Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.

URLhttps://doi.org/10.18429/JACoW-IPAC2026-MOP6311
TitleAI-ready lattice representation and ML optimization for the BNL booster-to-AGS transfer line
Authors
  • A. Kasparian, M. Schram, T. Satogata
    Thomas Jefferson National Accelerator Facility
  • W. Lin, K. Brown, L. Hajdu
    Brookhaven National Laboratory
  • E. Hamwi, G. Hoffstaetter
    Cornell University (CLASSE)
AbstractAs part of the Nuclear Physics AI-Ready Accelerator Data (NARAD) project, Brookhaven National Laboratory is developing a demonstration use case based on the Booster-to-AGS (BtA) transfer line. We establish an AI-ready representation of the BtA lattice using the Particle Accelerator Language Standard (PALS), extended with semantic metadata linking lattice elements to control system signals and device capabilities. This NARAD-PALS model enables direct mapping between simulation, operational devices, and machine data. We implement this framework for the BtA line and demonstrate semantic device queries and control-channel resolution within the BNL Accelerator Device Objects (ADO) system. This unified representation supports integration of streaming and archived data and provides a foundation for ML-based optimization of AGS injection and cross-facility interoperability.
Paperdownload: MOP6311.pdf
CiteBibTeX, LaTeX, Text/Word, RIS, EndNote
Conference17th International Particle Accelerator Conference
Series
LocationDeauville, France
Date17-22 May 2026
PublisherJACoW Publishing, Geneva, Switzerland
Editorial BoardEditorial Board
Online ISBN978-3-95450-252-3
Online ISSN2673-5350
Received12 May 2026
Revised15 May 2026
Accepted16 May 2026
Issued20 July 2026
DOI10.18429/JACoW-IPAC2026-MOP6311
Pages407-410