Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Particle physics is the study of the elementary building blocks of matter and radiation and their interaction. The fundamental particles are summarised by the standard model. This includes leptons (such as the electron), the quarks that make up protons and neutrons, and gauge bosons, which mediate forces between the other particles.
Simulating responses of a full particle physics detector with high granularity is computationally very expensive. Here, the authors develop a deep generative model that is able to model a detector with millions of information channel with good performances, reducing both storage demand and CPU time.
The paper addresses the task of extracting individual objects from multi-dimensional overlapping-sparse images, with valuable impact in high-energy physics (future high-precision long-baseline neutrino oscillation experiments). The developed tool will allow to reduce systematic errors and avoid model dependence, improving the neutrino energy resolution and sensitivity.
The US$665-million High Energy Photon Source (HEPS) outside Beijing puts China among only a handful of countries that have fourth-generation synchrotron light sources.