Search NASA⌕ Search

SEARCH · Search NASA

Results for “Latent”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Impact of Increased Latent Generations on Sensitivity Calculations with SCALE

Analyses of cross section sensitivity data from systems with fissile material allow analysts to associate an importance for each material, nuclide, reaction, and neutron energy by simulating real world criticality scenarios. Although criticality safety validation efforts can be guided by the cross-section sensitivity and uncertainty data generated for a particular system, these calculations can often be computationally expensive and sometimes cumbersome without proper guidance. The TSUNAMI suite within the SCALE code package has several methods for generating sensitivity data, including multigroup and continuous energy (CE) capabilities. The release of SCALE 6.3 has three different CE methods for generating cross section sensitivity data: (1) the Iterated Fission Probability (IFP) method with the KENO Monte Carlo transport solver, (2) the IFP method with the Shift Monte Carlo transport solver, and (3) the Contributon-Linked eigenvalue sensitivity/Uncertainty estimation via Tracklength importance CHaracterization (CLUTCH) method with the KENO Monte Carlo transport solver. Although the CLUTCH method has additional parameters for generating sensitivity data files relative to the IFP method, all three methods use latent generations, which are the generations between an event (i.e., fission) and the assessment of importance based on the asymptotic population of progeny neutrons. Increasing the number of latent generations in a calculation leads to increased discrimination of the sensitivity coefficients but at the cost of the increased uncertainty associated with those generated values. Analysts must balance the accuracy of the sensitivity calculations and its uncertainty with the associated computational cost involved in generating the values. This paper discusses the impact of adjusting the latent generation parameter for a range of sensitivity values and how these changes compare with the direct perturbation values obtained from a change of ±0.5% Δ k in both benchmark and safety application models. Two benchmarks from the International Handbook of Evaluated Criticality Safety Benchmark Experiments and the MPC-32 dual purpose canister for spent nuclear fuel are used for analysis.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations

This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of exogenous variables, such as control adjustment and ambient temperature. In the LSDNN model, an encoder–decoder architecture was designed to capture cross-correlation among different measured variables. In addition, a latent space dynamic structure was proposed to propagate the dynamics in the latent space to enable prediction. The prediction power of the LSDNN was utilized for monitoring a geothermal power plant and detecting abnormal events. The model was integrated with principal component analysis (PCA)-based process monitoring techniques to develop a fault-detection procedure. The performance of the proposed LSDNN model and fault detection approach was demonstrated using field data collected from a geothermal power plant.

15 GEOTHERMAL ENERGY↗
DOE OSTI2026

Reduced‐Order Modeling of Energetic Materials Using Physics‐Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)

Physics-aware deep learning (PADL) has gained popularity for use in spatiotemporal dynamics simulations, such as those in computational modeling of energetic materials (EM). We show that the challenge PADL methods face while learning complex field evolution problems can be simplified and accelerated by decoupling it into two tasks: learning complex geometric features in evolving fields and modeling dynamics over these features in a lower-dimensional feature space. We build upon our previous work on physics-aware recurrent convolutional neural networks (PARC). PARC embeds knowledge of underlying physics into its neural network architecture for more robust and accurate prediction of evolving physical fields. PARC was shown to effectively learn complex nonlinear features such as the formation of hotspots and coupled shock fronts in various initiation scenarios of EMs, as a function of microstructures, serving effectively as a microstructure-aware burn model. Here, we further accelerate PARC and reduce its computational cost by projecting the original dynamics onto a lower-dimensional invariant manifold, or “latent space.” The projected latent representation encodes the complex geometry of evolving fields (e.g., temperature and pressure) in a set of data-driven features. The reduced dimension of this latent space allows us to learn the dynamics during the initiation of EM with a lighter and more efficient model. We observe a significant decrease in training and inference time while maintaining results comparable to PARC at inference. This work takes steps towards enabling rapid prediction of EM thermomechanics at larger scales and characterization of EM structure–property–performance linkages at a full application scale.

