Cosmic ray muon clustering for the MicroBooNE liquid argon time projection chamber using sMask-RCNN

P. Abratenko, R. An, J. Anthony, L. Arellano, J. Asaadi, A. Ashkenazi, S. Balasubramanian, B. Baller, C. Barnes, G. Barr, J. Barrow, V. Basque, L. Bathe-Peters, O. Benevides Rodrigues, S. Berkman, A. Bhanderi, A. Bhat, M. Bishai, A. Blake, T. Bolton, Julia Book, L. Camilleri, D. Caratelli, I. Caro Terrazas, F. Cavanna, G. Cerati, Y. Chen, E. Church, D. Cianci, J. M. Conrad, M. Convery, L. Cooper-Troendle, J. I. Crespo-Anadón, M. Del Tutto, S. R. Dennis, P. Detje, Ann Devitt, R. Diurba, R. Dorrill, K. Duffy, S. Dytman, B. Eberly, A. Ereditato, J. J. Evans, R. Fine, G. A. Fiorentini Aguirre, R. S. Fitzpatrick, B. T. Fleming, N. Foppiani, D. Franco, A. P. Furmanski, D. Garcia-Gamez, S. Gardiner, G. Ge, S. Gollapinni, O. Goodwin, E. Gramellini, P. Green, H. Greenlee, W J Gu, R. Guenette, P. Guzowski, L. Hagaman, O. Hen, C. Hilgenberg, G. A. Horton-Smith, A. Hourlier, R. Itay, C. James, X. Ji, L. Jiang, J. H. Jo, Rob Johnson, Y.-j. Jwa, D. Kalra, N. Kamp, N. Kaneshige, G. Karagiorgi, W. Ketchum, Mike Kirby, T. Kobilarcik, I. Kreslo, I. Lepetic, J.-y. Li, Keke Li, Y. Li, K. Lin, B. R. Littlejohn, W. C. Louis, X. Luo, K. Manivannan, C. Mariani, D. Marsden, J. Marshall, D. A. Martínez Caicedo, K. Mason, A. Mastbaum, N. McConkey, V. C. N. Meddage, T. MettlerJournal of Instrumentation 2022 · DOI

TL;DR

This paper introduces sMask-RCNN, a modified Mask R-CNN network optimized for speed on CPUs by using sparse convolutions. It effectively clusters cosmic ray muons in the MicroBooNE liquid argon time projection chamber, significantly improving the ability to reject background events and enhance the purity of electron neutrino signals.

What Problem Does This Paper Address?

The MicroBooNE experiment, designed to study neutrinos, operates a large liquid argon time projection chamber (LArTPC) without significant overhead shielding. This leads to a high rate of cosmic ray muons interacting within the detector, which can be mistaken for neutrino interactions. Effectively distinguishing between these signals is crucial for accurate neutrino physics measurements. Traditional methods and even standard deep learning approaches can be computationally intensive, posing a challenge for processing the vast amount of data generated by MicroBooNE, especially when relying on CPU farms rather than GPUs.

Methods

The core of this work is the development of sMask-RCNN, a sparse implementation of the Mask R-CNN object detection and segmentation network. The key innovation lies in replacing the standard convolutional layers in the ResNet backbone with sparse submanifold convolutions. This technique significantly speeds up processing on sparse data (like the MicroBooNE wire readout images, where only a small fraction of pixels have signal) by avoiding computations on zero-valued pixels. This optimization is crucial for enabling the network to run efficiently on CPUs, which are more readily available in large-scale computing facilities like FermiGrid. The sMask-RCNN network takes 2D wire readout images as input and outputs individually labeled particle interactions, classifying them as either cosmic ray muons or electron neutrinos.

Datasets

The study utilizes:

  • Simulated MicroBooNE data: This includes simulated electron neutrino interactions and simulated cosmic ray muons (generated using CORSIKA).
  • Real MicroBooNE data: This includes off-beam data (cosmic ray-only background) and on-beam data (containing both neutrinos and cosmic rays).

The training data for the dense Mask-RCNN included various interaction classes, while the sparse Mask-RCNN was trained specifically on cosmic ray muons and electron neutrino interactions. Performance evaluations were conducted on a validation set of 9400 full-sized images.

Key Insights and Ideas

  • Sparse convolutions are key for CPU-based deep learning: The paper strongly demonstrates that sparse submanifold convolutions are essential for making complex deep learning models like Mask R-CNN computationally feasible on CPUs for large-scale physics experiments. This opens up possibilities for deploying advanced AI techniques where GPU resources are limited.
  • Cosmic ray identification is a critical first step: The effectiveness of sMask-RCNN in identifying and vetoing cosmic ray-only events highlights the importance of robust background rejection early in the reconstruction chain. This significantly improves the purity of the desired neutrino signal.
  • "Identification by negative" is more effective for background veto: The study found that using sMask-RCNN to identify and remove cosmic ray events (an "identification by negative" approach) is more effective than trying to directly identify neutrino events ("identification by positive"). This is attributed to the more consistent topology of cosmic ray muons compared to the diverse final states of electron neutrino interactions.
  • Combining sMask-RCNN with existing tools yields state-of-the-art results: Integrating sMask-RCNN's cosmic tagging capabilities with the existing Wire-Cell cosmic tagger significantly enhances background rejection, demonstrating the synergistic benefits of combining different techniques.

