AI/ML for the Electron Ion Collider

by Cristiano Fanelli (MIT)

Friday 6 May 2022, 16:00 → 18:00 Europe/Rome

Aula Conversi (Dipartimento di Fisica - Ed. G.Marconi)

The Electron-Ion Collider (EIC) is a cutting-edge accelerator facility proposed to study the nature of the ``glue'' that binds the building blocks of the visible matter in the universe. The proposed experiment will be realized at Brookhaven National Laboratory in approximately 10 years from now. Notably, EIC can be one of the first large-scale facilities to leverage Artificial Intelligence (AI) and Machine Learning (ML) starting from the design and R\&D phases. The EIC central detector is made by multiple sub-detectors, each in principle characterized by a multidimensional design space and multiple design criteria. Optimizing its design is therefore a complex problem which entails running compute-intensive simulations. In this context, AI can offer state of the art solutions to solve complex combinatorial problems in an efficient way. In particular the EIC Comprehensive Chromodynamics Experiment (ECCE), a consortium that is proposing a detector design based on a 1.5T solenoi! d, has ex plored during the detector proposal the possibility of using multi-objective optimization. In this talk I will describe our strategy and show results obtained for the ECCE tracking system. AI and ML are anticipated to play a key role in multiple aspects of the EIC detector program. In the remainder of the talk I will briefly mention prospects of AI/ML applications for Imaging Cherenkov detectors which constitute the backbone of Particle Identification for the EIC.

Zoom: https://uniroma1.zoom.us/j/87038625161?pwd=cEtGRjZNT2VWSlJIWmxaYmxSMDhRZz09