Mathematics and Computing↗
DOE OSTI2025

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↗
DOE OSTI2021

Using TRMM Latent Heat as a Source to Estimate Convection Induced Gravity Wave Momentum Flux in the Lower Stratosphere

Due to a lack of observations, it is a big challenge to quantify the momentum flux transported from the troposphere into the lower stratosphere by gravity waves generated by convection. This limits our understanding of the dynamics of general circulation in the stratosphere and the realism of simulations of the Quasi Biennial Oscillation. In the past decade, some general circulation models have linked the momentum flux to the latent heating from subgrid scale convective precipitation with some success. However, there is still a large uncertainty in the sources of subgrid scale convection in these models. This study applies the links between the momentum flux and convective latent heating directly to the convective precipitation derived from 16 years of TRMM precipitation radar observations in the tropics and subtropics. The total and directional momentum flux at 100 hPa are derived at individual convective pixels by using the TRMM Spectrum Latent Heating product and large-scale wind profiles from the ERA-Interim dataset. For the first time, we are able to estimate the geographical distribution of momentum flux at 100 hPa in tropics and subtropics from the observed convective sources. The diurnal, seasonal, and interannual variations of the derived momentum flux are presented and discussed. These results could provide a reference to validate the dynamic coupling between the tropical troposphere and the stratosphere in the general circulation models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics With Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and interconnected nature of complex patterns, which hinder the understanding of their underlying physical processes. Existing AI methods often face limitations in interpretability, computational efficiency, and scalability, reducing their applicability in real-world scenarios. This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs), to reduce complex patterns into lower-dimensional latent spaces and visualize them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN. These visualizations, presented through coordinated and interactive views and tailored glyphs, enable intuitive exploration of complex multivariate temporal patterns, identifying patterns’ similarities and uncover their potential correlations for a better interpretability of the AI outputs. The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes. Additionally, novel metrics and visualizations are introduced to validate the models and assess the performance, efficiency, and consistency of latent maps generated by VAE, which have been utilized in prior studies for latent space cartography and used as a benchmark in this study, and the emerging TFT architecture under various configurations. These analyses provide actionable insights for model parameter tuning and reliability improvements. Comparative results highlight that TFT achieves shorter run times and superior scalability to diverse time-series data shapes compared to VAE. This work advances fault diagnosis in multivariate time series, fostering explainable AI to support critical system operations.

Explainable AI↗
DOE OSTI2022

Non-Blind Deblurring for Fluorescence: A Deformable Latent Space Approach with Kernel Parameterization

We report N\non-blind deblurring (NBD) is a modeling method of the image deblurring problem in computer vision, where the blurring kernel is known or can be externally estimated. In this paper, we attempt to solve a parametric NBD problem, inspired by the simultaneous acquisition of ptychography and fluorescent imaging (FI). Ptychography is an imaging method that favors larger probes, i.e. convolutional kernels, while FI relies on a small probe for high resolution. Also, the kernel can be solved during ptychographic reconstruction. With Ptycho-FI using the same larger kernel, we can perform NBD on the blurred fluorescent images to achieve high-resolution FI, and thus speed up the experiments. To this end, we design a deep latent space deformation network that is directly parameterized by the kernel. The network consists of three components: encoder, deformer, and decoder, where the deformer is specifically meant to rectify the latent space representations of blurred images to a standard latent space, regardless of the kernel. The deformation network is trained with a two-stage training scheme. We conduct extensive experiments to confirm that our parametric model can adapt to drastically different blurring kernels and perform robust deblurring.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2022

Latent Space Dynamics Identification

LaSDI is a data-driven physical simulation software that forms a latent space for a given high-fidelity model and discovers a set of ordinary differential equations for the latent space dynamics. It allows a fast and accurate solution process, which is useful for multi-query decision making applications, such as design optimization and uncertainty quantification. The performance of the LaSDI framework is demonstrated on four different problems, i.e., 1D and 2D Burgers equations, nonlinear heat conduction, and radial advection problems. Both linear and nonlinear compression techniques, such as neural network and proper orthogonal decomposition, are used to form a latent space. A concept of local dynamics identification procedure is introduced to enable a parametric model, which enhances the accuracy level over a given parameter space.

