LPCC Fast Detector Simulation Workshop

Name: LPCC Fast Detector Simulation Workshop
Start: 2021-11-22T15:00:00+01:00
End: 2021-11-23T19:00:00+01:00
Location: No location set

22 Nov 2021, 15:00 → 23 Nov 2021, 19:00 Europe/Zurich

Alberto Ribon (CERN), Anna Zaborowska (CERN), Witold Pokorski (CERN)

Description

The goal of the workshop is to discuss the developments of the fast detector simulation and to identify common interests with room for collaboration. The workshop has been divided into 6 sessions to facilitate the discussions on the topic in focus. Please find the list of useful questions around the topic in the description of each session in the timetable.

The Workshop will be held in remote mode only.

Participants

Abhishek Yadav
Adam Davis
Ahmet Ilker Topuz
Alberto Ribon
Alexander Schilling
Aman Mukesh Desai
Andrea Cesarini
Andreas Ceulemans
Andrei Gheata
Anita Candiello
Ankur Yadav
Anna Zaborowska
Aref Eshkevar Vakili
Argyrios Kerezis
Balder Villagomez
Benno Kach
Benyounes Bel Moussa
Bilal Javed Mughal
Brahim Aitbenchikh
Claudius Krause
Constantine Chimpoesh
Dalila Salamani
David Rousseau
Debajyoti Sengupta
Denis Derkach
Dirk Krucker
Dmitri Konstantinov
Driss Benchekroun
El Mehdi Ghardi
Elizabeth Sexton-Kennedy
Engin Eren
Erik Buhmann
Evangelos Kourlitis
Fernando Monterde-Andrade
Frederic Engelke
Gabriele Cosmo
Gloria Corti
Graeme A Stewart
Guilherme Amadio
Guillaume Quétant
Gustavo Gil Da Silveira
Hasib Ahmed
Henry Ann Day-Hall
Ivana Hrivnacova
Jan Michal Dubinski
Javier Mauricio Duarte
Jean-Roch Vlimant
Jesus David Bermudez Sanchez
John Apostolakis
John Derek Chapman
Jonas Hahnfeld
Joshua Falco Beirer
Kamil Rafal Deja
Kevin Pedro
Kolja Kauder
Li Shuwei
Liza Mijovic
Lorenzo Pezzotti
Lucio Anderlini
Mahsa Farasat
Marc Verderi
Marilena Bandieramonte
Mary Touranakou
Matteo Barbetti
Matteo Rama
Maxim Potekhin
Michael Duehrssen-Debling
Michal Mazurek
Michele Faucci Giannelli
Mihaly Novak
Moritz Jonas Wolf
Moritz Scham
Mouftahou Bakary Latif
Muhammad Uzair Aslam
Nana Marie Werther
Nikita Kazeev
Otmane Abouhadid
Pere Mato Vila
Peter McKeown
Philip Clark
Raghav Kansal
Roberto Preghenella
Roberto Ribatti
Rui Wang
Rui Zhang
Samuel Louis Bein
Sandro Christian Wenzel
Saverio Mariani
Selaiman Ridouani
Seyed Shams Sajadi
Soham Bhattacharya
Thomas Michael Carter
Tobias Golling
Tobias Reiling
Tommaso Lari
Torre Wenaus
Tulay Cuhadar Donszelmann
Vinicius Massami Mikuni
Vladimir Ivantchenko
Walter Hopkins
Wenxing Fang
William Korcari
Witold Pokorski
Yassine El Ghazali
Zafar Yasin

68574150571

Anna Zaborowska

Join via phone

Monday 22 November
- Mon 22 Nov
- Tue 23 Nov
- 15:00 → 15:05
  
  Introduction 5m
  
  Speakers: Alberto Ribon (CERN), Anna Zaborowska (CERN), Witold Pokorski (CERN)
- 15:05 → 16:00
  Fast Simulation applicability and accuracy
  
  How is fast simulation used: applied to which detectors? Are there specific “sensitive” parts of the detector where it is difficult to get fast simulation? Is it used widely in production? Which physics analyses can use fast simulation, which cannot? What are the demands on the accuracy of the (fast) simulation? Do you/can you tune fast simulation to collision data to get better results than from the full simulation?
  
