SEARCH · Search NASA

Results for “compressed training”

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 235 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Enabling accurate chemical modeling of shocked energetic materials using a machine learning interatomic potential

Understanding the complex chemistry of organic materials under dynamic compression is important for many applications, but it is challenging due to the large number of reactions occurring at various time scales. Here, in this study, we develop a machine learning potential based on Chebyshev polynomials to study the insensitive energetic material 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) under detonation. We discuss a strategy for constructing diverse training data needed to capture the complex chemistry of TATB. Our potential demonstrates strong transferability across a wide range of thermodynamic conditions and other explosives, enabling accurate and reliable chemical modeling of organic materials under extreme conditions. The efficiency of our approach allows for simulations over several nanoseconds and for large system sizes, providing detailed insights into the chemistry of shocked TATB. The model accurately reproduces experimental Hugoniot equation of state data, and our simulations reveal the rapid formation of nitrogen-rich carbon clusters following shock. The methods and datasets developed here offer a robust framework for accurate chemical modeling of other shocked organic energetic materials.

Chemistry↗

NASA NTRS1995

Searching for patterns in remote sensing image databases using neural networks

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Paola, Justin D.↗

DOE OSTI2025

Modeling the Interaction of Laser-Produced Proton Beams with Matter

A major goal of this project is to significantly increase our understanding of isochoric heating of matter using laser produced proton beams, and the associated high energy density (HED) and warm dense matter (WDM) regimes generated. This will benefit research fields such as planetary science, fusion energy, plasma physics, and material science. For example, it will enhance our understanding of WDM properties of iron and silica under conditions encountered in planetary interiors and diagnostic components in fusion devices exposed to high fluxes of energetic plasma ions. The project is motivated by recent experiments that irradiated Si targets with proton beams generated by the 20 TW-laser at the SLAC MEC end-station. The HED/WDM states are probed using the 50 fs hard X-rays available in the 3rd harmonic of the LCLS. As part of this project, results from the phase contrast X-ray imaging, which shows the generation of compression waves that produces rear surface spallation, are compared with results from the 3D multi-physics multi- material code, PISALE, that combines Arbitrary Lagrangian-Eulerian (ALE) hydrodynamics with Adaptive Mesh Refinement (AMR). This comparison required modifications to several physics models in the PISALE (Pacific Island Structured-AMR with ALE) code. An important aspect of this project is the continued training of graduate students in HED physics and in conducting complex multiphysics simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Tensor Network Space-Time Spectral Collocation Method for Time-Dependent Convection-Diffusion-Reaction Equations

Emerging tensor network techniques for solutions of partial differential equations (PDEs), known for their ability to break the curse of dimensionality, deliver new mathematical methods for ultra-fast numerical solutions of high-dimensional problems. Here, we introduce a Tensor Train (TT) Chebyshev spectral collocation method, in both space and time, for the solution of the time-dependent convection-diffusion-reaction (CDR) equation with inhomogeneous boundary conditions, in Cartesian geometry. Previous methods for numerical solution of time-dependent PDEs often used finite difference for time, and a spectral scheme for the spatial dimensions, which led to a slow linear convergence. Spectral collocation space-time methods show exponential convergence; however, for realistic problems they need to solve large four-dimensional systems. We overcome this difficulty by using a TT approach, as its complexity only grows linearly with the number of dimensions. We show that our TT space-time Chebyshev spectral collocation method converges exponentially, when the solution of the CDR is smooth, and demonstrate that it leads to a very high compression of linear operators from terabytes to kilobytes in TT-format, and a speedup of tens of thousands of times when compared to a full-grid space-time spectral method. These advantages allow us to obtain the solutions at much higher resolutions.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Deep Koopman Neural Network for Analyzing High-Energy-Density Simulations of Electrical Wire Explosions

Megaampere-scale electrical wire experiments (EWEs) provide a platform for studying magnetohydrodynamic (MHD) instability growth in magneto-inertial fusion (MIF) devices. Even when nonlinear simulations of these experiments can digitally reproduce much of the experimentally observed instability growth, interpreting the results and understanding mode growth and evolution can be non-trivial. As a first step toward providing better interpretation of these simulation features, this work investigates the use of a deep neural network that uses Koopman operator theory to analyze the dynamics of pulsed-power-driven explosions of EWEs. This deep neural network is trained on 1-D resistive MHD simulations of EWEs. This neural network learns to transform the nonlinear data into a lower-dimensional representation where the time dynamics are linear. Layers of this neural network are shown to learn features of the simulations, including the locations of shock waves and different physical regimes of the simulation. Using the learned features, the network can compress a time state of the simulation consisting of 5120 data point into a 36-parameter lower-dimensional latent space embedding. Furthermore, these embeddings are shown to be clustered in the latent space by initial radius and time state.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Pressure-induced structural and dielectric changes in liquid water at room temperature

Understanding the pressure-dependent dielectric properties of water is crucial for a wide range of scientific and practical applications. In this study, we employ a deep neural network trained on density functional theory data to investigate the dielectric properties of liquid water at room temperature across a pressure range of 0.1–1000 MPa. We observe a nonlinear increase in the static dielectric constant ɛ 0 with increasing pressure, a trend that is qualitatively consistent with experimental observations. This increase in ɛ 0 is primarily attributed to the increase in water density under compression, which enhances collective dipole fluctuations within the hydrogen-bonding network as well as the dielectric response. Despite the increase in ɛ 0 , our results reveal a decrease in the Kirkwood correlation factor G K with increasing pressure. Furthermore, this decrease in G K is attributed to pressure-induced structural distortions in the hydrogen-bonding network, which weaken dipolar correlations by disrupting the ideal tetrahedral arrangement of water molecules.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Mesoscale shock structure in particulate composites

Multiscale experiments in heterogeneous materials and the knowledge of their physics under shock compression are limited. Here, this study examines the multiscale shock response of particulate composites comprised of soda-lime glass particles in a PMMA matrix using full-field high speed digital image correlation (DIC) for the first time. Normal plate impact experiments, and complementary numerical simulations, are conducted at stresses ranging from 1.1 - 3.1 GPa to elucidate the mesoscale mechanisms responsible for the distinct shock structure observed in particulate composites. The particle velocity from the macroscopic measurement at continuum scale shows a relatively smooth velocity profile, with shock thickness decreasing with an increase in shock stress, and the composite exhibits strain rate scaling as the second power of the shock stress. In contrast, the mesoscopic response was highly heterogeneous, which led to a rough shock front and the formation of a train of weak shocks traveling at different velocities. Additionally, the normal shock was seen to diffuse the momentum in the transverse direction, affecting the shock rise and the rounding-off observed at the continuum scale measurements. The numerical simulations indicate that the reflections at the interfaces, wave scattering, and interference of these reflected waves are the primary mechanisms for the observed rough shock fronts.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Understanding latent timescales in neural ordinary differential equation models of advection-dominated dynamical systems

The neural ordinary differential equation (ODE) framework has shown considerable promise in recent years in developing highly accelerated surrogate models for complex physical systems characterized by partial differential equations (PDEs). For PDE-based systems, state-of-the-art neural ODE strategies leverage a two-step procedure to achieve this acceleration: a nonlinear dimensionality reduction step provided by an autoencoder, and a time integration step provided by a neural-network based model for the resultant latent space dynamics (the neural ODE). This work explores the applicability of such autoencoder-based neural ODE strategies for PDEs in which advection terms play a critical role. More specifically, alongside predictive demonstrations, physical insight into the sources of model acceleration (i.e., how the neural ODE achieves its acceleration) is the scope of the current study. Such investigations are performed by quantifying the effects of both autoencoder and neural ODE components on latent system time-scales using eigenvalue analysis of dynamical system Jacobians. To this end, the sensitivity of various critical training parameters – de-coupled versus end-to-end training, latent space dimensionality, and the role of training trajectory length, for example – to both model accuracy and the discovered latent system timescales is quantified. Furthermore, this work specifically uncovers the key role played by the training trajectory length (the number of rollout steps in the loss function during training) on the latent system timescales: larger trajectory lengths correlate with an increase in limiting neural ODE time-scales, and optimal neural ODEs are found to recover the largest time-scales of the full-order (ground-truth) system. Demonstrations are performed across fundamentally different unsteady fluid dynamics configurations influenced by advection: (1) the Kuramoto–Sivashinsky equations (2) Hydrogen-Air channel detonations (the compressible reacting Navier–Stokes equations with detailed chemistry), and (3) 2D Atmospheric flow.

