Simulation and modeling of Resistive Plate Chamber using Garfield++ and decision tree regression model

The Resistive Plate Chamber (RPC) is a fast gaseous detector utilized at the Large Hadron Collider (LHC) to identify charged particles resulting from p-p collisions. Employed within the Compact Muon Solenoid (CMS) experiment at the LHC, RPCs serve as a dedicated trigger system in both the barrel and endcap regions. The operating gas within these detectors significantly influences their performance. This study aims to optimize the transport parameters of the operational gas using Garfield++ simulations and machine learning modeling. By rigorously evaluating key parameters such as drift velocity and diffusion coefficients, this research focuses on comparing the results obtained from Garfield++ simulations and decision tree regression model. Garfield++, a powerful simulation tool, offers detailed insights into the gas’s behavior under various conditions, thereby aiding in the identification of optimal transport parameters and enhancing RPC detector performance. Simultaneously, the decision tree regression model are employed to model the transport parameters based on datasets generated by Garfield++ simulations. This approach provides a unique perspective on gas transport parameters, complementing the insights gained from simulation analyses.