Machine learning for electron PID in ATLAS
- Event time: 1:00pm until 2:00pm
- Event date: 18th September 2017
- Speaker: Dr Troels Petersen (Niels Bohr Institute)
- Location: Room 6206, James Clerk Maxwell Building (JCMB) James Clerk Maxwell Building Peter Guthrie Tait Road Edinburgh EH9 3FD GB
ATLAS identifies electrons using a likelihood discriminator, as this is a general and transparent approach. However, machine learning algorithms have the ability to use the correlations between the variables and their differences between signal and background to separate these further. Unfortunately, the ATLAS simulation is not accurate enough to use for detailed training, and most of the gain from ML algorithms trained on simulation is lost in these differences, when applied to data. Tag&Probe selection of elections from Z->ee events typically provide samples of 80-95% purity, but using the independency of some variables on the probe electron, this has been increased to above 99%, allowing ML training on data. The resulting ML separation is a clear improvement, which varies significantly (and surprisingly) with energy and direction.
The experimental particle physics seminar series invites speakers from all over Europe to discuss the latest developments at the LHC, accelerator and non-accelerator based neutrino physics, hardware R&D and astroparticle physics. .