Exploring ZH → 6 Quark Jets at the FCC-ee using Machine Learning

While the Standard Model of particle physics is an extremely accurate description of fundamental particles and their interactions, it is incomplete. To better understand the nature of our universe, we want to find answers to questions that the Standard Model cannot address, which we can do by studying the Higgs boson and its properties. One key Higgs process to be studied at the Future Circular Collider (FCC-ee) is the Z(H-ZZ*)->6 jets, which is the decay of a Higgs boson in association with the Z boson into 6 jets. We want to isolate this process specifically, but there are many other similar-looking processes that the detectors observe, so it is important to distinguish between the desired process (the signal) and all the other processes with a similar detector signature (the background). In collaboration with the Omega Group and Brookhaven National Laboratory, I created and tested two different machine learning algorithms in Python, BDTs and neural networks, to separate these two processes and isolate the measurement of Higgs->ZZ*. The signal separated from these machine learning models can be used to extract the total Higgs decay width and the lifetime of the Higgs, independent of the predictions of the Standard Model. Any deviation of the Higgs lifetime from the predicted Standard Model values could indicate the presence of new physics.