Advection-dominated dynamical systems↗

DOE OSTI2021

Combining In-situ Diagnostics and Data Analytics for Discovery of Process-Structure-Property Relationships in AM parts – A Step Toward Digital Twins

In-situ additive manufacturing (AM) diagnostic tools (e.g., optical/infrared imaging, acoustic, etc.) already exist to correlate process anomalies to printed part defects. This current work aimed to augment existing capabilities by: 1) Incorporating in-situ imaging w/ machine learning (ML) image processing software (ORNL- developed "Peregrine") for AM process anomaly detection 2) Synchronizing multiple in-situ sensors for simultaneous analysis of AM build events 3) Correlating in-situ AM process data, generated part defects and part mechanical properties The key R&D question investigated was to determine if these new combined hardware/software tools could be used to successfully quantify defect distributions for parts build via SNL laser powder bed fusion (LPBF) machines, aiming to better understand data-driven process-structure-property- performance relationships. High resolution optical cameras and acoustic microphones were successfully integrated in two LPBF machines and linked to the Peregrine ML software. The software was successfully calibrated on both machines and used to image hundreds of layers of multiple builds to train the ML software in identifying printed part vs powder. The software's validation accuracy to identify this aspect increased from 56% to 98.8% over three builds. Lighting conditions inside the chamber were found to significantly impact ML algorithm predictions from in-situ sensors, so these were tailored to each machine's internal framework. Finally, 3D part reconstructions were successfully generated for a build from the compressed stack of layer-wise images. Resolution differences nearest and furthest from the optical camera were discussed. Future work aims to improve optical resolution, increase process anomalies identified, and integrate more sensor modalities.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Distilling particle knowledge for fast reconstruction at high-energy physics experiments

Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. Its main application is the compactification of large deep neural networks to free up computational resources, in particular on edge devices. In this article, we consider proton-proton collisions at the High-Luminosity Large Hadron Collider (HL-LHC) and demonstrate a successful knowledge transfer from an event-level graph neural network (GNN) to a particle-level small deep neural network (DNN). Our algorithm, DistillNet, is a DNN that is trained to learn about the provenance of particles, as provided by the soft labels that are the GNN outputs, to predict whether or not a particle originates from the primary interaction vertex. The results indicate that for this problem, which is one of the main challenges at the HL-LHC, there is minimal loss during the transfer of knowledge to the small student network, while improving significantly the computational resource needs compared to the teacher. This is demonstrated for the distilled student network on a CPU, as well as for a quantized and pruned student network deployed on a field programmable gate array. Our study proves that knowledge transfer between networks of different complexity can be used for fast artificial intelligence (AI) in high-energy physics that improves the expressiveness of observables over non-AI-based reconstruction algorithms. Such an approach can become essential at the HL-LHC experiments, e.g. to comply with the resource budget of their trigger stages.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

AGC-4 Specimen Post-Irradiation Examination Data Interim Report

This interim report documents preliminary results of the post-irradiation examination material property testing from the fourth advanced graphite creep (AGC), AGC 4, capsule specimens. This is the fourth of a series of six irradiation test trains planned as part of the AGC experiment to fully characterize the neutron irradiation effects and radiation creep behavior of current nuclear graphite grades to moderate dose levels (=7 dpa). The AGC 4 capsule was irradiated in the Idaho National Laboratory Advanced Test Reactor at a nominal temperature of 800°C and to a peak dose of 8 dpa. Half of the AGC-4 specimens were subjected to compressive stresses to induce irradiation creep. Post-irradiation testing and measurement results are reported with the exception of thermal testing, which is still in progress, and irradiation mechanical strength testing. Additionally, some specimens initially deemed too hot to be examined in the ART Graphite laboratory may still be measured. The data reported includes specimen dimensions for both stressed and unstressed specimens to establish the irradiation creep rates, mass and dimensional data necessary to derive density, elastic constants (Young?s modulus, shear modulus, and Poisson?s ratio) from ultrasonic time of flight velocity measurements, Young?s modulus from the fundamental frequency of vibration, and electrical resistivity. A more complete evaluation of trends in the material property changes, as well as irradiation-induced creep due to the irradiation environment and applied load on the specimens, will be discussed later in AGC 4 post-irradiation examination analysis reports.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2025

