Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “latent feature models”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Large Scale Tensor Factorization via Parallel Sketches

Tensor factorization methods have recently gained increased popularity. A key feature that renders tensors attractive is the ability to directly model multi-relational data. In this work, we propose ParaSketch, a parallel tensor factorization algorithm that enables massive parallelism, to deal with large tensors. The idea is to compress the large tensor into multiple small tensors, decompose each small tensor in parallel, and combine the results to reconstruct the desired latent factors. Prior art in this direction entails potentially very high complexity in the (Gaussian) compression and final combining stages. Adopting sketching matrices for compression, the proposed method enjoys a dramatic reduction in compression complexity, and features a much lighter combining step. Moreover, theoretical analysis shows that the compressed tensors inherit latent identifiability under mild conditions, hence establishing correctness of the overall approach. Numerical experiments corroborate the theory and demonstrate the effectiveness of the proposed algorithm.

block term decomposition↗
DOE OSTI2023

Daytime convective development over land: the role of surface forcing

Water availability at the Earth surface determines the portioning of the surface heat flux into its sensible and latent components, that is, the surface heat flux Bowen ratio. The two components affect differently the surface buoyancy flux and thus the development and growth of the convective boundary layer. As a result, the Bowen ratio has a strong impact on the daytime dry and moist convection development over land. Here, we use two canonical modeling test cases, one for the shallow convection and one for the shallow-to-deep convection transition, to document the impact of the surface Bowen ratio on daytime convection development. A simple approach is used where results from simulations featuring the original setup are contrasted with simulations where surface sensible heat flux takes on values of the latent heat flux and vice versa. Such a change illustrates the key impact of the surface water availability without changing the total surface heat flux. Because of the larger surface buoyancy flux, simulations with the reversed surface heat fluxes feature faster deepening of the convective boundary layer and wider clouds once moist convection develops. Mean cloud base width of cumulus clouds increases with the boundary layer depth. For shallow-to-deep convection transition, comparison of simulations with the observed large-scale flow that feature substantial lower-tropospheric shear with simulations with no mean horizontal flow suggests that the organization of convective circulations within the boundary layer strongly affects initial size and organization of shallow convection, as well as the subsequent width increase once convection deepens and eventually transitions to deep precipitating convection. A simple explanation is provided of why deeper well-mixed convective subcloud layer results in wider clouds. The key is the larger width of boundary layer coherent updraft structures when the mixed layer is deeper.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Comparing Sensor Fusion and Multimodal Chemometric Models for Monitoring U(VI) in Complex Environments Representative of Irradiated Nuclear Fuel

Optical sensors and chemometric models were leveraged for the quantification of uranium(VI) (0–100 μg mL –1 ), europium (0–150 μg mL –1 ), samarium (0–250 μg mL –1 ), praseodymium (0–350 μg mL –1 ), neodymium (0–1000 μg mL –1 ), and HNO 3 (2–4 M) with varying corrosion product (iron, nickel, and chromium) levels using laser fluorescence, Raman scattering, and ultraviolet–visible–near-infrared absorption spectra. In this paper, an efficient approach to developing and evaluating tens of thousands of partial least-squares regression (PLSR) models, built from fused optical spectra or multimodal acquisitions, is discussed. Each PLSR model was optimized with unique preprocessing combinations, and features were selected using genetic algorithm filters. The 7-factor D-optimal design training set contained just 55 samples to minimize the number of samples. The performance of PLSR models was evaluated by using an automated latent variable selection script. PLS1 regression models tailored to each species outperformed a global PLS2 model. PLS1 models built using fused spectra data and a multimodal (i.e., analyzed separately) approach yielded similar information, resulting in percent root-mean-square error of prediction values of 0.9–5.7% for the seven factors. Further, the optical techniques and data processing strategies established in this study allow for the direct analysis of numerous species without measuring luminescence lifetimes or relying on a standard addition approach, making it optimal for near-real-time, in situ measurements. Nuclear reactor modeling helped bound training set conditions and identified elemental ratios of lanthanide fission products to characterize the burnup of irradiated nuclear fuel. Leveraging fluorescence, spectrophotometry, experimental design, and chemometrics can enable the remote quantification and characterization of complex systems with numerous species, monitor system performance, help identify the source of materials, and enable rapid high-throughput experiments in a variety of industrial processes and fundamental studies.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗
NASA NTRS2004

Precipitation and Latent Heating Distributions from Satellite Passive Microwave Radiometry: Method and Uncertainties - Part 1

A revised Bayesian algorithm for estimating surface rain rate, convective rain proportion, and latent heating/drying profiles from satellite-borne passive microwave radiometer observations over ocean backgrounds is described. The algorithm searches a large database of cloud-radiative model simulations to find cloud profiles that are radiatively consistent with a given set of microwave radiance measurements. The properties of these radiatively consistent profiles are then composited to obtain best estimates of the observed properties. The revised algorithm is supported by an expanded and more physically consistent database of cloud-radiative model simulations. The algorithm also features a better quantification of the convective and non-convective contributions to total rainfall, a new geographic database, and an improved representation of background radiances in rain-free regions. Bias and random error estimates are derived from applications of the algorithm to synthetic radiance data, based upon a subset of cloud resolving model simulations, and from the Bayesian formulation itself. Synthetic rain rate and latent heating estimates exhibit a trend of high (low) bias for low (high) retrieved values. The Bayesian estimates of random error are propagated to represent errors at coarser time and space resolutions, based upon applications of the algorithm to TRMM Microwave Imager (TMI) data. Errors in instantaneous rain rate estimates at 0.5 deg resolution range from approximately 50% at 1 mm/h to 20% at 14 mm/h. These errors represent about 70-90% of the mean random deviation between collocated passive microwave and spaceborne radar rain rate estimates. The cumulative algorithm error in TMI estimates at monthly, 2.5 deg resolution is relatively small (less than 6% at 5 mm/day) compared to the random error due to infrequent satellite temporal sampling (8-35% at the same rain rate).

Olson, William S.↗
NASA NTRS2006

Precipitation and Latent Heating Distributions from Satellite Passive Microwave Radiometry: Improved Method and Uncertainties - Part 1

A revised Bayesian algorithm for estimating surface rain rate, convective rain proportion, and latent heating profiles from satellite-borne passive microwave radiometer observations over ocean backgrounds is described. The algorithm searches a large database of cloud-radiative model simulations to find cloud profiles that are radiatively consistent with a given set of microwave radiance measurements. The properties of these radiatively consistent profiles are then composited to obtain best estimates of the observed properties. The revised algorithm is supported by an expanded and more physically consistent database of cloud-radiative model simulations. The algorithm also features a better quantification of the convective and nonconvective contributions to total rainfall, a new geographic database, and an improved representation of background radiances in rain-free regions. Bias and random error estimates are derived from applications of the algorithm to synthetic radiance data, based upon a subset of cloud-resolving model simulations, and from the Bayesian formulation itself. Synthetic rain-rate and latent heating estimates exhibit a trend of high (low) bias for low (high) retrieved values. The Bayesian estimates of random error are propagated to represent errors at coarser time and space resolutions, based upon applications of the algorithm to TRMM Microwave Imager (TMI) data. Errors in TMI instantaneous rain-rate estimates at 0.5 -resolution range from approximately 50% at 1 mm/h to 20% at 14 mm/h. Errors in collocated spaceborne radar rain-rate estimates are roughly 50%-80% of the TMI errors at this resolution. The estimated algorithm random error in TMI rain rates at monthly, 2.5deg resolution is relatively small (less than 6% at 5 mm day.1) in comparison with the random error resulting from infrequent satellite temporal sampling (8%-35% at the same rain rate). Percentage errors resulting from sampling decrease with increasing rain rate, and sampling errors in latent heating rates follow the same trend. Averaging over 3 months reduces sampling errors in rain rates to 6%-15% at 5 mm day.1, with proportionate reductions in latent heating sampling errors.

Olson, William S.↗
NASA NTRS2016

What Causes Mars' Annular Polar Vortices?

A distinctive feature of the Martian atmosphere is that the winter polar vortices exhibit annuli of high potential vorticity (PV) with a local minimum near the pole. These annuli are seen in observations, reanalyses, and free-running general circulation model simulations of Mars, but are not generally a feature of Earth's polar vortices, where there is a monotonic increase in magnitude of PV with latitude. The creation and maintenance of the annular polar vortices on Mars are not well understood. Here we use simulations with a Martian general circulation model to the show that annular vortices are related to another distinctive, and possibly unique in the solar system, feature of the Martian atmosphere: the condensation of the predominant atmospheric gas species (CO2) in polar winter regions. The latent heat associated with CO2 condensation leads to destruction of PV in the polar lower atmosphere, inducing the formation of an annular PV structure.

Toigo, A. D.↗
DOE OSTI2020

Detect and correct bias in multi-site neuroimaging datasets

The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for unknown population stratification in genetics. Overall, our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonization also requires caution as it can easily remove relevant subject-specific information. Code is available at https://github.com/ai-med/Dataset-Bias.

42 ENGINEERING↗
DOE OSTI2020

Three-Phase Modeling in Sockeye

The heat pipe simulation tool Sockeye is given the capability to allow the presence of the solid phase of the heat pipe working fluid, which is necessary for modeling transients to and from room temperature, since microreactor designs feature high-temperature heat pipes employing metal working fluids. The liquid phase equations are converted to equations for the mixture of liquid and solid phases, with a simple latent heat relation determining the fractions of these phases. This capability is introduced while preserving equivalent solutions for the liquid-vapor regime. Theory is presented, along with numerical examples to illustrate the propagation of a melt front and startup from the solid state.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Deep generative learning of magnetic frustration in artificial spin ice from magnetic force microscopy images

Increasingly large datasets of microscopic images with nanoscale resolution facilitate the development of machine learning methods to identify and analyze subtle physical phenomena embedded within the images. In this work, microscopic images of honeycomb lattice spin-ice samples serve as datasets from which we automate the calculation of net magnetic moments and directional orientations of spin-ice configurations. In the first stage of our workflow, machine learning models are trained to accurately predict magnetic moments and directions within spin-ice structures. Variational Autoencoders (VAEs), an emergent unsupervised deep learning technique, are employed to generate high-quality synthetic magnetic force microscopy (MFM) images and extract latent feature representations, thereby reducing experimental and segmentation errors. The second stage of proposed methodology enables precise identification and prediction of frustrated vertices and nanomagnetic segments, effectively correlating structural and functional aspects of microscopic images. This facilitates the design of optimized spin-ice configurations with controlled frustration patterns, enabling potential on-demand synthesis.

36 MATERIALS SCIENCE↗
NASA NTRS1981

Heat pipe solar receiver with thermal energy storage

An HPSR Stirling engine generator system featuring latent heat thermal energy storge, excellent thermal stability and self regulating, effective thermal transport at low system delta T is described. The system was supported by component technology testing of heat pipes and of thermal storage and energy transport models which define the expected performance of the system. Preliminary and detailed design efforts were completed and manufacturing of HPSR components has begun.

Zimmerman, W. F.↗
NASA NTRS1992

DEPEND: A simulation-based environment for system level dependability analysis

The design and evaluation of highly reliable computer systems is a complex issue. Designers mostly develop such systems based on prior knowledge and experience and occasionally from analytical evaluations of simplified designs. A simulation-based environment called DEPEND which is especially geared for the design and evaluation of fault-tolerant architectures is presented. DEPEND is unique in that it exploits the properties of object-oriented programming to provide a flexible framework with which a user can rapidly model and evaluate various fault-tolerant systems. The key features of the DEPEND environment are described, and its capabilities are illustrated with a detailed analysis of a real design. In particular, DEPEND is used to simulate the Unix based Tandem Integrity fault-tolerance and evaluate how well it handles near-coincident errors caused by correlated and latent faults. Issues such as memory scrubbing, re-integration policies, and workload dependent repair times which affect how the system handles near-coincident errors are also evaluated. Issues such as the method used by DEPEND to simulate error latency and the time acceleration technique that provides enormous simulation speed up are also discussed. Unlike any other simulation-based dependability studies, the use of these approaches and the accuracy of the simulation model are validated by comparing the results of the simulations, with measurements obtained from fault injection experiments conducted on a production Tandem Integrity machine.

Goswami, Kumar↗
NASA NTRS1988

A fault injection experiment using the AIRLAB Diagnostic Emulation Facility

The preparation for, conduct of, and results of a simulation based fault injection experiment conducted using the AIRLAB Diagnostic Emulation facilities is described. An objective of this experiment was to determine the effectiveness of the diagnostic self-test sequences used to uncover latent faults in a logic network providing the key fault tolerance features for a flight control computer. Another objective was to develop methods, tools, and techniques for conducting the experiment. More than 1600 faults were injected into a logic gate level model of the Data Communicator/Interstage (C/I). For each fault injected, diagnostic self-test sequences consisting of over 300 test vectors were supplied to the C/I model as inputs. For each test vector within a test sequence, the outputs from the C/I model were compared to the outputs of a fault free C/I. If the outputs differed, the fault was considered detectable for the given test vector. These results were then analyzed to determine the effectiveness of some test sequences. The results established coverage of selt-test diagnostics, identified areas in the C/I logic where the tests did not locate faults, and suggest fault latency reduction opportunities.

Baker, Robert↗
DOE OSTI2024

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗
DOE OSTI2021

Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning

Many self-supervised methods have been proposed with the target of image anomaly detection. These methods often rely on the paradigm of data augmentation with predefined transformations such as flipping, cropping, and rotations. However, it is not straightforward to apply these techniques for non-image data, such as time series or tabular data, while the performance of the existing deep approaches has been under our expectation on tasks beyond images. In this work, we propose a novel active learning (AL) scheme that relied on neural autoregressive flows (NAF) for self-supervised anomaly detection, specifically on small-scale data. Unlike other generative models such as GANs or VAEs, flow-based models allow to explicitly learn the probability density and thus can assign accurate likelihoods to normal data which makes it usable to detect anomalies. The proposed NAF-AL method is achieved by efficiently generating random samples from latent space and transforming them into feature space along with likelihoods via invertible mapping. The samples with lower likelihoods are selected and further checked by outlier detection using Mahalanobis distance. The augmented samples incorporating with normal samples are used for training a better detector so as to approach decision boundaries. Compared with random transformations, NAF-AL can be interpreted as a likelihood-oriented data augmentation that is more efficient and robust. Extensive experiments show that our approach outperforms existing baselines on multiple time series and tabular datasets, and a real-world application in advanced manufacturing, with significant improvement on anomaly detection accuracy and robustness over the state-of-the-art.

Zhang, Jiaxin↗
DOE OSTI2023

A Graphical Model for Fusing Diverse Microbiome Data

This paper develops a Bayesian graphical model for fusing disparate types of count data. The motivating application is the study of bacterial communities from diverse high-dimensional features, in this case, transcripts, collected from different treatments. In such datasets, there are no explicit correspondences between the communities and each corresponds to different factors, making data fusion challenging. We introduce a flexible multinomial-Gaussian generative model for jointly modeling such count data. This latent variable model jointly characterizes the observed data through a common multivariate Gaussian latent space that parameterizes the set of multinomial probabilities of the transcriptome counts. The covariance matrix of the latent variables induces a covariance matrix of co-dependencies between all the transcripts, effectively fusing multiple data sources. We present a computationally scalable variational Expectation-Maximization (EM) algorithm for inferring the latent variables and the parameters of the model. Here, the inferred latent variables provide a common dimensionality reduction for visualizing the data and the inferred parameters provide a predictive posterior distribution. In addition to simulation studies that demonstrate the variational EM procedure, we apply our model to a bacterial microbiome dataset.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2004

NASA GEOS-3/TRMM Re-analysis: Capturing Observed Tropical Rainfall Variability in Global Analysis for Climate Research

Understanding climate variability over a wide range of space-time scales requires a comprehensive description of the earth system. Global analyses produced by a fixed assimilation system (i.e., re-analyses) - as their quality continues to improve - have the potential of providing a vital tool for meeting this challenge. But at the present time, the usefulness of re-analyses is limited by uncertainties in such basic fields as clouds, precipitation, and evaporation - especially in the tropics, where observations are relatively sparse. Analyses of the tropics have long been shown to be sensitive to. the treatment of cloud precipitation processes, which remains a major source of uncertainty in current models. Yet, for many climate studies it is crucial that analyses can accurately reproduce the observed rainfall intensity and variability since a small error of 1 mm/d in surface rain translates into an error of approx. 30 W/sq m in energy (latent heat) flux. Currently, discrepancies between the observed and analyzed monthly-mean rain rates averaged to 100 km x 100 km resolution can exceed 4 mm/d (or 120 W/sq m ), compared to uncertainties in surface radiative fluxes of approx. 10-20 W/sq m . Improving precipitation in analyses would reduce a major source of uncertainty in the global energy budget. Uncertainties in tropical precipitation have also been a major impediment in understanding how the tropics interact with other regions, including the remote response to El Nino/Southern Oscillation (ENSO) variability on interannual time scales, the influence of Madden-Julian Oscillation (MJO) and monsoons on intraseasonal time scales. A global analysis that can replicate the observed precipitation variability together with physically consistent estimates of other atmospheric variables provides the key to breaking this roadblock. NASA Goddard Space Flight Center has been exploring the use of satellite-based microwave rainfall measurements in improving global analyses and has recently produced a multi-year, 1 x 1 TRMM re-analysis , which assimilates 6-hourly TMI and SSM/I surface rain rates over tropical oceans using a ID variational continuous assimilation (VCA) procedure in the GEOS-3 global data assimilation system. The analysis period extends from 1 November 1997 through 3 1 December 2002. The goal is to produce a multi-year global analysis that is dynamically consistent with available tropical precipitation observations for the community to assess its utility in climate applications and identify areas for further improvements. A distinct feature of the GEOS-3RRMh4 re-analysis is that its precipitation analysis is not derived from a short-term forecast (as done in most operational systems) but is given by a time- continuous model integration constrained by precipitation observations within a 6-h analysis window, while the wind, temperature, and pressure fields are allowed to directly respond to the improved precipitation and associated latent heating structures within the same analysis window. In this talk, I will assess the impact VCA precipitation assimilation on analyses of climate signals ranging from a few weeks to interannual time scales and compare results against other operational and reanalysis products.

Hou, Arthur Y.↗
DOE OSTI2021

Characterizing Signatures of Geothermal Exploration Data with Machine Learning Techniques: An Application to the Nevada Play Fairway Analysis

We are introducing machine learning methods to the play fairway analysis to generate geothermal potential maps to support the evaluation of geothermal resource potential and the exploration for undiscovered blind geothermal systems in the Nevada Great Basin region. Our project aims to identify new ways to combine the play fairway data and empirically organize relationships between feature weights and labels in an improved workflow. As a means of doing this, we introduce machine learning methods to evaluate the influence of certain geological and geophysical features/feature sets in predicting geothermal favorability. This report highlights promising approaches based on supervised and unsupervised learning methods. First, we demonstrate a filter method applied to supervised classification modeling. The supervised filter method is based on permutation analysis to evaluate every possible feature combination/drop out scenario and rank feature influence based on the performance variance of supervised classification models. Additionally, we present an unsupervised factor analysis based on principal component analysis coupled with a semi-supervised kmeans clustering algorithm. This analysis allows us to identify the optimal number of groups/clusters for training sites and structural settings to identify feature patterns including correlation, variance, and latent and dominant feature relationships. The results from these methods offer a promising avenue for identifying favorable sources of predictive information to identify the locations of blind geothermal systems and furthering our understanding of complex geothermal feature and label relationships in the Great Basin region and beyond.

15 GEOTHERMAL ENERGY↗