Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network inference”

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 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Neural network methods for radiation detectors and imaging

Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).

edge computing↗
DOE OSTI2022

How Many Elements Matter?

Some studies of stars' multielement abundance distributions suggest at least 5–7 significant dimensions, but others show that many elemental abundances can be predicted to high accuracy from [Fe/H] and [Mg/Fe] (or [Fe/H] and age) alone. We show that both propositions can be, and are, simultaneously true. We adopt a machine-learning technique known as normalizing flow to reconstruct the probability distribution of Milky Way disk stars in the space of 15 elemental abundances measured by APOGEE. Conditioning on T eff and $\mathrm{log}\,g$ minimizes the differential systematics. After further conditioning on [Fe/H] and [Mg/Fe], the residual scatter for most abundances is σ [X/H] ≲ 0.02 dex, consistent with APOGEE's reported statistical uncertainties of ~0.01–0.015 dex and intrinsic scatter of 0.01–0.02 dex. Despite the small scatter, residual abundances display clear correlations between elements, which we show are too large to be explained by measurement uncertainties or by the finite sampling noise. We must condition on at least seven elements to reduce the correlations to a level consistent with the observational uncertainties. Our results demonstrate that cross-element correlations are a much more sensitive probe of a hidden structure than dispersion, and they can be measured precisely in a large sample even if the star-by-star measurement noise is comparable to the intrinsic scatter. We conclude that many elements have an independent story to tell, even for the mundane disk stars and elements produced by the core-collapse and Type Ia supernovae. The only way to learn these lessons is to measure the abundances directly, and not merely infer them.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons

Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with traditional methods. However, quantifying errors and uncertainties in NN-based inference is more complicated than in traditional methods. This is because in addition to aleatoric uncertainty associated with noisy data, there is also uncertainty due to limited data, but also due to NN hyperparameters, overparametrization, optimization and sampling errors as well as model misspecification. Although there are some recent works on uncertainty quantification (UQ) in NNs, there is no systematic investigation of suitable methods towards quantifying the total uncertainty effectively and efficiently even for function approximation, and there is even less work on solving partial differential equations and learning operator mappings between infinite-dimensional function spaces using NNs. In this work, we present a comprehensive framework that includes uncertainty modeling, new and existing solution methods, as well as evaluation metrics and post-hoc improvement approaches. Further, to demonstrate the applicability and reliability of our framework, we present an extensive comparative study in which various methods are tested on prototype problems, including problems with mixed input-output data, and stochastic problems in high dimensions. In the Appendix, we include a comprehensive description of all the UQ methods employed. Further, to help facilitate the deployment of UQ in Scientific Machine Learning research and practice, we present and develop in [1] an open-source Python library (github.com/Crunch-UQ4MI/neuraluq), termed NeuralUQ, that is accompanied by an educational tutorial and additional computational experiments.

11 physics-informed neural networks↗
NASA NTRS1995

Coronal structures deduced from photospheric magnetic field and He I lambda 10830 observations

The National Solar Observatory synoptic program provides an extensive and unique data base of high-resolution full-disk observations of the line-of-sight photospheric magnetic fields and of the He I lambda 10830 equivalent width. These data have been taken nearly daily for more than 21 years since 1974 and provide the opportunity to investigate the behavior of the magnetic fields in the photosphere and those inferred for the corona spanning on the time scales of a day to that of a solar cycle. The intensity of structures observed in He I lambda 10830 are strongly modulated by overlying coronal radiation; areas with low coronal emission are generally brighter in He I lambda 10830, while areas with high coronal emission are darker. For this reason, He I lambda 10830 was selected in the mid-1970's as way to identify and monitor coronal holes, magnetic fields with an open configuration, and the sources of high-speed solar wind streams. The He I lambda 10830 spectroheliograms also show a wide variety of other structures from small-scale, short-lived dark points (less than 30 arc-sec, hours) to the large-scale, long-lived two 'ribbon' flare events that follow the filament eruptions (1000 arc-sec, days). Such structures provide clues about the connections and changes in the large-scale coronal magnetic fields that are rooted in concentrations of magnetic network and active regions in the photosphere. In this paper, what observations of the photospheric magnetic field and He I lambda 10830 can tell us about the short- and long-term evolution of the coronal magnetic fields will be discussed, focussing on the quiet Sun and coronal holes. These data and what we infer from them will be compared with direct observations of the coronal structure from the Yohkoh Soft X-ray Telescope.

