Stratified sampling based on nonlinear dimensionality reduction for multi-fidelity estimators
Explore the source record for details and available documents.
Zanoni, Andrea [Scuola Normale Superiore]↗
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.
Efficient data-driven surrogate modeling of high-speed aerodynamic field data using dimensionality reduction and neural networks
Presentation for USNCCM on work on non-intrusive reduced order models for aerothermal modeling.
Blonigan, Patrick Joseph [Sandia National Laborato↗
LANDSAT-D thematic mapper image dimensionality reduction and geometric correction accuracy
When principal component analysis of a subscene of a section of the Sacramento River showed lower correlation among the TM spectral components that were observed for the MSS spectral components, principal component analysis was applied to a LANDSAT 2 MSS subscene of the same area for comparison purposes. Correlation coefficient matrices indicate the pairwise similarity and correlation of the data for the spectral components. The principal components transformation matrix, indicates the weights applied to the original components to generate the transformed components. The first two TM components can be described as visible and near infrared. For the MSS data, the first transformed component is roughly the average of the four original components. The second transformed component is roughly the difference between the visible and infrared components. Tables show that 97.0% of the variance in an MSS image is contained in only two transformed components.
Ford, G. E.↗
Hierarchical Gaussian Random Field Sampling for Multilevel Markov Chain Monte Carlo: Coupling Stochastic Partial Differential Equation and the Karhunen–Loève Decomposition
This work introduces structure preserving hierarchical decompositions for sampling Gaussian random fields (GRFs) within the context of multilevel Bayesian inference in high-dimensional space. Existing scalable hierarchical sampling methods, such as those based on stochastic partial differential equations (SPDEs), often reduce the dimensionality of the sample space at the cost of accuracy of inference. Other approaches, such that those based on Karhunen-Loève (KL) expansions, offer sample space dimensionality reduction but sacrifice GRF representation accuracy and ergodicity of the Markov chain Monte Carlo (MCMC) sampler and are computationally expensive for high-dimensional problems. The proposed method integrates the dimensionality reduction capabilities of KL expansions with the scalability of SPDE-based sampling, thereby providing a robust, unified framework for high-dimensional uncertainty quantification (UQ) that is scalable and accurate, preserves ergodicity, and offers dimensionality reduction of the sample space. The hierarchy in our multilevel algorithm is derived from the geometric multigrid hierarchy. By constructing a hierarchical decomposition that maintains the covariance structure across the levels in the hierarchy, the approach enables efficient coarse-to-fine sampling while ensuring that all samples are drawn from the desired distribution. The effectiveness of the proposed method is demonstrated on a benchmark subsurface flow problem, demonstrating its effectiveness in improving computational efficiency and statistical accuracy. Furthermore, our proposed technique is more efficient and accurate and displays better convergence properties than existing methods for high-dimensional Bayesian inference problems.
Gaussian random fields↗
Multispectral combination and display of ERTS-1 data
A significant problem in the use of ERTS-1 data is the extraction of information pertinent to each application and the presentation of that information in a form most suitable to users. When the information is to be displayed for visual study by an observer, the problem can be reduced to two steps: (1) Dimensionality reduction, an objective procedure which attempts to preserve most of the ERTS-1 information in a smaller number of components. (2) Display of the reduced number of components for optimum visibility by an observer. A specific dimensionality reduction technique has been applied to ERTS-1 data for several geographical areas in California and distinct types of earth resources. In the display of the reduced number of components, consideration has to be given to properties of the human visual system and the statistics of the data to be displayed. Previous work on digital image enhancement was applied to this problem to generate color composites which contain and display most of the information provided by the ERTS-1 sensors. Results of this approach were interesting, both in terms of the small mean-square caused by the dimensionality reduction, as well as for the examples of enhanced images that have been obtained.
Algazi, V. R.↗
Randomized Algorithms for Low-Rank Matrix and Tensor Decompositions
This paper surveys randomized algorithms in numerical linear algebra for low-rank decompositions of matrices and tensors. The survey begins with a review of classical matrix algorithms that can be accelerated by randomized dimensionality reduction, such as the singular value decomposition (SVD) or interpolative (ID) and CUR decompositions. Recent advances in randomized dimensionality reduction are discussed, including new methods of fast matrix sketching and sampling techniques, which are incorporated into classical matrix algorithms for fast low-rank matrix approximations. The extension of randomized matrix algorithms to tensors is then explored for several low-rank tensor decompositions in the CP and Tucker formats, including the higher-order SVD, ID, and CUR decomposition.
