Artificial Intelligence (AI)
Image courtesy of MicroBooNE Collaboration
Image of a candidate low energy νe interaction produced in the MicroBooNE detector by a beam of νμ particles. The MicroBooNE Deep Learning Low Energy Excess analysis used semantic segmentation to identify the detector hits as being caused by protons (HIP), muons (MIP), or electrons (Shower) based on their unique signatures in the MicroBooNE detector. The left image shows the raw ionization collected and the right image shows the result of the DL algorithm to associate the pixel hits with a specific particle.
High Energy Physics (HEP) supports fundamental research for public benefit to understand how our universe works at its most fundamental level. A long-standing core part of achieving that mission is the development and application of Artificial Intelligence (AI), Machine Learning (ML), and computational technology to augment or automate human skill. AI/ML have the potential to transform HEP research by harnessing DOE investments in experiments that produce massive datasets, improve operations at scientific user facilities, development of new models and algorithms that further understanding of fundamental AI/ML technologies, and make use of high-performance computing platforms. In a January 2018 Basic Needs Workshop, six Priority Research Directions were identified:
- Domain-Aware Scientific Machine Learning
- Interpretable Scientific Machine Learning
- Robust Scientific Machine Learning
- Data-Intensive Scientific Machine Learning
- Machine Learning-Enhanced Modeling and Simulation
- Intelligent Automation and Decision Support
HEP Funding Opportunity Announcements & Awards Lists
Funding Opportunities:
Two townhall meetings will provide information to interested applicants:
- Apr 13, 2022, at 2:00 PM Eastern Time
- DOE Presentation
- transcript of 4/13 Virtual Townhall
Award Lists:
Contacts
Jeremy Love
Computational HEP & QIS
jeremy.love@science.doe.gov
