Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Detector network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

High-dimensional anomaly detection with radiative return in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions

Experiments at a future $\mathcal{e}$⁺$\mathcal{e}$⁻ collider will be able to search for new particles with masses below the nominal centre-of-mass energy by analyzing collisions with initial-state radiation (radiative return). We show that machine learning methods that use imperfect or missing training labels can achieve sensitivity to generic new particle production in radiative return events. In addition to presenting an application of the classification without labels (CWoLa) search method in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions, our study combines weak supervision with variable-dimensional information by deploying a deep sets neural network architecture. We have also investigated some of the experimental aspects of anomaly detection in radiative return events and discuss these in the context of future detector design.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Differentiable vertex fitting for jet flavor tagging

This work explores the use of differentiable programming to integrate domain knowledge, in the form of domain specific software, into neural networks to develop scientific machine learning systems. We propose a differentiable vertex fitting algorithm that estimates the crossing point of multiple curves. In the high energy physics setting, these curves are defined by particle equations of motion and the crossing point represents the origin of particle production. This differentiable vertex fitting algorithm can be seamlessly integrated into neural networks, and we show its utility and efficacy in the high energy physics application of the classification of jets, i.e., collimated streams of particles in particle detectors whose originating parent particle we aim to classify. We demonstrate how differentiable vertex fitting can be integrated into larger transformer-based models for jet flavor tagging and show improvements in heavy flavor jet classification when compared to baseline models. Published by the American Physical Society 2024

Smith, Rachel E. C. (ORCID:0000000335851262)↗
DOE OSTI2021

Stabilization of the 81-channel coherent beam combination using machine learning

We develop a rapidly converging algorithm for stabilizing a large channel-count diffractive optical coherent beam combination. An 81-beam combiner is controlled by a novel, machine-learning based, iterative method to correct the optical phases, operating on an experimentally calibrated numerical model. A neural-network is trained to detect phase errors based on interference pattern recognition of uncombined beams adjacent to the combined one. Due to the non-uniqueness of solutions in the full space of possible phases, the network is trained within a limited phase perturbation/error range. This also reduces the number of samples needed for training. Simulations have proven that the network can converge in one step for small phase perturbations. When the trained neural-network is applied to a realistic case of 360 degree full range, an iterative scheme exploits random walking at the beginning, with the accuracy of prediction on phase feedback direction, to allow the neural-network to step into the training range for fast convergence. This neural-network-based iterative method of phase detection works tens of times faster than the commonly used stochastic parallel gradient descent approach (SPGD) using a single-detector and random dither when both are tested with random phase perturbations.

Wang, Dan↗
DOE OSTI2026

DUNE: Michel Electron Selection with SPINE

This poster details the evaluation of a Michel electron selection algorithm centered on the neural network-based software SPINE (Scalable Particle Imageing with Neural Embeddings). The algorithm was developed and calibrated using simulated data from the SBND (Short-Baseline Neutrino Detector) experiment before being applied to simulated data from DUNE (Deep Underground Neutrino Experiment).

Wilson, Dante [U. Colorado, Boulder]↗
DOE OSTI2023

Fast and accurate simulations of calorimeter showers with normalizing flows

In this study, we introduce caloflow, a fast detector simulation framework based on normalizing flows. For the first time, we demonstrate that normalizing flows can reproduce many-channel calorimeter showers with extremely high fidelity, providing a fresh alternative to computationally expensive geant4 simulations, as well as other state-of-the-art fast simulation frameworks based on generative adversarial networks (GANs) or variational autoencoders (VAEs). In addition to the usual histograms of physical features and images of calorimeter showers, we introduce a new metric for judging the quality of generative modeling: the performance of a classifier trained to differentiate real from generated images. We show that GAN-generated images can be identified by the classifier with nearly 100% accuracy, while images generated from caloflow are better able to fool the classifier. More broadly, normalizing flows offer several advantages compared to other state-of-the-art approaches (GANs and VAEs), including tractable likelihoods, stable and convergent training, and principled model selection. Normalizing flows also provide a bijective mapping between data and the latent space, which could have other applications beyond simulation, for example, to detector unfolding.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Persistent, “Mysterious” Seismoacoustic Signals Reported in Oklahoma State during 2019

