Artificial Intelligence and Machine Learning for Autonomous Optimization and Control of Accelerators and Detectors | DE FOA 0002875

Opportunity Information: Apply for DE FOA 0002875

The Department of Energy (DOE) Office of Science, through its Nuclear Physics (NP) program, issued this discretionary funding opportunity to support research and development projects that apply artificial intelligence and machine learning to the autonomous optimization and control of nuclear physics accelerators and detector systems. The core idea is to move beyond traditional, heavily manual tuning and operations by developing AI/ML-driven approaches that can improve how accelerator facilities and scientific instruments are simulated, controlled, monitored, and analyzed. The opportunity is focused on capabilities that matter for today s NP facilities as well as next generation facilities and instrumentation, with an emphasis on practical improvements that can shorten the cycle from setup and commissioning to reliable operations and ultimately faster scientific discovery.

The solicitation highlights several pain points common to modern accelerator and detector environments. Accelerator complexes and sophisticated detectors generate complex, high dimensional operational data, and they often require frequent tuning, calibration, and adaptation as conditions drift or as experimental configurations change. Likewise, advanced simulations and reconstruction workflows can be computationally expensive and difficult to integrate directly into real time decision making. The DOE is signaling strong interest in R and D that uses AI/ML to tackle these challenges in a way that enables more autonomous or semi autonomous operation, such as smarter feedback and control, faster optimization of machine settings, improved detector performance through automated calibration, and enhanced data acquisition and analysis pipelines that can react intelligently to changing conditions.

Administratively, the program is offered as a DOE grant under Funding Opportunity Number DE FOA 0002875 and falls under the Science and Technology and other Research and Development activity category (CFDA 81.049). Eligibility is listed as unrestricted, meaning a broad range of applicant types may apply if they can meet DOE requirements. The opportunity was created on 2022 11 09 and had an original closing date of 2023 01 11. The stated award ceiling is 2,000,000 dollars per award, indicating DOE anticipated funding projects at a scale suitable for serious algorithm development, integration with facility or instrument controls, and validation using realistic systems or datasets. While the listing notes expected awards without a specific number provided, the ceiling and framing suggest DOE was looking for a select set of strong, facility relevant projects rather than many small exploratory awards.

In short, this FOA is about accelerating progress in nuclear physics research by funding AI/ML methods that can meaningfully improve accelerator and detector performance and reduce the time and effort required to operate, tune, and extract physics results from complex experimental systems. It encourages work that bridges machine learning with real world accelerator and instrumentation constraints, with the end goal of more autonomous, efficient, and robust NP facility operations and faster experimental and computational discovery timelines.

• The Office of Science in the science and technology and other research and development sector is offering a public funding opportunity titled "Artificial Intelligence and Machine Learning for Autonomous Optimization and Control of Accelerators and Detectors" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 81.049.
• This funding opportunity was created on 2022-11-09.
• Applicants must submit their applications by 2023-01-11. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Each selected applicant is eligible to receive up to $2,000,000.00 in funding.
• Eligible applicants include: Unrestricted.

Apply for DE FOA 0002875

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: