Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “latent variables”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

The latent variable proximal point algorithm for variational problems with inequality constraints

The latent variable proximal point (LVPP) algorithm is a framework for solving infinite-dimensional variational problems with pointwise inequality constraints. The algorithm is a saddle point reformulation of the Bregman proximal point algorithm. At the continuous level, the two formulations are equivalent, but the saddle point formulation is more amenable to discretization because it introduces a structure-preserving transformation between a latent function space and the feasible set. Working in this latent space is much more convenient for enforcing inequality constraints than the feasible set, as discretizations can employ general linear combinations of suitable basis functions, and nonlinear solvers can involve general additive updates. LVPP yields numerical methods with observed mesh-independence for obstacle problems, contact, fracture, plasticity, and others besides; in many cases, for the first time. The framework also extends to more complex constraints, providing means to enforce convexity in the Monge–Ampère equation and handling quasi-variational inequalities, where the underlying constraint depends implicitly on the unknown solution. Here, in this paper, we describe the LVPP algorithm in a general form and apply it to ten problems from across mathematics.

Inequality constraints↗
DOE OSTI2025

A Latent-Variable Formulation of the Poisson Canonical Polyadic Tensor Model: Maximum Likelihood Estimation and Fisher Information

We establish parameter inference for the Poisson canonical polyadic (PCP) tensor model through a latent-variable formulation. Our approach exploits the observation that any random PCP tensor can be derived by marginalizing an unobservable random tensor of one dimension larger. The loglikelihood of this larger dimensional tensor, referred to as the “complete” loglikelihood, is comprised of multiple rank one PCP loglikelihoods. Using this methodology, we first derive maximum likelihood estimators for the PCP model and demonstrate that several existing algorithms for fitting non-negative matrix and tensor factorizations are Expectation-Maximization algorithms. Next, we derive the observed and expected Fisher information matrices for the PCP model. The Fisher information provides us crucial insights into the well-posedness of the tensor model, such as the role that tensor rank plays in identifiability and indeterminacy. For the special case of rank one PCP models, we demonstrate that these results are greatly simplified.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A simple introduction to the SiMPL method for density-based topology optimization

We introduce a novel method for solving density-based topology optimization problems: Sigmoidal Mirror descent with a Projected Latent variable (SiMPL). The SiMPL method (pronounced as “the simple method”) optimizes a design using only first-order derivative information of the objective function. The bound constraints on the density field are enforced with the help of the (negative) Fermi–Dirac entropy, which is also used to define a non-symmetric distance function called a Bregman divergence on the set of admissible designs. This Bregman divergence leads to a simple update rule that is further simplified with the help of a so-called latent variable. Because the SiMPL method involves discretizing the latent variable, it produces a sequence of pointwise-feasible iterates, even when high-order finite elements are used in the discretization. Numerical experiments demonstrate that the method outperforms other popular first-order optimization algorithms. In conclusion, to outline the general applicability of the technique, we include examples with (self-load) compliance minimization and compliant mechanism optimization problems.

Calculus of Variations and Optimization↗
DOE OSTI2024

Towards interpretable Cryo-EM: disentangling latent spaces of molecular conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Generalization error guaranteed auto-encoder-based nonlinear model reduction for operator learning

Many physical processes in science and engineering are naturally represented by operators between infinite-dimensional function spaces. The problem of operator learning, in this context, seeks to extract these physical processes from empirical data, which is challenging due to the infinite or high dimensionality of data. An integral component in addressing this challenge is model reduction, which reduces both the data dimensionality and problem size. In this paper, we utilize low-dimensional nonlinear structures in model reduction by investigating Auto-Encoder-based Neural Network (AENet). AENet first learns the latent variables of the input data and then learns the transformation from these latent variables to corresponding output data. Our numerical experiments validate the ability of AENet to accurately learn the solution operator of nonlinear partial differential equations. Furthermore, we establish a mathematical and statistical estimation theory that analyzes the generalization error of AENet. Finally, our theoretical framework shows that the sample complexity of training AENet is intricately tied to the intrinsic dimension of the modeled process, while also demonstrating the robustness of AENet to noise.