Here, we report on the source of seismoacoustic pulses that were observed across the state of Oklahoma (OK) during summer of 2019, and the subject of national media coverage and speculation. Seismic network data collected across four U.S. states and interviews with witnesses to the pulse’s effect on residential structures demonstrate that they were triggered by routine ammunition disposal operations conducted by McAlester Army Ammunition Plant (McAAP). During these operations, conventional explosives destroy obsolete munitions stored in pits through a controlled sequence of electronically timed shots that occur over tens of minutes. Despite noise-abatement efforts that reduce coupling of acoustic energy with air, some lower frequency, subaudible (infrasonic) sound radiates from these shots as discrete pulses. We use nine months of blast log documents, seismic network records, analyst picks, and physical modeling to demonstrate that seismic stations as far as 640 km from McAAP sample these pulses, which record seasonal patterns in stratospheric and tropospheric winds, as well as the dynamic formation of waveguides and shadow zones. Digital short-term average to long-term average detectors that we augment with dynamic thresholds and time-binning operations identify these pulses with a fair probability, when compared with visual observations. Our analyses thereby provide estimates of observation rates for both partial and full sequences of these pulses, as well as single shots. We suggest that disposal operations can exploit existing, composite seismic networks to predict where residents are likely to witness blasting. Crucially, our data also show that dense seismic networks can record multiscale atmospheric processes in the absence of infrasound arrays.

58 GEOSCIENCES↗
DOE OSTI2024

Search for a resonance decaying into a scalar particle and a Higgs boson in the final state with two bottom quarks and two photons in proton–proton collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

A search for the resonant production of a heavy scalar X decaying into a Higgs boson and a new lighter scalar S, through the process X → S(→ $b\overline{b}$)H(→γγ), where the two photons are consistent with the Higgs boson decay, is performed. The search is conducted using an integrated luminosity of 140 fb -1 of proton-proton collision data at a centre-of-mass energy of 13 TeV recorded with the ATLAS detector at the Large Hadron Collider. The search is performed over the mass range 170 ≤ m X ≤ 1000 GeV and 15 ≤ m S ≤ 500 GeV. Parameterised neural networks are used to enhance the signal purity and to achieve continuous sensitivity in a domain of the (m X , m S ) plane. No significant excess above the expected background is found and 95% CL upper limits are set on the cross section times branching ratio, ranging from 39 fb to 0.09 fb. The largest deviation from the background-only expectation occurs for (m X , m S ) = (575, 200) GeV with a local (global) significance of 3.5 (2.0) standard deviations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Demonstration of Algorithm for Sensor Placement Optimization using Simulation Data

This deliverable reports FY26 progress in advancing a neural-network-based Green’s-function framework for reconstructing neutron-flux distributions from ex-core measurements and for translating reconstruction requirements into a practical detector-layout strategy. Building on the FY25 formulation, the present work had two main objectives: (1) refine and re-evaluate the reconstruction methodology on an updated Purdue University Reactor Number One (PUR-1) model, and (2) develop a systematic, Green’s-function-guided procedure for boundary detector placement.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Advancing Artificial Intelligence with Liquid Argon Neutrino Experiments (Technical Report)

The grant allowed two main contributions: 1) The development of a first successful demonstration of the employment of Optimal Transport in liquid argon time projection chamber neutrino detectors. Optimal Transport, used in other contexts and specifically with LHC calorimetric data, was adapted to address a key particle identification challenge in LArTPCs: the separation of pi0 backgrounds from single-electrons produced in charged-current electron neutrino interactions. The work, leveraging ML methods such as k-nearest-neighbor (kNN) and support-vector-machine (SVM), showed an increase in background rejection of a factor of two or more. Work is now ongoing to incorporate this development in physics analyses for LArTPC experiments and more broadly expand the use of OT in LArTPC detectors including DUNE. This work was done in collaboration with the phenomenology group led by Nathaniel Craig at UCSB. 2) The deployment of NuGraph2, a graph neural network developed for LArTPC reconstruction, in the MicroBooNE experiment. NuGraph2 uses novel graph-neural-network methods on the rather simple LArTPC inputs of reconstructed hits, greatly simplifying the workflow compared to the use of waveform or signal-deconvolved wire ROIs. The network performed particle classification and was shown to address many challenging problems in LArTPC imaging including track-shower separation and the identification of protons and charged pions from primary muons. Our group collaborated with Giuseppe Cerati (FNAL scientist) who is one of the core developers of NuGraph2 to integrate this tool in MicroBooNE’s analysis framework. This consisted in tow key contributions: a) Studying performance on real data, which came with several months of iterations because the MC-trained version of the network was found to show significant bias that our group investigated and addressed. b) Integrating the output hit labeling of NuGraph2 into the existing particle tracking and shower reconstruction code. As a result of this work led by our team NuGraph2 is now enabling a suite of new analyses which benefit from enhanced capabilities and thus broader physics reach. The grant supported primarily the salary of UCSB graduate student Chuyue “Michaelia” Fang as well as partial summer salary support for PI Caratelli. Some funds were used for travel by Michaelia to ML related schools and conferences.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Measurement Of The Total Cross-Section Of Muon Neutrino Charged-Current Coherent Pion Production in NOvA Near Detector