Fries, William↗
DOE OSTI2020

Subcloud and Cloud-Base Latent Heat Fluxes during Shallow Cumulus Convection

Doppler and Raman lidar observations of vertical velocity and water vapor mixing ratio are used to probe the physics and statistics of subcloud and cloud-base latent heat fluxes during cumulus convection at the ARM Southern Great Plains (SGP) site in Oklahoma, United States. The statistical results show that latent heat fluxes increase with height from the surface up to ~0.8 Z i (where Z i is the convective boundary layer depth) and then decrease to ~0 at Z i . Peak fluxes aloft exceeding 500 W m −2 are associated with periods of increased cumulus cloud cover and stronger jumps in the mean humidity profile. These entrainment fluxes are much larger than the surface fluxes, indicating substantial drying over the 0–0.8 Z i layer accompanied by moistening aloft as the CBL deepens over the diurnal cycle. We also show that the boundary layer humidity budget is approximately closed by computing the flux divergence across the 0–0.8 Z i layer. Composite subcloud velocity and water vapor anomalies show that clouds are linked to coherent updraft and moisture plumes. The moisture anomaly is Gaussian, most pronounced above 0.8 Z i and systematically wider than the velocity anomaly, which has a narrow central updraft flanked by downdrafts. This size and shape disparity results in downdrafts characterized by a high water vapor mixing ratio and thus a broad joint probability density function (JPDF) of velocity and mixing ratio in the upper CBL. We also show that cloud-base latent heat fluxes can be both positive and negative and that the instantaneous positive fluxes can be very large (~10 000 W m −2 ). However, since cloud fraction tends to be small, the net impact of these fluxes remains modest.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Reification of latent microstructures: On supervised unsupervised and semi-supervised deep learning applications for microstructures in materials informatics

Machine learning (ML), including deep learning (DL), has become increasingly popular in the last few years due to its continually outstanding performance. In this context, we apply machine learning techniques to "learn" the microstructure using both supervised and unsupervised DL techniques. In particular, we focus (1) on the localization problem bridging (micro)structure (localized) property using supervised DL and (2) on the microstructure reconstruction problem in latent space using unsupervised DL. The goal of supervised and semi-supervised DL is to replace crystal plasticity finite element model (CPFEM) that maps from (micro)structure (localized) property, and implicitly the (micro)structure (homogenized) property relationships, while the goal of unsupervised DL is (1) to represent high-dimensional microstructure images in a non-linear low-dimensional manifold, and (2) to discover a way to interpolate microstructures via latent space associating with latent microstructure variables. At the heart of this report is the applications of several common DL architectures, including convolutional neural networks (CNN), autoencoder (AE), and generative adversarial network (GAN), to multiple microstructure datasets, and the quest of neural architecture search for optimal DL architectures.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Impact of Increased Latent Generations on Sensitivity Calculations with SCALE [Slides]

Depending on the system, energy, and/or nuclide, altering the number of latent generations can significantly impact generated sensitivity coefficients. In general, as the number of latent generations increases, the accuracy of the generated sensitivity value compared with the DP value increases and there is a significant increase in the uncertainty with generated sensitivity values. IFP generated sensitivities appear to be more stable than those with CLUTCH. Complex systems, even with IFP and increased latent generations can still produce poor results (i.e., MPC- 32). This reiterates the importance of performing DPs to confirm sensitivities. IFP-Shift and CLUTCH can take advantage of parallel computing abilities. Work continues in this area as additional parameters and calculational methods are examined to provide analysts insights to successfully generating sensitivity coefficients for confirmatory analyses and validation efforts.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Oracle-Preserving Latent Flows

A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Corrosion evaluation of metal foams in eutectic molten salts for high temperature latent heat energy storage application

