Integration of Machine Learning-Based Plasma Acceleration Simulations into Geant4: A Case Study with the PALLAS Experiment
Abstract
We present the development and integration of a Machine Learning (ML)-based surrogate model, trained on Particle-In-Cell (PIC) simulations of laser-driven plasma wakefield acceleration source of electrons, into Geant4 simulation toolkit. Our model enables the generation and tracking of plasma-accelerated beams within complete experimental setups, unifying plasma acceleration and Monte Carlo-based simulations, which significantly reduces their complexity and computational cost. Our implementation focuses on the PALLAS laser-plasma accelerator test facility, integrating its full experimental setup into Geant4. We describe the ML model, its integration into Geant4, and key simulation results, demonstrating the feasibility of start-to-end simulations of plasma acceleration facilities and applications within a unified framework.
Keywords
Cite
@article{arxiv.2503.12154,
title = {Integration of Machine Learning-Based Plasma Acceleration Simulations into Geant4: A Case Study with the PALLAS Experiment},
author = {A. Sytov and K. Cassou and V. Kubytskyi and M. Lenivenko and A. Huber},
journal= {arXiv preprint arXiv:2503.12154},
year = {2025}
}