15–18 Dec 2026
Duke University
America/New_York timezone
Artificial Intelligence for the Electron Ion Collider (2026)

AI-Enhanced Readout and Real-Time Calorimeter Reconstruction for the EIC

Not scheduled
15m
LSRC B101 Love Auditorium (Duke University)

LSRC B101 Love Auditorium

Duke University

Durham, NC 27710
Calibration, Monitoring, and Experimental Control in Streaming Environments Calibration, Monitoring, and Experimental Control in Streaming Environments

Speaker

Norbert Novitzky (ORNL)

Description

The Electron-Ion Collider (EIC) presents exciting opportunities to integrate artificial intelligence (AI) and machine learning (ML) into calorimeter readout, online event reconstruction, and particle identification. Based on the Longitudinally segmented Forward Hadronic CALorimeter (LFHCAL) of ePIC we are exploring an AI-assisted readout and reconstruction framework designed to optimize the use of calorimeter information, with a primary focus on distinguishing electromagnetic from hadronic showers, resolving overlapping showers and independently determining their energies, enabling improved reconstruction of complex events. Opportunities include using ML-based methods to characterize electron and hadron responses, improve particle identification, and ultimately optimize the effective electron-to-hadron response ratio (e/h) and, as a consequence, the energy resolution of calorimeter systems. We will resent the plan to combine front-end data processing, waveform fitting, high-speed data aggregation, and GPU-accelerated algorithms, the proposed approach aims to perform individual shower reconstruction in real time on the same computing nodes used for data acquisition, reducing the computational cost and latency of downstream processing. The presentation will discuss the potential integration of these techniques utilizing the EIC streaming readout outline future directions for AI-driven clustering, shower separation, particle-flow reconstruction, and data-quality optimization.

Authors

Balazs Ujvari (University of Debrecen) Gabor David (SBU) Norbert Novitzky (ORNL)

Presentation materials

There are no materials yet.