High-temperature Thermal Energy Storage (TES) has drawn great attention as a technology that can increase the role and profitability of micro nuclear reactors in the decentralized clean energy market. Various research needs have been proposed by Idaho National Laboratory (INL) in "the Integrated Energy Systems: 2020 Roadmap" with the goal of utilizing the high temperature of 550 degrees or more generated in the 4th generation reactor to industrial purposes from the standpoint of integrated energy systems [1]. With the recent development of the 4th generation nuclear power plant, including micro nuclear reactor, there is a great deal of interest in researching how to efficiently couple a heat source to an industrial process through thermal processing. Texas A&M University (TAMU) and INL are currently collaborating to develop a novel latent heat storage design called HITB (Heat pipe-Integrated Thermal Battery). As part of the small-scale experimental demonstration research for HITB, a study for storage medium selection was conducted at TAMU. Eutectic salts have attracted interest as high-temperature heat storage medium for HITB. Especially, chloride molten salts and fluoride molten salts are considered promising candidates due to their high melting temperature, thermal stability, and high latent heat of fusion. Since eutectic salts have poor thermal conductivity in general, it is critical to distribute materials with high thermal conductivity evenly to facilitate the charging and discharging of heat. In this study, metal foam was considered in the HITB system to overcome the poor heat transfer characteristics of eutectic salts. In order to improve heat transfer, it is necessary to study materials with high thermal conductivity, corrosion resistant to molten salts, such as fins, extended surfaces, particles, microcapsulation, or foam structure. Porous structure of copper or aluminum can increase heat transfer area, form a thermal transfer network, and increase the effective thermal conductivity of thermal storage medium [2]. Since the melting temperature is required to be at least 450? in the current HITB design, various eutectic salts are being considered. FLiNaK and FLiBe, which are famous for fluoride salts, are good candidates, but due to the sharp rise in the price of LiF recently, they are excluded for economic reasons to be applied to large-capacity thermal energy storage. On the other hand, chloride salts are very cheap and easy to obtain, have a high melting temperature, and have a high latent heat of fusion, so they are recently in the spotlight as a phase change material. However, because of the hygroscopic nature of chloride salts, HCl gas due to impurity is easy to be released and is particularly vulnerable to corrosion. Chloride eutectic salts have been tested and suggested for metal alloys that are particularly resistant to corrosion, such as SS304, SS316, Hastelloy, Inconel 625, Incoloy 800H, which has low thermal conductivity, and is very expensive [3-6]. Porous materials with high thermal conductivity such as copper and aluminum have been tested for stability in fluids such as paraffin or water as metal foam or metal fin structures, but high temperature corrosion tests were not performed on various eutectic salts yet. Therefore, this study investigated the high temperature corrosion characteristics of metal alloys, such as C10100 foam, C10100 plate, 6101 alloy foam, and SS316 plate, while immersed in the candidate eutectic salts. A total of 20 tests for SS316 coupons and 10 tests for C10100 coupons were performed to ensure the repeatability of the present measurements. Since it is difficult to completely remove the salt inside metal foam due to the complex inner structure of the metal foam, only the surface condition was observed with a microscopy and scanning electron microscopy (SEM) image, except for measuring the corrosion rate and average mass loss.

25 ENERGY STORAGE↗
DOE OSTI2021

Evaluation of Formate Salt PCM’s for Latent Heat Thermal Energy Storage

This work examines formate salts as potential phase change materials (PCMs) for middle-high temperature (≤250 °C) latent heat thermal energy storage applications. The thermophysical properties of three formate salts were characterized: pure sodium formate and binary blends of sodium/potassium formate and sodium/calcium formate. The stability of formate PCM’s was evaluated by thermal cycling using differential scanning calorimetry where sodium formate and sodium/potassium formate appeared stable over 600 cycles, while sodium/calcium formate exhibited a monotonic decrease in heat of fusion over the test period. A longer test with sodium formate led to gas release and decomposition of the salt. FTIR analysis of the PCM showed degradation of formate to oxalate. T-history experiments with 50-g PCM quantities demonstrated a bulk supercooling of only 2–3 °C for these salts. Thermal conductivity enhancement of over 700% was achieved by embedding aluminum in the solid PCM. Finally, mild carbon steel was immersed in molten sodium formate for up to 2000 h. Sodium formate was found to be non-corrosive, as calculated by mass loss and confirmed by cross-sectional high-resolution microscopy. FTIR analysis of the PCM after 2000 h shows oxidation at the free surface, while the bulk PCM remained unchanged, further indicating a need to protect the formate from atmospheric exposure when used as a PCM.phase change materials; formate salts; latent heat thermal energy storage; thermal cycling; supercooling; thermal conductivity enhancement; corrosion

25 ENERGY STORAGE↗
DOE OSTI2022

Latent Mechanisms of Polarization Switching from In Situ Electron Microscopy Observations