Key Results

  • Speedup: sMask-RCNN achieves a 20x speedup in ResNet processing time on a CPU compared to the dense Mask-RCNN.
  • Pixel Clustering Efficiency: sMask-RCNN has an average pixel clustering efficiency of 85.9%, slightly lower than the dense network's 89.1%.
  • Cosmic-Only Event Veto: When combined with the Wire-Cell cosmic tagger, sMask-RCNN can remove 70% of the remaining cosmic ray muon background events at the same electron neutrino signal efficiency.
  • Improved Signal-to-Background Ratio: This event veto strategy can provide 99.7% rejection of cosmic ray-only background events while maintaining an electron neutrino event-level signal efficiency of 80.1%. This improves the signal-to-background ratio from 1.26 to 4.14 for general electron neutrino events.

Limitations and Future Work

  • Dense vs. Sparse Performance: While sMask-RCNN offers significant speed advantages, the dense implementation generally shows slightly better performance in terms of efficiency and purity metrics. The paper notes that it's difficult to definitively attribute this difference solely to the sparse convolutions versus other training differences (e.g., training on crops vs. full images).
  • Unresponsive Wire Regions: The network struggles with interactions that fall in regions of unresponsive wires in the LArTPC, leading to zero efficiency. This is an inherent limitation of the detector geometry and data acquisition.
  • Small/Low-Charge Interactions: Visually small interactions or those with less deposited charge can also lead to lower efficiency, as they are harder for the network to detect and cluster.
  • Future Work: The authors suggest that sMask-RCNN could be extended to identify other particle interaction types in 3D-tracking detectors. Further improvements could involve increasing the required confidence score for neutrino classification or retraining the network with adjusted penalties. The study also highlights the potential for further optimization by applying sparse convolutions to later stages of the network.

Summary updated

Abstract

Abstract In this article, we describe a modified implementation of Mask Region-based Convolutional Neural Networks (Mask-RCNN) for cosmic ray muon clustering in a liquid argon TPC and applied to MicroBooNE neutrino data. Our implementation of this network, called sMask-RCNN, uses sparse submanifold convolutions to increase processing speed on sparse datasets, and is compared to the original dense version in several metrics. The networks are trained to use wire readout images from the MicroBooNE liquid argon time projection chamber as input and produce individually labeled particle interactions within the image. These outputs are identified as either cosmic ray muon or electron neutrino interactions. We find that sMask-RCNN has an average pixel clustering efficiency of 85.9% compared to the dense network's average pixel clustering efficiency of 89.1%. We demonstrate the ability of sMask-RCNN used in conjunction with MicroBooNE's state-of-the-art Wire-Cell cosmic tagger to veto events containing only cosmic ray muons. The addition of sMask-RCNN to the Wire-Cell cosmic tagger removes 70% of the remaining cosmic ray muon background events at the same electron neutrino event signal efficiency. This event veto can provide 99.7% rejection of cosmic ray-only background events while maintaining an electron neutrino event-level signal efficiency of 80.1%. In addition to cosmic ray muon identification, sMask-RCNN could be used to extract features and identify different particle interaction types in other 3D-tracking detectors.
BibTeX
@article{abratenko2022cosmic,
  author = {P. Abratenko and R. An and J. Anthony and L. Arellano and J. Asaadi and A. Ashkenazi and S. Balasubramanian and B. Baller and C. Barnes and G. Barr and J. Barrow and V. Basque and L. Bathe-Peters and O. Benevides Rodrigues and S. Berkman and A. Bhanderi and A. Bhat and M. Bishai and A. Blake and T. Bolton and Julia Book and L. Camilleri and D. Caratelli and I. Caro Terrazas and F. Cavanna and G. Cerati and Y. Chen and E. Church and D. Cianci and J. M. Conrad and M. Convery and L. Cooper-Troendle and J. I. Crespo-Anadón and M. Del Tutto and S. R. Dennis and P. Detje and Ann Devitt and R. Diurba and R. Dorrill and K. Duffy and S. Dytman and B. Eberly and A. Ereditato and J. J. Evans and R. Fine and G. A. Fiorentini Aguirre and R. S. Fitzpatrick and B. T. Fleming and N. Foppiani and D. Franco and A. P. Furmanski and D. Garcia-Gamez and S. Gardiner and G. Ge and S. Gollapinni and O. Goodwin and E. Gramellini and P. Green and H. Greenlee and W J Gu and R. Guenette and P. Guzowski and L. Hagaman and O. Hen and C. Hilgenberg and G. A. Horton-Smith and A. Hourlier and R. Itay and C. James and X. Ji and L. Jiang and J. H. Jo and Rob Johnson and Y.-J. Jwa and D. Kalra and N. Kamp and N. Kaneshige and G. Karagiorgi and W. Ketchum and Mike Kirby and T. Kobilarcik and I. Kreslo and I. Lepetic and J.-Y. Li and Keke Li and Y. Li and K. Lin and B. R. Littlejohn and W. C. Louis and X. Luo and K. Manivannan and C. Mariani and D. Marsden and J. Marshall and D. A. Martínez Caicedo and K. Mason and A. Mastbaum and N. McConkey and V. C. N. Meddage and T. Mettler},
  title = {{Cosmic ray muon clustering for the MicroBooNE liquid argon time projection chamber using sMask-RCNN}},
  journal = {Journal of Instrumentation},
  year = {2022},
  doi = {10.1088/1748-0221/17/09/p09015},
}
Figure