Pearce, Katherine J. [The University of Texas at A↗
High dimensional feature reduction via projection pursuit
The recent development of more sophisticated remote sensing systems enables the measurement of radiation in many more spectral intervals than previously possible. An example of that technology is the AVIRIS system, which collects image data in 220 bands. As a result of this, new algorithms must be developed in order to analyze the more complex data effectively. Data in a high dimensional space presents a substantial challenge, since intuitive concepts valid in a 2-3 dimensional space to not necessarily apply in higher dimensional spaces. For example, high dimensional space is mostly empty. This results from the concentration of data in the corners of hypercubes. Other examples may be cited. Such observations suggest the need to project data to a subspace of a much lower dimension on a problem specific basis in such a manner that information is not lost. Projection Pursuit is a technique that will accomplish such a goal. Since it processes data in lower dimensions, it should avoid many of the difficulties of high dimensional spaces. In this paper, we begin the investigation of some of the properties of Projection Pursuit for this purpose.
Jimenez, Luis↗
Multidimensional scaling informed by F -statistic: Visualizing grouped microbiome data with inference
Multidimensional scaling (MDS) is a widely used dimensionality reduction technique in microbial ecology data analysis that captures the multivariate structure of the data while preserving pairwise distances between samples. While improvements in MDS have enhanced the ability to reveal group-specific data patterns, these MDS-based methods require prior assumptions for inference, limiting their application in general microbiome analysis. Here, in this study, we introduce a new MDS-based ordination method, “F-informed MDS,” which configures the data distribution based on the F-statistic, the ratio of dispersion between groups sharing common and different characteristics. Using semisynthetic datasets, we demonstrate that the proposed method is robust to hyperparameter selection while maintaining statistical significance throughout the ordination process. Various quality metrics for evaluating dimensionality reduction confirm that F-informed MDS is comparable to state-of-the-art methods in preserving both local and global data structures. Its application to a diatom-associated bacterial community suggests the role of this new method in interpreting the community’s response to the host. Our approach offers a well-founded refinement of MDS that aligns with statistical test results, which can be beneficial for broader multidimensional data analyses in microbiology and ecology. This new visualization tool can be incorporated into standard microbiome data analyses.
Biological and medical sciences↗
Nonintrusive projection-based reduced order modeling using stable learned differential operators
Nonintrusive projection-based reduced order models (ROMs) are essential for dynamics prediction in multi-query applications where underlying governing equations are known but the access to the source of the underlying full order model (FOM) is unavailable; that is, FOM is a glass-box. This article proposes a learn-then-project approach for nonintrusive model reduction. In the first step of this approach, high-dimensional stable sparse learned differential operators (S-LDOs) are determined using the generated data. In the second step, the ordinary differential equations, comprising these S-LDOs, are used with suitable dimensionality reduction and low-dimensional subspace projection methods to provide equations for the evolution of reduced states. This approach allows easy integration into the existing intrusive ROM framework to enable nonintrusive model reduction while allowing the use of Petrov–Galerkin projections. The applicability of the proposed approach is demonstrated for Galerkin and LSPG projection-based ROMs through four numerical experiments: 1-D scalar advection, 1-D Burgers, 2-D scalar advection and 1-D scalar advection–diffusion–reaction equations. In conclusion, the results indicate that the proposed nonintrusive ROM strategy provides accurate and stable dynamics prediction.
42 ENGINEERING↗
Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder-decoder-based generative models for nonlinear dimensionality reduction, focusing on disentangling low-dimensional latent variables corresponding to independent physical factors. Introducing Aux-VAE, a novel architecture within the classical Variational Autoencoder framework, we achieve disentanglement with minimal modifications to the standard VAE loss function by leveraging prior statistical knowledge through auxiliary variables. These variables guide the shaping of the latent space by aligning latent factors with learned auxiliary variables. We validate the efficacy of Aux-VAE through comparative assessments on multiple datasets, including astronomical simulations.
97 MATHEMATICS AND COMPUTING↗
An interactive machine learning platform for analyzing multi-particle coincidence data from cold target recoil ion momentum spectroscopy
We present SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training), a comprehensive software platform for analyzing tabulated high-dimensional multi-particle coincidence data from Cold Target Recoil Ion Momentum Spectroscopy (COLTRIMS) experiments. The software addresses critical challenges in modern momentum spectroscopy by integrating advanced machine learning techniques with physics-informed analysis in an interactive web-based environment. SCULPT implements uniform manifold approximation and projection for non-linear dimensionality reduction to reveal correlations in high-dimensional data. We also discuss potential extensions to deep autoencoders for feature learning and genetic programming for automated discovery of physically meaningful observables. A novel adaptive confidence scoring system provides quantitative reliability assessments by evaluating user-selected clustering quality metrics with predefined weights that reflect each metric’s robustness. The platform features configurable molecular profiles for different experimental systems, interactive visualization with selection tools, and comprehensive data filtering capabilities. Utilizing a subset of SCULPT’s capabilities, we analyze photo-double-ionization data measured using the COLTRIMS method for three-body dissociation of the D 2 O molecule, revealing distinct fragmentation channels and their correlations with physics parameters. The software’s modular architecture and web-based implementation make it accessible to the broader atomic and molecular physics community, significantly reducing the time required for complex multi-dimensional analyses. This opens the door to finding and isolating rare events exhibiting non-linear correlations on the fly during experimental measurements, which can help steer exploration and improve the efficiency of experiments.