Charged Current (CC) coherent neutrino-nucleus pion production is characterized by small momentum transferred to the nucleus, which is left in its ground state. Despite the relatively large uncertainties on the production cross-section, coherent production of mesons by neutrinos represents an important process, as it can shed light on the structure of the weak current and can also constitute a potential source of background for modern neutrino oscillation experiments and searches for Beyond Standard Model (BSM) physics. This Ph.D. thesis presents a new measurement of CC coherent pion production in the NOvA near detector at the Fermi National Accelerator Laboratory (Fermilab). The analysis is based on the use of both particle identification and kinematic selection criteria based on Convolutional Neural Networks (CNN) to achieve a selection purity of 60%. Given the energy range 1-5 GeV accessible with the available NOvA exposure in the NuMI beam, the results will also be relevant for f uture neutrino experiments like the Deep Underground Neutrino Experiment (DUNE).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Search for a light charged Higgs boson in t → H±b decays, with H± → cb, in the lepton+jets final state in proton-proton collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

A search for a charged Higgs boson, H ± , produced in top-quark decays, t → H ± b, is presented. The search targets H ± decays into a bottom and a charm quark, H ± → cb. The analysis focuses on a selection enriched in top-quark pair production, where one top quark decays into a leptonically decaying W boson and a bottom quark, and the other top quark decays into a charged Higgs boson and a bottom quark. This topology leads to a lepton-plus-jets final state, characterised by an isolated electron or muon and at least four jets. The search exploits the high multiplicity of jets containing b-hadrons, and deploys a neural network classifier that uses the kinematic differences between the signal and the background. The search uses a dataset of proton-proton collisions collected at a centre-of-mass energy $\sqrt{s}$ = 13 TeV between 2015 and 2018 with the ATLAS detector at CERN’s Large Hadron Collider, amounting to an integrated luminosity of 139 fb -1 . Observed (expected) 95% confidence-level upper limits between 0.15% (0.09%) and 0.42% (0.25%) are derived for the product of branching fractions $\mathscr{B}$ (t → H ± b) × $\mathscr{B}$(H ± → cb) for charged Higgs boson masses between 60 and 160 GeV, assuming the SM production of the top-quark pairs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Demonstration of event position reconstruction based on diffusion in the NEXT-white detector

Noble element time projection chambers are a leading technology for rare event detection in physics, such as for dark matter and neutrinoless double beta decay searches. Time projection chambers typically assign event position in the drift direction using the relative timing of prompt scintillation and delayed charge collection signals, allowing for reconstruction of an absolute position in the drift direction. In this paper, alternate methods for assigning event drift dis tance via quantification of electron diffusion in a pure high pressure xenon gas time projection chamber are explored. Data from the NEXT-White detector demonstrate the ability to achieve good position assignment accuracy for both high and low-energy events. Using point-like energy deposits from 83m Kr calibration electron captures (E ~ 45 keV), the position of origin of low-energy events is determined to 2 cm precision with bias < 1 mm. A convolutional neural network approach is then used to quantify diffusion for longer tracks (E ≥ 1.5 MeV), from radiogenic electrons, yielding a precision of 3 cm on the event barycenter. The precision achieved with these methods indicates the feasibility energy calibrations of better than 1% FWHM at Q ββ in pure xenon, as well as the potential for event fiducialization in large future detectors using an alternate method that does not rely on primary scintillation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Detection of the Large Surface Explosion Coupling Experiment by a Sparse Network of Balloon-Borne Infrasound Sensors

