Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models
Imaging Cherenkov detectors are crucial for particle identification (PID) in nuclear and particle physics experiments. Fast reconstruction algorithms are essential for near real-time alignment, calibration, data quality control, and efficient analysis. At the future electron–ion collider (EIC), the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada8f4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860611583311872 |
|---|---|
| author | C Fanelli J Giroux J Stevens |
| author_facet | C Fanelli J Giroux J Stevens |
| author_sort | C Fanelli |
| collection | DOAJ |
| description | Imaging Cherenkov detectors are crucial for particle identification (PID) in nuclear and particle physics experiments. Fast reconstruction algorithms are essential for near real-time alignment, calibration, data quality control, and efficient analysis. At the future electron–ion collider (EIC), the ePIC detector will feature a dual Ring Imaging Cherenkov (RICH) detector in the hadron direction, a Detector of Internally Reflected Cherenkov (DIRC) in the barrel, and a proximity focus RICH in the electron direction. This paper focuses on the DIRC detector, which presents complex hit patterns and is also used for PID of pions and kaons in the experiment at JLab. We present Deep(er)RICH, an extension of the seminal DeepRICH work, offering improved and faster PID compared to traditional methods and, for the first time, fast and accurate simulation. This advancement addresses a major bottleneck in Cherenkov detector simulations involving photon tracking through complex optical elements. Our results leverage advancements in Vision Transformers, specifically hierarchical Swin Transformer and normalizing flows. These methods enable direct learning from real data and the reconstruction of complex topologies. We conclude by discussing the implications and future extensions of this work, which can offer capabilities for PID for multiple cutting-edge experiments like the future EIC. |
| format | Article |
| id | doaj-art-e7eb1eeb868f4f5a841aeecf9550e1a7 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-e7eb1eeb868f4f5a841aeecf9550e1a72025-02-10T12:08:22ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101502810.1088/2632-2153/ada8f4Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow modelsC Fanelli0https://orcid.org/0000-0002-1985-1329J Giroux1https://orcid.org/0000-0001-6487-7870J Stevens2https://orcid.org/0000-0002-0816-200XDepartment of Data Science, William & Mary , Williamsburg, VA 23185, United States of America; Department of Physics, William & Mary , Williamsburg, VA 23185, United States of AmericaDepartment of Data Science, William & Mary , Williamsburg, VA 23185, United States of AmericaDepartment of Physics, William & Mary , Williamsburg, VA 23185, United States of AmericaImaging Cherenkov detectors are crucial for particle identification (PID) in nuclear and particle physics experiments. Fast reconstruction algorithms are essential for near real-time alignment, calibration, data quality control, and efficient analysis. At the future electron–ion collider (EIC), the ePIC detector will feature a dual Ring Imaging Cherenkov (RICH) detector in the hadron direction, a Detector of Internally Reflected Cherenkov (DIRC) in the barrel, and a proximity focus RICH in the electron direction. This paper focuses on the DIRC detector, which presents complex hit patterns and is also used for PID of pions and kaons in the experiment at JLab. We present Deep(er)RICH, an extension of the seminal DeepRICH work, offering improved and faster PID compared to traditional methods and, for the first time, fast and accurate simulation. This advancement addresses a major bottleneck in Cherenkov detector simulations involving photon tracking through complex optical elements. Our results leverage advancements in Vision Transformers, specifically hierarchical Swin Transformer and normalizing flows. These methods enable direct learning from real data and the reconstruction of complex topologies. We conclude by discussing the implications and future extensions of this work, which can offer capabilities for PID for multiple cutting-edge experiments like the future EIC.https://doi.org/10.1088/2632-2153/ada8f4swin transformernormalizing flowCherenkovfast simulationPID |
| spellingShingle | C Fanelli J Giroux J Stevens Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models Machine Learning: Science and Technology swin transformer normalizing flow Cherenkov fast simulation PID |
| title | Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models |
| title_full | Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models |
| title_fullStr | Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models |
| title_full_unstemmed | Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models |
| title_short | Deep(er) reconstruction of imaging Cherenkov detectors with swin transformers and normalizing flow models |
| title_sort | deep er reconstruction of imaging cherenkov detectors with swin transformers and normalizing flow models |
| topic | swin transformer normalizing flow Cherenkov fast simulation PID |
| url | https://doi.org/10.1088/2632-2153/ada8f4 |
| work_keys_str_mv | AT cfanelli deeperreconstructionofimagingcherenkovdetectorswithswintransformersandnormalizingflowmodels AT jgiroux deeperreconstructionofimagingcherenkovdetectorswithswintransformersandnormalizingflowmodels AT jstevens deeperreconstructionofimagingcherenkovdetectorswithswintransformersandnormalizingflowmodels |