Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “High dimensional data,”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning

As the size and complexity of HPC systems grow in line with advancements in hardware and software technology, HPC systems increasingly suffer from performance variation due to shared resource contention as well as software- and hardware-related problems. Such performance variations can lead to failures and inefficiencies, and are among the main challenges in system resiliency. To minimize the impact of performance variation, one must quickly and accurately detect and diagnose the anomalies that cause the variation and take mitigating actions. However, it is difficult to identify anomalies based on the voluminous, high-dimensional, and noisy data collected by system monitoring infrastructures. This paper presents a novel machine learning based framework to automatically diagnose performance anomalies at runtime. Our framework leverages historical resource usage data to extract signatures of previously-observed anomalies. We first convert the collected time series data into easy-to-compute statistical features. We then identify the features that are required to detect anomalies, and extract the signatures of these anomalies. At runtime, we use these signatures to diagnose anomalies with negligible overhead. Here, we evaluate our framework using experiments on a real-world HPC supercomputer and demonstrate that our approach successfully identifies 98% of injected anomalies and consistently outperforms existing anomaly diagnosis techniques.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data

Here, we present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems. The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation. The summary network encodes raw observations into a fixed-size vector of summary features, while the inference network generates samples of the approximate posterior distribution of the model parameters based on these summary features. The posterior samples are produced in a deep generative fashion by sampling from a latent Gaussian distribution and passing these samples through an invertible transformation. We construct this invertible transformation by sequentially alternating conditional invertible neural network and conditional neural spline flow layers. The summary and inference networks are trained simultaneously. We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations of the system’s hydraulic head responses. The conductivity field is represented with 706 degrees of freedom in the considered problem. Comparison with the likelihood-based iterative ensemble smoother PEST-IES method demonstrates that the proposed method accurately estimates the parameter posterior distribution and the observations’ predictive posterior distribution at a fraction of the inference time of PEST-IES.

conditional invertible neural network↗
NASA NTRS1977

Two-dimensional wind-tunnel tests of a NASA supercritical airfoil with various high-lift systems. Volume 1: Data analysis

High-lift systems for a NASA, 9.3%, method for calculating the viscous flow about two-dimensional multicomponent airfoils was evaluated by comparing its predictions with test data. High-lift systems derived from supercritical airfoils were compared in terms of performance to high-lift systems derived from conventional airfoils. The high-lift systems for the supercritical airfoil were designed to achieve maximum lift and consisted of: a single-slotted flap; a double-slotted flap and a leading-edge slat; and a triple-slotted flap and a leading-edge slat. Agreement between theoretical predictions and experimental results are also discussed.

Omar, E.↗
DOE OSTI2015

Applications of aggregation theory to sustainability assessment

In order to aid in transition towards operations that promote sustainability goals, researchers and stakeholders use sustainability assessments. Although assessments take various forms, many utilize diverse sets of indicators that can number anywhere from two to over 2000. Indices, composite indicators, or aggregate values are used to simplify high dimensional and complex data sets and to clarify assessment results. Although the choice of aggregation function is a key component in the development of the assessment, there are few examples to be found in literature to guide appropriate aggregation function selection. This paper develops a connection between the mathematical study of aggregation functions and sustainability assessment in order to aid in providing criteria for aggregation function selection. Relevant mathematical properties of aggregation functions are presented and interpreted. Lastly, we provide cases of these properties and their relation to previous sustainability assessment research. Examples show that mathematical aggregation properties can be used to address the topics of compensatory behavior and weak versus strong sustainability, aggregation of data under varying units of measurements, multiple site multiple indicator aggregation, and the determination of error bounds in aggregate output for normalized and non-normalized indicator measures.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2018

Modeling and Simulation of High-Frequency Solar Irradiance

As the use of solar power as a source of electricity is increasing, so is the interest in modeling radiation at high temporal resolutions. High-dimensional remote sensing data products depend on cloud cover variability, atmosphere aerosol levels, and other atmospheric parameters. Because of weather fronts and aerosols, it is difficult to quantify solar power variability based on distributed solar networks. The global horizontal irradiance (GHI) component in the National Solar Radiation Database (NSRDB) is available at a 30-min time resolution. The algorithm proposed in this paper produces 1-min-resolution GHI samples at locations where NSRDB data are available. The synthetic irradiance datasets are produced using log-additive non-Gaussian mixture models and resampling techniques. The model is trained over historical data, and predicted values are compared with in situ data. This approach allows for estimating the solar irradiance at subhourly temporal resolutions, while featuring variability for locations where measurements are otherwise not available.

