515664 research outputs found
Sort by
Autoregressive Models for the Fast Calorimeter Simulation of the ATLAS Calorimeter
No full textSlide approval for the ACAT talk corresponding to the PUB note https://cds.cern.ch/record/2940474/?ln=de. Presented is the new voxelization and new state of the art machine learning models for calorimeter simulations. ACAT talk page: https://indico.cern.ch/event/1488410/contributions/6562801
Unsupervised Machine Learning for Anomaly Detection in LHC Collider Searches
No full textSearches for new physics at the LHC at CERN traditionally use advanced simulations to model Standard Model (SM) processes in high-energy collisions and compare them with new-physics theories. The lack of recent direct discoveries has motivated the development of model-independent approaches in HEP to complement existing hypothesis-driven analyses, particularly Anomaly Detection. A review of the latest efforts in BSM searches with anomaly detection is presented in these proceedings, focusing on contributions within the ATLAS collaboration at LHC and discussing Variational Recurrent Neural Network (VRNN), Deep Transformer and Graph Anomaly Detection applications
Rare top processes in ATLAS and CMS
No full textThe high center-of-mass energy of proton-proton collisions and the large available datasets at the CERN Large Hadron Collider allow the study of rare processes of the Standard Model with unprecedented precision. Measurements of rare SM processes provide new tests of the SM predictions with the potential to unveil discrepancies with the SM predictions or provide important input for the improvement of theoretical calculations. In this contribution results on rare production processes including top-quarks are shown using data taken with the ATLAS Experiment at a center-of-mass-energy of 13 TeV
Reprocessing and integration results for luminosity measurement
No full textWe detail the reprocessing used to deliver physics-quality luminosity from multiple luminometers: apply nonlinearity and stability corrections (e.g. ), veto anomalies, and combine detectors consistently. Before/after comparisons show reduced per-channel spread and consistent integrated results, enabling use of a single once is corrected for out-of-time effects, nonlinearity, and drifts
Enhanced reconstruction of dileptonic top quark-antiquark events using supervised machine learning methods
No full textThe reconstruction of the top quark-antiquark kinematic system is crucial for precision measurements of top quark properties and plays a central role in many searches for beyond standard model physics involving top quarks at the LHC. In the dileptonic decay channel of , the presence of two neutrinos poses a significant challenge to reconstruct the kinematic system. In this note, a multilayer perceptron and a transformer model are trained on Monte Carlo simulations of the dileptonic decay channel to estimate the four-momenta of both top quarks in each event. The transformer achieves an average of 30\% improvement in resolution of top quark and kinematic variables compared to the commonly used existing analytical method, and also outperforms the multilayer perceptron model by about 7\%. It is also able to reconstruct approximately 5\% of events that the -weighting method cannot reconstruct
Resistive MPGD-based HCAL for future colliders
No full textCalorimeters at future colliders will require excellent energy resolution to differentiate between hadronic decays of W and Z bosons, a granularity at the (O(cm2)) level and time resolution of a few ns, to be compliant with the Particle Flow Algorithm for jet reconstruction. We propose a hadronic calorimeter (HCAL) consisting of a sampling of absorber material and resistive Micro Pattern Gaseous Detectors (MPGD) as the active layer for the future muon collider. We simulated a small-size (~1λ) MPGD-based HCAL prototype and studied its performance with pion beams. Furthermore, we performed the experimental characterization studies of MPGD prototypes with an active area of 20×20 cm2 in order to assess their performance under MIP irradiation, in terms of efficiency, time resolution, and response uniformity. We built a calorimeter prototype instrumented with 20×20 cm2 MPGDs and characterized its response under pion beams. New MPGD prototypes with a larger area (50×50 cm2) are currently under construction with the goal to assess the response uniformity, which is crucial for the hadronic shower reconstruction. In this paper, we report the simulation studies of a ~1.5λ calorimeter prototype including the new 50×50 cm2 detectors
