys.40 ,125203(2013),ar Xiv:1306.3067.
7 P.Ferrario,et al.(The NEXT collaboration),J.High Energy Phys.01,104(2016).
8 P.Baldi,K.Bauer,C.Eng,P.Sadowski,and D.Whiteson,Phys.Rev.D 93,094034(2016),ar Xiv:1603.09349.
9 J.Barnard,E.N.Dawe,M.J.Dolan,and N.Rajcic,Phys.Rev.D 95,014018(2017),ar Xiv:1609.00607.
10 A.Aurisano,A.Radovic,D.Rocco,A.Himmel,M.D.Messier,E.Niner,G.Pawloski,F.Psihas,A.Sousa,and P.Vahle,J.Inst.11,P09001(2016),ar Xiv:1604.01444.
11 P.T.Komiske,E.M.Metodiev,and M.D.Schwartz,J.High Energy Phys.01,110(2017).
12 C.F.Madrazo,I.H.Cacha,L.L.Iglesias,and J.M.de Lucas,ar Xiv:1708.07034.
13 R.Haake,in 2017 European Physical Society Conference on High Energy Physics(EPS-HEP 2017)Venice,Italy,July 5-12(2017)(Proceeding of Science,New York,2017).
14 H.Luo,M.Luo,K.Wang,T.Xu,and G.Zhu,ar Xiv:1712.03634.
15 J.Renner,et al.(NEXT collaboration),J.Inst.12,T01004(2017),ar Xiv:1609.06202.
16 X.G.Cao,et al.(Panda X-I collaboration),Sci.China-Phys.Mech.Astron.57,1476(2014),ar Xiv:1405.2882.
17 A.Tan,et al.(Panda X-II collaboration),Phys.Rev.D 93,122009(2016).
18 I.G.Irastorza,F.Aznar,J.Castel,S.Cebri′an,T.Dafni,J.Gal′an,J.A.Garcia,J.G.Garza,H.G′omez,D.C.Herrera,F.J.Iguaz,G.Luzon,H.Mirallas,E.Ruiz,L.Segu′?,and A.Tom′as,J.Cosmol.Astropart.Phys.2016,033(2016),ar Xiv:1512.07926.
19 S.Agostinelli,et al.(GEANT4 collaboration),Nucl.Instrum.Methods Phys.Res.Sect.A 506,250(2003).
20 J.Allison,et al.(GEANT4 collaboration),IEEE Trans.Nucl.Sci.53,270(2006).
21 O.A.Ponkratenko,V.I.Tretyak,and Y.G.Zdesenko,Phys.Atom.Nuclei 63,1282(2000).
22 E.Aprile,and T.Doke,Rev.Mod.Phys.82,2053(2010),ar Xiv:0910.4956.
23 A.Krizhevsky,I.Sutskever,and G.E.Hinton,in Advances in Neural Information Processing Systems 25,edited by F.Pereira,C.J.C.Burges,L.Bottou,and K.Q.Weinberger(Neural Information Processing Systems(NIPS),Lake Tahoe,2012).pp.1097-1105.
24 M.D.Zeiler,and R.Fergus,ar Xiv:1311.2901.
25 K.Simonyan,and A.Zisserman,ar Xiv:1409.1556.
26 K.He,and J.Sun,ar Xiv:1412.1710.
27 K.He,X.Zhang,S.Ren,and J.Sun,ar Xiv:1512.03385.
1)http://magboltz.web.cern.ch/magboltz/
2 )https://garfieldpp.web.cern.ch/garfieldpp/
3)https://github.com/keras-team/keras