Search NASA⌕ Search

SEARCH · Search NASA

Results for “Dimensionality Reduction”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values

Non-negative matrix factorization (NMF) is a dimensionality reduction technique that has shown promise for analyzing noisy data, especially astronomical data. For these datasets, the observed data may contain negative values due to noise even when the true underlying physical signal is strictly positive. Prior NMF work has not treated negative data in a statistically consistent manner, which becomes problematic for low signal-to-noise data with many negative values. In this paper we present two algorithms, Shift-NMF and Nearly-NMF, that can handle both the noisiness of the input data and also any introduced negativity. Both of these algorithms use the negative data space without clipping or masking and recover non-negative signals without any introduced positive offset that occurs when clipping or masking negative data. We demonstrate this numerically on both simple and more realistic examples, and prove that both algorithms have monotonically decreasing update rules.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Visual Analytics of Multivariate Networks With Representation Learning and Composite Variable Construction

Multivariate networks are commonly found in real-world data-driven applications. Uncovering and understanding the relations of interest in multivariate networks is not a trivial task. This article presents a visual analytics workflow for studying multivariate networks to extract associations between different structural and semantic characteristics of the networks (e.g., what are the combinations of attributes largely relating to the density of a social network?). The workflow consists of a neural-network-based learning phase to classify the data based on the chosen input and output attributes, a dimensionality reduction and optimization phase to produce a simplified set of results for examination, and finally an interpreting phase conducted by the user through an interactive visualization interface. A key part of our design is a composite variable construction step that remodels nonlinear features obtained by neural networks into linear features that are intuitive to interpret. We demonstrate the capabilities of this workflow with multiple case studies on networks derived from social media usage and also evaluate the workflow with qualitative feedback from experts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Characterization and differentiation of aluminum powders used in improvised explosive devices – Part 1: Proof of concept of the utility of particle micromorphometry

Abstract Aluminum (Al) powders are commonly used in improvised explosive devices as metallic fuels, a component of explosive mixtures. These powders can be obtained readily from industrial‐scale and consumer products, and produced using unsophisticated “kitchen chemistry” techniques. This research demonstrates the potential of automated particle micromorphometry for comparisons between known source and questioned Al powders recovered from IEDs, as well as for insight into the method of Al powder manufacture. Al powder samples were obtained from legitimate manufacturers, and 56 samples were produced “in‐house” from Al‐containing spray paints and ball‐milled Al foils. Transmitted light microscope images of Al powder particles were acquired using an automated stage with automated z‐focus; 17 size and shape parameters were measured for all particles. Approximately 37,000–2,500,000 particles/sample were analyzed using an open‐source statistical package with customized code. Dimensionality reduction was required for processing the large datasets: eight of the 17 measured variables were selected based on inspection of the correlation matrix. Data from four subsamples from each of the 56 samples produced using “in‐house” methods were analyzed using ANOVA to assess the within‐ and between‐sample variation. High within‐sample variation was noted; however, ANOVA and post‐hoc Tukey's honestly significant difference (HSD) tests demonstrated that the between‐sample variation was substantially larger than the within‐sample variation. Each sample could be differentiated from all other samples in the test set. Future experiments will focus on ways to reduce the within‐sample variation, and additional statistical and microanalytical methods to classify sources and confidently constrain the method of Al powder manufacture.

Baldaino, JenaMarie↗
DOE OSTI2024

Quantitative analysis of three-dimensional fatigue crack path selection in Mg alloy WE43 using high-energy X-ray diffraction microscopy

Fatigue short-cracks in Mg alloys display complex growth behavior due to high plastic anisotropy and crack path dependence on local microstructural features. In this study, the three-dimensional crystallography of short-crack paths in Mg alloy WE43 was characterized by mapping near-field high-energy X-ray diffraction microscopy (HEDM) reconstructed grain maps to high-resolution X-ray CT reconstructions of the fracture surfaces in the crack initiation and short-crack growth regions of six ultrasonic fatigue specimens. Crack–grain–boundary intersections were analyzed at 81 locations across the six crack paths. The basal intragranular, non-basal intragranular, or intergranular character of short-crack growth following each boundary intersection was correlated to crystallographic and geometric parameters of the trailing and leading grains, three-dimensional grain boundary plane, and advancing crack front. The results indicate that crack paths are dependent on the combined crystallographic and geometric character of the local microstructure, and crack path prediction can be improved by use of dimensionality reduction on subsets of high-linear-correlation microstructural parameters.

