A new technique based on convolutional neural networks to measure the energy of protons and electrons with a single Timepix detector
- NázevTitle
- A new technique based on convolutional neural networks to measure the energy of protons and electrons with a single Timepix detectorA new technique based on convolutional neural networks to measure the energy of protons and electrons with a single Timepix detector
- Druh výsledkuResult type
- Článek v časopiseJournal article
- AutořiAuthors
- M. Ruffenach, S. Bourdarie, B. Bergmann, S. Gohl
- DOIDOI
- 10.1109/TNS.2021.3071583
- Časopis / citaceJournal / citation
- IEEE Transactions on Nuclear Science. 2021, 68(8), 1746-1753. ISSN 0018-9499.
- RokYear
- 2021
- JazykLanguage
- eng
- WoSWoS
- 000687247300030
- ScopusScopus
- 2-s2.0-85103875554
- RIVRIV
- RIV/68407700:21670/21:00350009!RIV22-MSM-21670___
- ProjektProject
- Institucionální podpora na rozvoj výzkumné org.Institucionální podpora na rozvoj výzkumné org.
AbstraktAbstract
The Timepix chip has been exposed to the outer space for the first time with the Space Application of Timepix-based Radiation Monitor (SATRAM) instrument on Project for On-Board Autonomy Vegetation (Proba-V), a European Space Agency's (ESA) satellite. The objective of this study is to develop a new technique to improve the separation of protons and electrons, which are detected by the single-layer Timepix detector in SATRAM. The current identification method proposed by Gohl et al. (2019) is based on pattern recognition and stopping power measurements. In this article, the limitations of this method are discussed. A new method based on neural network trained with Geant4 data is proposed. Its validation with SATRAM data is presented. Similarly, a neural network trained with Geant4 data is introduced. Its purpose is to deduce the particles' incident energy using the energy deposited in the Timepix.
The Timepix chip has been exposed to the outer space for the first time with the Space Application of Timepix-based Radiation Monitor (SATRAM) instrument on Project for On-Board Autonomy Vegetation (Proba-V), a European Space Agency's (ESA) satellite. The objective of this study is to develop a new technique to improve the separation of protons and electrons, which are detected by the single-layer Timepix detector in SATRAM. The current identification method proposed by Gohl et al. (2019) is based on pattern recognition and stopping power measurements. In this article, the limitations of this method are discussed. A new method based on neural network trained with Geant4 data is proposed. Its validation with SATRAM data is presented. Similarly, a neural network trained with Geant4 data is introduced. Its purpose is to deduce the particles' incident energy using the energy deposited in the Timepix.