Neural Network Approach to Impact Parameter Estimation in High-Energy Collisions Using Microchannel Plate Detector Data

Estimating the impact parameter in a single high-energy ion collision event is an important problem in data analysis in particle physics, because knowledge of the impact parameter is crucial for extracting information about the properties of nuclear matter. In this study, we present the use of a neural network approach for estimating the impact parameter and determining the collision class (head-on or peripheral collisions). We have modeled the data sourced from microchannel plate detectors in two geometries based on the Au+Au collision dataset at energies √sNN=11 GeV obtained by the QGSM MC event generator. We utilized the spatial distribution of particles and their time-of-flight data as event features. The addition of time-of-flight information improves the quality of impact parameter estimation. By comparing two detector geometries with different pseudorapidity acceptances ( 3.5<η<5.8 and 4.4<η<5.8 ), we demonstrated that a wider interval significantly enhances the results. The proposed algorithm was able to successfully classify more than 98 $$%$$ of Au+Au head-on collision events with an impact parameter of less than 5 fm and can be further useful as a fast trigger system. We also discuss further developments and improvements for possible applications of this technique in future experimental setups.