This Project Grant award of $487,503.00 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) will support research to leverage advanced artificial intelligence (AI) techniques to improve the reconstruction of sub-TeV neutrinos using the IceCube DeepCore subdetector. The award recipient, Georgia Tech Research Corp, will design a novel AI architecture to more accurately manage the spatiotemporal irregularities in IceCube's sensor data while embedding physics-informed inductive biases. This will enhance computational efficiency for real-time processing of millions of neutrino events, enable robust training to address systematic uncertainties, and investigate approximate symmetry modeling to allow AI models to adapt to practical deviations. These innovations are expected to significantly improve the angular resolution and sensitivity of DeepCore to sub-TeV neutrinos, enabling transformative discoveries about astrophysical sources. The award period is from July 1, 2025 to June 30, 2027. No subawards are planned.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $487.5k | 6/17/25 |