Auto-encoder↗
DOE OSTI2024

Data driven discovery and quantification of hyperspectral leaf reflectance phenotypes across a maize diversity panel

Abstract Estimates of plant traits derived from hyperspectral reflectance data have the potential to efficiently substitute for traits, which are time or labor intensive to manually score. Typical workflows for estimating plant traits from hyperspectral reflectance data employ supervised classification models that can require substantial ground truth datasets for training. We explore the potential of an unsupervised approach, autoencoders, to extract meaningful traits from plant hyperspectral reflectance data using measurements of the reflectance of 2151 individual wavelengths of light from the leaves of maize ( Zea mays ) plants harvested from 1658 field plots in a replicated field trial. A subset of autoencoder‐derived variables exhibited significant repeatability, indicating that a substantial proportion of the total variance in these variables was explained by difference between maize genotypes, while other autoencoder variables appear to capture variation resulting from changes in leaf reflectance between different batches of data collection. Several of the repeatable latent variables were significantly correlated with other traits scored from the same maize field experiment, including one autoencoder‐derived latent variable (LV8) that predicted plant chlorophyll content modestly better than a supervised model trained on the same data. In at least one case, genome‐wide association study hits for variation in autoencoder‐derived variables were proximal to genes with known or plausible links to leaf phenotypes expected to alter hyperspectral reflectance. In aggregate, these results suggest that an unsupervised, autoencoder‐based approach can identify meaningful and genetically controlled variation in high‐dimensional, high‐throughput phenotyping data and link identified variables back to known plant traits of interest.

Tross, Michael C.↗
DOE OSTI2024

Application of Partial Least Squares Approaches to Pyroprocessing ER Data

Multivariate approaches show promise for application to process monitoring for safeguards of pyroprocessing. Past MPACT work explored the application of Principal Component Analysis (PCA) to detect off-normal conditions in pyroprocessing electrorefiner (ER) data from in the Hot Fuel Examination Facility (HFEF) at Idaho National Laboratory (INL) known as the Scalable Pyrochemical Recycling testbed (SPyRe) ER. PCA, however, does not consider the output variables. In FY24, multivariate analysis was extended from PCA to Partial Least Squares (PLS) analysis. PLS maximizes the variance between both the input signals and output variables. In the case of this work, PLS was applied in two different manners: Predictive PLS and Discriminant PLS. Predictive PLS maximizes the covariance between the process variables of the ER and the measured U concentration from in-situ voltammetry. Discriminant PLS maximizes the covariance between the process variables and a set of training process “states” such as known off-normal conditions. By projecting into the latent variable space in PLS, the process variables can be regressed onto the outputs and predictions can be made for new data sets. In this work, by applying predictive PLS, a penalized non-linear PLS approach was able to make predictions of concentration based on test and training data and detect when operations were off-normal. However, the predictive PLS does not classify the signals to which off-normal operations are attributable. Discriminant PLS can be used to classify off-normal operations but is inadequate to properly classify specific off-normal classes like power supply faults when the Discriminant PLS model is only specifically trained to detect that off-normal class. When all faults are trained against the observation data, all three operational classes are accurately classified and distinguished. Thus, future application of latent variable techniques should not select any given method, but should use a mixture of PCA, Predictive PLS, and Discriminant PLS.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Full event particle-level unfolding with variable-length latent variational diffusion

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic t\bar{t} t t ‾ production at the Large Hadron Collider.

