CONTEXT

• Over 40 000 accelerators worldwide.
• Very high scientific productivity
• Very diverse applications from health, environment, energy, history, art, ...

Accelerators pose quasi-industrial challenges in terms of

• Operation and reliability

• Detecting, preventing anomalies

• Optimising beam time

• Frugal complex physics simulations

• Imprived models

Challenges

STATE OF THE ART

Developments have been striving

Yet implementation and impact are very limited

Aggravated by disparities in RIs, projects, ...

WAYS

• We bring the missing piece of FAIRness 
  in data, methods and tools in ML for RI
• We build upon existing
  knowledge and experience
• And we push it to its edge(s)
  in an integrated smart pilot/prototype
• Making sure the challenge stays realistic
  within a given time frame and budget.

SCOPE

• Name of the call :
  INFRA-2024-TECH-01-01 ;
• Call opening : 2023/12/06 ;
• Call deadline : 2024/03/12 ;
• Budget/project : 5 to 10 M€
• Total budget : 63.5 M€

AIM

CONSORTIUM

• First meeting in March 2023
• Workshop at CERN in July 2023 (35 participants)
• Workshop in November 2023 (70 participants)

• 30 partners

• 12 countries

• 3 companies

• 15 Research Infrastructures

• 7 RI on the ESFRI roadmap

• 8 universities

Consortium

• All required services from beam-time to computing and storage

• All required skills specific and non specific to AI

Consortium

CLUSTERING ACTIVITIES

Over 50 use cases received and clustered.

Organized in :

- Core use cases (critical actions)

- Study cases (data challenges)

methodology WORK-FLOW

implementation WORK-FLOW

GOVERNING STRUCTURE

GANIL

ESF

UM/RTU

ULIV/ESS

DESY/CERN

GSI/HOPS

INFN/UKRI

CNRS / ESS / OXFORD

Mayer Brown

DiPLO

ESA

...