From strange-quark tagging to fragmentation tagging with machine learning + What's New With the ATLAS Zero Degree Calorimeter

by Edo Ofir + Lion Sudit

at Particles and Fields Seminar

Mon, 08 Jul 2024, 14:00
Sacta-Rashi Building for Physics (54), room 207


[Note we have two half hour talks this week]
[1st Talk] We apply advanced machine learning techniques to two challenging jet classification problems at the LHC. The first is strange-quark tagging, in particular distinguishing strange-quark jets from down-quark jets. The second, which we term fragmentation tagging, involves identifying the fragmentation channel of a quark. We exemplify the latter by training neural networks to differentiate between bottom jets containing a bottom baryon and those containing a bottom meson. The common challenge in the two problems is that neither the quark lifetimes or masses nor parton showering provide discriminating tools, and one must rely on differences in the distributions of the hadron types contained in each type of jet and their kinematics. For these classification tasks, we employ a Graph Convolutional Network (GCN) and a variation of the Particle Transformer (ParT) that receive jet and all constituent properties as inputs. We compare their performances to a simple Multi-Layer Perceptron (MLP) that uses simple variables. We find that the more sophisticated architectures do not improve $s$-quark versus $d$-quark jet differentiation by a significant amount, but they do lead to a significant gain in $b$-baryon versus $b$-meson jet differentiation.

[2nd Talk] The Zero Degree Calorimeter is essential for the ATLAS heavy ion program at the LHC. I will present the recent detector upgrade, including a new subdetector capable of measuring the collision reaction plane, new electronics, and an LED-based calibration system. In parallel to the upgrades, improvements in the offline ZDC analysis have allowed us to calibrate and use ZDC data recorded in 2016 p-Pb run which was previously only marginally usable. This opens new analysis opportunities, an example of which will be presented.

Created on 05-07-2024 by Citron, Zvi (zhcitron)
Updaded on 05-07-2024 by Citron, Zvi (zhcitron)