Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Convolution”

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 1,387 records · Page 77
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Analysis and mitigation of parasitic resistance effects for analog in-memory neural network acceleration

To support the increasing demands for efficient deep neural network processing, accelerators based on analog in-memory computation of matrix multiplication have recently gained significant attention for reducing the energy of neural network inference. However, analog processing within memory arrays must contend with the issue of parasitic voltage drops across the metal interconnects, which distort the results of the computation and limit the array size. This work analyzes how parasitic resistance affects the end-to-end inference accuracy of state-of-the-art convolutional neural networks, and comprehensively studies how various design decisions at the device, circuit, architecture, and algorithm levels affect the system's sensitivity to parasitic resistance effects. Here, a set of guidelines are provided for how to design analog accelerator hardware that is intrinsically robust to parasitic resistance, without any explicit compensation or re-training of the network parameters.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Femtosecond pulse parameter estimation from photoelectron momenta using machine learning

Abstract Deep learning models have provided huge interpretation power for image-like data. Specifically, convolutional neural networks (CNNs) have demonstrated incredible acuity for tasks such as feature extraction or parameter estimation. Here we test CNNs on strong-field ionization photoelectron spectra, training on theoretical data sets to ‘invert’ experimental data. Pulse characterization is used as a ‘testing ground’, specifically we retrieve the laser intensity, where ‘traditional’ measurements typically lead to 20% uncertainty. We report on crucial data augmentation techniques required to successfully train on theoretical data and return consistent results from experiments, including accounting for detector saturation. The same procedure can be repeated to apply CNNs in a range of scenarios for strong-field ionization. Using a predictive uncertainty estimation, reliable laser intensity uncertainties of a few percent can be extracted, which are consistently lower than those given by traditional techniques. Using interpretability methods can reveal parts of the distribution that are most sensitive to laser intensity, which can be directly associated with holographic interferences. The CNNs employed provide an accurate and convenient ways to extract parameters, and represent a novel interpretational tool for strong-field ionization spectra.

Szołdra, Tomasz (ORCID:0000000228970506)↗
DOE OSTI2020

An accurate perturbative approach to redshift space clustering of biased tracers in modified gravity

We extend the scale-dependent Gaussian Streaming Model (GSM) to produce analytical predictions for the anisotropic redshift-space correlation function for biased tracers in modified gravity models. Employing the Convolution Lagrangian Perturbation Theory (CLPT) re-summation scheme, with a local Lagrangian bias schema provided by the peak-background split formalism, we predict the necessary ingredients that enter the GSM, the real-space halo pairwise velocity and the pairwise velocity dispersion. We further consider effective field theory contributions to the pairwise velocity dispersion in order to model correctly its large scale behavior. We apply our method on two widely-considered modified gravity models, the chameleon-screened ƒ(R) Hu-Sawicki model and the nDGP Vainshtein model and compare our predictions against state-of-the-art N-body simulations for these models. We demonstrate that the GSM approach to predict the monopole and the quadrupole of the redshift-space correlation function for halos, gives very good agreement with the simulation data, for a wide range of screening mechanisms, levels of screening and halo masses at z = 0.5 and z = 1. Our work shows the applicability of the GSM, for cosmologies beyond GR, demonstrating that it can serve as a powerful predictive tool for the next stage of cosmological surveys like DESI, Euclid, LSST and WFIRST.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Reconstructing cosmic polarization rotation with ResUNet-CMB

Cosmic polarization rotation, which may result from parity-violating new physics or the presence of primordial magnetic fields, converts E-mode polarization of the cosmic microwave background (CMB) into B-mode polarization. Anisotropic cosmic polarization rotation leads to statistical anisotropy in CMB polarization and can be reconstructed with quadratic estimator techniques similar to those designed for gravitational lensing of the CMB. At the sensitivity of upcoming CMB surveys, lensing-induced B-mode polarization will act as a limiting factor in the search for anisotropic cosmic polarization rotation, meaning that an analysis which incorporates some form of delensing will be required to improve constraints on the effect with future surveys. In this study we extend the ResUNet-CMB convolutional neural network to reconstruct anisotropic cosmic polarization rotation in the presence of gravitational lensing and patchy reionization, and we show that the network simultaneously reconstructs all three effects with variance that is lower than that from the standard quadratic estimator nearly matching the performance of an iterative reconstruction method.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Mind the gap: the discrepancy between simulation and reality drives interpretations of the Galactic Center Excess

