Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTrack Seed Classification with Deep Neural Networks
88
0
0.0
(
0
)
Authors
Felix Dietrich
Ask ChatGPT about the research
No Arabic abstract
Future upgrades to the LHC will pose considerable challenges for traditional particle track reconstruction methods. We investigate how artificial Neural Networks and Deep Learning could be used to complement existing algorithms to increase performance. Generating seeds of detector hits is an important phase during the beginning of track reconstruction and improving the current heuristics of seed generation seems like a feasible task. We find that given sufficient training data, a comparatively compact, standard feed-forward neural network can be trained to classify seeds with great accuracy and at high speeds. Thanks to immense parallelization benefits, it might even be worthwhile to completely replace the seed generation process with the Neural Network instead of just improving the seed quality of existing generators.
rate research
Read More
Nowadays the implementation of artificial neural networks in high-energy physics has obtained excellent results on improving signal detection. In this work we propose to use neural networks (NNs) for event discrimination in HAWC. This observatory is a water Cherenkov gamma-ray detector that in recent years has implemented algorithms to identify horizontal muon tracks. However, these algorithms are not very efficient. In this work we describe the implementation of three NNs: two based on image classification and one based on object detection. Using these algorithms we obtain an increase in the number of identified tracks. The results of this study could be used in the future to improve the performance of the Earth-skimming technique for the indirect measurement of neutrinos with HAWC.
We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.
To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promising of these solutions, graph neural networks (GNN), process the event as a graph that connects track measurements (detector hits corresponding to nodes) with candidate line segments between the hits (corresponding to edges). Detector information can be associated with nodes and edges, enabling a GNN to propagate the embedded parameters around the graph and predict node-, edge- and graph-level observables. Previously, message-passing GNNs have shown success in predicting doublet likelihood, and we here report updates on the state-of-the-art architectures for this task. In addition, the Exa.TrkX project has investigated innovations in both graph construction, and embedded representations, in an effort to achieve fully learned end-to-end track finding. Hence, we present a suite of extensions to the original model, with encouraging results for hitgraph classification. In addition, we explore increased performance by constructing graphs from learned representations which contain non-linear metric structure, allowing for efficient clustering and neighborhood queries of data points. We demonstrate how this framework fits in with both traditional clustering pipelines, and GNN approaches. The embedded graphs feed into high-accuracy doublet and triplet classifiers, or can be used as an end-to-end track classifier by clustering in an embedded space. A set of post-processing methods improve performance with knowledge of the detector physics. Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.
We apply deep neural networks (DNN) to data from the EXO-200 experiment. In the studied cases, the DNN is able to reconstruct the relevant parameters - total energy and position - directly from raw digitized waveforms, with minimal exceptions. For the first time, the developed algorithms are evaluated on real detector calibration data. The accuracy of reconstruction either reaches or exceeds what was achieved by the conventional approaches developed by EXO-200 over the course of the experiment. Most existing DNN approaches to event reconstruction and classification in particle physics are trained on Monte Carlo simulated events. Such algorithms are inherently limited by the accuracy of the simulation. We describe a unique approach that, in an experiment such as EXO-200, allows to successfully perform certain reconstruction and analysis tasks by training the network on waveforms from experimental data, either reducing or eliminating the reliance on the Monte Carlo.
The MicroBooNE liquid argon time projection chamber located at Fermilab is a neutrino experiment dedicated to the study of short-baseline oscillations, the measurements of neutrino cross sections in liquid argon, and to the research and development of this novel detector technology. Accurate and precise measurements of calorimetry are essential to the event reconstruction and are achieved by leveraging the TPC to measure deposited energy per unit length along the particle trajectory, with mm resolution. We describe the non-uniform calorimetric reconstruction performance in the detector, showing dependence on the angle of the particle trajectory. Such non-uniform reconstruction directly affects the performance of the particle identification algorithms which infer particle type from calorimetric measurements. This work presents a new particle identification method which accounts for and effectively addresses such non-uniformity. The newly developed method shows improved performance compared to previous algorithms, illustrated by a 94% proton selection efficiency and a 10% muon mis-identification rate, with a fairly loose selection of tracks performed on beam data. The performance is further demonstrated by identifying exclusive final states in $ u_{mu} CC$ interactions. While developed using MicroBooNE data and simulation, this method is easily applicable to future LArTPC experiments, such as SBND, ICARUS, and DUNE.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