AGC-4 Specimen Post-Irradiation Examination Data Interim Report

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2025

A Parametric, Data-Driven, Non-Intrusive Reduced-Order Model Framework for Crystal Plasticity Simulations of Voids

The influence of the internal structure at micrometer length scales on the deformation of polycrystalline materials can be effectively captured using crystal plasticity finite element methods (CPFEM). However, the complexity and nonlinearity of the deformation equations CPFEM solves demand significant computational power and resources to achieve accurate predictions, limiting its broader application. To address this challenge, we have identified a reduced-order representation of the complex data in order to establish a computationally efficient reduced-order models (ROM) and drastically reduce the computational expense of CPFEM. Specifically, in this work, we developed a parametric, data-driven, and non-intrusive ROM framework for CPFEM using proper orthogonal decomposition (POD) and sparse variational Gaussian process (SVGP) regression for single-crystal microstructures under tensile loading conditions. The developed protocol enables one to compress field into a latent/low-dimensional space described by principal component analysis (PCA) via the singular value decomposition (SVD) algorithm. As a result, the high-dimensional data are reduced to a significantly smaller amount of dimensions with POD bases and POD coefficients. Furthermore, we deployed an ensemble of SVGPs—extended from the classical Gaussian process (GP) regression for scalability and handling big data—in a massively parallel manner to train and predict latent POD coefficients using known POD bases from a set of previously obtained simulations results. Lastly, using the predicted POD coefficients, we reconstructed the full-field results and showed reasonable agreement compared with the true values obtained from running CPFEM. The developed framework is validated with a set of CPFEM simulations of a single embedded void in single-crystal aluminum alloy. While the framework is broadly applicable, this work specifically focuses on single-crystal microstructures, a single load case (e.g., tensile), and a specific void geometry (spherical).

Anisotropy↗

DOE OSTI2023

Lorentz group equivariant autoencoders

Abstract There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $$\textrm{SO}^+(3,1)$$ SO + ( 3 , 1 ) , with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

Expanding Access to Science Participation: A FAIR Framework for Petascale Data Visualization and Analytics

The massive data generated by scientists daily serve as both a major catalyst for new discoveries and innovations, as well as a significant roadblock that restricts access to the data. Here, our paper introduces a new approach to removing Big Data barriers and democratizing access to petascale data for the broader scientific community. Our novel data fabric abstraction layer allows user-friendly querying of scientific information while hiding the complexities of dealing with file systems or cloud services. We enable FAIR (Findable, Accessible, Interoperable, and Reusable) access to datasets such as NASA’s petascale climate datasets. Our paper presents an approach to managing, visualizing, and analyzing petabytes of data within a browser on equipment ranging from the top NASA supercomputer to commodity hardware like a laptop. Our novel data fabric abstraction utilizes state-of-the art progressive compression algorithms and machine-learning insights to power scalable visualization dashboards for petascale data. The result provides users with the ability to identify extreme events or trends dynamically, expanding access to scientific data and further enabling discoveries. We validate our approach by improving the ability of climate scientists to visually explore their data via three fully interactive dashboards. We further validate our approach by deploying the dashboards and simplified training materials in the classroom at a minority-serving institution. These dashboards, released in simplified form to the general public, contribute significantly to a broader push to democratize the access and use of climate data.

