Real-time discrimination of photon pairs using machine learning at the LHC

Information

LHCb-DP-2019-004
arXiv:1906.09058 [PDF]

(Submitted on 21 Jun 2019)
SciPost Phys. 7, 062 (2019)
Inspire 1740869

Tools

Abstract

ALP-mediated decays and other as-yet unobserved $B$ decays to di-photon final states are a challenge to select in hadron collider environments due to the large backgrounds that come directly from the $pp$ collision. We present the strategy implemented by the LHCb experiment in 2018 to efficiently select such photon pairs. A fast neural network topology, implemented in the LHCb real-time selection framework achieves high efficiency across a mass range of $4-20$ GeV$/c^{2}$. We discuss implications and future prospects for the LHCb experiment.

Figures and captions

Output probability of the classifier for the different topologies. Upper left: 0CV, upper right: 1CV DD, lower 1CV LL	three_[..].pdf [20 KiB] HiDef png [245 KiB] Thumbnail [195 KiB]
Signal and background distributions of information used to train the 1CV LL classifier. Variables are explained in the text.	LL_convm.png [5 KiB] HiDef png [68 KiB] Thumbnail [25 KiB]
	LL_xpt.png [5 KiB] HiDef png [71 KiB] Thumbnail [26 KiB]
	LL_xipchi2.png [5 KiB] HiDef png [64 KiB] Thumbnail [25 KiB]
	LL_gprob.png [6 KiB] HiDef png [67 KiB] Thumbnail [24 KiB]
	LL_ge49.png [6 KiB] HiDef png [75 KiB] Thumbnail [28 KiB]
	LL_ptasym.png [5 KiB] HiDef png [68 KiB] Thumbnail [23 KiB]
Signal and background distributions of information used to train the 1CV DD classifier. Variables are explained in the text.	DD_convm.png [6 KiB] HiDef png [78 KiB] Thumbnail [28 KiB]
	DD_xpt.png [6 KiB] HiDef png [72 KiB] Thumbnail [27 KiB]
	DD_gprob.png [5 KiB] HiDef png [70 KiB] Thumbnail [25 KiB]
	DD_ge49.png [5 KiB] HiDef png [70 KiB] Thumbnail [25 KiB]
	DD_ptasym.png [5 KiB] HiDef png [68 KiB] Thumbnail [24 KiB]
Signal and background distributions of information used to train the 0CV classifier. Variables are explained in the text.	None_xpt.png [6 KiB] HiDef png [79 KiB] Thumbnail [32 KiB]
	None_m[..].png [5 KiB] HiDef png [70 KiB] Thumbnail [25 KiB]
	None_m[..].png [6 KiB] HiDef png [72 KiB] Thumbnail [27 KiB]
	None_m[..].png [6 KiB] HiDef png [77 KiB] Thumbnail [29 KiB]
	None_m[..].png [6 KiB] HiDef png [81 KiB] Thumbnail [31 KiB]
ROC curves for the test data using the different topologies. 0CV NN (left) , 1CV DD NN (center),1CV LL NN (right) .	ROC_curves.pdf [79 KiB] HiDef png [79 KiB] Thumbnail [48 KiB]
Animated gif made out of all figures.	DP-2019-004.gif Thumbnail

Tables and captions

Selection applied in the \texttt{Hlt1B2GammaGamma} and \texttt{Hlt1B2GammaGammaHighMass} HLT1 trigger selection. Energies and masses given here are computed with $2\times2$ cell clusters.	Table_1.pdf [69 KiB] HiDef png [53 KiB] Thumbnail [26 KiB] tex code
Percentage efficiency relative to all candidates accepted by the Photon and Electron channels of the L0 hardware trigger for the $ B ^0_ s $ and ALP samples, combining all the $\gamma$ reconstruction modes.	Table_2.pdf [67 KiB] HiDef png [67 KiB] Thumbnail [33 KiB] tex code
Sample sizes for the signal decays and background after reconstruction and trigger requirements.	Table_3.pdf [65 KiB] HiDef png [54 KiB] Thumbnail [24 KiB] tex code
Kolmogorov-Smirnov p-values for the comparison of the classifier's distribution between the test and training samples for the different topologies	Table_4.pdf [45 KiB] HiDef png [41 KiB] Thumbnail [20 KiB] tex code
Percentage efficiency for the $ B ^0_ s $ and ALP samples relative to the reconstructed and loosely selected samples.	Table_5.pdf [70 KiB] HiDef png [68 KiB] Thumbnail [33 KiB] tex code