Charged particle reconstruction in CLAS12 using Machine Learning

Thomadakis, Polykarpos; Garner, Kevin; Gavalian, G.; Chrisochoides, Nikos

doi:10.1016/j.cpc.2023.108694

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in CLAS12 leads to an increase in statistics of multi-particle final states of 50%-75% depending on kinematics [5]. Furthermore, an Artificial Intelligence approach to track reconstruction was developed to estimate track parameters (such as momentum and direction) based on cluster positions of the track [7], it was shown that the AI-estimated track parameters are closer to the values reconstructed using the Kalman-filter than the conventional hit-based tracking.…”

Section: Jinst 19 C05050mentioning

confidence: 99%

“…Examples of track classification can be seen in figure 4. Once the tracks are identified in the event the track parameters (consisting of six numbers representing the segment positions in each super-layer) are passed to another neural network which predicts the particle momentum and direction [7]. By using three neural networks (a segment finder, a track classifier, and a tracker parameter estimator), the tracks in each event are reconstructed based only on hit positions in the drift chambers.…”

Section: Track Finding Using Neural Network Approachmentioning

confidence: 99%

See 1 more Smart Citation

Real-time charged track reconstruction for CLAS12

Gavalian

2024

J. Inst.

View full text Add to dashboard Cite

This paper presents the results of charged particle track reconstruction in CLAS12 using artificial intelligence. In our approach, we use machine learning algorithms to reconstruct tracks, including their momentum and direction, with high accuracy from raw hits of the CLAS12 drift chambers. The reconstruction is performed in real-time, with the rate of data acquisition, and allows for the identification of event topologies in real-time. This approach revolutionizes the Nuclear Physics experiments' data processing, allowing us to identify and categorize the experimental data on the fly, and will lead to a significant reduction in experiment data processing. It can also be used in streaming readout applications leading to more efficient data acquisition and post-processing.

show abstract

Section: Jinst 19 C05050mentioning

confidence: 99%

Section: Track Finding Using Neural Network Approachmentioning

confidence: 99%