Computer science↗

NASA NTRS1995

A comparison of model-based VQ compression with other VQ approaches

In our previous work on Model-Based Vector Quantization (MVQ), we presented some performance comparisons (both rate distortion and decompression time) with VQ and JPED/DCT. In this paper, we compare the MVQ's rate distortion performance with Mean Removed Vector Quantization (MRVQ) and include our previous comparison with VQ. Both MVQ and MRVQ compute the mean of each vector (raster-scanned image block) and produce mean removed residual vectors by subtracting the block mean from the elements of each vector. In the case of MRVQ, a codebook of residual vectors is generated using a training set. For MVQ, an internal codebook is generated based on the statistical properties of the residual vectors, and upon correlations derived from a Human Visual System (HVS) model. In both MVQ and MRVQ, the block mean and address of the codevector from the codebook that most closely matches each input vector are transmitted to the decoder. MVQ, a single additional statistical parameter is transmitted to the decoder. For MRVQ, we assume that the codebook of residual vectors is available to the decoder. In our experiments, we found that the rate of distortion performance of MVQ is almost always better than VQ, and is comparable to MRVQ. Further, MVQ is much easier to use than either VQ or MRVQ, since the training and management of codebooks is not required.

Manohar, Mareboyana↗

NASA NTRS2015

Physiological Health Challenges for Human Missions to Mars

During the next decades, manned space missions are expected to be aiming at the Lagrange points, near Earth asteroids, and Mars flyby and/or landing. The question is therefore: Are we ready to go? To answer this with a yes, we are currently using the International Space Station to develop an integrated human physiological countermeasure suite. The integrated countermeasure suite will most likely encounter: 1) Exercise devices for aerobic, dynamic and resistive exercise training; 2) sensory‐motor computer training programs and anti‐motion sickness medication for preparing EVAs and G‐transitions; 3) lower limb bracelets for preventing and/or treating the VIIP (vision impairment and intracranial pressure) syndrome; 4) nutritional components for maintenance of bone, muscle, the cardiovascular system and preventing oxidative stress and damage and immune deficiencies (e. g. omega‐3 fatty acids, PRO/K, anti‐oxidants and less salt and iron); 5) bisphosphonates for preventing bone degradation.; 6) lower body compression garment and oral salt and fluid loading for landing on a planetary surface to combat orthostatic intolerance; 7) laboratory analysis equipment for individualized monitoring of biomarkers in blood, urine and saliva for estimation of health status in; 8) advanced ultrasound techniques for monitoring bone and cardiovascular health; and 9) computer modeling programs for individual health status assessments of efficiency and subsequent adjustments of countermeasures. In particular for future missions into deep space, we are concerned with the synergistic effects of weightlessness, radiation, operational constraints and other spaceflight environmental factors. Therefore, increased collaboration between physiological, behavioral, radiation and space vehicle design disciplines are strongly warranted. Another venue we are exploring in NASA's Human Research Program is the usefulness of artificial gravity for mitigating the health risks of long duration weightlessness.

Norsk, Peter↗

NASA NTRS1995

A comparison of model-based VQ compression with other VQ approaches

In our previous work on Model-Based Vector Quantization (MVQ), we presented some performance comparisons (both rate distortion and decompression time) with VQ and JPEG/DCT. In this paper, we compare the MVQ's rate distortion performance with Mean Removed Vector Quantization (MRVQ) and include our previous comparison with VQ. MVQ is similar to MRVQ in many ways. Both of these techniques extract means of the vectors (raster-scanned image blocks) and reduce them to mean removed residuals by subtracting block means from the elements of the vectors. In the case of MRVQ, a codebook of residual vectors is generated using a training set. For every vector from the input image, the block mean and address of the codevector from the codebook that matches the input vector closest are transmitted to the decoder. The codebook is generated using generalized Lloyd algorithm on training set of residual vectors. For MVQ the pairs consist of vector means and address of the closest matching vector from codebook generated by models based on statistical properties of the residuals and Human Visual System (HVS). In our experiments, we found that MVQ performance in rate distortion sense is almost always better than VQ and is comparable to MRVQ. Further, MVQ is much easier to use than either VQ or MRVQ, since the training and managing of explicit codebooks is not required.

Manohar, Mareboyana↗