Search

Modern high-energy physical detectors provide a huge amount of data, and for future high-luminosity colliders such as NICA, an Exabyte data scale is expected. Particle track reconstruction in such a dense environment is a very challenging task. Common algorithms make use of hand-engineered features and do not scale well with detector occupancy. This work is a logical continuation of the research presented on the XXII International Scientific Conference of Young Scientists and Specialists (AYSS-2018), where we have already introduced the approach of sequential tracking with the help of ad-hoc deep recurrent neural network named TrackNET. But that first version had a number of shortcomings. To address them, we introduce here the TrackNETv2, which is faster, has much fewer parameters and is able to be trained directly from Monte-Carlo simulated events. [ABSTRACT FROM AUTHOR]

Tracking particles is a challenging problem in modern high-energy physics detectors producing a vast amount of data such, as experiments on the future NICA collider. Particle track reconstruction is one of the important parts of such experiments, but existing tracking algorithms do not scale well with a growing data stream. In the same time, new effective tracking methods based on graph neural network (GNN) are actively developed and tested in the HEP.TrkX project at CERN. We introduce our GNN approach for the GEM detector of BM@N experiment of the NICA megaproject. This approach is well-adapted for solving the known fake hit problem inherent to strip detectors like GEM with help of minimum branching tree algorithms. Preliminary results for simulated events of the BM@N GEM detector are presented. [ABSTRACT FROM AUTHOR]