Abstract
Accurate and fast simulation of particle physics processes is crucial for the high-energy physics community. Simulating particle interactions with the detector is both time consuming and computationally expensive. With its proton-proton collision energy of 13 TeV, the Large Hadron Collider is uniquely positioned to detect and measure the rare phenomena that can shape our knowledge of new interactions. The High-Luminosity Large Hadron Collider (HLLHC) upgrade will put a significant strain on the computing infrastructure and budget due to increased event rate and levels of pile-up. Simulation of highenergy physics collisions needs to be significantly faster without sacrificing the physics accuracy. Machine learning approaches can offer faster solutions, while maintaining a high level of fidelity. We introduce a graph generative model that provides effiective reconstruction of LHC events on the level of calorimeter deposits and tracks, paving the way for full detector level fast simulation.
Highlights
Simulations of particle interactions are crucial for particle physics research
Advanced computational paradigms, including advanced machine learning techniques and dedicated hardware that accelerates their application for detector simulation and event reconstruction, will be necessary to attain the main physics goals of the HL-LHC [4] due to significant challenges posed by increased levels of pile-up and the rarity of sought-after signals
The input data contains a total of 30000 samples, each containing 3 channels: Tracks, Electromagnetic Calorimeter (ECAL) and Hadronic Calorimeter (HCAL), respectively, all of which are target channels for the purpose of this work
Summary
Simulations of particle interactions are crucial for particle physics research. The Large Hadron Collider is delivering the highest energy proton-proton collisions ever recorded in the laboratory, permitting a detailed exploration of elementary particle physics. Advanced computational paradigms, including advanced machine learning techniques and dedicated hardware that accelerates their application for detector simulation and event reconstruction, will be necessary to attain the main physics goals of the HL-LHC [4] due to significant challenges posed by increased levels of pile-up and the rarity of sought-after signals. Where P is the probability density of observing a set of reconstructed objects given a point in the parameter space, H refers to the hadronization process where mapping from the parton to the particle level occurs and R(particles) is the detector response [5]. The latter is estimated using Monte Carlo-based full simulation or parametric methods. Parametrized models such as [7] are faster but suffer from a loss in fidelity compared to full simulation which limits their utility
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
