Machine Learning for New Physics Searches in B → K∗0µ+µ− Decays

Dubey, S.S.DubeyBrowder, T. E.T. E.BrowderKohani, S.S.KohaniMandal, R.R.MandalSibidanov, A.A.SibidanovSinha, R.R.SinhaVahsen, S. E.S. E.Vahsen2025-08-312025-08-312024-05-0610.1051/epjconf/2024295090242-s2.0-85212201281https://repository.iitgn.ac.in/handle/IITG2025/28918We report the status of a neural network regression model trained to extract new physics (NP) parameters in Monte Carlo (MC) simulation data. We utilize a new EvtGen NP MC generator to generate B → K∗0µ+µ− events according to the deviation of the Wilson Coefficient C<inf>9</inf> from its SM value, δC<inf>9</inf>. We train a three-dimensional ResNet regression model, using images built from the angular observables and the invariant mass of the di-muon system, to extract values of δC<inf>9</inf> directly from the MC data samples. This work is intended for future analyses at the Belle II experiment but may also find applicability at other experiments.en-UStrueMachine Learning for New Physics Searches in B → K∗0µ+µ− DecaysConference Paperhttps://www.epj-conferences.org/articles/epjconf/pdf/2024/05/epjconf_chep2024_09024.pdf2100014X6 May 20240090240