Shmakov, Alexander↗
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 OSTI2026

Human Factors and Technologies Design to Improve User Acceptance of Pooled Rideshare for Increasing Transportation System Energy Efficiency

This multi-year project delivered a comprehensive, human-factors-driven framework to understand, model, and improve pooled rideshare (PR) adoption in the United States. Through three large-scale national survey studies involving more than 16,000 participants across multiple cities and demographic groups, the research established one of the most extensive datasets to date on user perceptions, behavioral barriers, and service expectations related to pooled rideshare. These data revealed key human factors barriers of user acceptance of PR and suggested potential actionable experience optimizations that could lead to increased PR usage. This foundational knowledge guided the development of novel human-factors models and behavioral choice models that quantify how psychological, demographic, and trip-level factors influence willingness to pool. Building on these empirical insights, the project developed advanced behavioral modeling tools, including mixed logit and integrated choice and latent variable models, to capture both observable and latent influences on PR adoption. These models significantly improved the ability to predict riders’ acceptance of pooled trips, explaining choice heterogeneity through latent constructs such as safety, service experience, privacy concerns, time sensitivity, and environmental attitudes. Together, these models provide a robust analytical foundation for designing PR systems that more effectively meet user needs. The project translated human-factors insights and behavioral models into actionable technology innovations by extending POLARIS—an agent-based, activity-based travel simulation platform—into a fully functional pooled rideshare simulation environment. New PR modules, acceptance models, and regional scenarios were implemented for Greenville, SC and Austin, TX, enabling high-fidelity validation of algorithmic strategies under realistic demand and traffic conditions. The simulation platform supported the development and evaluation of adaptive discount-based assignment algorithms, enhanced willingness-to-pay formulations, demographic-aware incentive mechanisms, and a proactive joint assignment and repositioning strategy. Simulation results demonstrated substantial gains in pooling uptake, average vehicle occupancy, energy efficiency, and fleet profitability. In Greenville, pooling adoption more than doubled, while reductions in vehicle-miles traveled and energy consumption were significant. In Austin, pooling improvements were achieved with minimal service-quality trade-offs, and profitability increased across all fleet sizes. Through this research, we developed a comprehensive understanding of the human factors barriers that limit user acceptance of pooled rideshare services. These insights enabled the design of human-factors-aware pooled rideshare technologies that more effectively address user concerns and improve adoption rates. By integrating these models into an advanced agent-based simulation framework, we demonstrated that higher adoption of pooled rideshare can lead to measurable improvements in energy efficiency and system performance. Together, these contributions establish a validated pathway from human-centered analysis to technology development and energy-saving outcomes, supporting national goals for more sustainable and efficient mobility systems.

Jia, Yunyi↗
DOE OSTI2026

Final technical report for DE-SC0022255: Discovering Physically Meaningful Structures from Climate Extreme Data

The past two decades have witnessed natural disasters and extreme weather events that affect millions of people. At the same time, the data volume from high-resolution climate models, satellite, in-situ and ground-based measurements have substantially increased to petabyte scales. These new and readily accessible datasets create the previously missing pipeline required for scientific machine learning (ML) and therefore new opportunities for improved understanding and prediction capability of climate extreme events. This project developed a deep latent variable model framework to discover physically meaningful hidden structures from high-dimensional, spatiotemporal climate extreme data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

An explainable variational autoencoder model for three-dimensional acoustic emission source localization in hollow cylindrical structures

We introduce an explainable variational autoencoder for three-dimensional (3D) localization of acoustic emission sources in hollow cylindrical structures, with an unsupervised approach. This research capitalizes on multi-arrival waveforms generated by helical path propagation in cylindrical geometries to enable efficient two-receiver localization. By integrating the modal characteristics of Lamb modes under multi-path conditions, we demonstrate that two sets of time-of-arrival differences and peak amplitudes extracted from one receiver can serve as effective localization features. This initial approach identifies four potential source locations, highlighting the feasibility of two-receiver source localization using traditional feature extraction methods. However, direct extraction can be challenging when mode overlaps occur, complicating the localization process. To address this, our work proposes a novel waveform-based method. This method leverages the consistent dispersion characteristics within isotropic materials, where each unique combination of mode arrival times and peak amplitudes constructs a distinct waveform. This distinctiveness overcomes the ambiguities associated with mode overlaps, significantly enhancing the method’s precision and robustness. Our approach adopts a data-driven strategy for waveform-based localization using variational autoencoder (VAE). VAE discerns waveform patterns for localization, while also addressing data uncertainties. The VAE’s encoder and decoder networks capture the localization process and the source’s influence on waveform generation, respectively, guiding latent variables to segregate waveforms by source in the latent space. The design of the learning process focuses on specific localization characteristics to enhance result explainability. Localization predictions are generated by projecting test waveforms, not included in the training set, onto a trained latent space. The prediction is determined using a nearest-neighbor approach based on the closest latent representation of a source. Validation with pencil-lead-break tests on a metallic pipe confirmed our method’s effectiveness, achieving an averaged 3D localization accuracy of 0.84.