36 MATERIALS SCIENCE↗
DOE OSTI2023

MACHINE LEARNING-ENABLED PREDICTION OF TRANSIENT INJECTION MAP IN AUTOMOTIVE INJECTORS WITH UNCERTAINTY QUANTIFICATION

Accurate prediction of injection profiles is a critical aspect of linking injector operation with engine performance and emissions. However, highly resolved injector simulations can take one to two weeks of wall-clock time, which is incompatible with engine design cycles with desired turnaround times of less than a day. Hence, it is important to reduce the time-to-solution of the internal flow simulations by several orders of magnitude to make it compatible with engine simulations. This work demonstrates a data-driven approach for tackling the computational overhead of injector simulations, whereby the transient injection profiles are emulated for a side-oriented, single-hole diesel injector using a Bayesian machine-learning framework. First, an interpretable Bayesian learning strategy was employed to understand the effect of design parameters on the total void fraction field. Then, autoencoders are utilized for efficient dimensionality reduction of the flowfields. Gaussian process models are finally used to predict the spatiotemporal void fraction field at the injector exit for unknown operating conditions. The Gaussian process models produce principled uncertainty estimates associated with the emulated flowfields, which provide the engine designer with valuable information of where the data-driven predictions can be trusted in the design space. The Bayesian flowfield predictions are compared with the corresponding predictions from a deep neural network, which has been transfer-learned from static needle simulations from a previous work by the authors. The emulation framework can predict the void fraction field at the exit of the orifice within a few seconds, thus achieving a speed-up factor of up to 38 x 10(6) over the traditional simulation-based approach of generating transient injection maps.

machine learning↗
DOE OSTI2024

Process damping identification using Bayesian learning and time domain simulation

Process damping can provide improved machining productivity by increasing the stability limit at low spindle speeds. However, existing methods for identifying process damping models experimentally require specialized setups and/or multiple cutting tests. While the phenomenon is well known, the modeling challenges limit pre-process parameter selection that leverages the potential increases in material removal rates. This paper proposes a physics-informed Bayesian method that can identify the cutting force and process damping models from a limited set of test cuts without requiring direct measurements of cutting force or vibration. The method uses time domain simulation to incorporate process damping and provide a basis for test selection. Here, new strategies for efficient sampling and dimensionality reduction are applied to lower computation time and minimize the effect of model error. The proposed method is demonstrated and the identified cutting and damping force coefficients are compared to values obtained using machining tests and least-squares fitting.

42 ENGINEERING↗
DOE OSTI2026

DP-TwoLevel: two-stage gradient subspace learning for differentially private federated learning

Federated learning (FL) enables collaborative model training across distributed data sources without sharing raw data, but faces fundamental challenges in communication efficiency and privacy. Differentially private (DP) training mitigates information leakage but introduces noise that degrades model performance, especially in high-dimensional settings. We propose DP-TwoLevel, a hierarchical gradient projection method that improves utility under fixed DP constraints by exploiting low-dimensional structure in model updates. Our approach learns a two-level PCA-based representation of gradients and applies DP noise in a reduced-dimensional subspace, thereby lowering the effective noise magnitude while preserving dominant signal components. We evaluate the method across three datasets (MNIST, Fashion-MNIST, CIFAR-10) and three privacy regimes (ϵ∈0.5, 1.0, 2.0). Across nine experimental settings, DP-TwoLevel consistently outperforms DP-FedAvg, achieving an average accuracy improvement of 9.44%, with larger gains observed in lower ϵ(higher-noise) regimes (up to +22.31%). We further analyze scalability across models ranging from 100K to 1.49M parameters and identify a variance-based success criterion: performance remains strong when the projection preserves more than 75% of gradient variance, degrades in a marginal regime (65–75%), and fails below this threshold. Our results demonstrate that structure-aware dimensionality reduction can significantly improve the privacy–utility tradeoff in FL without modifying formal privacy guarantees. We also provide empirical evidence of scaling limitations for global projections and motivate per-layer extensions for larger models.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2015

