Speaker
Description
Detector response simulation is a computationally expensive step in the Monte Carlo production chain for High Energy Physics experiments. For the MPD experiment at NICA (JINR), we developed a method to accelerate the simulation of the Time Projection Chamber (TPC) response using a Generative Adversarial Network (GAN). Trained on data from standard GEANT4-based simulations, the GAN replaces traditional deterministic calculations for generating detector signatures. The proposed approach achieves a reduction in computation time at this stage by several orders of magnitude, which is critical during the experiment's preparation phase. Crucially, key physical metrics of the simulated events are preserved at a level suitable for design and planning purposes. This method enables rapid iteration in detector design and optimization tuning.