  How does it look now, but also how it changes for Run3 & HL-LHC?
  - 15:05
    
    CMS 10m
    
    Session: Applicability and accuracy
    
    Speaker: Samuel Louis Bein (Hamburg University (DE))
    
    LPCCFastSimApplicability.pdf
  - 15:15
    
    ATLAS 10m
    
    Session: Applicability and accuracy
    
    Speakers: Joshua Falco Beirer (Georg August Universitaet Goettingen (DE)), Joshua Falco Beirer (CERN, Georg-August-Universitaet Goettingen (DE)), Joshua Falco Beirer (Georg August Universitaet Goettingen (DE))
    
    LPCC_2021_Beirer.pdf
  - 15:25
    
    ALICE 10m
    
    Session: Applicability and accuracy
    
    Speaker: Roberto Preghenella (INFN, Bologna (IT))
    
    LPCC Fast Sim.pdf
  - 15:35
    
    LHCb 10m
    
    Session: Applicability and accuracy
    
    Speaker: Constantine Chimpoesh
    
    [LPCC]-Generative_models_uncertainty_estimation.pdf
  - 15:45
    
    Discussion 15m
- 16:00 → 16:55
  Data preprocessing
  
  Which particle types and properties (energy, angle) are considered?
  How large is the full sim dataset used to extract parametrization/train the network? Is the dataset balanced (is the number of events for the different particle properties almost the same?)
  How the structure of the input data is defined (hits, cells, clusters, custom voxels,..)?
  Which data structure is used for the ML training (1D vector, images, graphs..)?
  Is input data scaled? How?
  How do you store the preprocessed data?
  How are the condition values for the ML training (energy of the particle, angle,..) encoded?
  - 16:00
    
    LHCb 10m
    
    Session: Data preprocessing
    
    Speaker: Saverio Mariani (Universita e INFN, Firenze (IT))
    
    Mariani_LPCC_Preprocessing_20211122.pdf
  - 16:10
    
    CMS 10m
    
    Session: Data preprocessing
    
    Speaker: Moritz Scham (Deutsches Elektronen-Synchrotron (DE))
    
    lpcc-preprocessing-21-11-22_handout.pdf
  - 16:20
    
    ATLAS 10m
    
    Session: Data preprocessing
    
    Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT))
    
    2021-11-22 LPCC meeting, preprocessing.pdf
  - 16:30
    
    ALICE 10m
    
    Session: Data preprocessing
    
    Speaker: Jan Michal Dubinski (Warsaw University of Technology (PL))
    
    ALICE LPCC Fast Sim.pdf
  - 16:40
    
    Discussion 15m
- 16:55 → 17:10
  
  Break 15m
- 17:10 → 18:00
  Tuning
  
  How the extraction and tuning of parameters for the fast simulation are done?
  For ML, how training is performed? What hyperparameter tuning approach is adopted? What metric is used to compare the performance of the model during the tuning process?
  - 17:10
    
    ATLAS 10m
    
    Session: Tuning
    
    Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT))
    
    2021-11-22 LPCC meeting, tuning.pdf
  - 17:20
    
    ALICE 10m
    
    Session: Tuning
    
    Speaker: Jan Michal Dubinski (Warsaw University of Technology (PL))
    
    ALICE LPCC Fast Sim.pdf
  - 17:30
    
    LHCb 10m
    
    Session: Tuning
    
    Speaker: Matteo Barbetti (Universita e INFN, Firenze (IT))
    
    20211122_LPCC_Tuning_LHCb_Barbetti.pdf
  - 17:40
    
    CMS 10m
    
    Session: Tuning
    
    Speaker: Moritz Jonas Wolf (Hamburg University (DE))
    