SU-E-T-630: Predictive Modeling of Mortality, Tumor Control, and Normal Tissue Complications After Stereotactic Body Radiotherapy for Stage I Non-Small Cell Lung Cancer

Purpose: While rates of local control have been well characterized after stereotactic body radiotherapy (SBRT) for stage I non-small cell lung cancer (NSCLC), less data are available characterizing survival and normal tissue toxicities, and no validated models exist assessing these parameters after SBRT. We evaluate the reliability of various machine learning techniques when applied to radiation oncology datasets to create predictive models of mortality, tumor control, and normal tissue complications. Methods: A dataset of 204 consecutive patients with stage I non-small cell lung cancer (NSCLC) treated with stereotactic body radiotherapy (SBRT) at the University of Pennsylvania between 2009 and 2013 was used to create predictive models of tumor control, normal tissue complications, and mortality in this IRB-approved study. Nearly 200 data fields of detailed patient- and tumor-specific information, radiotherapy dosimetric measurements, and clinical outcomes data were collected. Predictive models were created for local tumor control, 1- and 3-year overall survival, and nodal failure using 60% of the data (leaving the remainder as a test set). After applying feature selection and dimensionality reduction, nonlinear support vector classification was applied to the resulting features. Models were evaluated for accuracy and area under ROC curve on the 81-patient test set. Results: Models for common events in the dataset (such as mortality at one year) had the highest predictive power (AUC = .67, p < 0.05). For rare occurrences such as radiation pneumonitis and local failure (each occurring in less than 10% of patients), too few events were present to create reliable models. Conclusion: Although this study demonstrates the validity of predictive analytics using information extracted from patient medical records and can most reliably predict for survival after SBRT, larger sample sizes are needed to develop predictive models for normal tissue toxicities and more advanced machine learning methodologies need be consider in the future.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2016

MO-DE-207B-08: Radiomic CT Features Complement Semantic Annotations to Predict EGFR Mutations in Lung Adenocarcinomas

Purpose: To compare the complementary value of quantitative radiomic features to that of radiologist-annotated semantic features in predicting EGFR mutations in lung adenocarcinomas. Methods: Pre-operative CT images of 258 lung adenocarcinoma patients were available. Tumors were segmented using the sing-click ensemble segmentation algorithm. A set of radiomic features was extracted using 3D-Slicer. Test-retest reproducibility and unsupervised dimensionality reduction were applied to select a subset of reproducible and independent radiomic features. Twenty semantic annotations were scored by an expert radiologist, describing the tumor, surrounding tissue and associated findings. Minimum-redundancy-maximum-relevance (MRMR) was used to identify the most informative radiomic and semantic features in 172 patients (training-set, temporal split). Radiomic, semantic and combined radiomic-semantic logistic regression models to predict EGFR mutations were evaluated in and independent validation dataset of 86 patients using the area under the receiver operating curve (AUC). Results: EGFR mutations were found in 77/172 (45%) and 39/86 (45%) of the training and validation sets, respectively. Univariate AUCs showed a similar range for both feature types: radiomics median AUC = 0.57 (range: 0.50 – 0.62); semantic median AUC = 0.53 (range: 0.50 – 0.64, Wilcoxon p = 0.55). After MRMR feature selection, the best-performing radiomic, semantic, and radiomic-semantic logistic regression models, for EGFR mutations, showed a validation AUC of 0.56 (p = 0.29), 0.63 (p = 0.063) and 0.67 (p = 0.004), respectively. Conclusion: Quantitative volumetric and textural Radiomic features complement the qualitative and semi-quantitative radiologist annotations. The prognostic value of informative qualitative semantic features such as cavitation and lobulation is increased with the addition of quantitative textural features from the tumor region.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

