Machine learning has opened up new possibilities in the search for undiscovered particles within the vast data collected at the Large Hadron Collider (LHC). A team of scientists, including researchers from the U.S. Department of Energy’s Argonne National Laboratory, utilized a brain-inspired machine learning algorithm known as a neural network to analyze particle collision data.
Traditionally, particle physicists have relied on theoretical models to guide their search for new particles, comparing predictions from the Standard Model to real data from experiments like ATLAS. However, with billions of collisions recorded at the LHC and no significant deviations observed, scientists are exploring alternative approaches to uncover new physics.
In this study, the team employed anomaly detection, a machine learning technique that identifies unusual patterns in data without preconceived notions. By training the neural network to recognize typical events based on the Standard Model, the researchers were able to detect anomalies that deviated from expected particle interactions.
While the neural network did not find any definitive signs of new physics in the data analyzed from LHC Run-2, it did identify a potential anomaly related to an exotic particle decay. Although this discovery requires further investigation, it could potentially indicate the presence of an undiscovered particle.
Moving forward, the scientists plan to apply this approach to data collected during the LHC Run-3 period, which began in 2022. By harnessing the power of machine learning and anomaly detection, researchers aim to unravel the mysteries of particle physics and explore uncharted territory within the realm of fundamental particles.
This groundbreaking study, funded in part by the DOE Office of Science and the National Science Foundation, showcases the promising potential of machine learning in particle physics research. With continued advancements in technology and data analysis techniques, scientists are optimistic about the prospects of uncovering new particles and expanding our understanding of the universe.
