SEARCH · Search NASA

Results for “NN”

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.

SourceResearch connectionFrom yearThrough year

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

At least 505 records · Page 28

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Evidence of Mass Ordering of Charm and Bottom Quark Energy Loss in Au+Au Collisions at RHIC

Abstract Partons traversing the strongly interacting medium produced in heavy-ion collisions are expected to lose energy depending on their color charge and mass. We measure the nuclear modification factors for charm- and bottom-decay electrons, defined as the ratio of yields, divided by the number of binary nucleon–nucleon collisions, in $$\sqrt{s_{\textrm{NN}}}=200$$ s NN = 200 GeV Au+Au collisions to p + p collisions ( $$R_{\textrm{AA}}$$ R AA ), or in central to peripheral Au+Au collisions ( $$R_{\textrm{CP}}$$ R CP ). We find the bottom-decay electron $$R_{\textrm{AA}}$$ R AA and $$R_{\textrm{CP}}$$ R CP to be significantly higher than those of charm-decay electrons. Model calculations including mass-dependent parton energy loss in a strongly coupled medium are consistent with the measured data. These observations provide evidence of mass ordering of charm and bottom quark energy loss when traversing through the strongly coupled medium created in heavy-ion collisions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

Constraining the $\overline{K}$N coupled channel dynamics using femtoscopic correlations at the LHC

The interaction of K – with protons is characterised by the presence of several coupled channels, systems like $\overline{K}$ 0 n and πΣ with a similar mass and the same quantum numbers as the K – p state. The strengths of these couplings to the K – p system are of crucial importance for the understanding of the nature of the Λ(1405) resonance and of the attractive K – p strong interaction. In this article, we present measurements of the K – p correlation functions in relative momentum space obtained in pp collisions at $\sqrt{s}$=13 Te, in p–Pb collisions at $\sqrt{s_{NN}}$= 5.02 Te, and (semi)peripheral Pb–Pb collisions at $\sqrt{s_{NN}}$= 5.02 Te. The emitting source size, composed of a core radius anchored to the K + p correlation and of a resonance halo specific to each particle pair, varies between 1 and 2 fm in these collision systems. The strength and the effects of the $\overline{K}$ 0 n and πΣ inelastic channels on the measured K – p correlation function are investigated in the different colliding systems by comparing the data with state-of-the-art models of chiral potentials. A novel approach to determine the conversion weights ω, necessary to quantify the amount of produced inelastic channels in the correlation function, is presented. In this method, particle yields are estimated from thermal model predictions, and their kinematic distribution from blast-wave fits to measured data. The comparison of chiral potentials to the measured K – p interaction indicates that, while the πΣ –K – p dynamics is well reproduced by the model, the coupling to the $\overline{K}$ 0 n channel in the model is currently underestimated.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

Detecting nuclear mass distribution in isobar collisions via charmonium

Abstract The collective properties of final state hadrons produced in the high statistics $$_{44}^{96}$$ 44 96 Ru + $$_{44}^{96}$$ 44 96 Ru and $$_{40}^{96}$$ 40 96 Zr + $$_{40}^{96}$$ 40 96 Zr collisions at $$\sqrt{s_\textrm{NN}} = 200~\textrm{GeV}$$ s NN = 200 GeV are found to be significantly different. Such differences were argued to be precise probes of the difference in nucleon distribution in the isobar nuclei. We investigate the $$J/\psi $$ J / ψ production in the isobar collision via a relativistic transport approach. By comparing the isobar systems according to equal centrality bin and equal multiplicity bin, we find that the yield ratio of $$J/\psi $$ J / ψ is sensitive to the differences in both the number of binary collisions and the medium evolution. Besides, the elliptic flow $$v_2$$ v 2 of $$J/\psi $$ J / ψ is qualitatively different from the light hadrons, and the ratio between Ru + Ru and Zr + Zr collisions is sensitive to the medium evolution. The charmonium production provides an independent probe to study the nucleon distribution in the isobar system.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2025

