Finding anomalous physics events at the LHC
Project: Real-time Anomaly Detection at the L1 Trigger of CMS Experiment
Scientists at CERN’s CMS experiment are using artificial intelligence to identify unusual particle collisions in real time, sifting through data from 40 million collisions per second. This allows them detect potential signs of new physics, while managing a data stream that only allows approximatively 1,000 events per second to be saved for further study.
AXOL1TL, short for Anomaly eXtraction Online Level-1 Trigger aLgorithm, uses an algorithm called Autoencoder to identify atypical events in the particle collider. Running on an FPGA, it makes real-time decisions within nanoseconds of collision in the detector, capturing events that would otherwise be missed and ultimately increasing the chance of discovery.