In situ scanning transmission electron microscopy enables observation of the domain dynamics in ferroelectric materials as a function of externally applied bias and temperature. The resultant data sets contain a wealth of information on polarization switching and phase transition mechanisms. However, identification of these mechanisms from observational data sets has remained a problem due to a large variety of possible configurations, many of which are degenerate. Here, an approach based on a combination of deep learning-based semantic segmentation, rotationally invariant variational autoencoder (VAE), and non-negative matrix factorization to enable learning of a latent space representation of the data with multiple real-space rotationally equivalent variants mapped to the same latent space descriptors is introduced. By varying the size of training sub-images in the VAE, the degree of complexity in the structural descriptors is tuned from simple domain wall detection to the identification of switching pathways. Importantly, this yields a powerful tool for the exploration of the dynamic data in mesoscopic electron, scanning probe, optical, and chemical imaging. Moreover, this work adds to the growing body of knowledge of incorporating physical constraints into the machine and deep-learning methods to improve learned descriptors of physical phenomena.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Dynamic modeling of heat pipe integrated thermal battery latent heat storage system experiment validation

A heat pipe integrated thermal battery system has been constructed to investigate a high-temperature latent heat thermal energy storage technology that takes advantage of near isothermal operation of latent heat storage and heat pipes to potentially enable high-energy isothermal heat storage. A dynamic model constructed in Modelica has been validated, showing errors between 2.5 °C–39.7 °C across 10-h to 47-h simulations against experiment results, showing good prediction capability of experiment output, especially against phase change time. Model calibrations showing vessel heat-up capability of 3 kW and heat pipes combining to provide 600 W each during experiment operation validate experiment circumstances including reduced material loading and reduced power capability. The experiment configuration uses an Al-Mg-Zn eutectic metal as the storage material, heated via heat tape wrapped around the vessel and guide tubes to bring the system to operation range (>400 °C) and to simulate charging heat exchange, respectively, with heat rejection occurring through the surfaces of the material and facilitated via guide tubes with less insulation wrapping. The model is available in the open-source repository HYBRID on Github.

25 - ENERGY STORAGE↗
DOE OSTI2021

A fast reduced model for a shell-and-tube based latent heat thermal energy storage heat exchanger and its application for cost optimal design by nonlinear programming

Numerical simulation of latent heat thermal energy storage (LHTES) systems plays a fundamental role in studying the physical process and guiding the engineering design. Discretization of the PDEs describing the nonlinear solidification/melting process of phase change materials (PCMs) leads to a large-scale complex dynamics system, where the system behavior depends on a set of parameters. In a design setting, repeated model evaluations are required over the set of parameters results in significant computational burden. In this paper, an explicit analytic solution was built for the propagation of the solidification front in a cylindrical coordinate. The analytic solution approach is further employed to develop a low computational reduced model (RM) as a module for a shell-and-tube based LHTES heat exchanger. The levelized Cost of Energy (LCOE) is used as a design metric and the RM model is used to apply system-level constraints in the nonlinear programming formulation that facilitates efficient global optimal design of the PCM properties, flow conditions and tube geometries. The use of LCOE as the design metric prevents over design of the heat transfer rate and also establishes a fair ground for evaluation of different thermal storage technologies and their integrated applications with other systems. Optimal results showed that a higher effectiveness results in a higher LCOE; the velocity of the HTF and the length of the channel are highly correlated with each other; both larger PCM latent energy and conductivity result in lower LCOE.

25 ENERGY STORAGE↗
DOE OSTI2021

Analysis of basic airflow configurations for separate sensible and latent cooling systems with indoor air recirculation

Separate sensible and latent cooling (SSLC) is a technology with efficiency and comfort advantages over conventional cooling systems used for space conditioning of buildings. Using multiple cooling processes at different temperatures allows SSLC to save energy by raising the evaporation temperature of the sensible cooling process. In this paper, all possible airflow configurations of SSLC systems are enumerated under the following constraints: exactly two heat exchangers are used, and air is recirculated to the conditioned space (no exhaust or outdoor air treatment). Seven designs are identified, with varying free operating variables, and each is modeled. Analysis reveals that several configurations are equivalent, and there is only one unique basic airflow SSLC configuration: the one with the sensible and latent heat exchangers placed in series. The efficiency of the SSLC system is compared against that of the conventional system. Under standard conditions, an SSLC system can improve the coefficient of performance by 14.8%. In addition to the numerical simulation, the optimal operating condition of the basic air configuration of the SSLC system is derived analytically. The basic SSLC system is shown to offer the highest performance improvement when the outdoor temperature is relatively cool and the space sensible heat ratio is high.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