System size and energy dependence of the mean transverse momentum fluctuations at the LHC

Event-by-event fluctuations of the event-wise mean transverse momentum, $\langle$p T $\rangle$, of charged particles produced in proton–proton (pp) collisions at $\sqrt{s}$ = 5.02 TeV, Xe–Xe collisions at $\sqrt{s_{NN}}$ = 5.44 TeV, and Pb–Pb collisions at $\sqrt{s_{NN}}$ = 5.02 TeV are studied using the ALICE detector based on the integral correlator $\langle$$\langle$Δp T Δp T $\rangle$$\rangle$. The correlator strength is found to decrease monotonically with increasing produced charged-particle multiplicity measured at midrapidity in all three systems. In Xe–Xe and Pb–Pb collisions, the multiplicity dependence of the correlator deviates significantly from a simple power-law scaling as well as from the predictions of the HIJING and AMPT models. The observed deviation from power-law scaling is expected from transverse radial flow in semicentral to central Xe–Xe and Pb–Pb collisions. In pp collisions, the correlation strength is also studied by classifying the events based on the transverse spherocity, S 0 , of the particle production at midrapidity, used as a proxy for the presence of a pronounced back-to-back jet topology. Low-spherocity (jetty) events feature a larger correlation strength than those with high spherocity (isotropic). The strength and multiplicity dependence of jetty and isotropic events are well reproduced by calculations with the PYTHIA 8 and EPOS LHC models.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2025

Flavour-dependent chemical freeze-out of light nuclei in relativistic heavy-ion collisions

We study the production of light nuclei in Au+Au collisions at $\sqrt{s_{NN}}$ = 7.7–200 GeV and Pb+Pb collisions at $\sqrt{s_{NN}}$ = 2.76 and 5.02 TeV within a flavour-dependent chemical freeze-out scenario, assuming different flavoured hadrons undergo separate chemical freeze-out. Using the Thermal-FIST package, thermal parameters extracted from fits to various sets of hadron yields, including and excluding light nuclei, are used to calculate the ratios of the yields of light nuclei, namely, d/p, $\overline{d}$/$\overline{p}$, t/p, t/d, 4 He/ 3 He, and 3 H Λ / 3 He. A comparison with experimental data from the STAR and ALICE collaborations shows that a sequential freeze-out scenario provides a better description of light nuclei yield ratios than the traditional single freeze-out approach. These results suggest the flavour-dependent chemical freeze-out for final state light nuclei production persists in heavy-ion collisions at both RHIC and LHC energies.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2023

Toward learning Lattice Boltzmann collision operators

In this work, we explore the possibility of learning from data collision operators for the Lattice Boltzmann Method using a deep learning approach. We compare a hierarchy of designs of the neural network (NN) collision operator and evaluate the performance of the resulting LBM method in reproducing time dynamics of several canonical flows. In the current study, as a first attempt to address the learning problem, the data were generated by a single relaxation time BGK operator. We demonstrate that vanilla NN architecture has very limited accuracy. On the other hand, by embedding physical properties, such as conservation laws and symmetries, it is possible to dramatically increase the accuracy by several orders of magnitude and correctly reproduce the short and long time dynamics of standard fluid flows.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores

Over the years, accelerating neural networks with quantization has been widely studied. Unfortunately, prior efforts with diverse precisions (e.g., 1-bit weights and 2-bit activations) are usually restricted by limited precision support on GPUs (e.g., int1 and int4). To break such restrictions, we introduce the first Arbitrary Precision Neural Network framework (APNN-TC) to fully exploit quantization benefits on Ampere GPU Tensor Cores. Specifically, APNN-TC first incorporates a novel emulation algorithm to support arbitrary short bit-width computation with int1 compute primitives and XOR/AND Boolean operations. Second, APNN-TC integrates arbitrary precision layer designs to efficiently map our emulation algorithm to Tensor Cores with novel batching strategies and specialized memory organization. Third, APNN-TC embodies a novel arbitrary precision NN design to minimize memory access across layers and further improve performance. Extensive evaluations show that APNN-TC can achieve significant speedup over CUTLASS kernels and various NN models, such as ResNet and VGG.

Feng, Boyuan↗

DOE OSTI2024

End-to-end codesign of Hessian-aware quantized neural networks for FPGAs

Here, we develop an end-to-end workflow for the training and implementation of co-designed neural networks (NNs) for efficient field-programmable gate array (FPGA) hardware. Our approach leverages Hessian-aware quantization of NNs, the Quantized Open Neural Network Exchange intermediate representation, and the hls4ml tool flow for transpiling NNs into FPGA firmware. This makes efficient NN implementations in hardware accessible to nonexperts in a single open sourced workflow that can be deployed for real-time machine-learning applications in a wide range of scientific and industrial settings. We demonstrate the workflow in a particle physics application involving trigger decisions that must operate at the 40-MHz collision rate of the CERN Large Hadron Collider (LHC). Given the high collision rate, all data processing must be implemented on FPGA hardware within the strict area and latency requirements. Based on these constraints, we implement an optimized mixed-precision NN classifier for high-momentum particle jets in simulated LHC proton-proton collisions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2023

Iterative multi-task learning and inference from seismic images

Seismic interpretation aims to extract quantitative and interpretable attributes from a seismic image produced using some migration method to inform characteristics of a subsurface reservoir or target of interest. Current paradigms for computing seismic attributes mostly rely on single-task algorithms. We develop an iterative, multi-task machine learning method to learn and infer multiple attributes from a seismic image. This method is composed of two stages: a multi-task inference stage and a multi-modal, multi-task refinement stage. The basic mechanism of this method is that we train a multi-task inference neural network (NN) to estimate a set of attributes, including a relative geological time (RGT), a denoised higher-resolution (DHR) seismic image, and multiple fault attributes (including probability, dip, and strike), from a low-resolution, noisy seismic image; then we input the inferred attributes to a multi-task refinement NN to enhance the raw inference results iteratively. The two multi-task NNs are trained separately based on synthetic seismic images and associated attributes generated by a geological modeling algorithm. The software we intend to release is a PyTorch implementation of this multi-task learning method for both 2D and 3D cases along with scripts to run the training/validation. The algorithm and software can be a useful tool for automatic seismic interpretation.

Gao, Kai↗

DOE OSTI2021

Learning curves for drug response prediction in cancer cell lines

Motivated by the size and availability of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies continue generating drug response data, a common question is whether the generalization performance of existing prediction models can be further improved with more training data. We utilize empirical learning curves for evaluating and comparing the data scaling properties of two neural networks (NNs) and two gradient boosting decision tree (GBDT) models trained on four cell line drug screening datasets. The learning curves are accurately fitted to a power law model, providing a framework for assessing the data scaling behavior of these models. The curves demonstrate that no single model dominates in terms of prediction performance across all datasets and training sizes, thus suggesting that the actual shape of these curves depends on the unique pair of an ML model and a dataset. The multi-input NN (mNN), in which gene expressions of cancer cells and molecular drug descriptors are input into separate subnetworks, outperforms a single-input NN (sNN), where the cell and drug features are concatenated for the input layer. In contrast, a GBDT with hyperparameter tuning exhibits superior performance as compared with both NNs at the lower range of training set sizes for two of the tested datasets, whereas the mNN consistently performs better at the higher range of training sizes. Moreover, the trajectory of the curves suggests that increasing the sample size is expected to further improve prediction scores of both NNs. These observations demonstrate the benefit of using learning curves to evaluate prediction models, providing a broader perspective on the overall data scaling characteristics. A fitted power law learning curve provides a forward-looking metric for analyzing prediction performance and can serve as a co-design tool to guide experimental biologists and computational scientists in the design of future experiments in prospective research studies.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Effects of nitrogen fertilization and bioenergy crop type on topsoil organic carbon and total Nitrogen contents in middle Tennessee USA