14 SOLAR ENERGY↗
DOE OSTI2025

Toward particle accelerator machine state embeddings as a modality for large language models

Understanding and diagnosing the state of a particle accelerator requires navigating high-dimensional control system data, often involving hundreds of interdependent parameters. We propose a novel multimodal embedding framework that jointly learns representations of machine states from both numerical control system readouts and natural language descriptions. This enables the translation of complex machine conditions into human-readable summaries while maintaining fidelity to the underlying physical system. The obtained embeddings are subsequently adapted to an open-weights large language model via cross-attention conditioning. We demonstrate a first implementation trained on European XFEL machine state data. This work covers the embedding model architecture, training methodology, and presents initial examples demonstrating the model's capabilities in action. Due to the general concept of machine state, the model can be easily adapted to other facilities and control system environments.

Accelerator Physics↗
NASA NTRS2018

Machine Learning Application to Atmospheric Chemistry Modeling

Atmospheric chemistry is a high-dimensionality, large-data problem and thus may be suited to machine-learning algorithms. We show here the potential of a random forest regression algorithm to replace the gas-phase chemistry solver in the GEOS-Chem chemistry model. In this proof-of-concept study, we used one month of model output to train random forest regression models to predict the concentrations of each long-lived chemical species after integration based upon the physical and chemical conditions before the chemical integration. The choice of prediction type has a strong impact on the skill of the regression model. We find best results from predicting the change in concentration for very long-lived species and the absolute concentration for shorter lived species. The skill of the machine learning algorithm is further improved by using a family approach for NO and NO2 rather than treating them independently.By replacing the numerical integrator with the random forest algorithm and running this model for one month, we find that the model is able to reproduce many of the features of the reference chemistry simulation. Replacing the integration methodology with a machine learning algorithm has the potential to be substantially faster. There are a wide range of applications for such an approach, e.g. to generate boundary conditions, for use in air quality forecasts or chemical data assimilation systems, etc.

Keller, Christoph A.↗
NASA NTRS2019

Deep Learning Emulation of Atmospheric Correction for Geostationary Sensors

New generation geostationary satellites make reflectance observations available at a continental scale with unprecedented spatiotemporal resolution and spectral range. Generating Earth monitoring products from these observations requires retrieval of the basic parameter, surface reflectance (SR), by atmospheric correction (AC). Algorithms for atmospheric correction, including Multi-Angle Implementation of Atmospheric Correction (MAIAC), are adapted for each sensor and are too computationally complex to be run in real time, relying instead on look-up tables with precomputed values. Machine learning methods, including convolutional neural networks, have demonstrated performance in learning complex, nonlinear mappings and extracting insight from high-dimensional remote sensing data. In this work, we present a deep learning emulator of MAIAC to retrieve both SR and cloud products. Using this adaptation of deep learning-based emulation to remote sensing, we demonstrate stable SR retrieval over a variety of land covers and viewing conditions and accurate cloud detection. Further, a comparison of computation time suggests emulation as a compelling alternative for expensive physical simulation, especially for applications benefited by near-real time data, such as agricultural management and disaster response.

Duffy, Kate↗
NASA NTRS2022

Coevolution of Machine Learning and Process-Based Modelling to Revolutionize Earth and Environmental Sciences: A Perspective

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.

Saman Razavi↗
DOE OSTI2025

Investigation of the Performance and Explainability Tradeoffs for Machine-Learning Models for Predictive Maintenance of Circulating Water Systems in Nuclear Power Plants

Predictive maintenance (PdM) has shown great potential for achieving substantial cost savings and enhancing the economic competitiveness of nuclear power plants (NPPs) in today's energy market. Among the different modeling approaches that exist, machine learning (ML) tools in particular have a demonstrated ability to handle high dimensional and multivariate data and to extract hidden relationships within data in industrial environments. While ML methods show great potential, their lack of explainability---especially for black-box models---is a major hurdle to their adoption. Moreover, considering the supposed trade-off between explainability and performance challenges, careful consideration must be made as to which of these quality aspects takes precedence in light of multiple modeling options, resource availability, and domain characteristics. The present work evaluates the performance of six ML models, each with a different degree of explainability, in classifying the conditions of circulating water pumps (CWPs) by utilizing sensor data from nuclear power plants. To determine the drivers behind the trade-offs presented by this array of models, this work also tests different combinations of CWP units as the training and testing data, degrees of data imbalance, and objective functions for hyperparameter tuning. It was found that black-box models tend to afford superior performance in cases where there are far more instances of one type of labeled data than of any other type. It is recommended that a guided procedure be followed for designing and delivering an ML system that is sufficiently explainable to all involved stakeholders.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1989

Visions of visualization aids - Design philosophy and observations

Aids for the visualization of high-dimensional scientific or other data must be designed. Simply casting multidimensional data into a two-dimensional or three-dimensional spatial metaphor does not guarantee that the presentation will provide insight or a parsimonious description of phenomena implicit in the data. Useful visualization, in contrast to glitzy, high-tech, computer-graphics imagery, is generally based on preexisting theoretical beliefs concerning the underlying phenomena. These beliefs guide selection and formatting of the plotted variables. Visualization tools are useful for understanding naturally three-dimensional data bases such as those used by pilots or astronauts. Two examples of such aids for spatial maneuvering illustrate that informative geometric distortion may be introduced to assist visualization and that visualization of complex dynamics alone may not be adequate to provide the necessary insight into the underlying processes.

Ellis, Stephen R.↗
DOE OSTI2015

MAPPING THE GALAXY COLOR–REDSHIFT RELATION: OPTIMAL PHOTOMETRIC REDSHIFT CALIBRATION STRATEGIES FOR COSMOLOGY SURVEYS

Calibrating the photometric redshifts of ≳10{sup 9} galaxies for upcoming weak lensing cosmology experiments is a major challenge for the astrophysics community. The path to obtaining the required spectroscopic redshifts for training and calibration is daunting, given the anticipated depths of the surveys and the difficulty in obtaining secure redshifts for some faint galaxy populations. Here we present an analysis of the problem based on the self-organizing map, a method of mapping the distribution of data in a high-dimensional space and projecting it onto a lower-dimensional representation. We apply this method to existing photometric data from the COSMOS survey selected to approximate the anticipated Euclid weak lensing sample, enabling us to robustly map the empirical distribution of galaxies in the multidimensional color space defined by the expected Euclid filters. Mapping this multicolor distribution lets us determine where—in galaxy color space—redshifts from current spectroscopic surveys exist and where they are systematically missing. Crucially, the method lets us determine whether a spectroscopic training sample is representative of the full photometric space occupied by the galaxies in a survey. We explore optimal sampling techniques and estimate the additional spectroscopy needed to map out the color–redshift relation, finding that sampling the galaxy distribution in color space in a systematic way can efficiently meet the calibration requirements. While the analysis presented here focuses on the Euclid survey, similar analysis can be applied to other surveys facing the same calibration challenge, such as DES, LSST, and WFIRST.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Learning nonlinear level sets for dimensionality reduction in function approximation

We developed a Nonlinear Level-set Learning (NLL) method for dimensionality reduction in high-dimensional function approximation with small data. This work is motivated by a variety of design tasks in real-world engineering applications, where practitioners would replace their computationally intensive physical models (e.g., high-resolution fluid simulators) with fast-to-evaluate predictive machine learning models, so as to accelerate the engineering design processes. There are two major challenges in constructing such predictive models: (a) high-dimensional inputs (e.g., many independent design parameters) and (b) small training data, generated by running extremely time-consuming simulations. Thus, reducing the input dimension is critical to alleviate the over-fitting issue caused by data insufficiency. Existing methods, including sliced inverse regression and active subspace approaches, reduce the input dimension by learning a linear coordinate transformation; our main contribution is to extend the transformation approach to a nonlinear regime. Specifically, we exploit reversible networks (RevNets) to learn nonlinear level sets of a high-dimensional function and parameterize its level sets in low-dimensional spaces. A new loss function was designed to utilize samples of the target functions' gradient to encourage the transformed function to be sensitive to only a few transformed coordinates. The NLL approach is demonstrated by applying it to three 2D functions and two 20D functions for showing the improved approximation accuracy with the use of nonlinear transformation, as well as to an 8D composite material design problem for optimizing the buckling-resistance performance of composite shells of rocket inter-stages.

Zhang, Guannan↗
DOE OSTI2014

Full-dimensional diabatic potential energy surfaces including dissociation: The {sup 2}E{sup ″} state of NO{sub 3}

A scheme to produce accurate full-dimensional coupled diabatic potential energy surfaces including dissociative regions and suitable for dynamical calculations is proposed. The scheme is successfully applied to model the two-sheeted surface of the {sup 2}E{sup ″} state of the NO{sub 3} radical. An accurate potential energy surface for the NO{sub 3}{sup −} anion ground state is developed as well. Both surfaces are based on high-level ab initio calculations. The model consists of a diabatic potential matrix, which is expanded to higher order in terms of symmetry polynomials of symmetry coordinates. The choice of coordinates is key for the accuracy of the obtained potential energy surfaces and is discussed in detail. A second central aspect is the generation of reference data to fit the expansion coefficients of the model for which a stochastic approach is proposed. A third ingredient is a new and simple scheme to handle problematic regions of the potential energy surfaces, resulting from the massive undersampling by the reference data unavoidable for high-dimensional problems. The final analytical diabatic surfaces are used to compute the lowest vibrational levels of NO{sub 3}{sup −} and the photo-electron detachment spectrum of NO{sub 3}{sup −} leading to the neutral radical in the {sup 2}E{sup ″} state by full dimensional multi-surface wave-packet propagation for NO{sub 3} performed using the Multi-Configuration Time Dependent Hartree method. The achieved agreement of the simulations with available experimental data demonstrates the power of the proposed scheme and the high quality of the obtained potential energy surfaces.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2022

Intrinsic Dimensionality as a Metric for the Impact of Mission Design Parameters

High-resolution space-based spectral imaging of the Earth's surface delivers critical information for monitoring changes in the Earth system as well as resource management and utilization. Orbiting spectrometers are built according to multiple design parameters, including ground sampling distance (GSD), spectral resolution, temporal resolution, and signal-to-noise ratio. Different applications drive divergent instrument designs, so optimization for wide-reaching missions is complex. The Surface Biology and Geology component of NASA's Earth System Observatory addresses science questions and meets applications needs across diverse fields, including terrestrial and aquatic ecosystems, natural disasters, and the cryosphere. The algorithms required to generate the geophysical variables from the observed spectral imagery each have their own inherent dependencies and sensitivities, and weighting these objectively is challenging. Here, we introduce intrinsic dimensionality (ID), a measure of information content, as an applications-agnostic, data-driven metric to quantify performance sensitivity to various design parameters. ID is computed through the analysis of the eigenvalues of the image covariance matrix, and can be thought of as the number of significant principal components. This metric is extremely powerful for quantifying the information content in high-dimensional data, such as spectrally resolved radiances and their changes over space and time. We find that the ID decreases for coarser GSD, decreased spectral resolution and range, less frequent acquisitions, and lower signal-to-noise levels. This decrease in information content has implications for all derived products. ID is simple to compute, providing a single quantitative standard to evaluate combinations of design parameters, irrespective of higher-level algorithms, products, applications, or disciplines.

Intrinsic dimensionality↗
NASA NTRS1992

SAR processing based on the exact two-dimensional transfer function

The two-dimensional transfer functions of several synthetic aperture radar (SAR) focusing algorithms are derived considering the spaceborne SAR environments. The formulation includes the factors of the earth rotation and the antenna squint angles. The resultant transfer functions are explicitly expressed in terms of Doppler centroid frequency and Doppler frequency rate, which can be accurately estimated from the SAR data. Point target simulation results show that the algorithm based on the two-dimensional Fourier transformation outperforms the one-dimensional one for processing data acquired from high squint angles. The two-dimensional Fourier transformation approach appears to be a viable and simple solution for the processor design of future spaceborne SAR systems.

Chang, C. Y.↗