Harvey, Karen L.↗
DOE OSTI2025

Bayesian calibration of bubble size dynamics applied to CO 2 gas fermenters

To accelerate the scale-up of gaseous CO 2 fermentation reactors, computational models need to predict gas-to-liquid mass transfer which requires capturing the bubble size dynamics, i.e. bubble breakup and coalescence. However, the applicability of existing models beyond air–water mixtures remains to be established. Here, an inverse modeling approach, accelerated with a neural network surrogate, calibrates the breakup and coalescence closure models, that are used in class methods for population balance modeling (PBM). The calibration is performed based on experimental results obtained in a CO 2 -air–water-coflowing bubble column reactor. Bayesian inference is used to account for noise in the experimental dataset and bias in the simulation results. To accurately capture gas holdup and interphase mass transfer, the results show that the breakage rate needs to be increased by one order of magnitude. In conclusion, the inferred model parameters are then used on a separate configuration and shown to also improve bubble size distribution predictions.

09 BIOMASS FUELS↗
DOE OSTI2023

Multi-scale VLBI observations of the candidate host galaxy of GRB 200716C

We present the discovery and the subsequent follow up of radio emission from SDSS J130402.36+293840.6 (J1304+2938), the candidate host galaxy of the gamma-ray burst (GRB) GRB 200716C. The galaxy is detected in the RACS (0.89 GHz), the NVSS, the Apertif imaging survey, and the FIRST (1.4 GHz), the VLASS (3 GHz), and in public LOFAR (130–170 MHz), WISE (3.4–22 μm), and SDSS (z, i, r, g, u filters) data. The luminosity inferred at 1.4 GHz is (5.1 ± 0.2) × 10 30 erg s -1 Hz -1 . To characterise the emission and distinguish between different components within the galaxy, we performed dedicated, high-sensitivity and high-resolution observations with the European VLBI Network (EVN) + e-MERLIN at 1.6 and 5 GHz. We did not detect any emission from a compact core, suggesting that the presence of a radio-loud active galactic nucleus (AGN) is unlikely, and therefore we ascribe the emission observed in the public surveys to star-forming regions within the galaxy. We confirm and refine the redshift estimate, z = 0.341 ± 0.004, with a dedicated Telescopio Nazionale Galileo (TNG) spectroscopic observation. Finally, we compiled a list of all the known hosts of GRB afterglows detected in radio and computed the corresponding radio luminosity: if GRB 200716C belongs to J1304+2938, this is the third most radio-luminous host of a GRB, implying one of the highest star-formation rates (SFRs) currently known, namely SFR ~ 324±61 M ⊙ yr -1 . On the other hand, through the analysis of the prompt emission light curve, recent works suggest that GRB 200716C might be a short-duration GRB located beyond J1304+2938 and gravitationally lensed by an intermediate-mass black hole (IMBH) hosted by the galaxy. Neither the public data nor our Very Long Baseline Interferometry (VLBI) observations can confirm or rule out the presence of an IMBH acting as a (milli-)lens hosted by the galaxy, a scenario still compatible with the set of radio observations presented in this work.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1989

Carrier phase ambiguity resolution for the Global Positioning System applied to geodetic baselines up to 2000 km

A technique for resolving the ambiguities in the GPS carrier phase data (which are biased by an integer number of cycles) is described which can be applied to geodetic baselines up to 2000 km in length and can be used with dual-frequency P code receivers. The results of such application demonstrated that a factor of 3 improvement in baseline accuracy could be obtained, giving centimeter-level agreement with coordinates inferred by very-long-baseline interferometry in the western United States. It was found that a method using pseudorange data is more reliable than one using ionospheric constraints for baselines longer than 200 km. It is recommended that future GPS networks have a wide spectrum of baseline lengths (ranging from baselines shorter than 100 km to those longer than 1000 km) and that GPS receivers be used which can acquire dual-frequency P code data.

