Search NASA⌕ Search

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.

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

At least 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

Quasi-periodic Fast-mode Wave Trains Within a Global EUV Wave and Sequential Transverse Oscillations Detected by SDO-AIA

We present the first unambiguous detection of quasi-periodic wave trains within the broad pulse of a global EUV wave (so-called EIT wave) occurring on the limb. These wave trains, running ahead of the lateral coronal mass ejection (CME) front of 2-4 times slower, coherently travel to distances greater than approximately solar radius/2 along the solar surface, with initial velocities up to 1400 kilometers per second decelerating to approximately 650 kilometers per second. The rapid expansion of the CME initiated at an elevated height of 110 Mm produces a strong downward and lateral compression, which may play an important role in driving the primary EUV wave and shaping its front forwardly inclined toward the solar surface. The wave trains have a dominant 2 minute periodicity that matches the X-ray flare pulsations, suggesting a causal connection. The arrival of the leading EUV wave front at increasing distances produces an uninterrupted chain sequence of deflections and/or transverse (likely fast kink mode) oscillations of local structures, including a flux-rope coronal cavity and its embedded filament with delayed onsets consistent with the wave travel time at an elevated (by approximately 50%) velocity within it. This suggests that the EUV wave penetrates through a topological separatrix surface into the cavity, unexpected from CME-caused magnetic reconfiguration. These observations, when taken together, provide compelling evidence of the fast-mode MHD wave nature of the primary (outer) fast component of a global EUV wave, running ahead of the secondary (inner) slow component of CME-caused restructuring.

Solar Corona↗
NASA NTRSDate not supplied

Compression of Solar Spectroscopic Observations: a Case Study of MgII k Spectral Line Profiles Observed by NASA’s IRIS Satellite

In this study we extract the deep features and investigate the compression of the MgII k spectral line profiles observed in quiet Sun regions by NASA’s IRIS satellite. The data set of line profiles used for the analysis was obtained on April 20th, 2020, at the center of the solar disc, and contains almost 300,000 individual MgII k line profiles after data cleaning. The data are separated into train and test subsets. The train subset was used to train the autoencoder of the varying embedding layer size. The early stopping criterion was implemented on the test subset to prevent the model from overfitting. Our results indicate that it is possible to compress the spectral line profiles more than 27 times (which corresponds to the reduction of the data dimensionality from 110 to 4) while having a 4DN average reconstruction error, which is comparable to the variations in the line continuum. The mean squared error and the reconstruction error of even statistical moments sharply decrease when the dimensionality of the embedding layer increases from 1 to 4 and almost stop decreasing for higher numbers. The observed occasional improvements in training for values higher than 4 indicate that a better compact embedding may potentially be obtained if other training strategies and longer training times are used. The features learned for the critical four-dimensional case can be interpreted. In particular, three of these four features mainly control the line width, line asymmetry, and line dip formation respectively. The presented results are the first attempt to obtain a compact embedding for spectroscopic line profiles and confirm the value of this approach, in particular for feature extraction, data compression, and denoising.

SMD↗
NASA NTRS2009

Hardware Implementation of Lossless Adaptive and Scalable Hyperspectral Data Compression for Space

On-board lossless hyperspectral data compression reduces data volume in order to meet NASA and DoD limited downlink capabilities. The technique also improves signature extraction, object recognition and feature classification capabilities by providing exact reconstructed data on constrained downlink resources. At JPL a novel, adaptive and predictive technique for lossless compression of hyperspectral data was recently developed. This technique uses an adaptive filtering method and achieves a combination of low complexity and compression effectiveness that far exceeds state-of-the-art techniques currently in use. The JPL-developed 'Fast Lossless' algorithm requires no training data or other specific information about the nature of the spectral bands for a fixed instrument dynamic range. It is of low computational complexity and thus well-suited for implementation in hardware. A modified form of the algorithm that is better suited for data from pushbroom instruments is generally appropriate for flight implementation. A scalable field programmable gate array (FPGA) hardware implementation was developed. The FPGA implementation achieves a throughput performance of 58 Msamples/sec, which can be increased to over 100 Msamples/sec in a parallel implementation that uses twice the hardware resources This paper describes the hardware implementation of the 'Modified Fast Lossless' compression algorithm on an FPGA. The FPGA implementation targets the current state-of-the-art FPGAs (Xilinx Virtex IV and V families) and compresses one sample every clock cycle to provide a fast and practical real-time solution for space applications.

FPGA implementation↗
NASA NTRS2009

Fast and Adaptive Lossless On-Board Hyperspectral Data Compression System for Space Applications

Efficient on-board lossless hyperspectral data compression reduces the data volume necessary to meet NASA and DoD limited downlink capabilities. The techniques also improves signature extraction, object recognition and feature classification capabilities by providing exact reconstructed data on constrained downlink resources. At JPL a novel, adaptive and predictive technique for lossless compression of hyperspectral data was recently developed. This technique uses an adaptive filtering method and achieves a combination of low complexity and compression effectiveness that far exceeds state-of-the-art techniques currently in use. The JPL-developed 'Fast Lossless' algorithm requires no training data or other specific information about the nature of the spectral bands for a fixed instrument dynamic range. It is of low computational complexity and thus well-suited for implementation in hardware, which makes it practical for flight implementations of pushbroom instruments. A prototype of the compressor (and decompressor) of the algorithm is available in software, but this implementation may not meet speed and real-time requirements of some space applications. Hardware acceleration provides performance improvements of 10x-100x vs. the software implementation (about 1M samples/sec on a Pentium IV machine). This paper describes a hardware implementation of the JPL-developed 'Fast Lossless' compression algorithm on a Field Programmable Gate Array (FPGA). The FPGA implementation targets the current state of the art FPGAs (Xilinx Virtex IV and V families) and compresses one sample every clock cycle to provide a fast and practical real-time solution for Space applications.

image compression↗
DOE OSTI2021

AN AUTOMATED MACHINE LEARNING-GENETIC ALGORITHM FRAMEWORK WITH ACTIVE LEARNING FOR DESIGN OPTIMIZATION

The use of machine learning (ML)-based surrogate models is a promising technique to significantly accelerate simulation-driven design optimization of internal combustion (IC) engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, training the ML models requires hyperparameter selection, which is often done using trial-and-error and domain expertise. Another challenge is that the data required to train these models are often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a super learner model. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization while also reducing the number of simulations needed for performing surrogate-based design optimization.

Owoyele, Opeoluwa↗
DOE OSTI2020

Predicting the proximity to macroscopic failure using local strain populations from dynamic in situ X-ray tomography triaxial compression experiments on rocks

Predicting the proximity of large-scale dynamic failure is a critical concern in the engineering and geophysical sciences. Here we use evolving contractive, dilatational, and shear strain deformation preceding failure in dynamic X-ray tomography experiments to examine which strain components best predict the proximity to failure. We develop machine learning models to predict the proximity to failure using time series of three-dimensional local incremental strain tensor fields acquired in rock deformation experiments under stress conditions of the upper crust. Three-dimensional scans acquired in situ throughout triaxial compression experiments provide a distribution of density contrasts from which we estimate the three-dimensional incremental strain that accumulates between each scan acquisition. Training machine learning models on multiple experiments of six rock types provides suites of feature importance that indicate the predictive power of each feature. Comparing the average importance of groups of features that include information about each strain component quantifies the ability of the contractive, dilatational and shear strain to predict the proximity of macroscopic failure. A total of 24 models of four machine learning algorithms with six rock types indicate that 1) the dilatational strain provides the best predictive power of the strain components, and 2) the intermediate values (25th-75th percentile) of the strain population provide the best predictive power of the statistics of the strain populations. In addition, the success of the predictions of models trained on one rock type and tested on other rock types quantifies the similarities and differences of the precursory strain accumulation process in the six rock types. These similarities suggest the potential existence of a unified theory of brittle rock deformation for a range of rock types.

58 GEOSCIENCES↗
DOE OSTI2020

Provable Convergence of Plug-and-Play Priors With MMSE Denoisers

Plug-and-play priors (PnP) is a methodology for regularized image reconstruction that specifies the prior through an image denoiser. While PnP algorithms are well understood for denoisers performing maximum a posteriori probability (MAP) estimation, they have not been analyzed for the minimum mean squared error (MMSE) denoisers. Here we address this gap by establishing the first theoretical convergence result for the iterative shrinkage/thresholding algorithm (ISTA) variant of PnP for MMSE denoisers. We show that the iterates produced by PnP-ISTA with an MMSE denoiser converge to a stationary point of some global cost function. We validate our analysis on sparse signal recovery in compressive sensing by comparing two types of denoisers, namely the exact MMSE denoiser and the approximate MMSE denoiser obtained by training a deep neural net.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Artificial Neural Network Models for Octane Number and Octane Sensitivity: A Quantitative Structure Property Relationship Approach to Fuel Design

Octane sensitivity (OS), defined as the research octane number (RON) minus the motor octane number (MON) of a fuel, has gained interest among researchers due to its effect on knocking conditions in internal combustion engines. Compounds with a high OS enable higher efficiencies, especially within advanced compression ignition engines. RON/MON must be experimentally tested to determine OS, requiring time, funding, and specialized equipment. Thus, predictive models trained with existing experimental data and molecular descriptors (via quantitative structure-property relationships (QSPRs)) would allow for the preemptive screening of compounds prior to performing these experiments. Here, the present work proposes two methods for predicting the OS of a given compound: using artificial neural networks (ANNs) trained with QSPR descriptors to predict RON and MON individually to compute OS (derived octane sensitivity (dOS)), and using ANNs trained with QSPR descriptors to directly predict OS. Twenty-five ANNs were trained for both RON and MON and their test sets achieved an overall 6.4% and 5.2% error, respectively. Twenty-five additional ANNs were trained for both dOS and OS; dOS calculations were found to have 15.3% error while predicting OS directly resulted in 9.9% error. A chemical analysis of the top QSPR descriptors for RON/MON and OS is conducted, highlighting desirable structural features for high-performing molecules and offering insight into the inner mathematical workings of ANNs; such chemical interpretations study the interconnections between structural features, descriptors, and fuel performance showing that connectivity, structural diversity, and atomic hybridization consistently drive fuel performance.

09 BIOMASS FUELS↗
NASA NTRS1989

Vector excitation speech or audio coder for transmission or storage

A vector excitation coder compresses vectors by using an optimum codebook designed off line, using an initial arbitrary codebook and a set of speech training vectors exploiting codevector sparsity (i.e., by making zero all but a selected number of samples of lowest amplitude in each of N codebook vectors). A fast-search method selects a number N.sub.c of good excitation vectors from the codebook, where N.sub.c is much smaller tha ORIGIN OF INVENTION The invention described herein was made in the performance of work under a NASA contract, and is subject to the provisions of Public Law 96-517 (35 USC 202) under which the inventors were granted a request to retain title.

Davidson, Grant↗
NASA NTRS2015

On the Recovery Stress of a Ni50.3Ti29.7Hf20 High Temperature Shape Memory Alloy

Recovery stress in shape memory alloys (SMAs), also known as blocking stress, is an important property generally obtained during heating under a dimensional constraint as the material undergoes the martensitic phase transformation. This property has been instinctively utilized in most SMA shape-setting procedures, and has been used in numerous applications such as fastening and joining, rock splitting, safety release mechanisms, reinforced composites, medical devices, and many other applications. The stress generation is also relevant to actuator applications where jamming loads (e.g., in case the actuator gets stuck and is impeded from moving) need to be determined for proper hardware sizing. Recovery stresses in many SMA systems have been shown to reach stresses in the order of 800 MPa, achieved via thermo-mechanical training such as pre-straining, heat treatments or other factors. With the advent of high strength, high temperature SMAs, recovery stress data has been rarely probed, and there is no information pertinent to the magnitudes of these stresses. Thus, the purpose of this work is to investigate the recovery stress capability of a precipitation strengthened, Ni50.3Ti29.7Hf20 (at.) high temperature SMA in uniaxial tension and compression. This material has been shown to exhibit outstanding strength and stability during constant-stress, thermal cycling, but no data exists on constant-strain thermal cycling. Several training routines were implemented as part of this work including isothermal pre-straining, isobaric thermal cycling, and isothermal cyclic training routines. Regardless of the training method used, the recovery stress was characterized using constant-strain (strain-controlled condition) thermal cycling between the upper and lower cycle temperatures. Preliminary results indicate recovery stresses in excess of 1.5 GPa were obtained after a specific training routine. This stress magnitude is significantly higher than conventional NiTi stress generation capability.

Recovery Stress↗
NASA NTRS2023

Neural-Based Compression Scheme for Solar Image Data

Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold decision to make. Stronger compression methods, by distorting the data, can increase data throughput at the cost of accuracy which could affect scientific analysis of the data. On the other hand, preserving subtle details in the compressed data requires a high amount of data to be transferred, reducing the desired gains from compression. In this work, we propose a neural network-based lossy compression method to be used in NASA’s data-intensive imagery missions. We chose NASA’s Solar Dynamics Observatory (SDO) mission which transmits 1.4 terabytes of data each day as a proof of concept for the proposed algorithm. In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image resulting in a better trade-off in rate-distortion (RD) compared to conventional hand-engineered codecs. The RD variational autoencoder used in this work is jointly trained with a channel-dependent entropy model as a shared prior between the analysis and synthesis transforms to make the entropy coding of the latent code more effective. We also studied how optimizing perceptual losses could help our neural compressor to preserve high-frequency details of the data in the reconstructed compressed image. Our neural image compression algorithm outperforms currently-in-use and state-of-the-art codecs such as JPEG and JPEG-2000 in terms of the RD performance when compressing extreme-ultraviolet (EUV) data. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole (CH) detection using our compressed images, and generated consistent segmentations, even at a compression rate of ∼ 0.1 bits per pixel (compared to 8 bits per pixel on the original data) using EUV data from SDO.

Image coding↗
DOE OSTI2026

Development of an ab initio learned model of electron deposition range in deuterium-tritium plasmas through time-dependent density functional theory calculations and machine learning

Accurate hydrodynamic modeling for laser-direct-drive (LDD) inertial-confinement-fusion (ICF) relies on precise calculations of the electron thermal conduction in all target materials. The nonlocal stopping range of electrons in ICF plasmas directly influences thermal conduction; yet, no first principles model exists for the electron mean free path in the conduction-zone regime. This work utilized time-dependent stochastic density-functional theory (TD-sDFT) to calculate the electron stopping power in deuterium-tritium (DT) plasmas at (ρ, T) conditions relevant to the conduction zone and the compressed shell in ICF. Using a combination of our TD-sDFT data and already established analytical models, we developed and trained an artificial neural network to create a global model for the nonlocal electron deposition range, λ E . We compared our machine-learning (ML) based model for λ E to the currently-used modified-Lee-More model in LDD radiation-hydrodynamic codes, such as lilac, and saw an overall decrease in the deposition range. To understand the effects of λ E on LDD ICF implosion dynamics, we implemented the ML-based model into lilac; specifically, we looked at designs consistent with a current experiment on the OMEGA laser and for a newly designed LDD-ICF target for the future OMEGA-Next facility. In both cases, we saw an overall drop in predicted ablation pressure, peak areal density, and neutron yield due to the reduced thermal conduction (smaller λ E ) in DT plasmas. Comparisons with the experiment on OMEGA are also made.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1993

Active stabilization to prevent surge in centrifugal compression systems

This report documents an experimental and analytical study of the active stabilization of surge in a centrifugal engine. The aims of the research were to extend the operating range of a compressor as far as possible and to establish the theoretical framework for the active stabilization of surge from both an aerodynamic stability and a control theoretic perspective. In particular, much attention was paid to understanding the physical limitations of active stabilization and how they are influenced by control system design parameters. Previously developed linear models of actively stabilized compressors were extended to include such nonlinear phenomena as bounded actuation, bandwidth limits, and robustness criteria. This model was then used to systematically quantify the influence of sensor-actuator selection on system performance. Five different actuation schemes were considered along with four different sensors. Sensor-actuator choice was shown to have a profound effect on the performance of the stabilized compressor. The optimum choice was not unique, but rather shown to be a strong function of some of the non-dimensional parameters which characterize the compression system dynamics. Specifically, the utility of the concepts were shown to depend on the system compliance to inertia ratio ('B' parameter) and the local slope of the compressor speedline. In general, the most effective arrangements are ones in which the actuator is most closely coupled to the compressor, such as a close-coupled bleed valve inlet jet, rather than elsewhere in the flow train, such as a fuel flow modulator. The analytical model was used to explore the influence of control system bandwidth on control effectiveness. The relevant reference frequency was shown to be the compression system's Helmholtz frequency rather than the surge frequency. The analysis shows that control bandwidths of three to ten times the Helmholtz frequency are required for larger increases in the compressor flow range. This has important implications for implementation in gas turbine engines since the Helmholtz frequencies can be over 100 Hz, making actuator design extremely challenging.

Epstein, Alan H.↗
NASA NTRS1994

The effects of Above Real-Time Training (ARTT) in an F-16 simulator

In this application of above real-time training (ARTT), 24 mission-capable F-16 pilots performed three tasks on a part-task F-16A flight simulator under varying levels of time compression (i.e., 1.0x, 1.5x, 2.0x, and random). All subjects were then tested in a real-time (1.0x) environment. The three tasks under study were an emergency procedure (EP) task, a one versus two air combat maneuvering (ACM) task, and a stern conversion or air intercept task. All ARTT pilots performed the EP task with 28 percent greater accuracy and were better at dealing with a simultaneous MIG threat, reflected by a six-fold increase in the number of MIG kills compared to a real-time control group. In the stern conversion task, there were no statistical differences between groups. In the ACM task, those pilots trained in the mixed time accelerations were faster to acquire lock and were faster to kill both MIG threats than the other groups. These findings are generally consistent with previous findings that show positive effects of task variations (including time variations) during training. Also discussed are related research findings that support the benefits of ARTT and ARTT's impact on emergency procedure training. Further, a synthesis of multidiscipline research outlining the underlying theoretical basis for ARTT is presented. A proposed model of ARTT based on an analogy to Einstein's theory of special relativity is suggested. Conclusions and an outline of future research directions are presented. Successful current commercialization efforts are related as well as future efforts.

