Machine learning improves accuracy of particle identification at LHC

November 1, 2018, National Research University Higher School of Economics
Credit: CC0 Public Domain

Scientists from the Higher School of Economics have developed a method that allows physicists at the Large Hadron Collider (LHC) to separate between various types of elementary particles with a high degree of accuracy. The results were published in the Journal of Physics.

One of major unsolved problems of modern physics is the predominance of matter over antimatter in the universe. They both formed within a second after the Big Bang, in presumably equal fractions, and physicists are trying to understand where antimatter has disappeared to. Back in 1966, Russian scientist Andrei Sakharov suggested that the imbalance between matter and antimatter appeared as a result of CP violation, i.e., an asymmetry between particles and antiparticles. Thus, only particles remained after their annihilation (mutual destruction) of resulting unbalanced contributions.

The Large Hadron Collider beauty experiment (LHCb) studies unstable particles called B-mesons. Their decays demonstrate the clearest asymmetry between matter and antimatter. The LHCb consists of several specialised detectors, specifically, calorimeters to measure the of . Calorimeters also identify different types of particles. These are done by search and analysis of corresponding clusters of energy deposition. It is, however, not easy to separate signals from two types of photons—primary photons and photons from energetic π0 meson decay. HSE scientists developed a method that to classify these two with high accuracy.

The authors of the study applied and gradient boosting (a machine-learning algorithm) to classify energies collected in the individual cells of the energy cluster.

"We took a five-by-five matrix with a centre at the calorimeter cell with the largest energy," says Fedor Ratnikov, one of the study's authors and a leading researcher in the HSE Laboratory of Methods for Big Data Analysis. "Instead of analysing the special characteristics constructed from raw energies in cluster cells, we pass these raw energies directly to the algorithm for analysis. The machine was able to make sense of the data better than a person."

Compared with the previous method of data pre-processing, the new machine-learning-based method has quadrupled quality metrics for the identification of on the calorimeter. The algorithm improved the classification quality from 0.89 to 0.97; the higher this figure is, the better the classifier works. With a 98 percent effectiveness rate of initial photon identification, the new approach has lowered the false photon identification rate from 60 percent to 30 percent.

The proposed is unique in that it allows for to be identified without initially studying the characteristics of the cluster being analysed. "We pass the data to machine learning in the hope that the algorithm finds correlations we might not have considered. The approach obviously worked out in this case," Fedor Ratnikov concludes.

Explore further: New source of asymmetry between matter and antimatter

More information: Viktoria Chekalina et al, Machine Learning approach to γ/π0 separation in the LHCb calorimeter, Journal of Physics: Conference Series (2018). DOI: 10.1088/1742-6596/1085/4/042036

Related Stories

New source of asymmetry between matter and antimatter

January 31, 2017

The LHCb experiment has found hints of what could be a new piece of the jigsaw puzzle of the missing antimatter in our universe. They have found tantalising evidence of a phenomenon dubbed charge-parity (CP) violation in ...

Looking for charming asymmetries

September 29, 2016

One of the biggest challenges in physics is to understand why everything we see in our universe seems to be formed only of matter, whereas the Big Bang should have created equal amounts of matter and antimatter.

LHCb experiment observes new matter-antimatter difference

April 24, 2013

(Phys.org) —The LHCb collaboration at CERN today submitted a paper to Physical Review Letters on the first observation of matter-antimatter asymmetry in the decays of the particle known as the B0s. It is only the fourth ...

Recommended for you

Scientists produce 3-D chemical maps of single bacteria

November 16, 2018

Scientists at the National Synchrotron Light Source II (NSLS-II)—a U.S. Department of Energy (DOE) Office of Science User Facility at DOE's Brookhaven National Laboratory—have used ultrabright x-rays to image single bacteria ...

Quantum science turns social

November 15, 2018

Researchers in a lab at Aarhus University have developed a versatile remote gaming interface that allowed external experts as well as hundreds of citizen scientists all over the world to optimize a quantum gas experiment ...

Bursting bubbles launch bacteria from water to air

November 15, 2018

Wherever there's water, there's bound to be bubbles floating at the surface. From standing puddles, lakes, and streams, to swimming pools, hot tubs, public fountains, and toilets, bubbles are ubiquitous, indoors and out.

Terahertz laser pulses amplify optical phonons in solids

November 15, 2018

A study led by scientists of the Max Planck Institute for the Structure and Dynamics of Matter (MPSD) at the Center for Free-Electron Laser Science in Hamburg/Germany presents evidence of the amplification of optical phonons ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.