The Galactic Center Excess (GCE) in GeV gamma rays has been debated for over a decade, with the possibility that it might be due to dark matter annihilation or undetected point sources such as millisecond pulsars (MSPs). This study investigates how the gamma-ray emission model (γEM) used in Galactic center analyses affects the interpretation of the GCE's nature. To address this issue, we construct an ultra-fast and powerful inference pipeline based on convolutional Deep Ensemble Networks. We explore the two main competing hypotheses for the GCE using a set of γEMs with increasing parametric freedom. We calculate the fractional contribution (f src ) of a dim population of MSPs to the total luminosity of the GCE and analyze its dependence on the complexity of the γEM. For the simplest γEM, we obtain fsrc = 0.10 ± 0.07, while the most complex model yields f src = 0.79 ± 0.24. In conclusion, we find that the statement about the nature of the GCE (dark matter or not) strongly depends on the assumed γEM. The quoted results for f src do not account for the additional uncertainty arising from the fact that the observed gamma-ray sky is out-of-distribution concerning the investigated γEM iterations. We quantify the reality gap between our γEMs using deep-learning-based One-Class Deep Support Vector Data Description networks, revealing that all employed γEMs have gaps to reality. Finally, our study casts doubt on the validity of previous conclusions regarding the GCE and dark matter, and underscores the urgent need to account for the reality gap and consider previously overlooked "out of domain" uncertainties in future interpretations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning

We reconstruct the extra-galactic gamma-ray source-count distribution, or dN/dS, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the Fermi-LAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the (1,10) GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from cataloged sources, and then extends as dN/dS ~ S -2 in the unresolved regime, down to fluxes of 5 · 10 -12 cm -2 s -1 . The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Full Modeling and parameter compression methods in configuration space for DESI 2024 and beyond

In the contemporary era of high-precision spectroscopic surveys, led by projects like DESI, there is an increasing demand for optimizing the extraction of cosmological information from clustering data. This work conducts a thorough comparison of various methodologies for modeling the full shape of the two-point statistics in configuration space. We investigate the performance of both direct fits (Full Modeling) and the parameter compression approaches (ShapeFit and Standard). We utilize the ABACUS-SUMMIT simulations, tailored to exceed DESI's precision requirements. Particularly, we fit the two-point statistics of three distinct tracers (LRG, ELG, and QSO), by employing a Gaussian Streaming Model in tandem with Convolution Lagrangian Perturbation Theory and Effective Field Theory. We explore methodological setup variations, including the range of scales, the set of galaxy bias parameters, the inclusion of the hexadecapole, as well as model extensions encompassing varying ns and allowing for w 0 w a CDM dark energy model. Throughout these varied explorations, while precision levels fluctuate and certain configurations exhibit tighter parameter constraints, our pipeline consistently recovers the parameter values of the mocks within 1σ in all cases for a 1-year DESI volume. Additionally, we compare the performance of configuration space analysis with its Fourier space counterpart using three models: PyBird, FOLPS and velocileptors, presented in companion papers. We find good agreement with the results from all these models.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Massive νs through the CNN lens: interpreting the field-level neutrino mass information in weak lensing