VAIM-CFF: a variational autoencoder inverse mapper solution to Compton form factor extraction from deeply virtual exclusive reactions

We develop a new methodology for extracting Compton form factors (CFFs) from deeply virtual exclusive reactions such as the unpolarized DVCS cross section using a specialized inverse problem solver, a variational autoencoder inverse mapper (VAIM). The VAIM-CFF framework not only allows us access to a fitted solution set possibly containing multiple solutions in the extraction of all 8 CFFs from a single cross section measurement, but also accesses the lost information contained in the forward mapping from CFFs to cross section. We investigate various assumptions and their effects on the predicted CFFs such as cross section organization, number of extracted CFFs, use of uncertainty quantification technique, and inclusion of prior physics information. We then use dimensionality reduction techniques such as principal component analysis to visualize the missing physics information tracked in the latent space of the VAIM framework. Through re-framing the extraction of CFFs as an inverse problem, we gain access to fundamental properties of the problem not comprehensible in standard fitting methodologies: exploring the limits of the information encoded in deeply virtual exclusive experiments.

Accelerator Physics↗
DOE OSTI2019

Evaluating the Effects of Missing Values and Mixed Data Types on Social Sequence Clustering Using t-SNE Visualization

© 2019 Association for Computing Machinery. The goal of this work is to investigate the impact of missing values in clustering joint categorical social sequences. Identifying patterns in sociodemographic longitudinal data is important in a number of social science settings. However, performing analytical operations, such as clustering on life course trajectories, is challenging due to the categorical and multidimensional nature of the data, their mixed data types, and corruption by missing and inconsistent values. Data quality issues were investigated previously on single variable sequences. To understand their effects on multivariate sequence analysis, we employ a dataset of mixed data types and missing values, a dissimilarity measure designed for joint categorical sequence data, together with dimensionality reduction methodologies in a systematic design of sequence clustering experiments. Given the categorical nature of our data, we employ an “edit” distance using optimal matching. Because each data record has multiple variables of different types, we investigate the impact of mixing these variables in a single dissimilarity measure. Between variables with binary values and those with multiple nominal values, we find that the ability to overcome missing data problems is more difficult in the nominal domain than in the binary domain. Additionally, alignment of leading missing values can result in systematic biases in dissimilarity matrices and subsequently introduce both artificial clusters and unrealistic interpretations of associated data domains. We demonstrate the usage of t-distributed stochastic neighborhood embedding to visually guide mitigation of such biases by tuning the missing value substitution cost parameter or determining an optimal sequence span.

Lazar, Alina↗
DOE OSTI2020

Characterization and identification of HPC applications at leadership computing facility

High Performance Computing (HPC) is an important method for scientific discovery via large-scale simulation, data analysis, or artificial intelligence. Leadership-class supercomputers are expensive, but essential to run large HPC applications. The Petascale era of supercomputers began in 2008, with the first machines achieving performance in excess of one petaflops, and with the advent of new supercomputers in 2021 (e.g., Aurora, Frontier), the Exascale era will soon begin. However, the high theoretical computing capability (i.e., peak FLOPS) of a machine is not the only meaningful target when designing a supercomputer, as the resources demand of applications varies. A deep understanding of the characterization of applications that run on a leadership supercomputer is one of the most important ways for planning its design, development and operation. In order to improve our understanding of HPC applications, user demands and resource usage characteristics, we perform correlative analysis of various logs for different subsystems of a leadership supercomputer. This analysis reveals surprising, sometimes counter-intuitive patterns, which, in some cases, conflicts with existing assumptions, and have important implications for future system designs as well as supercomputer operations. For example, our analysis shows that while the applications spend significant time on MPI, most applications spend very little time on file I/O. Combined analysis of hardware event logs and task failure logs show that the probability of a hardware FATAL event causing task failure is low. Combined analysis of control system logs and file I/O logs reveals that pure POSIX I/O is used more widely than higher level parallel I/O. Based on holistic insights of the application gained through combined and co-analysis of multiple logs from different perspectives and general intuition, we engineer features to "fingerprint" HPC applications. We use t-SNE (a machine learning technique for dimensionality reduction) to validate the explainability of our features and finally train machine learning models to identify HPC applications or group those with similar characteristic. To the best of our knowledge, this is the first work that combines logs on file I/O, computing, and inter-node communication for insightful analysis of HPC applications in production.

