A5076600659- Particle physics theoretical and experimental studies
- High-Energy Particle Collisions Research
- Particle Detector Development and Performance
- Dark Matter and Cosmic Phenomena
- Astrophysics and Cosmic Phenomena
- Soil Moisture and Remote Sensing
- Computational Physics and Python Applications
- Granular flow and fluidized beds
- Radiation Detection and Scintillator Technologies
- Radio Astronomy Observations and Technology
- Medical Imaging Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Superconducting and THz Device Technology
Deutsches Elektronen-Synchrotron DESY
2023-2024
Lawrence Berkeley National Laboratory
2023
Universität Hamburg
2023
Taras Shevchenko National University of Kyiv
2020-2021
Accurate simulation of physical processes is crucial for the success modern particle physics. However, simulating development and interaction showers with calorimeter detectors a time consuming process drives computing needs large experiments at LHC future colliders. Recently, generative machine learning models based on deep neural networks have shown promise in speeding up this task by several orders magnitude. We investigate use new architecture -- Bounded Information Bottleneck...
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...
Given the increasing data collection capabilities and limited computing resources of future collider experiments, interest in using generative neural networks for fast simulation events is growing. In our previous study, Bounded Information Bottleneck Autoencoder (BIB-AE) architecture generating photon showers a high-granularity calorimeter showed high accuracy modeling various global differential shower distributions. this work, we investigate how BIB-AE encodes physics information its...
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 The demands placed on computational resources by the simulation requirements of high energy physics experiments motivate development novel tools. Machine learning based generative models offer a solution that is both fast and accurate. In this work we extend Bounded Information Bottleneck Autoencoder (BIB-AE) architecture, designed for particle showers in highly granular calorimeters, two key directions. First, generalise model to multi-parameter conditioning scenario, while...
Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (GANs). We introduce a post-hoc correction further improve their fidelity, based on the Deep networks using Classification for Tuning Reweighting (DCTR) protocol. The takes form of reweighting function that can be applied generated examples when making predictions from simulation. illustrate this approach GANs trained standard...
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...
The demands placed on computational resources by the simulation requirements of high energy physics experiments motivate development novel tools. Machine learning based generative models offer a solution that is both fast and accurate. In this work we extend Bounded Information Bottleneck Autoencoder (BIB-AE) architecture, designed for particle showers in highly granular calorimeters, two key directions. First, generalise model to multi-parameter conditioning scenario, while retaining degree...
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...
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...