Journal
PHYSICAL REVIEW D
Volume 104, Issue 1, Pages -Publisher
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevD.104.016001
Keywords
-
Funding
- DOE [DE-FG03-95ER40965, DE-SC0016286]
- DOE Topical Collaboration on TMDs
- SURA [C2019-FEMT-002-04, C2020-FEMT-00605]
- U.S. Department of Energy (DOE) [DE-SC0016286] Funding Source: U.S. Department of Energy (DOE)
Ask authors/readers for more resources
The study proposes a machine learning based approach for deeply virtual Compton scattering, introducing a deep neural network (FemtoNet) that accurately approximates the cross section while revealing emergent features in the data. This method shows promising results in predicting outcomes for unpolarized and polarized electron beams, suggesting potential extrapolation for specific variables in the experiments.
We present a machine learning based approach to the cross section and asymmetries for deeply virtual Compton scattering from an unpolarized proton target using both an unpolarized and polarized electron beam. Machine learning methods are needed to study and eventually interpret the outcome of deeply virtual exclusive experiments since these reactions are characterized by a complex final state with a larger number of kinematic variables and observables, exponentially increasing the difficulty of quantitative analyses. Our deep neural network (FemtoNet) uncovers emergent features in the data and learns an accurate approximation of the cross section that outperforms standard baselines. FemtoNet reveals that the predictions in the unpolarized case systematically show a smaller relative median error than the polarized that can be ascribed to the presence of the Bethe-Heitler process. It also suggests that the t dependence can be more easily extrapolated than for the other variables, namely the skewness, xi and four-momentum transfer, Q(2). Our approach is fully scalable and will be capable of handling larger datasets as they arc released from future experiments.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available