Lee, Guan-Wei↗
DOE OSTI2024

ML-based Dimension Reduction Strategies

Deep learning (DL)--based surrogate models have achieved success in various applications in carbon capture and storage (CCS). However, the model training on high-dimensional spaces is computationally expensive and impractical for large-scale and complex geological models, because the models usually contain hundreds of thousands to millions of grid cells, each with a set of parameters. Furthermore, the high cost of generating training data with sufficient variation is another limitation of model training on high-dimensional spaces, which may result in overfitting and reduce the model efficiency and prediction performance. We proposed the workflow incorporating dimension reduction methods and deep learning models, which aim to extract the latent variables of input parameters and output state variables, and then build the mapping function at the latent spaces. The proposed workflow can significantly reduce the computational complexity in solving both forward and inverse problems compared to models trained on high-dimensional spaces. Dimensionality reduction models showed great potential in workflows for fast reservoir simulation, history matching, prior model generation, visualization, and more, ultimately enhancing DL model performance in related SMART Work Packages.

Hosseini, Seyyed↗
DOE OSTI2024

Physical discovery in representation learning via conditioning on prior knowledge

Recent advances in electron, scanning probe, optical, and chemical imaging and spectroscopy yield bespoke data sets containing the information of structure and functionality of complex systems. In many cases, the resulting data sets are underpinned by low-dimensional simple representations encoding the factors of variability within the data. The representation learning methods seek to discover these factors of variability, ideally further connecting them with relevant physical mechanisms. However, generally, the task of identifying the latent variables corresponding to actual physical mechanisms is extremely complex. Here, we present an empirical study of an approach based on conditioning the data on the known (continuous) physical parameters and systematically compare it with the previously introduced approach based on the invariant variational autoencoders. The conditional variational autoencoder (cVAE) approach does not rely on the existence of the invariant transforms and hence allows for much greater flexibility and applicability. Interestingly, cVAE allows for limited extrapolation outside of the original domain of the conditional variable. However, this extrapolation is limited compared to the cases when true physical mechanisms are known, and the physical factor of variability can be disentangled in full. We further show that introducing the known conditioning results in the simplification of the latent distribution if the conditioning vector is correlated with the factor of variability in the data, thus allowing us to separate relevant physical factors. We initially demonstrate this approach using 1D and 2D examples on a synthetic data set and then extend it to the analysis of experimental data on ferroelectric domain dynamics visualized via piezoresponse force microscopy.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

tLaSDI: Thermodynamics-informed latent space dynamics identification

Here we propose a latent space dynamics identification method, namely tLaSDI, that embeds the first and second principles of thermodynamics. The latent variables are learned through an autoencoder as a nonlinear dimension reduction model. The latent dynamics are constructed by a neural network-based model that precisely preserves certain structures for the thermodynamic laws through the GENERIC formalism. An abstract error estimate is established, which provides a new loss formulation involving the Jacobian computation of autoencoder. The autoencoder and the latent dynamics are simultaneously trained to minimize the new loss. Computational examples demonstrate the effectiveness of tLaSDI, which exhibits robust generalization ability, even in extrapolation. In addition, an intriguing correlation is empirically observed between a quantity from tLaSDI in the latent space and the behaviors of the full-state solution.

97 MATHEMATICS AND COMPUTING↗