Searching for Dark Photon Production in Simulated Proton-Proton Collisions

Overview

Dark matter has been a key area of research in physics for over ninety years. The dark photon is a proposed model of dark matter that extends the Standard Model to add a new force mediator to interact with the dark sector. This study investigates the plausibility of using modern computational techniques to simulate and detect dark photon production via meson decay. To simulate dark photon production, the Pythia8.3 library was used to create a dataset of 500,000 points. A two-stage machine learning pipeline was developed to identify dark photon events in the simulated data. The model achieved a high ROC-AUC, demonstrating the potential of machine learning in enhancing sensitivity to dark photon production in high-energy physics experiments.

Searching for Dark Photon Production in Simulated Proton-Proton Collisions

Overview

Competition history

Related projects

Axion Detection via CNNs: A Computational Approach to Unveiling Dark Matter

Optimisation of a Neural Network for Dark Matter Research

The Search for Dark Matter Through Soft Unclustered Energy Patterns at CMS

Examining a New Method for the Discovery of Hypothetical Exotic Particles

Improving Particle Classification in WIMP Dark Matter Detection Experiments Using Neural Networks

Achieving Improved Accuracy Model for Jet Energy Measurements in the Large Hadron Collider (LHC) Using Machine Learning

Accelerating LHC Exotic Physics Discovery via Optimal Transport Flow Matching Calorimeter Simulation

The Higgs Boson: Improving the Detection of Fundamental Particles Using Neural Networks

Browse more like this