inclusiveAI: A machine learning representation of the $F_2$ structure function over all charted $Q^2$ and $x$ range

TL;DR

This paper introduces a machine learning model that accurately predicts the $F_2$ structure function across a wide range of $Q^2$ and $x$, aiding future experimental planning and analysis.

Contribution

It presents a novel machine learning approach capable of modeling the $F_2$ structure function over all charted $Q^2$ and $x$ ranges, with high accuracy and computational efficiency.

Findings

Reproduces hydrogen and deuterium data at 7% accuracy

Model is at least ten times faster than existing parameterizations

Extensible to other nuclei and wider kinematic ranges

Abstract

Structure function data provide insight into the nucleon quark distribution. They are relatively straightforward to extract from the world's vast, and growing, amount of inclusive lepto-production data. In turn, structure functions can be used to model the physical processes needed for planning and optimizing future experiments. In this paper a machine learning algorithm capable of predicting, using a unique set of parameters, the $F_2$ structure function, for four-momentum transfer $0.055 \leq Q^2 \leq 800.0$ GeV$^2$ and for Bjorken $x$ from $2.8 \times 10^{-5}$ to the pion threshold is presented. The model was trained and reproduces the hydrogen and the deuterium data at the 7~\% level, comparable with the average uncertainty of the experimental data. Extending the model to other nuclei or expanding the kinematic range are straightforward. The model is at least ten times faster than existing structure functions parameterizations, making it an ideal candidate for event generators and systematic studies.