The CMS collaboration at CERN has made progress in searching for the decay of the Higgs boson into charm quarks using AI techniques. This discovery helps physicists understand how the Higgs boson gives matter its mass. The Higgs boson, found at the Large Hadron Collider (LHC) in 2012, is important in particle physics.
It gives particles like quarks their mass through interactions. While the Higgs boson and heavier quarks match the Standard Model well, its interactions with lighter quarks, like the charm quark, are hard to study. Researchers look at how the Higgs boson decays or is made with other particles during high-energy collisions at the LHC.
The CMS collaboration reported results of their first search for a Higgs boson decaying into charm quarks, especially when the Higgs boson is made with two top quarks. Using AI techniques, this search has set the strictest limits so far on the Higgs-charm quark interaction. Making a Higgs boson with a top-quark pair, and the Higgs decaying into quarks, is rare and hard to tell apart from similar background events.
AI-enhanced charm jet tagging
Quarks make jets of hadrons, which makes it tricky to identify jets from charm quarks versus other quarks. This search required a paradigm shift in analysis techniques,” says Sebastian Wuchterl, a research fellow at CERN.
Because charm quarks are harder to tag than bottom quarks, we relied on advanced machine learning to separate the signal from backgrounds.
The CMS researchers used machine-learning models for two main challenges. First, they identified charm jets using a graph neural network algorithm. Second, they told Higgs boson signals apart from background processes with a transformer network, like those used in language models.
The charm-tagging algorithm was trained on hundreds of millions of simulated jets, improving its recognition of charm jets. Using data from 2016 to 2018 and combining results from previous searches, the CMS team achieved a 35% improvement in limits on the Higgs-charm interaction, greatly limiting possible differences from the Standard Model prediction. “Our findings mark a major step,” says Jan van der Linden, a postdoctoral researcher at Ghent University.
With more data from upcoming LHC runs and improved analysis techniques, we may gain direct insight into the Higgs boson’s interaction with charm quarks—a task thought impossible a few years ago.
As the LHC collects more data, better charm tagging and event classification could confirm the Higgs boson’s decay into charm quarks. This would be a key step in understanding the Higgs boson’s role in generating mass for all quarks and testing the Standard Model further.
Senior Software Engineer with a passion for building practical, user-centric applications. He specializes in full-stack development with a strong focus on crafting elegant, performant interfaces and scalable backend solutions. With experience leading teams and delivering robust, end-to-end products, he thrives on solving complex problems through clean and efficient code.
