Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSemantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE
158
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino properties and interactions. SparseSSNet is a submanifold sparse convolutional neural network, which provides the initial machine learning based algorithm utilized in one of MicroBooNEs $ u_e$-appearance oscillation analyses. The network is trained to categorize pixels into five classes, which are re-classified into two classes more relevant to the current analysis. The output of SparseSSNet is a key input in further analysis steps. This technique, used for the first time in liquid argon time projection chambers data and is an improvement compared to a previously used convolutional neural network, both in accuracy and computing resource utilization. The accuracy achieved on the test sample is $geq 99%$. For full neutrino interaction simulations, the time for processing one image is $approx$ 0.5 sec, the memory usage is at 1 GB level, which allows utilization of most typical CPU worker machine.
rate research
Read More
For a large liquid argon time projection chamber (LArTPC) operating on or near the Earths surface to detect neutrino interactions, the rejection of cosmogenic background is a critical and challenging task because of the large cosmic ray flux and the long drift time of the TPC. We introduce a superior cosmic background rejection procedure based on the Wire-Cell three-dimensional (3D) event reconstruction for LArTPCs. From an initial 1:20,000 neutrino to cosmic-ray background ratio, we demonstrate these tools on data from the MicroBooNE experiment and create a high performance generic neutrino event selection with a cosmic contamination of 14.9% (9.7%) for a visible energy region greater than O(200)~MeV. The neutrino interaction selection efficiency is 80.4% and 87.6% for inclusive $ u_mu$ charged-current and $ u_e$ charged-current interactions, respectively. This significantly improved performance compared to existing reconstruction algorithms, marks a major milestone toward reaching the scientific goals of LArTPC neutrino oscillation experiments operating near the Earths surface.
The Jiangmen Underground Neutrino Observatory (JUNO) is designed to determine the neutrino mass ordering and measure neutrino oscillation parameters. A precise muon reconstruction is crucial to reduce one of the major backgrounds induced by cosmic muons. This article proposes a novel muon reconstruction method based on convolutional neural network (CNN) models. In this method, the track information reconstructed by the top tracker is used for network training. The training dataset is augmented by applying a rotation to muon tracks to compensate for the limited angular coverage of the top tracker. The muon reconstruction with the CNN model can produce unbiased tracks with performance that spatial resolution is better than 10 cm and angular resolution is better than 0.6 degrees. By using a GPU accelerated implementation a speedup factor of 100 compared to existing CPU techniques has been demonstrated.
It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance information of images, which put limit on their generality and robustness for various application scenes. In this paper, we proposed a novel strategy that reformulated the popularly-used convolution operation to multi-layer convolutional sparse coding block to ease the aforementioned deficiency. This strategy can be possibly used to significantly improve the segmentation performance of any semantic segmentation model that involves convolutional operations. To prove the effectiveness of our idea, we chose the widely-used U-Net model for the demonstration purpose, and we designed CSC-Unet model series based on U-Net. Through extensive analysis and experiments, we provided credible evidence showing that the multi-layer convolutional sparse coding block enables semantic segmentation model to converge faster, can extract finer semantic and appearance information of images, and improve the ability to recover spatial detail information. The best CSC-Unet model significantly outperforms the results of the original U-Net on three public datasets with different scenarios, i.e., 87.14% vs. 84.71% on DeepCrack dataset, 68.91% vs. 67.09% on Nuclei dataset, and 53.68% vs. 48.82% on CamVid dataset, respectively.
The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects.
The liquid argon ionization current in a sampling calorimeter cell can be analyzed to determine the energy of detected particles. In practice, experimental artifacts such as pileup and electronic noise make the inference of energy from current a difficult process. The beam intensity of the Large Hadron Collider will be significantly increased during the Phase-II long shut down of 2024-2026. Signal processing techniques that are used to extract the energy of detected particles in the ATLAS detector will suffer a significant loss in performance under these conditions. This paper compares the presently used optimal filter technique to convolutional neural networks for energy reconstruction in the ATLAS liquid argon hadronic end cap calorimeter. In particular, it is shown that convolutional neural networks trained with an appropriately tuned and novel loss function are able to outperform the optimal filter technique.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
