Development of a Deep Neural Network for the data analysis of the NeuLAND neutron detector

Douma, C. A.; Hoemann, E.; Kalantar‐Nayestanaki, N.; Mayer, J.

doi:10.1016/j.nima.2020.164951

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some features like the number of hits and the total deposited energy depend only slightly on the physics lists used, and their distributions can be easily compared to the actual experimental distributions. For models that analyze individual patterns within the detector, e.g., the 3D-or LTSM networks, a high-quality emulation of the experimental data is vital, as the description of interactions in the detector can differ substantially between physics implementations [19]. However, new models can be developed in parallel to this task, and then retrained based on the results.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Classical and machine learning methods for event reconstruction in NeuLAND

Mayer

Boretzky

Douma

et al. 2021

Nuclear Instruments and Methods in Physics Research Section A:

Self Cite

View full text Add to dashboard Cite

NeuLAND, the New Large Area Neutron Detector, is a key component to investigate the origin of matter in the universe with experimental nuclear physics. It is a core component of the Reactions with Relativistic Radioactive Beams setup at the Facility for Antiproton and Ion Research, Germany. Neutrons emitted from these reactions create a wide range of patterns in NeuLAND. From these patterns, the number of neutrons (multiplicity) and their first interaction points must be reconstructed to determine the neutrons' four-momenta. In this paper, we detail the challenges involved in this reconstruction and present a range of possible solutions. Scikit-Learn classification models and simple Keras-based neural networks were trained on a wide range of input-scaler combinations and compared to classical models. While the improvement in multiplicity reconstruction is limited due to the overlap between features, the machine learning methods achieve a significantly better first interaction point selection, which directly improves the resolution of physical quantities.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The interactions simulated in the Monte-Carlo codes are based on several different models and implementations, assembled into so-called physics lists. In other investigations, it was found that they introduce some uncertainty [19]. In this paper, we restrict the discussion to the QGSP INCLXX HP physics lists [20,21].…”

Section: Simulationmentioning

confidence: 99%