Nitrogen (N) fertilization affects bioenergy crop growth and productivity and consequently carbon (C) and N contents in soil, it however remains unclear whether N fertilization and crop type individually or interactively influence soil organic carbon (SOC) and total N (TN). In a three-year long fertilization experiment in switchgrass (SG: Panicum virgatum L.) and gamagrass (GG: Tripsacum dactyloides L.) croplands in Middle Tennessee USA, soil samples (0–15cm) were collected in plots with no N input (NN), low N input (LN: 84 kg N ha -1 yr -1 in urea) and high N input (HN: 168 kg N ha -1 yr -1 in urea). Besides SOC and TN, the aboveground plant biomass was also quantified. In addition to a summary of published root morphology data based on a separated mesocosm experiment, the root leachable dissolved organic matter (DOM) of both crops was also measured using archived samples. Results showed no significant interaction of N fertilization and crop type on SOC, TN or plant aboveground biomass (ABG). Relative to NN, HN (not LN) significantly increased SOC and TN in both crops. Though SG showed a 15–68% significantly higher ABG than GG, GG showed a 9.3–12% significantly higher SOC and TN than SG. The positive linear relationships of SOC or TN with ABG were identified for SG. However, GG showed structurally more complex and less readily decomposed root DOM, a larger root volume, total root length and surface area than SG. Collectively, these suggested that intensive N fertilization could increase C and N stocks in bioenergy cropland soils but these effects may be more likely mediated by the aboveground biomass in SG and root chemistry and morphology in GG. Future studies are expected to examine the root characteristics in different bioenergy croplands under the field fertilization experiment.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Autoencoder Neural Network for chemically reacting systems

Incorporating detailed chemical kinetic models is critical for accurate simulations of reacting flows. However, detailed models involve a large number of thermochemical (TC) state variables. Solving the governing equations to evolve these TC variables becomes impractical for real-world applications. In this work, we propose an autoencoder (AE) neural network (NN)-based reduced model to accelerate such simulations. The AE NN is first trained to find a low-dimensional latent representation of the TC states. Then, the evolving state of a chemical system can be tracked by solving the equations of the latent variables instead of the original TC equations. We demonstrate the reduced model in a syngas CO/H 2 combustion system, using training data collected from canonical perfectly stirred reactors (PSRs). It is found that the AE model can reduce the dimension of the combustion system from 12 to 2 while maintaining low reconstruction error and excellent elemental mass conservation for the test dataset. In the a posteriori test, the combustion states obtained from solving the two latent equations are compared to those from solving the 12 equations of the full model. The AE reduced method is found to be able to capture the diverse combustion states on the top two branches of the S-curve well including the extinction turning point, but with higher prediction errors for states near the ignition turning point.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Applying Machine Learning and Bayesian Inference to Identify and Locate Moving Anthropogenic Sources Using Distributed Acoustic Sensing Data

Distributed acoustic sensing (DAS) systems, which use existing telecommunication fibers, offer high‐resolution capabilities ideal for recording anthropogenic sources. However, the complexity of urban environments and the large amount of data recorded by DAS require automated methods to efficiently detect and categorize anthropogenic sources. Here, we evaluate how well three machine learning models (k‐nearest neighbor [k‐NN], convolutional neural networks, and recurrent‐convolutional neural networks) can identify various anthropogenic sources recorded by DAS. Our findings reveal that both k‐NN and neural network methods perform well in high signal‐to‐noise ratio (SNR) settings. However, their accuracy decreases at SNRs <4. We also use Kalman filtering, a form of Bayesian inference, on backprojected locations of these sources to recover locations that generally fall within standard smartphone Global Positioning System errors. By combining machine learning and Kalman filter results, we calculate a multidimensional model of moving anthropogenic sources. These results demonstrate the potential of DAS data in urban seismology for accurately identifying and locating such sources. Depending on the research objectives, these sources can be further studied or filtered out to improve the quality of seismic data for earthquake studies. Such methods provide a valuable tool for urban seismology and seismic hazard analysis.