Modern cosmological surveys probe the Universe deep into the nonlinear regime, where massive neutrinos suppress cosmic structure. Traditional cosmological analyses, which use the 2-point correlation function to extract information, are no longer optimal in the nonlinear regime, and there is thus much interest in extracting beyond-2-point information to improve constraints on neutrino mass. Quantifying and interpreting the beyond-2-point information is thus a pressing task. We study the field-level information in weak lensing convergence maps using convolution neural networks. We find that the network performance increases as higher source redshifts and smaller scales are considered — investigating up to a source redshift of 2.5 and ℓ max ≃ 10 4 — verifying that massive neutrinos leave a distinct effect on weak lensing. However, the performance of the network significantly drops after scaling out the 2-point information from the maps, implying that most of the field-level information can be found in the 2-point correlation function alone. We quantify these findings in terms of the likelihood ratio and also use Integrated Gradient saliency maps to interpret which parts of the map the network is learning the most from. We find that, in the absence of noise, the network extracts a similar amount of information from the most overdense and underdense regions. However, upon adding noise, the information in underdense regions is distorted as noise disproportionately washes out void-like structures.

Golshan, Malika [University of California, Berkele↗
DOE OSTI2025

Constraining primordial non-Gaussianity with DESI 2024 LRG and QSO samples

We analyse the large-scale clustering of the Luminous Red Galaxy (LRG) and Quasar (QSO) sample from the first data release (DR1) of the Dark Energy Spectroscopic Instrument (DESI). In particular, we constrain the primordial non-Gaussianity (PNG) parameter f NL loc via the large-scale scale-dependent bias in the power spectrum using 1,631,716 LRGs (0.6 < z < 1.1) and 1,189,129 QSOs (0.8 < z < 3.1). This new measurement takes advantage of the enormous statistical power at large scales of DESI DR1 data, surpassing the latest data release (DR16) of the extended Baryon Oscillation Spectroscopic Survey (eBOSS). For the first time in this kind of analysis, we use a blinding procedure to mitigate the risk of confirmation bias in our results. We improve the model of the radial integral constraint proposing an innovative technique allowing the correction through the window matrix convolution. We also carefully test the mitigation of the dependence of the target selection on the photometry qualities by incorporating an angular integral constraint contribution to the window function, and validate our methodology with the blinded data. Finally, combining the two samples, we measure f NL loc = -3.6 -9.1 +9.0 at 68% confidence, where we assume the universality relation for the LRG sample and a recent merger model for the QSO sample about the response of bias to primordial non-Gaussianity. Adopting the universality relation for the PNG bias in the QSO analysis leads to f NL loc = 3.5 -7.4 +10.7 at 68% confidence. Due to restricted selection in the LRG sample, the inclusion of the LRGs allows for 10% improvement. This measurement is the most precise determination of primordial non-Gaussianity using large-scale structure to date, surpassing the latest result from eBOSS by a factor of 2.3.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Using active learning to improve quasar identification for the DESI spectra processing pipeline

The Dark Energy Spectroscopic Instrument (DESI) survey uses an automatic spectral classification pipeline to classify spectra. QuasarNET is a convolutional neural network used as part of this pipeline originally trained using data from the Baryon Oscillation Spectroscopic Survey (BOSS). In this paper we implement an active learning algorithm to optimally select spectra to use for training a new version of the QuasarNET weights file using only DESI data, with the goal of improving classification accuracy. This active learning algorithm includes a novel outlier rejection step using a Self-Organizing Map to ensure we label spectra representative of the larger quasar sample observed in DESI. We perform two iterations of the active learning pipeline, assembling a final dataset of 5600 labeled spectra, a small subset of the approximately 1.3 million quasar targets in DESI's Data Release 1. When splitting the spectra into training and validation subsets we achieve similar performance to the previously trained weights file in completeness and purity calculated on the validation dataset but do so with less than one tenth of the amount of training data. The new weights also more consistently classify objects in the same way when used on unlabeled data compared to the old weights file. In the process of improving QuasarNET's classification accuracy we discovered a systemic error in QuasarNET's redshift estimation and used our findings to improve our understanding of QuasarNET's redshifts.

