---
title: "Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)"
authors:
  - "Yasir Alanazi"
  - "Nobuo Sato"
  - "Tianbo Liu"
  - "Wally Melnitchouk"
  - "Pawel Ambrozewicz"
  - "Florian Hauenstein"
  - "Michelle P. Kuchera"
  - "Evan Pritchard"
  - "Michael Robertson"
  - "Ryan Strauss"
  - "Luisa Velasco"
  - "Yaohang Li"
doi: "10.24963/ijcai.2021/293"
url: "https://ijcai.org/proceedings/2021/293"
pdf: "https://ijcai.org/proceedings/2021/0293.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2126-2132"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Natural Sciences"
  - "Machine Learning: Learning Generative Models"
  - "Machine Learning: Deep Learning"
---

# Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)

Yasir Alanazi, Nobuo Sato, Tianbo Liu, Wally Melnitchouk, Pawel Ambrozewicz, Florian Hauenstein, Michelle P. Kuchera, Evan Pritchard, Michael Robertson, Ryan Strauss, Luisa Velasco, Yaohang Li

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2126-2132. DOI: [10.24963/ijcai.2021/293](https://doi.org/10.24963/ijcai.2021/293)

## Abstract

We apply generative adversarial network (GAN) technology to build an event generator that simulates particle production in electron-proton scattering that is free of theoretical assumptions about underlying particle dynamics. The difficulty of efficiently training a GAN event simulator lies in learning the complicated patterns of the distributions of the particles physical properties. We develop a GAN that selects a set of transformed features from particle momenta that can be generated easily by the generator, and uses these to produce a set of augmented features that improve the sensitivity of the discriminator. The new Feature-Augmented and Transformed GAN (FAT-GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. The developed technology can play a significant role in boosting the science of existing and future accelerator facilities, such as the Electron-Ion Collider.