Jet Substructure

Jet substructure analysis focuses on deciphering the internal structure of jets—collimated sprays of particles produced in high-energy collisions—to identify the underlying particles and processes. Current research heavily utilizes machine learning, employing various architectures like graph neural networks, variational autoencoders, and deep neural networks to analyze jet data and improve reconstruction techniques. These advancements aim to enhance the precision and speed of particle identification and anomaly detection, ultimately leading to a more comprehensive understanding of fundamental physics and improved analyses of collider data.