Deep machine learning for the PANDA software trigger
Abstract Deep machine learning methods have been studied for the software trigger of the future PANDA experiment at FAIR, using Monte Carlo simulated data from the GEANT-based detector simulation framework PandaRoot. Ten physics channels that cover the main physics topics, including electromagnetic,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-04-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | https://doi.org/10.1140/epjc/s10052-023-11494-y |
| _version_ | 1797822650090782720 |
|---|---|
| author | Peiyong Jiang Klaus Götzen Ralf Kliemt Frank Nerling Klaus Peters the P.A.N.D.A. Collaboration |
| author_facet | Peiyong Jiang Klaus Götzen Ralf Kliemt Frank Nerling Klaus Peters the P.A.N.D.A. Collaboration |
| author_sort | Peiyong Jiang |
| collection | DOAJ |
| description | Abstract Deep machine learning methods have been studied for the software trigger of the future PANDA experiment at FAIR, using Monte Carlo simulated data from the GEANT-based detector simulation framework PandaRoot. Ten physics channels that cover the main physics topics, including electromagnetic, exotic, charmonium, open charm, and baryonic reaction channels, have been investigated at four different anti-proton beam momenta. Different classification concepts and network architectures have been studied. Finally a residual convolutional neural network with four residual blocks in a binary classification scheme has been chosen due to its extendability, performance and stability. The presented study represents a feasibility study of a completely software-based trigger system. Compared to a conventional selection method, the deep machine learning approach achieved a significant efficiency gain of up to 200%, while keeping the background reduction factor at the required level of 1/1000. Furthermore, it is shown that the use of additional input variables can improve the data quality for subsequent analysis. This study shows that the PANDA software trigger can benefit greatly from the deep machine learning methods. |
| first_indexed | 2024-03-13T10:12:15Z |
| format | Article |
| id | doaj.art-123e63bec0944867b5c455a982bb27d0 |
| institution | Directory Open Access Journal |
| issn | 1434-6052 |
| language | English |
| last_indexed | 2024-03-13T10:12:15Z |
| publishDate | 2023-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj.art-123e63bec0944867b5c455a982bb27d02023-05-21T11:24:22ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60522023-04-0183411310.1140/epjc/s10052-023-11494-yDeep machine learning for the PANDA software triggerPeiyong Jiang0Klaus Götzen1Ralf Kliemt2Frank Nerling3Klaus Peters4the P.A.N.D.A. CollaborationGSI Helmholtzzentrum für Schwerionenforschung GmbHGSI Helmholtzzentrum für Schwerionenforschung GmbHGSI Helmholtzzentrum für Schwerionenforschung GmbHGSI Helmholtzzentrum für Schwerionenforschung GmbHGSI Helmholtzzentrum für Schwerionenforschung GmbHAbstract Deep machine learning methods have been studied for the software trigger of the future PANDA experiment at FAIR, using Monte Carlo simulated data from the GEANT-based detector simulation framework PandaRoot. Ten physics channels that cover the main physics topics, including electromagnetic, exotic, charmonium, open charm, and baryonic reaction channels, have been investigated at four different anti-proton beam momenta. Different classification concepts and network architectures have been studied. Finally a residual convolutional neural network with four residual blocks in a binary classification scheme has been chosen due to its extendability, performance and stability. The presented study represents a feasibility study of a completely software-based trigger system. Compared to a conventional selection method, the deep machine learning approach achieved a significant efficiency gain of up to 200%, while keeping the background reduction factor at the required level of 1/1000. Furthermore, it is shown that the use of additional input variables can improve the data quality for subsequent analysis. This study shows that the PANDA software trigger can benefit greatly from the deep machine learning methods.https://doi.org/10.1140/epjc/s10052-023-11494-y |
| spellingShingle | Peiyong Jiang Klaus Götzen Ralf Kliemt Frank Nerling Klaus Peters the P.A.N.D.A. Collaboration Deep machine learning for the PANDA software trigger European Physical Journal C: Particles and Fields |
| title | Deep machine learning for the PANDA software trigger |
| title_full | Deep machine learning for the PANDA software trigger |
| title_fullStr | Deep machine learning for the PANDA software trigger |
| title_full_unstemmed | Deep machine learning for the PANDA software trigger |
| title_short | Deep machine learning for the PANDA software trigger |
| title_sort | deep machine learning for the panda software trigger |
| url | https://doi.org/10.1140/epjc/s10052-023-11494-y |
| work_keys_str_mv | AT peiyongjiang deepmachinelearningforthepandasoftwaretrigger AT klausgotzen deepmachinelearningforthepandasoftwaretrigger AT ralfkliemt deepmachinelearningforthepandasoftwaretrigger AT franknerling deepmachinelearningforthepandasoftwaretrigger AT klauspeters deepmachinelearningforthepandasoftwaretrigger AT thepandacollaboration deepmachinelearningforthepandasoftwaretrigger |