Blewitt, Geoffrey↗
DOE OSTI2026

Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network

Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge jumps), causing correlated errors that challenge fault-tolerant quantum computing while simultaneously providing a detection signature for quantum sensing applications. Current detection methods operate offline, introducing latency incompatible with in-the-loop qubit control. In this paper, an online detector of charge jumps for superconducting qubits, based on a dilated causal convolutional neural network (DCCNN) designed for in-the-loop deployment on the Quantum Instrumentation Control Kit (QICK) platform, is presented. The network is trained on synthetic Ramsey tomography scans generated from qubit templates measured at the Northwestern Experimental Underground Site (NEXUS) at Fermilab, and translated to FPGA firmware via hls4ml with ap_fixed$\langle 16,6 \rangle$ quantization, reaching a per-inference latency of $6.19 μ$s on the Zynq UltraScale+ RFSoC ZCU216. At this operating point the DCCNN matches the detection efficiency of the established offline $χ^2$ algorithm ($0.843 \pm 0.022$ vs. $0.866 \pm 0.020$ on $|Δq| \in [0.1, 0.5] e$ at matched false-positive rate), while requiring no per-qubit hyperparameter tuning. This shifts charge-jump detection from a post-hoc diagnostic to a control-loop primitive, enabling adaptive protocols that respond to radiation-induced events in situ, with applications to quantum-computing error mitigation and to the use of superconducting qubits as particle detectors.

Gaytan-Villarreal, Daniel [Carnegie Mellon U.]↗
DOE OSTI2023

Direct Bayesian inference for fault severity assessment in Digital-Twin-Based fault diagnosis

For applications in condition-based maintenance of nuclear systems, the assessment of fault severity is crucial. In this work, we developed a framework that allows for direct inference of the probability distributions of possible faults in a system. Here, we employed a model-based approach with model residuals generated from analytical redundancy relations provided by physics-based models of the system components. From real-time sensor readings, the values of the model residuals can be calculated, and the posterior probability distributions of the faults can be computed directly using the methods of Bayesian networks. From the posterior distribution of each fault, one can estimate the fault probability based on a chosen threshold and assess the severity of the fault. By eliminating the discretization and simplifications in middle steps, this approach allows us to leverage the available computational resources to provide more accurate fault probability estimates and severity assessments.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Improving deep learning model performance under parametric constraints for materials informatics applications

Abstract Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties.

36 MATERIALS SCIENCE↗
DOE OSTI2020

nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications

Physics-informed neural networks (PINNs) are effective in solving inverse problems based on differential and integro-differential equations with sparse, noisy, unstructured, and multifidelity data. PINNs incorporate all available information, including governing equations (reflecting physical laws), initial-boundary conditions, and observations of quantities of interest, into a loss function to be minimized, thus recasting the original problem into an optimization problem. In this paper, we extend PINNs to parameter and function inference for integral equations such as nonlocal Poisson and nonlocal turbulence models, and we refer to them as nonlocal PINNs (nPINNs). The contribution of the paper is three-fold. First, we propose a unified nonlocal Laplace operator, which converges to the classical Laplacian as one of the operator parameters, the nonlocal interaction radius δ goes to zero, and to the fractional Laplacian as δ goes to infinity. This universal operator forms a super-set of classical Laplacian and fractional Laplacian operators and, thus, has the potential to fit a broad spectrum of data sets. We provide theoretical convergence rates with respect to δ and verify them via numerical experiments. Second, we use nPINNs to estimate the two parameters, δ and α, characterizing the kernel of the unified operator. The strong non-convexity of the loss function yielding multiple (good) local minima reveals the occurrence of the operator mimicking phenomenon, that is, different pairs of estimated parameters could produce multiple solutions of comparable accuracy. Third, we propose another nonlocal operator with spatially variable order α(γ), which is more suitable for modeling turbulent Couette flow. Our results show that nPINNs can jointly infer this function as well as δ. More importantly, these parameters exhibit a universal behavior with respect to the Reynolds number, a finding that contributes to our understanding of nonlocal interactions in wall-bounded turbulence.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Extension of the PINN diffusion model to k-eigenvalue problems

This paper extends our recent work on the Physics-Informed Neural Networks (PINN) approach for the fixed source diffusion models and applies it to the diffusion theory based k-eigenvalue problems. To make the PINN equitable for the eigenvalue problems, we introduce a novel integral regularization term to the loss function in the framework, and allow the direct inference of the principal eigenvalue and the associated eigenfunction. The regularization term enforces a pre-defined value on the integration of the model predictions, and this value can be directly related to a physical property of the system. We also introduce an additional learnable parameter to approximate the principal eigenvalue. As a proof of principle, we solve the one-group two-dimensional k-eigenvalue neutron diffusion equation in this work. We then provide two numerical examples to demonstrate the applicability of the PINN approach. In each example, we solve the k-eigenvalue diffusion equation in a multi-region configuration constrained with a set of Robin boundary conditions for generality. We use a FEM solution based on the power-iteration method to verify the results of the PINN solution. The results showed relative percentage error in the predicted eigenvalue of about 0.77% and about 1.2% for example 1 and example 2, respectively. The mean absolute error in the predicted flux for example 1 is ∼ 0.002 and for example 2 is ∼ 0.0024. These results indicate some preliminary successes of the PINN application to k-eigenvalue problems. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Observable optimization for precision theory: machine learning energy correlators