Machine learning↗
DOE OSTI2026

Pre-training Vision Models for the Classification of Alerts from Wide-field Time-domain Surveys

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Search for two-neutrino double-beta decay of 136 Xe to the $0$$^{+}_{1}$ excited state of 136 Ba with the complete EXO-200 dataset*

A new search for two-neutrino double-beta (2νββ) decay of 136 Xe to the $0$$^{+}_{1}$ excited state of 136 Ba is performed with the full EXO-200 dataset. A deep learning-based convolutional neural network is used to discriminate signal from background events. Signal detection efficiency is increased relative to previous searches by EXO-200 by more than a factor of two. With the addition of the Phase II dataset taken with an upgraded detector, the median 90% confidence level half-life sensitivity of 2νββ decay to the $0$$^{+}_{1}$ state of 136 Ba is 2.9 x 10 24 yr using a total 136 Xe exposure of 234.1 kg yr. Furthermore, no statistically significant evidence for 2νββ decay to the $0$$^{+}_{1}$ state is observed, leading to a lower limit of $T$$^{2v}_{1/2}$(0 + → $0$$^{+}_{1}$) > 1.4 x 10 24 yr at 90% confidence level, improved by 70% relative to the current world's best constraint.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Single-trial classification of evoked responses to auditory tones using OPM- and SQUID-MEG

Abstract Objective. Optically pumped magnetometers (OPMs) are emerging as a near-room-temperature alternative to superconducting quantum interference devices (SQUIDs) for magnetoencephalography (MEG). In contrast to SQUIDs, OPMs can be placed in a close proximity to subject’s scalp potentially increasing the signal-to-noise ratio and spatial resolution of MEG. However, experimental demonstrations of these suggested benefits are still scarce. Here, to compare a 24-channel OPM-MEG system to a commercial whole-head SQUID system in a data-driven way, we quantified their performance in classifying single-trial evoked responses. Approach. We measured evoked responses to three auditory tones in six participants using both OPM- and SQUID-MEG systems. We performed pairwise temporal classification of the single-trial responses with linear discriminant analysis as well as multiclass classification with both EEGNet convolutional neural network and xDAWN decoding. Main results. OPMs provided higher classification accuracies than SQUIDs having a similar coverage of the left hemisphere of the participant. However, the SQUID sensors covering the whole helmet had classification scores larger than those of OPMs for two of the tone pairs, demonstrating the benefits of a whole-head measurement. Significance. The results demonstrate that the current OPM-MEG system provides high-quality data about the brain with room for improvement for high bandwidth non-invasive brain–computer interfacing.

Iivanainen, Joonas (ORCID:0000000160344604)↗
DOE OSTI2024

Tokamak edge localized mode onset prediction with deep neural network and pedestal turbulence

Abstract A neural network, BES-ELMnet, predicting a quasi-periodic disruptive eruption of the plasma energy and particles known as edge localized mode (ELM) onset is developed with observed pedestal turbulence from the beam emission spectroscopy system in DIII-D. BES-ELMnet has convolutional and fully-connected layers, taking two-dimensional plasma fluctuations with a temporal window of size 128 µ s and generating a scalar output which can be interpreted as a probability of the upcoming ELM onset. As approximately labeled inter-ELM broadband ( 15 kHz ⩽ f ⩽ 150 kHz ) fluctuations are given to the network, BES-ELMnet learns by itself ELM-related precursors arising before the onsets through supervised learning scheme. BES-ELMnet achieves the gradually increasing ELM onset probabilities between two consecutive ELMs during the inter-ELM phases and can forecast the first ELM onsets which occur after the high confinement mode transition. We further investigate the network generality in terms of the selected frequency band to ensure the use of BES-ELMnet for various operation regimes without changing the trained architecture. Therefore, our novel prediction method will enhance a proactive high confinement mode control of fusion-grade plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Development of a data-driven neural network model for electron thermal transport in NSTX