Artificial neural networks↗
MOOSE ProbML: Parallelized probabilistic machine learning and uncertainty quantification for computational energy applications
Here, this paper presents the development and demonstration of massively parallel probabilistic machine learning (ML) and uncertainty quantification (UQ) capabilities within the Multiphysics Object-Oriented Simulation Environment (MOOSE), an open-source computational platform for parallel finite element and finite volume analyses. In addressing the computational expense and uncertainties inherent in complex multiphysics simulations, this paper integrates Gaussian process (GP) variants, active learning, Bayesian inverse UQ, adaptive forward UQ, Bayesian optimization, evolutionary optimization, and Markov chain Monte Carlo (MCMC) within MOOSE. It also elaborates on the interaction among key MOOSE systems — Sampler, MultiApp, Reporter, and Surrogate — in enabling these capabilities. The modularity offered by these systems enables development of a multitude of probabilistic ML and UQ algorithms in MOOSE. Example code demonstrations include parallel active learning and parallel Bayesian inference via active learning. The impact of these developments is illustrated through five applications relevant to computational energy applications: UQ of nuclear fuel fission product release, using parallel active learning Bayesian inference; very rare events analysis in nuclear microreactors using active learning; advanced manufacturing process modeling using multi-output GPs (MOGPs) and dimensionality reduction; fluid flow using deep GPs (DGPs); and tritium transport model parameter optimization for fusion energy, using batch Bayesian optimization. These capabilities are part of the MOOSE framework.
97 - MATHEMATICS AND COMPUTING↗
SO(3)-invariant PCA with application to molecular data
Principal component analysis (PCA) is a fundamental technique for dimensionality reduction and denoising; however, its application to three-dimensional data with arbitrary orientations -- common in structural biology -- presents significant challenges. A naive approach requires augmenting the dataset with many rotated copies of each sample, incurring prohibitive computational costs. In this paper, we extend PCA to 3D volumetric datasets with unknown orientations by developing an efficient and principled framework for SO(3)-invariant PCA that implicitly accounts for all rotations without explicit data augmentation. By exploiting underlying algebraic structure, we demonstrate that the computation involves only the square root of the total number of covariance entries, resulting in a substantial reduction in complexity. We validate the method on real-world molecular datasets, demonstrating its effectiveness and opening up new possibilities for large-scale, high-dimensional reconstruction problems.
Fraiman, Michael [Tel Aviv Univ., Tel Aviv (Israel↗
A Class of Sparse Johnson–Lindenstrauss Transforms and Analysis of their Extreme Singular Values
The Johnson–Lindenstrauss (JL) lemma is a powerful tool for dimensionality reduction in modern algorithm design. The lemma states that any set of high-dimensional points in a Euclidean space can be projected into lower dimensions while approximately preserving pairwise Euclidean distances. Random matrices satisfying this lemma are called JL transforms (JLTs). Inspired by existing $s$-hashing JLTs with exactly $s$ nonzero elements on each column, the present work introduces an ensemble of sparse matrices encompassing so-called $s$-hashing-like matrices whose expected number of nonzero elements on each column is $s$. The independence of the sub-Gaussian entries of these matrices and the knowledge of their exact distribution play an important role in their analyses. Using properties of independent sub-Gaussian random variables, these matrices are demonstrated to be JLTs, and their smallest nontrivial singular values and largest singular values are estimated nonasymptotically using a technique from geometric functional analysis. As the dimensions of the matrix grow to infinity, these singular values are proved to converge almost surely to fixed quantities (by using the universal Bai–Yin law) and in distribution to the Gaussian orthogonal ensemble Tracy–Widom law after proper rescalings. Understanding the behaviors of extreme singular values is important in general because they are often used to define a measure of stability of matrix algorithms. For example, JLTs were recently used in derivative-free optimization algorithmic frameworks to select random subspaces in which are constructed random models or poll directions to achieve scalability, and hence estimating their smallest singular value in particular helps determine the dimension of these subspaces.
97 MATHEMATICS AND COMPUTING↗
Uncertainty propagation and sensitivity analysis for constrained optimization of nuclear waste vitrification
Abstract The vitrification of high‐level waste (HLW) by heating a mixture of glass‐forming chemicals (GFCs) with the waste can be improved using a constrained optimization problem. This study explores how different uncertainty propagation (UP) methods implemented with the optimization process can affect the glass formulation of nuclear waste glasses. UP is the effort of propagating uncertain inputs through a system to understand and quantify output distributions. Uncertainty intervals are crafted from output distributions to inform the optimization algorithm. UP is often implemented with Monte Carlo (MC) sampling for large nonlinear systems, which can be difficult to implement within a constrained optimization algorithm that requires derivative information. Other UP methods often used for optimization under uncertainty (OUU) can be designed to work within an established constrained optimization framework. Methods of UP are evaluated in this study including iterative sampling approaches, first‐order approximations, and surrogate modeling with machine learning (ML). A method of dimensional reduction based on global sensitivity analysis is introduced to support the UP methods for the large dimensionality of the problem. Analytical UP methods able to achieve similar optimums 10 times faster than the baseline MC approach, and produce 93.9% similar output distributions are reported.
12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
Experimental Realization of One-Dimensional Helium
Abstract As the spatial dimension is lowered, locally stabilizing interactions are reduced, leading to the emergence of strongly fluctuating phases of matter without classical analogues. Realizing 1D platforms has been elusive, due to their inherent lack of stability, with a few notable exceptions such as spin chains and ultracold low-density gasses. The inability of such systems to exhibit long range order is essential to their universal description in terms of the Tomonaga-Luttinger liquid theory. Here we report on the experimental observation of a one-dimensional quantum liquid of $$^4$$ 4 He using nanoengineering to confine it within a porous material preplated with a noble gas to enhance dimensional reduction. The resulting excitations of the confined $$^4$$ 4 He, confirmed by neutron scattering, are qualitatively different than three- and two-dimensional superfluid helium, and consistent with Quantum Monte Carlo calculations. The results can be analyzed in terms of a mobile impurity in an otherwise linear Luttinger liquid allowing for the extraction of the microscopic parameters describing the emergent quantum liquid.
Sokol, Paul E.↗
In Situ Data Analysis Through Physics-informed Tensor Decompositions (LDRD Final Report)
We introduce a new low-dimensional model of high-dimensional numerical simulation data based on low-rank tensor decompositions. Our new model aims to minimize differences between the model data and simulation data as well as functions of the model data and functions of the simulation data. This novel approach to dimensionality reduction of simulation data provides a means of directly incorporating quantities of interests and invariants associated with conservation principles associated with the simulation data into the low-dimensional model, thus enabling more accurate analysis of the simulation without requiring access to the full set of high-dimensional data. Computational results of applying this approach to two standard low-rank tensor decompositions of data arising from simulation of combustion and plasma physics are presented.
97 MATHEMATICS AND COMPUTING↗
A two-stage optical fusion framework for wildfire severity mapping across the conterminous United States
Accurate wildfire severity mapping (WSM) is essential for post-fire recovery planning, erosion risk assessment, ecosystem monitoring, and disaster risk reduction. Although Landsat and Sentinel optical imagery have been widely used for burn severity assessment, the added value of fusing multiple optical sensors has not been sufficiently quantified across diverse fire events, particularly since the launch of Landsat-9. This study evaluates whether multisensor optical fusion improves wildfire severity mapping relative to single-sensor baselines using Sentinel-2, Landsat-8, and Landsat-9 imagery across 40 wildfire events in the conterminous United States. We tested a two-stage fusion framework that combines feature-level fusion with pixel-level dimensionality reduction. First, feature-level fused datasets were created through early fusion by combining standardized post-fire bands from each sensor into a single predictor stack. Both raw reflectance bands and pairwise spectral transforms were retained to capture within- and cross-sensor spectral interactions. Second, Linear Discriminant Analysis was applied to both single-sensor and fused datasets to produce comparable low-dimensional feature spaces. Six machine-learning classifiers were then used to benchmark model performance with repeated spatially buffered train–test splits. Results show that Landsat-9 was the strongest single-sensor baseline. Among the fusion strategies, Sentinel-2 + Landsat-9 produced the most consistent improvement and reduced performance variability. Landscape-condition analysis further showed that this fusion was most beneficial in shrubland-dominated and high-terrain fires, where it achieved the highest overall mean accuracy and the fewest failures. In contrast, its benefits were less reliable in evergreen forests, mixed vegetation, and low- to moderate-elevation terrain. In operational settings, the Sentinel-2 + Landsat-9 configuration offers a practical solution for post-fire recovery planning, erosion-risk assessment, watershed management, and ecological monitoring when field observations are available and timely satellite-based information is needed.
Landsat↗