The practice of collider physics typically involves the marginalization of multi-dimensional collider data to uni-dimensional observables relevant for some physics task. In many cases, such as classification or anomaly detection, the observable can be arbitrarily complicated, such as the output of a neural network. However, for precision measurements, the observable must correspond to something computable systematically beyond the level of current simulation tools. In this work, we demonstrate that precision-theory-compatible observable space exploration can be systematized by using neural simulation-based inference techniques from machine learning. We illustrate this approach by exploring the space of marginalizations of the energy 3-point correlator to optimize sensitivity to the top quark mass. We first learn the energy-weighted probability density from simulation, then search in the space of marginalizations for an optimal triangle shape. Although simulations and machine learning are used in the process of observable optimization, the output is an observable definition which can be then computed to high precision and compared directly to data without any memory of the computations which produced it. We find that the optimal marginalization is isosceles triangles on the sphere with a side ratio approximately $1 : 1 : \sqrt{2}$ (i.e. right triangles) within the set of marginalizations we consider.

Jets and Jet Substructure↗
DOE OSTI2022

Analyzing Data Privacy for Edge Systems

Internet-of-Things (IoT)-based streaming applications are all around us. Currently, we are transitioning from IoT processing being performed on the cloud to the edge. While moving to the edge provides significant networking efficiency benefits, IoT edge computing creates significant data privacy concerns. We propose a methodology that can successfully privacy protect the continual data streams generated by sensors on the edge device. We implement local differential privacy on streaming data and incorporate Bayesian inference and Gaussian process to evaluate the privacy policy. We demonstrate our methodology on a real-world smart meter testbed and identify the optimal privacy protection settings.

Kotevska, Olivera↗
DOE OSTI2022

SPANet: Generalized permutationless set assignment for particle physics using symmetry preserving attention

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19% - 35% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are available at https://github.com/Alexanders101/SPANet

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Simple and Sophisticated Models of Taylor's Cylinder Impact

We present a study based on the simplest possible models for Taylor’s cylinder impact problem, in addition to examination of using convolutional neural networks (CNNs) to map cylinder profiles to strength calibrations. We find that the approximate treatments of Taylor and Hawkyard compare well with hydrodynamic simulations using an equivalent assumption of constant flow stress. The CNN models prove to be well suited to successfully infer parameterizations of the Preston-Tonks-Wallace model of plastic deformation based on the deformed profile of an impacted cylinder

36 MATERIALS SCIENCE↗
NASA NTRSDate not supplied

SafeDNN: Understanding and Verifying Neural Networks

The SafeDNN project at NASA Ames explores analysis techniques and tools to ensure that systems that use Deep Neural Networks (DNN) are safe, robust and interpretable. Research directions we are pursuing include: symbolic execution for DNN analysis, label-guided clustering to automatically identify input regions that are robust, parallel and compositional approaches to improve formal SMT-based verification, property inference and automated program repair for DNNs, adversarial training and detection, probabilistic reasoning for DNNs. In this talk I will highlight some of the research advances from SafeDNN, that were already published.

Corina Pasareanu↗
DOE OSTI2023

BitGNN: Unlocking the Performance Potential of Binary Graph Neural Networks on GPUs

Graph Neural Networks (GNNs) have shown compelling results in many graph-based learning tasks. They are, however, time-consuming. Recent work has shown a promising direction in improving GNN speed and shrinking the size — network binarization, which binarizes network values and operations. Prior work, however, mainly focused on algorithm designs, leaving it open on how to fully materialize the performance potential. This work fills the gap by proposing techniques to best map binary GNNs and their computations to fit the nature of bit manipulations, optimizations and algorithms to maximize BSpMM kernel efficiency, and solutions to other factors influencing the end-to-end time on GPUs. Results on real-world graphs show that the proposed techniques outperform state of-the-art binary GNN implementations by 21-67× with little accuracy loss.

Chen, Jou-An↗