English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The high-luminosity upgrade of the LHC will come with unprecedented physicsand computing challenges. One of these challenges is the accuratereconstruction of particles in events with up to 200 simultaneous proton-protoninteractions. The planned CMS High Granularity Calorimeter offers fine spatialresolution for this purpose, with more than 6 million channels, but also posesunique challenges to reconstruction algorithms aiming to reconstruct individualparticle showers. In this contribution, we propose an end-to-endmachine-learning method that performs clustering, classification, and energyand position regression in one step while staying within memory andcomputational constraints. We employ GravNet, a graph neural network, and anobject condensation loss function to achieve this task. Additionally, wepropose a method to relate truth showers to reconstructed showers by maximisingthe energy weighted intersection over union using maximal weight matching. Ourresults show the efficiency of our method and highlight a promising researchdirection to be investigated further.

Multi-particle reconstruction in the High Granularity Calorimeter using object condensation and graph neural networks