An algorithm finally manages to shed light on the race that the beams of billions of particles make in accelerators, such as the LHC of Cern in Geneva: by combining techniques based on Artificial Intelligence with the equations that describe the behavior of the particles, researchers led by the Laboratory American national linear accelerator Slac have succeeded in developing a formula that more accurately predicts the positions and speeds of particles as they hurtle through an accelerator. The study, published in the journal Physical Review Letters, constitutes a real change of pace for the way in which the data produced by these experiments are analysed, a necessity given the ever higher energies reaching the structures.
“We have many different ways to manipulate particle beams inside accelerators, but we don’t have a really precise way to describe their shape and speed,” explains Ryan Roussel, who is leading the study together with Auralee Edelen. “Our algorithm takes into account beam information that is normally discarded and uses it to paint a more detailed picture.”
Generally, in fact, researchers can choose between describing a beam of particles in an approximate way using only a few data, and reconstructing its behavior in detail, but paying a very high price in terms of amount of data and computing power needed. .
The authors of the study therefore tried a different approach, including notions of physics in their algorithm. In this way, they managed to reconstruct the details of the particle beam with precision using a much lower amount of data than usual: “We have shown – comments Edelen – that we can predict the complicated shape of the beams starting from surprisingly small amounts of data” .
Source: Ansa
I am a journalist with over 6 years of experience working in the news industry. I currently work as an author for Global Happenings, and my coverage focuses on Technology news. I have written for various publications, including Reuters, The New York Times and The Guardian.