    20211122_LPCC_Tuning_CMS_MoritzWolf.pdf
  - 17:50
    
    Discussion 10m
- 18:00 → 19:00
  
  Further discussions 1h
  
  In case we need more time.
Tuesday 23 November
- Mon 22 Nov
- Tue 23 Nov
- 15:00 → 15:55
  Validation
  
  How do you validate fast simulation?
  Is it on e.g. particle shower characteristics (longitudinal/transverse profiles, etc.), on high-level results of physics analyses, ...?
  For ML, what is the metric used to validate the model and what is the objective function you are optimizing during the training?
  - 15:00
    
    ALICE 10m
    
    Session: Validation
    
    Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL))
    
    LPCC Fast Sim validation.pdf
  - 15:10
    
    LHCb 10m
    
    Session: Validation
    
    Speaker: Lucio Anderlini (Universita e INFN, Firenze (IT))
    
    LPCC Fast Detector Simulation Workshop Validation of the Fast Simulation.pdf
  - 15:20
    
    ATLAS 10m
    
    Session: Validation
    
    Speaker: Debajyoti Sengupta (Universite de Geneve (CH))
    
    LPCC_ATLAS_Validation.pdf
  - 15:30
    
    CMS 10m
    
    Session: Validation
    
    Speaker: Raghav Kansal (Univ. of California San Diego (US))
    
    LPCC FastSim Workshop Validation Techniques.pdf
  - 15:40
    
    Discussion 15m
- 15:55 → 16:50
  Fast sim model integration
  
  How is fast simulation integrated into the experiment's framework?
  How is the model stored (file format, size, ...)? Are there any specific files to store in addition to the model?
  For ML, which inference library is used?
  How much time does it take to generate one event?
  What is the memory footprint?
  Are there any optimization approaches considered to reduce the memory?
  Has the ML simulation been tested on GPU?
  - 15:55
    
    ATLAS 10m
    
    Session: Integration
    
    Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT))
    
    2021-11-22 LPCC meeting, integration.pdf
  - 16:05
    
    LHCb 10m
    
    Session: Integration
    
    Speaker: Michal Mazurek (CERN)
    
    LPCC_MMazurek_v2.pdf
  - 16:15
    
    CMS 10m
    
    Session: Integration
    
    Speaker: Kevin Pedro (Fermi National Accelerator Lab. (US))
    
    lpcc inference nov 23 2021.pdf
  - 16:25
    
    ALICE 10m
    
    Session: Integration
    
    Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL))
    
    LPCC Fast Sim integration.pdf
  - 16:35
    
    EP-SFT 10m
    
    Session: Integration
    
    Speaker: Anna Zaborowska (CERN)
    
    LPCC_fastsim_inferenceGeant4.pdf
  - 16:45
    
    Discussion 5m
- 16:50 → 17:10
  
  Break 20m
- 17:10 → 18:05
  Reusability and Generalisation
  
  Are there any valuable lessons to be learnt by others?
  Tools that can be reused?
  Maybe some ideas have failed for your detectors (or parts of it) and it can be useful to others?
  What are your plans, maybe there is room for collaboration?
  - 17:10
    
    LHCb 10m
    
    Session: Reusability & Generalization
    
    Speaker: Adam Davis (University of Manchester (GB))
    
    davis_lpcc_2021_11_23_v3.pdf
  - 17:20
    
    CMS 10m
    
    Session: Reusability & Generalization
    
    Speaker: Erik Buhmann (Hamburg University (DE))
    
    LPCC_Fastsim_BIB-AE_talk.pdf
  - 17:30
    
    ALICE 10m
    
    Session: Reusability & Generalization
    
    Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL))
    
    LPCC Fast Sim rg.pdf
  - 17:40
    
    ATLAS 10m
    
    Session: Reusability & Generalization
    
    Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT))
    
    2021-11-22 LPCC meeting, reusability.pdf
  - 17:50
    
    EP-SFT 10m
    
    Session: Reusability & Generalization
    
    Speaker: Dalila Salamani (CERN)
    
    Reusability & generalisation
  - 18:00
    
    Discussion 5m
- 18:05 → 19:00
  
  Further discussions 55m
  
  In case we need more time.