Abstract
We present a method for measurement analyses based on probabilistic deep neural networks that provide several advantages over conventional analyses with phenomenological models. These include predicting physical quantities directly from data, the rapid generation of statistically robust uncertainties, and the ability to bypass some parameters that may induce ambiguities and complications in data analysis. As deep learning methods make predictions through "black boxes,"the uncertainty quantification is typically challenging. We use a probabilistic framework that provides thorough uncertainty quantification and is straightforward to follow in practice. With the network architecture based on the Transformer, we demonstrate the current method for predicting nuclear resonance parameters from scattering data using the phenomenological R-matrix model.
| Original language | English |
|---|---|
| Article number | 054609 |
| Journal | Physical Review C |
| Volume | 110 |
| Issue number | 5 |
| DOIs | |
| State | Published - Nov 2024 |
Funding
We thank D. Phillips for helpful discussions on this study. This work was supported by National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT), Grants No. RS-2024-00338255 and No. 2020R1A2C1005981. This work was also supported in part by the Institute for Basic Science, Grant No. IBS-R031-D1; by the National Science Foundation, Grant No. NSF PHY-2011890; by the U.S. Department of Energy (DOE), Office of Science, Office of Nuclear Physics, Grants No. DE-AC05-00OR22725 and No. DE-FG02-88ER40387; and by the U.S. DOE, National Nuclear Security Administration, Grant No. DE-NA0004065. Computational works for this research were performed on the data analysis hub Olaf in the IBS Research Solution Center.