In recent years, high-altitude infrasound sensing has become more prolific, demonstrating an enormous value especially when utilized over regions inaccessible to traditional ground-based sensing. Similar to ground-based infrasound detectors, airborne sensors take advantage of the fact that impulsive atmospheric events such as explosions can generate low frequency acoustic waves, also known as infrasound. Due to negligible attenuation, infrasonic waves can travel over long distances, and provide important clues about their source. Here, we report infrasound detections of the Apollo detonation that was carried on 29 October 2020 as part of the Large Surface Explosion Coupling Experiment in Nevada, USA. Infrasound sensors attached to solar hot air balloons floating in the stratosphere detected the signals generated by the explosion at distances 170–210 km. Three distinct arrival phases seen in the signals are indicative of multipathing caused by the small-scale perturbations in the atmosphere. We also found that the local acoustic environment at these altitudes is more complex than previously thought.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Improvement of the NOvA Near Detector Event Reconstruction and Primary Vertexing through the Application of Machine Learning Methods

The purpose of this work is to examine the application of a deep learning model in event reconstruction of neutrino interactions. The challenges faced in event reconstruction include the placement of an accurate primary neutrino interaction vertex which is used to support the particle track and prong algorithms. The result of accurate primary vertex ensures all particles involved in a neutrino interaction are included. We propose a regression-based Convolutional Neural Network (CNN) method to predict the primary vertex of a particle interaction. We show that with raw two-dimensional pixel map views as input, the regression-based CNN can predict the primary vertex in all three coordinates. This work is applied as part of the NOvA (NuMI Off-axis $\nu_e$ Appearance) near detector reconstruction efforts. The primary vertex predicted by the regression-based CNN model shows promising results for future applications. This deep learning method can be extended to secondary vertexing through a Kernel Density Estimate algorithm discussed in this work.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

First measurement of neutron capture multiplicity in neutrino-oxygen neutral-current quasielasticlike interactions using an accelerator neutrino beam

We report the first measurement of neutron capture multiplicity in neutrino-oxygen neutral-current quasielasticlike interactions at the gadolinium-loaded Super-Kamiokande detector using the T2K neutrino beam, which has a peak energy of about 0.6 GeV. A total of 30 neutral-current quasielasticlike event candidates were selected from T2K data corresponding to an exposure of 1.76 × 10 20 protons on target. The 𝛾 ray signals resulting from neutron captures were identified using a neural network. The flux-averaged mean neutron capture multiplicity was measured to be 1.37 ± 0.33 (stat.)$^{+0.17}_{−0.27}$ (syst.), which is compatible within 2.3 sigma than predictions obtained using our nominal simulation. We discuss potential sources of systematic uncertainty in the prediction and demonstrate that a significant portion of this discrepancy arises from the modeling of hadron-nucleus interactions in the detector medium.

particle interactions↗
DOE OSTI2023

Differentiable Earth mover’s distance for data compression at the high-luminosity LHC

Abstract The Earth mover’s distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent. In this paper, we train a convolutional neural network (CNN) to learn a differentiable, fast approximation of the EMD and demonstrate that it can be used as a substitute for computing-intensive EMD implementations. We apply this differentiable approximation in the training of an autoencoder-inspired neural network (encoder NN) for data compression at the high-luminosity LHC at CERN The goal of this encoder NN is to compress the data while preserving the information related to the distribution of energy deposits in particle detectors. We demonstrate that the performance of our encoder NN trained using the differentiable EMD CNN surpasses that of training with loss functions based on mean squared error.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

O'Hare Airport roadway traffic prediction via data fusion and Gaussian process regression

This study proposes an approach of leveraging information gathered from multiple traffic data sources at different resolutions to obtain approximate inference on the traffic distribution of Chicago's O'Hare Airport area. Specifically, it proposes the ingestion of traffic datasets at different resolutions to build spatiotemporal models for predicting the distribution of traffic volume on the road network. Due to its good adaptability and flexibility for spatiotemporal data, the Gaussian process (GP) regression was employed to provide short-term forecasts using data collected by loop detectors (sensors) and supplemented by telematics data. The GP regression is used to make predictions of the distribution of the proportion of sensor data traffic volume represented by the telematics data for each location of the sensors. Consequently, the fitted GP model can be used to determine the approximate traffic distribution for a testing location outside of the training points. Policymakers in the transportation sector can find the results of this work helpful for making informed decisions relating to current and future transportation conditions in the area.

42 ENGINEERING↗