UMinho students want to use artificial intelligence to accelerate knowledge of the universe

At CERN – European Particle Physics Laboratory (Switzerland) there are around six hundred million proton collisions per second and all this data is analyzed by tens of thousands of scientists from all over the world. Miguel Caçador and Gabriela Oliveira, master’s students in Physics Engineering at the University of Minho, propose to accelerate this process by applying artificial intelligence to a quantum computer, to detect new events in physics (helping to decipher the universe) and to better understand quantum technology.

His study was published in the renowned magazine Frontiers in Artificial Intelligence.

In a statement, the Minho academy explains that the students are researching at the Instrumentation and Experimental Particle Physics Laboratory at the UMinho School of Sciences (LIP-Minho), guided by professor Nuno Castro.

First, they gather large amounts of data that simulate physics events (such as proton shocks) from CERN experiments. Then, they use pre-processing techniques so that they can classify the data with quantum machine learning (QML).

They focus in particular on high energy physics and its application to search for new physics phenomena, that is, processes not predicted by the standard model of particle physics.

Finding a needle in a haystack

“We take techniques that are developed in the area of ​​quantum computing and study their application to particle physics”, says Miguel Caçador, quoted in the statement. From CERN, the largest particle accelerator in the world, comes a lot of data and discovering the really interesting ones is more difficult than finding a needle in a haystack, he emphasizes. The idea is to create a model that distinguishes events coming from known physical phenomena from those that could signal something new.

To fairly compare models of machine learning classical and QML, scientists carried out a systematic study of traditional analysis methods of similar complexity to the quantum algorithms used. The performance between the models was similar, which “is promising given the current state of quantum computers”, says Gabriela Oliveira.

For Nuno Castro, this project shows that the involvement of undergraduate and master’s students in research is strategic for the teaching and learning of experimental sciences, allowing students to begin scientific activity and develop the skills that they will later use in their professional careers. .

The study also involved Miguel Crispim Romão and Inês Ochoa, both from LIP.

Portuguese researchers, especially from LIP and academies such as the UMinho School of Sciences, have collaborated at CERN for many years, having played a central role in the construction of the hadronic calorimeter of the ATLAS detector, in the trigger of the CMS accelerator, as well as in the precision measurements of the properties of the top quarkin the discovery of the Higgs boson, in the first direct observation of the coupling between those two particles and, also, in the search for new elementary particles.

CERN has a 27-kilometer circular tunnel 100 meters deep, on the French-Swiss border.