Skip to Main content Skip to Navigation
Other publications

The TrackML Particle Tracking Challenge

Abstract : Can Machine Learning assist High Energy Physics (HEP) in discovering and characterizing of new particules? With event rates already reaching hundred of millions of collisions per second, physicists must sift through ten of petabytes of data per year. Ever better software is needed for real-time pre-processing and filtering of the most promising events, as the resolution of detectors improve, leading to an ever larger quantity of data. To mobilise the scientific community around this problem, we are organizing the TrackML challenge, whose objective is to use machine learning to quickly reconstruct particle tracks from dotted line traces left in the silicon detectors. The challenge refers to recognizing trajectories in the 3D images of proton collisions at the Large Hadron Collider (LHC) at CERN. Think of this as the picture of a fireworks: the time information is lost, but all particle trajectories have roughly the same origin and therefore there is a correspondence between arc length and time ordering. Given the coordinates of the impact of particles on detectors (3D points), the problem is to ``connect the dots'' or rather the points, i.e. return all sets of points belonging to alleged particle trajectories. The challenge will be conducted in 2 phases, the first one favoring innovation over efficiency and the second one aiming at real-time reconstruction.
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download
Contributor : Cecile Germain Connect in order to contact the contributor
Submitted on : Sunday, October 28, 2018 - 5:56:02 PM
Last modification on : Saturday, June 25, 2022 - 10:33:54 PM
Long-term archiving on: : Tuesday, January 29, 2019 - 12:58:24 PM


Files produced by the author(s)


  • HAL Id : hal-01680537, version 2


David Rousseau, Sabrina Amrouche, Paolo Calafiura, Victor Estrade, Steven Farrell, et al.. The TrackML Particle Tracking Challenge. 2018. ⟨hal-01680537v2⟩



Record views


Files downloads