Liu, Zhengchun↗
DOE OSTI2014

Band Excitation in Scanning Probe Microscopy: Recognition and Functional Imaging

Field confinement at the junction between a biased scanning probe microscope s (SPM) tip and solid surface enables local probing of various bias-induced transformations such as polarization switching, ionic motion, or electrochemical reactions to name a few. The nanoscale size of the biased region is smaller or comparable to features like grain boundaries and dislocations, potentially allows for the study of kinetics and thermodynamics at the level of a single defect. In contrast to classical statistically averaged approaches, this allows one to link structure to functionality and deterministically decipher associated mesoscopic and atomistic mechanisms. Furthermore, this type of information can serve as a fingerprint of local material functionality, allowing for local recognition imaging. Here, current progress in multidimensional SPM techniques based on band-excitation time and voltage spectroscopies is illustrated, including discussions on data acquisition, dimensionality reduction, and visualization along with future challenges and opportunities for the field.

Jesse, Stephen↗
DOE OSTI2019

Function Preserving Projection

With function preserving projection (FPP), we aim to address high-dimensional data exploration challenges common in many scientific applications. Instead of preserving the global or local geometric structure of a dataset like traditional dimensionality reduction methods (e.g., principal component analysis, t-stochastic neighborhood embedding), the proposed approach finds a linear projection that reveal interpretable (yet potentially nonlinear) pattern of the properties of interests defined on a highdimensional domain (e.g., simulation yield defined on the input parameter space). The key insight driving FPP is the fact that while non-linear embeddings are difficult to interpret, humans are highly skilled in understanding complex visual patterns. FPP lets users select the complexity of a pattern they consider interpretable, allows to find a joint projection that explains multiple functions, and provides a confidence statistic (akin to a p-value) indicating how salient the resulting pattern is. We demonstrate the efficacy of the proposed method on several synthetic and scientific datasets for both continuous (regression) and discrete (classification) problems of interests and illustrate the scalability of FPP by finding an optimal projection for close to 40 gigabytes in around 10 minutes.

Liu, SHUSEN↗
DOE OSTI2019

XPCA - R Implementation

Principal component analysis (PCA) is arguably the most popular tool in multivariate exploratory data analysis. We consider the question of how to handle heterogeneous variables that include continuous, binary, and ordinal. In the probabilistic interpretation of low-rank PCA, the data has a normal multivariate distribution and, therefore, normal marginal distributions for each column. If some marginals are continuous but not normal, the semiparametric copula-based principal component analysis (COCA) method is an alternative to PCA that combines a Gaussian copula with nonparametric marginals. If some marginals are discrete or semi-continuous, we present a new extended PCA (XPCA) method that also uses a Gaussian copula and nonparametric marginals and accounts for discrete variables in the likelihood calculation by integrating over appropriate intervals. Like PCA, the factors produced by XPCA can be used to find latent structure in data, build predictive models, and perform dimensionality reduction. We implement the new model, XPCA, and its ancestors PCA and COCA in both R and Python. This software provides implementations of XPCA, COCA, and probabilistic PCA in both R and Python. XPCA is written in arXiv report https://arxiv.org/abs/1808.07510. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525. SAND2019-10591 M

