The CMS collaboration used advanced machine learning techniques to search for new particles in jets produced by proton-proton collisions at the LHC.
The Standard Model of particle physics is a very well-tested theory that describes fundamental particles and their interactions. However, there are some important limitations. For example, it does not explain why dark matter and neutrinos have mass.
Therefore, one of the main objectives of particle experiments at the moment is to search for signs of new physical phenomena beyond the Standard Model.
If we can discover something new like this, we will find a better theoretical model of particle physics, one that can explain things that the Standard Model cannot.
These searches often involve looking for rare or unexpected signals in high-energy particle collisions, such as those at CERN’s Large Hadron Collider (LHC).
A new paper published by the CMS collaboration used a new analytical method to search for new particles produced by proton-proton collisions at the LHC.
These particles collapse into two jets, but they have an unusual internal structure that is not typical of known particles like quarks and gluons.
The researchers used advanced machine learning techniques to identify jets with different substructures and applied different anomaly detection methods to maximize sensitivity to unknown signals.
Unlike traditional strategies, anomaly detection techniques allow AI models to identify anomalous patterns in the data without being provided with specific simulation examples, increasing sensitivity to a wider range of potential new particles.
This time, we did not find any significant deviations from the expected background values. Although no new particles were discovered, the results allowed the team to test several new theoretical models for the first time. They were also able to place an upper limit on the production rate of some hypothetical particles.
Most importantly, this study demonstrates that machine learning can significantly improve the search sensitivity for new physics and provide a powerful tool for future discoveries at the LHC.
