DOE · DOE-485 · record R3348

Unleashing AI Transformer Models on FPGAs for Accelerating LHC and Particle Physics

Department of Energy · FNAL - Fermi National Accelerator (SC43 OIM)

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: The use case does not have an effect on civil rights/liberties/privacy, access to education/housing/insurance/credit/employment, access to critical government resources/services, human health/safety, critical infrastructure/public safety
Start date: 2025-09-25 (day precision)Source: 2025-09-25T00:00:00
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Science
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

This project centers on the deployment of Transformer models for Field Programmable Gate Arrays (FPGA), in order to seamlessly integrate AI capabilities into particle physics experiments, specifically focusing on the L1 triggering schemes and real-ti

Expected benefits

This effort focuses on Transformer models for representation learning on Field Programmable Gate Arrays (FPGA), in order to seamlessly integrate AI capabilities into particle physics experiments, specifically focusing on the CMS level-1 (L1) trigger at the High-Luminosity LHC (HL-LHC) and real-time magnet quench detection. While conventional methods for event identification have limitations, modern AI and machine learning techniques offer superior alternatives.

System outputs

This AI system has two fold use cases, represnetation learning for LHC Trigger and multi-modal magnet quench detection algorithms.

Technology

AI classification: Classical / predictive MLSource: Classical/Predictive Machine Learning: Models trained on data to make predictions or classifications based on identified patterns or relatio…
System name(s): Not reported
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: No
Demographic features: Not reported
Training and evaluation data: research datasets from scientific experiments
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported