A5083230034- Particle physics theoretical and experimental studies
- High-Energy Particle Collisions Research
- Quantum Chromodynamics and Particle Interactions
- Particle Detector Development and Performance
- Dark Matter and Cosmic Phenomena
- Computational Physics and Python Applications
- Neutrino Physics Research
- Cosmology and Gravitation Theories
- Astrophysics and Cosmic Phenomena
- Black Holes and Theoretical Physics
- Distributed and Parallel Computing Systems
- Stochastic processes and financial applications
- Granular flow and fluidized beds
- Soil Moisture and Remote Sensing
- Noncommutative and Quantum Gravity Theories
- Atomic and Subatomic Physics Research
- Nuclear reactor physics and engineering
- Big Data Technologies and Applications
- Parallel Computing and Optimization Techniques
- Nuclear Physics and Applications
- Nuclear physics research studies
- Random Matrices and Applications
- Particle Accelerators and Free-Electron Lasers
- Particle accelerators and beam dynamics
- Stochastic processes and statistical mechanics
Universität Hamburg
2021-2025
Institute of High Energy Physics
2022-2024
A. Alikhanyan National Laboratory
2022-2024
University of Antwerp
2024
Deutsches Elektronen-Synchrotron DESY
2022-2023
Lawrence Berkeley National Laboratory
2023
Abstract Fast simulation of the energy depositions in high-granular detectors is needed for future collider experiments at ever-increasing luminosities. Generative machine learning (ML) models have been shown to speed up and augment traditional chain physics analysis. However, majority previous efforts were limited relying on fixed, regular detector readout geometries. A major advancement recently introduced CaloClouds model, a geometry-independent diffusion which generates calorimeter...
Abstract Motivated by the computational limitations of simulating interactions particles in highly-granular detectors, there exists a concerted effort to build fast and exact machine-learning-based shower simulators. This work reports progress on two important fronts. First, previously investigated Wasserstein generative adversarial network bounded information bottleneck autoencoder models are improved successful learning hadronic showers initiated charged pions segment calorimeter...
Abstract Simulating showers of particles in highly-granular detectors is a key frontier the application machine learning to particle physics. Achieving high accuracy and speed with generative models would enable them augment traditional simulations alleviate major computing constraint. This work achieves breakthrough this task by, for first time, directly generating point cloud few thousand space points energy depositions detector 3D without relying on fixed-grid structure. made possible by...
Abstract We introduce a Python package that provides simple and unified access to collection of datasets from fundamental physics research—including particle physics, astroparticle hadron- nuclear physics—for supervised machine learning studies. The contain hadronic top quarks, cosmic-ray-induced air showers, phase transitions in matter, generator-level histories. While public multiple disciplines already exist, the common interface provided reference models simplify future work on...
Generative machine learning models offer a promising way to efficiently amplify classical Monte Carlo generators’ statistics for event simulation and generation in particle physics. Given the already high computational cost of expected increase data high-precision era LHC at future colliders, such fast surrogate simulators are urgently needed. This contribution presents status update on simulating showers granularity calorimeters colliders. Building prior work using Adversarial Networks...
Simulating showers of particles in highly-granular detectors is a key frontier the application machine learning to particle physics. Achieving high accuracy and speed with generative models would enable them augment traditional simulations alleviate major computing constraint. This work achieves breakthrough this task by, for first time, directly generating point cloud few thousand space points energy depositions detector 3D without relying on fixed-grid structure. made possible by two...
Motivated by the computational limitations of simulating interactions particles in highly-granular detectors, there exists a concerted effort to build fast and exact machine-learning-based shower simulators. This work reports progress on two important fronts. First, previously investigated WGAN BIB-AE generative models are improved successful learning hadronic showers initiated charged pions segment calorimeter International Large Detector (ILD) is demonstrated for first time. Second, we...
While simulation plays a crucial role in high energy physics, it also consumes significant fraction of the available computational resources, with these computing pressures being set to increase drastically for upcoming luminosity phase LHC and future colliders. At same time, significantly higher granularity present detectors increases physical accuracy required surrogate simulator. Machine learning methods based on deep generative models hold promise provide computationally efficient...
While simulation is a crucial cornerstone of modern high energy physics, it places heavy burden on the available computing resources. These pressures are expected to become major bottleneck for upcoming luminosity phase LHC and future colliders, motivating concerted effort develop computationally efficient solutions. Methods based generative machine learning models hold promise alleviate computational strain produced by simulation, while providing physical accuracy required surrogate...
Fast simulation of the energy depositions in high-granular detectors is needed for future collider experiments with ever-increasing luminosities. Generative machine learning (ML) models have been shown to speed up and augment traditional chain physics analysis. However, majority previous efforts were limited relying on fixed, regular detector readout geometries. A major advancement recently introduced CaloClouds model, a geometry-independent diffusion which generates calorimeter showers as...