Abstract
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 data sets as they are released from future experiments.
Highlights
Artificial intelligence (AI) methods including machine learning (ML), deep learning (DL) and neural networks (NN) have been increasingly applied to attack several of the outstanding questions on strongly interacting systems in quantum chromodynamics (QCD), ranging from both the sign problem, and the inverse problem in lattice QCD, to extracting the behavior of parton distributions functions (PDFs) from data
In this paper we address the recently developed science of nuclear femtography, which aims at reconstructing the spatial structure of hadrons, or nucleon tomography, using information from deeply virtual electron proton exclusive photoproduction, ep → e0p0γ, and various other related reactions
Note that for this prototypical process, the cross section is a function of four independent kinematic variables: the angle between the lepton and hadron planes, φ, the scale, Q2, the skewness, ξ, which is related to Bjorken x, and t; generalized parton distributions (GPDs) for all quark flavors appear in the cross section embedded in convolutions over x known as Compton form factors (CFFs), with complex kernels depending on (x; ξ; Q2)
Summary
Artificial intelligence (AI) methods including machine learning (ML), deep learning (DL) and neural networks (NN) have been increasingly applied to attack several of the outstanding questions on strongly interacting systems in quantum chromodynamics (QCD), ranging from both the sign problem (see [1,2,3] and references therein), and the inverse problem in lattice QCD, to extracting the behavior of parton distributions functions (PDFs) from data. A competing background process given by the Bethe-Heitler (BH) reaction is present, where the photon is emitted from the electron and the matrix elements measure the proton elastic form factors Note that for this prototypical process, the cross section is a function of four independent kinematic variables: the angle between the lepton and hadron planes, φ, the scale, Q2, the skewness, ξ, which is related to Bjorken x, and t; GPDs for all quark flavors appear in the cross section embedded in convolutions over x known as Compton form factors (CFFs), with complex kernels depending on (x; ξ; Q2).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