Luckie, Thomas William [Sandia National Laboratori↗

DOE OSTI2022

Joule heating in bad and slow metals

Heat supplied to a metal is absorbed by the electrons and then transferred to the lattice. In conventional metals energy is released to the lattice by phonons emitted from the Lindhard continuum. However in a 'bad' metal, with short mean free path, the low energy Lindhard continuum is destroyed. To describe energy transfer to the lattice in these cases we obtain a general Kubo formula for the energy relaxation rate in terms of the electronic density spectral weight \text{lm} \, G^R_{nn}(\omega_{k},k) lm G n n R ( ω k , k ) evaluated on the phonon dispersion \omega_k ω k . We apply our Kubo formula to the high temperature Hubbard model, using recent data from quantum Monte Carlo and experiments in ultracold atoms to characterize \text{lm} \, G^R_{nn}(\omega_{k},k) lm G n n R ( ω k , k ) . We furthermore use recent data from electron energy-loss spectroscopy to estimate the energy relaxation rate of the cuprate strange metal to a high energy optical phonon. As a second, distinct, application of our formalism we consider 'slow' metals. These are defined to have Fermi velocity less than the sound velocity, so that particle-hole pairs are kinematically unable to emit phonons. We obtain an expression for the energy relaxation rate of a slow metal in terms of the optical conductivity.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Power System Waveform Classification Using Time-Frequency and CNN

Many modern reclosers and circuit breakers have microprocessor relays that record waveforms of system events. In some cases, utilities may record a half-a-dozen event captures for every event. This is thousands of events per year. The industry needs faster, more automated, more conclusive, and easy-to-use systems that can process massive amounts of event recordings without extensive input/support from power system engineers. To address the need for a commercially viable solution that can classify waveform data, energies were directed to develop a universal neural network (NN) structure (deep learning algorithm) that works for a wide variety of system event types. The structure that showed the most promise was one that included the use of spectrograms. The technique has shown positive results in audio engineering, particularly with respect to speech recognition. A waveform signature could be treated as a spoken word like audio waveforms for specific things such as “YES” or “UP”. No two people produce the exact same waveform when speaking each of these words, but audio processing algorithms based on spectrograms and convolutional neural networks (CNN) can still distinguish the word regardless of the speaker. No two circuits produce the exact same waveform for a given event, but the NN can be trained to classify the event type regardless of the circuit or location on the circuit. A Power System Neural Network (PSNN) has been developed to use a CNN to classify events within waveform data for power systems. The waveform is converted to an array of values by way of spectrograms and interpreted as an image. This image is passed into the CNN. The test results on independent simulated test and validation datasets show greater than 99% accuracy. While the results thus far are based on simulated data, the performance of the PSNN is very promising and should work for a wide variety of power system conditions of interest. Ultimately, much of the custom code and tools used today and much of the manual effort expended today may be automated using this PSNN.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

Model-Form Epistemic Uncertainty Quantification for Modeling with Differential Equations: Application to Epidemiology