A data-driven electron thermal transport neural network (ETT-NN) model, trained on TRANSP interpretative analysis results of National Spherical Torus Experiment (NSTX), was developed to enable faster and more accurate ETT computation for spherical tokamaks (STs). The model incorporates both convolutional NNs and recurrent NNs, allowing it to simultaneously account for the spatial and temporal non-localities and multi-scale features of turbulent transport, which have been considered only in a limited manner in conventional models. The model was validated through interpretative analysis and predictive simulations using Tokamak Reactor Integrated Automated Suite for Simulation and Computation, demonstrating relatively high accuracy. Additionally, parameter scans were performed on test discharges known to exhibit specific turbulent modes, such as microtearing mode, trapped electron mode, kinetic ballooning mode, and electron temperature gradient mode. The scanning results revealed that the ETT-NN model exhibits the same trends as those observed in conventional gyrokinetic simulations or theories, while also capturing the global nature of turbulent transport, indicating that the data-driven model accurately reflects the underlying physical characteristics. Furthermore, due to the dimensionless nature of the model, we can feasibly expand its applicability by incorporating data from other devices and uncovering the characteristics of ETT in STs in the future.

NSTX↗
DOE OSTI2023

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers

The Exa.TrkX project presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the Large Hadron Collider (LHC). Graphs describing particle interactions are formed by treating each detector hit as a node, with edges describing the relationships between hits. We utilise a multi-head attention message passing network which performs graph convolutions in order to label each node with a particle type.We present an updated variant of our GNN architecture, with several improvements. After testing the model on more realistic simulation with regions of unresponsive wires, the target was modified from edge classification to node classification in order to increase robustness. Removing edges as a classification target opens up a broader possibility space for edge-forming techniques; we explore the model’s performance across a variety of approaches, such as Delaunay triangulation, kNN, and radius-based methods. We also extend this model to the 3D context, sharing information between detector views. By using reconstructed 3D spacepoints to map detector hits from each wire plane, the model naively constructs 2D representations that are independent yet fully consistent.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Recovery of coincident frequency domain multiplexed detector pulses using sequential deconvolution

Multiplexing of radiation detector signals into a single channel significantly reduces the need for a large number of digitizer channels, which reduces the cost and the power consumption of a data acquisition system. We previously demonstrated frequency domain multiplexing by convolution using a prototype system that multiplexed two EJ-309 organic scintillators signals into a single channel. Each detector pulse was converted to a damped sinusoid which was then combined into a single channel. The combined signal was digitized and the original detector signal was recovered from the damped sinusoid by deconvolution. In this paper, we demonstrate the recovery of multiple detector signals that arrive during the same digitized record via a new sequential deconvolution method. Here, when two detectors produce signals in the same digitized record and their pulses do not overlap in time, we found that the charge, arrival time, and particle type can be estimated fairly precisely for the first pulse, but the second pulse exhibits substantial degradation in the precision of the estimated charge and arrival time. When the pulses overlap in time, we demonstrate both theoretically and experimentally that the part of the first pulse that does not overlap with the second can be recovered accurately, so the arrival time and amplitude of the first pulse can be estimated fairly precisely, but not the charge or particle type. None of these quantities can be estimated precisely for the second pulse when the two pulses overlap.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Deep-Learning based Reconstruction of the Shower Maximum $X_{\mathrm{max}}$ using the Water-Cherenkov Detectors of the Pierre Auger Observatory

The atmospheric depth of the air shower maximum X max is an observable commonly used for the determination of the nuclear mass composition of ultra-high energy cosmic rays. Direct measurements of X max are performed using observations of the longitudinal shower development with fluorescence telescopes. At the same time, several methods have been proposed for an indirect estimation of X max from the characteristics of the shower particles registered with surface detector arrays. In this paper, we present a deep neural network (DNN) for the estimation of X max . The reconstruction relies on the signals induced by shower particles in the ground based water-Cherenkov detectors of the Pierre Auger Observatory. The network architecture features recurrent long short-term memory layers to process the temporal structure of signals and hexagonal convolutions to exploit the symmetry of the surface detector array. We evaluate the performance of the network using air showers simulated with three different hadronic interaction models. Thereafter, we account for long-term detector effects and calibrate the reconstructed X max using fluorescence measurements. Finally, we show that the event-by-event resolution in the reconstruction of the shower maximum improves with increasing shower energy and reaches less than 25 g/cm 2 at energies above 2 × 10 19 eV.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