Kincher-Winoto, Kina↗
DOE OSTI2019

XPCA -Python Implementation

Principal component analysis (PCA) is arguably the most popular tool in multivariate exploratory data analysis. We consider the question of how to handle heterogeneous variables that include continuous, binary, and ordinal. In the probabilistic interpretation of low-rank PCA, the data has a normal multivariate distribution and, therefore, normal marginal distributions for each column. If some marginals are continuous but not normal, the semiparametric copula-based principal component analysis (COCA) method is an alternative to PCA that combines a Gaussian copula with nonparametric marginals. If some marginals are discrete or semi-continuous, we present a new extended PCA (XPCA) method that also uses a Gaussian copula and nonparametric marginals and accounts for discrete variables in the likelihood calculation by integrating over appropriate intervals. Like PCA, the factors produced by XPCA can be used to find latent structure in data, build predictive models, and perform dimensionality reduction. We implement the new model, XPCA, and its ancestors PCA and COCA in both R and Python. This software provides implementations of XPCA, COCA, and probabilistic PCA in both R and Python. XPCA is written in arXiv report https://arxiv.org/abs/1808.07510. SAND2019-10591 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Kincher-Winoto, Kina↗
DOE OSTI2025

SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training) v1

SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training) is a comprehensive data visualization and analysis application focused on working with COLTRIMS (COLd Target Recoil Ion Momentum Spectroscopy) data, which is used in atomic and molecular physics experiments. The application offers several powerful features: - Data uploading and processing capabilities for COLTRIMS files - Multiple visualization methods using UMAP (Uniform Manifold Approximation and Projection) for dimensionality reduction - Interactive selection of data points across multiple views - Feature engineering through various methods: - Manual feature selection from calculated physics parameters - Deep autoencoder for dimension reduction - Genetic programming for discovering meaningful features - Mutual information-based feature selection - Multiple clustering approaches (DBSCAN, KMeans, Agglomerative) - Quality metrics for evaluating clustering results - Export capabilities for selections and generated features

Daoud, Hazem [Lawrence Berkeley National Laborator↗
DOE OSTI2025

Moltensaltpropnet

MoltenSaltPropnet is a physics-informed machine learning framework that aims to predict the thermophysical properties of molten fluoride and chloride salt mixtures, which are crucial for the design and safety of Generation IV molten salt reactors. The code processes data from the Molten-Salt Thermal Properties Database (MSTDB-TP) and the Janz compendium, converting critically evaluated correlations into fast, differentiable surrogate models for density, viscosity, thermal conductivity, and heat capacity across 448 distinct salt systems. The implementation consists of several key components: 1. Data Curation: The code parses and cleans the raw data, normalizing elemental mole fractions and extracting relevant regression coefficients for various thermophysical properties. 2. Feature Engineering: It generates fixed-length numerical descriptors that encapsulate the composition and temperature, incorporating polynomial interaction terms and dimensionality-reduction techniques to optimize model performance. 3. Coefficient Learning: Four different machine learning architectures are employed: a deep residual network (ResNet), a Kolmogorov–Arnold network (KAN), a sparsity-inducing neural network (SNN), and classical regression models. Each model learns to predict coefficients that define the temperature-dependent correlations for the thermophysical properties. 4. Property Reconstruction: The predicted coefficients are used to compute temperature-dependent property values, ensuring positivity and monotonic trends through a composite loss function that enforces physical constraints. 5. User Interface: An open-source web application enables users to filter the database, train task-specific models, and visualize the results, allowing for rapid exploration of candidate salt mixtures. MoltenSaltPropnet bridges the gap between limited experimental data and high-fidelity reactor simulations, providing a powerful tool for researchers in the field of molten salt reactors and advanced nuclear energy systems.

Retamales, Mauricio Eduardo Tano [Idaho National L↗