Modeling real-world phenomena to any degree of accuracy is a challenge that the scientific research community has navigated since its foundation. Lack of information and limited computational and observational resources necessitate modeling assumptions which, when invalid, lead to model-form error (MFE). The work reported herein explored a novel method to represent model-form uncertainty (MFU) that combines Bayesian statistics with the emerging field of universal differential equations (UDEs). The fundamental principle behind UDEs is simple: use known equational forms that govern a dynamical system when you have them; then incorporate data-driven approaches – in this case neural networks (NNs) – embedded within the governing equations to learn the interacting terms that were underrepresented. Utilizing epidemiology as our motivating exemplar, this report will highlight the challenges of modeling novel infectious diseases while introducing ways to incorporate NN approximations to MFE. Prior to embarking on a Bayesian calibration, we first explored methods to augment the standard (non-Bayesian) UDE training procedure to account for uncertainty and increase robustness of training. In addition, it is often the case that uncertainty in observations is significant; this may be due to randomness or lack of precision in the measurement process. This uncertainty typically manifests as “noisy” observations which deviate from a true underlying signal. To account for such variability, the NN approximation to MFE is endowed with a probabilistic representation and is updated using available observational data in a Bayesian framework. By representing the MFU explicitly and deploying an embedded, data-driven model, this approach enables an agile, expressive, and interpretable method for representing MFU. In this report we will provide evidence that Bayesian UDEs show promise as a novel framework for any science-based, data-driven MFU representation; while emphasizing that significant advances must be made in the calibration of Bayesian NNs to ensure a robust calibration procedure.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Implementing machine learning methods on QICK hardware for qubit readout & control

Quantum readout and control is a fundamental aspect of quantum computing that requires accurate measurement of qubit states. Errors emerge in all stages, from initialization to readout, and identifying errors in post-processing necessitates resource-intensive statistical analysis. In our work, we use a lightweight fully-connected neural network (NN) to classify states of a transmon system with no prior processing. Our NN accelerator yields higher fidelities (92%) than the classical matched filter method (84%). By exploiting the natural parallelism of NNs and their placement near the source of data on field-programmable gate arrays (FPGAs), we can achieve ultra-low latency on the Quantum Instrumentation Control Kit (QICK). Integrating machine learning methods on QICK opens several pathways for efficient real-time processing of quantum circuits.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Performance Comparison of Machine Learning Models for Ultrasonic Nondestructive Evaluation of Alkali-Silica Reaction in Concrete

Alkali-silica reaction (ASR) causes concrete degradation, leading to cracking, rebar corrosion, and reduced structural integrity, which raises safety concerns. Ultrasonic nondestructive evaluation (NDE) effectively assesses concrete properties and monitors ASR progression. However, its deployment and analysis require specialized expertise and subjective interpretation. As computational power increases, artificial intelligence (AI) and machine learning (ML) algorithms are increasingly being used to automate NDE data analysis across various industries for AI-assisted automation. Regulatory agencies are adapting to this technological shift, prompting a need to evaluate current ML technologies’ capabilities and limitations in assessing concrete material properties and damage. This report presents a comparative analysis of four ML regression models for predicting concrete material damage induced by ASR expansion using long-term ultrasonic data monitoring. The models investigated include linear regression (LR), support vector regression (SVR), shallow neural networks (NN), and deep neural networks (DNN). LR, SVR, and shallow NN models use features extracted from ultrasonic signals, whereas the DNN model processes time-domain ultrasonic signals and frequency spectra directly. The study systematically compared the models’ performance from various perspectives, including model input, prediction performance, and generalization ability. The findings indicate significant variability in model performance, with some ML algorithms achieving very high or very low prediction accuracy depending on the preprocessing and feature engineering (extraction and selection) applied. Key insights include the observation that shallow ML models (LR, SVR, and shallow NNs) require meticulous preprocessing and feature extraction to achieve high accuracy. In contrast, the DNN model, although it bypasses the need for feature engineering, necessitates extensive preprocessing to mitigate noise and computational demands. The SVR model emerged as the top performer among the shallow models, and the DNN model exhibited superior performance on specific datasets but struggled with generalization across specimens from different batches. Additionally, the SVR model is sensitive to temperature variations, whereas the DNN model is robust in this regard. Using recurrent neural networks is recommended for future ASR expansion prediction studies. Recurrent neural networks’ inherent ability to capture temporal dependencies and long-term patterns makes them well suited for analyzing sequential ultrasonic monitoring data. Overall, the results and conclusions of this study could provide insights into the capabilities and effectiveness of ML when applied to ultrasonic NDE data and help identify best practices for using ML for ultrasonic NDE of concrete material properties.

36 MATERIALS SCIENCE↗