This challenge is part of an effort to explore the use of machine learning to assist high energy physicists in discovering and characterizing new particles.
Particles are the tiny constituents of matter generated in a collision between proton bunches. Physicists at CERN study particles using particle accelerators. The Large Hadron Collider (LHC) at CERN is the world’s largest and most powerful particle accelerator and is used to accelerate and collide protons as well as heavy lead ions. The LHC consists of a 27-kilometre ring of superconducting magnets with a number of accelerating structures to boost the energy of the particles along the way.
In the LHC, proton bunches (beams) circulates and collide at high energy. Each beam collision (also called an event) produces a firework of new particles. To identify the types of these particles, a complex apparatus, the detector records the small energy deposited by the particles when they impact well-defined locations in the detector.
Particle Identification (PID) is fundamental to particle physics experiments. Currently no machine learning solution exists for PID.
The goal of this challenge is to build a machine learning model to read images of particles and identify their type.
This challenge was provided by Sabrina Amrouche and Dalila Salamani who are researchers at CERN and are hosting a session on machine learning at the 10th Conference on High Energy and Astro Particles.
About the Tenth International Conference on High Energy and Astro Particles (event)
This Tenth edition of the International Conference on High Energy and Astroparticle Physics (TIC-HEAP) will be held at Mentouri University, Constantine in Algeria during the period of 19th-21st October 2019. Held in close coordination with the DGRSDT (The Algerian General Direction of Scientific Research), it will focus on discussing the latest development on particle physics, astroparticle and cosmology, as well as strategically planning for Algeria to become an active participating member of the CERN.