Guckenberger, Dutch↗
DOE OSTI2022

Multi-frame, ultrafast, x-ray microscope for imaging shockwave dynamics

Inertial confinement fusion (ICF) holds increasing promise as a potential source of abundant, clean energy, but has been impeded by defects such as micro-voids in the ablator layer of the fuel capsules. It is critical to understand how these micro-voids interact with the laser-driven shock waves that compress the fuel pellet. At the Matter in Extreme Conditions (MEC) instrument at the Linac Coherent Light Source (LCLS), we utilized an x-ray pulse train with ns separation, an x-ray microscope, and an ultrafast x-ray imaging (UXI) detector to image shock wave interactions with micro-voids. To minimize the high- and low-frequency variations of the captured images, we incorporated principal component analysis (PCA) and image alignment for flat-field correction. After applying these techniques we generated phase and attenuation maps from a 2D hydrodynamic radiation code (xRAGE), which were used to simulate XPCI images that we qualitatively compare with experimental images, providing a one-to-one comparison for benchmarking material performance. Moreover, we implement a transport-of-intensity (TIE) based method to obtain the average projected mass density (areal density) of our experimental images, yielding insight into how defect-bearing ablator materials alter microstructural feature evolution, material compression, and shock wave propagation on ICF-relevant time scales.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC

Federated Learning (FL) is critical for edge and High Performance Computing (HPC) where data is not centralized and privacy is crucial. We present OmniFed, a modular framework designed around decoupling and clear separation of concerns for configuration, orchestration, communication, and training logic. Its architecture supports configuration-driven prototyping and code-level override-what-you-need customization. We also support different topologies, mixed communication protocols within a single deployment, and popular training algorithms. It also offers optional privacy mechanisms including Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Aggregation (SA), as well as compression strategies. These capabilities are exposed through well-defined extension points, allowing users to customize topology and orchestration, learning logic, and privacy/compression plugins, all while preserving the integrity of the core system. We evaluate multiple models and algorithms to measure various performance metrics. By unifying topology configuration, mixed-protocol communication, and pluggable modules in one stack, OmniFed streamlines FL deployment across heterogeneous environments. Github repository is available at https://github.com/at-aaims/OmniFed.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗
NASA NTRS1974

New theoretical models and ratio imaging techniques associated with the NASA earth resources spectral information system

Four independent investigations are reported; in general these are concerned with improving and utilizing the correlation between the physical properties of natural materials as evidenced in laboratory spectra and spectral data collected by multispectral scanners. In one investigation, two theoretical models were devised that permit the calculation of spectral emittance spectra for rock and mineral surfaces of various particle sizes. The simpler of the two models can be used to qualitatively predict the effect of texture on the spectral emittance of rocks and minerals; it is also potentially useful as an aid in predicting the identification of natural atmospheric aerosol constituents. The second investigation determined, via an infrared ratio imaging technique, the best pair of infrared filters for silicate rock-type discrimination. In a third investigation, laboratory spectra of natural materials were compressed into 11-digit ratio codes for use in feature selection, in searches for false alarm candidates, and eventually for use as training sets in completely automatic data processors. In the fourth investigation, general outlines of a ratio preprocessor and an automatic recognition map processor are developed for on-board data processing in the space shuttle era.

Vincent, R. K.↗
DOE OSTI2025

Exploring Black-box Adversarial Attacks on Low-rank Constrained Neural Networks

Low-rank compression has been shown as an effective tool to reduce parameter counts of convolutional and vision transformer architectures; however, low-rank training often reduces model robustness to adversarial perturbations. In this work, we explore the effects of low-rank training on black-box attacks, where attacked images are generated without knowledge of the low-rank parameters. We find that low-rank training is not sufficient as a black-box defense and can sometimes produce worse than expected as compared to baseline models. Influencing the spectrum of the low-rank models during training, which is known to increase model robustness against white-box attacks, improves black-box performance as well.

Schnake, Stefan [ORNL] (ORCID:0000000215183538)↗