DESC0024243
Project Grant
Overview
Grant Description
Beam condition forecasting with adaptive graph neural networks
Awardee
Grant Program (CFDA)
Awarding Agency
Funding Agency
Place of Performance
Boulder,
Colorado
80301-3346
United States
Geographic Scope
Single Zip Code
Related Opportunity
Analysis Notes
Amendment Since initial award the End Date has been extended from 07/09/24 to 08/31/24.
RadiaSoft was awarded
Project Grant DESC0024243
worth $205,848
from the Office of Science in July 2023 with work to be completed primarily in Boulder Colorado United States.
The grant
has a duration of 1 year 1 months and
was awarded through assistance program 81.049 Office of Science Financial Assistance Program.
The Project Grant was awarded through grant opportunity FY 2023 Phase I Release 2.
SBIR Details
Research Type
SBIR Phase I
Title
C56-39b. Beam Condition Forecasting with Adaptive Graph Neural Networks
Abstract
Beam diagnostics is a fundamental concern at particle accelerator facilities. Many diagnostic measurements use well known, but perturbative, methods, and can affect the beam dynamics in ways that are poorly understood. Accelerator facilities require robust, accurate, and efficient methods to predict potentially problematic beam conditions, enabling them to institute corrections, or take preventive measures, in a timely manner. We will develop a novel machine learning technique for predicting and forecasting the beam condition over the long-term operation of accelerator facilities. Our methods will enable fast, efficient, and cost-effective methods for monitoring and stabilizing important beam characteristics. During Phase I we will work with accelerator scientists to collect and analyze the experimental and simulated particle beam data necessary for developing our machine learning framework. We will then prototype machine learning algorithms with physics-aware capabilities and benchmark them against standard beam diagnostic methods. Our methods will also include techniques that, using the newly developed models, can efficiently reduce simulation uncertainty. Our new algorithms will be deployed on edge computing hardware, with adaptive forecasting that will enable long-term stable operation of particle beams at accelerator facilities. Particle accelerators therefore define our near-term market for the new algorithms and technologies developed during the project. However, the techniques developed here—to perform machine learning for non-destructive beam prediction and forecasting—have applications outside of accelerators, including to, for example, weather forecasting.
Topic Code
C56-39b
Solicitation Number
DE-FOA-0002903
Status
(Complete)
Last Modified 7/23/24
Period of Performance
7/10/23
Start Date
8/31/24
End Date
Funding Split
$205.8K
Federal Obligation
$0.0
Non-Federal Obligation
$205.8K
Total Obligated
Activity Timeline
Transaction History
Modifications to DESC0024243
Additional Detail
Award ID FAIN
DESC0024243
SAI Number
None
Award ID URI
SAI EXEMPT
Awardee Classifications
Small Business
Awarding Office
892430 SC CHICAGO SERVICE CENTER
Funding Office
892401 SCIENCE
Awardee UEI
LKPJVNM8BMS5
Awardee CAGE
6ZAU0
Performance District
CO-02
Senators
Michael Bennet
John Hickenlooper
John Hickenlooper
Budget Funding
Federal Account | Budget Subfunction | Object Class | Total | Percentage |
---|---|---|---|---|
Science, Energy Programs, Energy (089-0222) | General science and basic research | Grants, subsidies, and contributions (41.0) | $205,848 | 100% |
Modified: 7/23/24