Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “predictive mapping”

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 757 records · Page 42
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Kinetic Deep Learning v0.1

Here, we present a method that uses protein levels to predict times series of metabolite concentrations. Understanding this type of pathway dynamics is important in order to predict the behavior of the pathway and, more pragmatically, to be able to design biological systems (such as strains bioengineered to produce chemical products) reliably. Typically, for this purpose, kinetic models consisting of differential equations based on the Michaelis-Menten dynamics have been used in the past. However, these methods can rarely produce good fits to measured data time series. Possibly, this happens because the kinetic constants are unknown or are different from the ones measured in vivo, or perhaps because Michaelis-Menten dynamics is not a satisfactory description. In order to improve the predictive nature of these kinetic models we have eliminated the Michaelis-Menten description of pathway dynamics and we have substituted it by algorithms that automatically learn these dynamics from previously obtained metabolomics and proteomics data using machine learning approaches. Specifically, kinetic deep learning uses deep learning to map proteomics time series to metabolite concentration time series, instead of learning the first metabolite derivative and integrating in (as in the first version of kinetic learning). This approach is shown to provide good to excellent results with a data set specifically collected for this purpose.

Garcia Martin, Hector [Joint BioEnergy Institute (↗
DOE OSTI2023

A Physics-Based Data-Driven Approach for Modeling of Environmental Degradation in Elastomers

Abstract Elastomers are now commonly used in a number of industries, including aerospace, structure, transportation, shipbuilding, and automotive, due to their excellent workability, formability, and flexibility. During their activity, elastomers are subjected to harsh environmental conditions, which decreases their resilience. False predictions made early in their lives can have major financial and environmental implications. Elastomers’ performance and properties, such as strength, durability, and density, are influenced by chemical changes in these materials, known as degradation, which occurs over time. This process can alter the morphology of a polymer matrix as well as cause chain scission and cross-linking, resulting in different behaviors than that of the unaged material. To demonstrate the effect of thermaloxidative aging on the mechanical behavior of elastomers, several experimental and theoretical models have been proposed. In view of the large volume of experimental data available on micro-structural evolution in the course of aging, we propose a physics-based data-driven approach to overcome the shortcomings of both phenomenological and micro-mechanical models. This work presents a novel thermodynamically consistent, multiagent machine-learned model for predicting the constitutive behavior of cross-linked elastomers during environmental aging, such as thermo-oxidative and hydrolytic aging for various states of deformation. Single mechanism degradation changes the polymer matrix over time where it is causing chain scission, reduction of cross-links, and morphology change. To capture the idealized Mullins effect and permanent set due to the effect of single aging mechanisms on nonlinear mechanical responses of elastomers, we propose a data-driven model for simulating inelastic elements in a polymer matrix. By using a sequential order reduction, we were able to reduce the 3D stress-strain tensor mapping problem to a small number of super-constrained 1D mapping problems. To systematically classify such mapping problems into a few categories, an assembly of multiple replicated conditional neural network learning agents (L-agents) is used based on our recent work. Each category is represented by a different type of agent. The effect of deformation history, aging time, and aging temperature is captured by this model. The model is validated using a broad collection of data, ranging from our experimental results to data from the literature. In addition, thermodynamic consistency and frame independence are investigated. The most significant achievements of this model are its precision, simplicity, and prediction of inelasticity under various states of deformation. The model’s accuracy and simplicity make it a good option for commercial and industrial applications. Conveniently, due to the model modular nature, it can be expanded in the future to include viscoelasticity and non-isotropic formation for better precision.

Ghaderi, Aref↗
DOE OSTI2020

Bayesian Poroelastic Aquifer Characterization From InSAR Surface Deformation Data. Part I: Maximum A Posteriori Estimate

Characterizing the properties of groundwater aquifers is essential for predicting aquifer response and managing groundwater resources. In this work, we develop a high-dimensional scalable Bayesian inversion framework governed by a three-dimensional quasi-static linear poroelastic model to characterize lateral permeability variations in groundwater aquifers. In this work, we determine the maximum a posteriori (MAP) point of the posterior permeability distribution from centimeter-level surface deformation measurements obtained from Interferometric Synthetic Aperture Radar (InSAR). The scalability of our method to high parameter dimension is achieved through the use of adjoint-based derivatives, inexact Newton methods to determine the MAP point, and a Mat´ern class sparse prior precision operator. Together, these guarantee that the MAP point is found at a cost, measured in number of forward/adjoint poroelasticity solves, that is independent of the parameter dimension. We apply our methodology to a test case for a municipal well in Mesquite, Nevada, in which InSAR and GPS surface deformation data are available. We solve problems with up to 320,824 state variable degrees of freedom (DOFs) and 16,896 parameter DOFs. A consistent treatment of noise level is employed so that the aquifer characterization result does not depend on the pixel spacing of surface deformation data. Our results show that the use of InSAR data significantly improves characterization of lateral aquifer heterogeneity, and the InSAR-based aquifer characterization recovers complex lateral displacement trends observed by independent daily GPS measurements.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Stability of heterogeneous single-atom catalysts: a scaling law mapping thermodynamics to kinetics

Heterogeneous single-atom catalysts (SACs) hold the promise of combining high catalytic performance with maximum utilization of often precious metals. We extend the current thermodynamic view of SAC stability in terms of the binding energy (E bind ) of single-metal atoms on a support to a kinetic (transport) one by considering the activation barrier for metal atom diffusion. A rapid computational screening approach allows predicting diffusion barriers for metal–support pairs based on E bind of a metal atom to the support and the cohesive energy of the bulk metal (E c ). Metal–support combinations relevant to contemporary catalysis are explored by density functional theory. Assisted by machine-learning methods, we find that the diffusion activation barrier correlates with (E bind ) 2 /E c in the physical descriptor space. This diffusion scaling-law provides a simple model for screening thermodynamics to kinetics of metal adatom on a support.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Mapping charge excitations in generalized Wigner crystals

Transition metal dichalcogenide-based moiré superlattices exhibit strong electron-electron correlations, thus giving rise to strongly correlated quantum phenomena such as generalized Wigner crystal states. Evidence of Wigner crystals in transition metal dichalcogenide moire superlattices has been widely reported from various optical spectroscopy and electrical conductivity measurements, while their microscopic nature has been limited to the basic lattice structure. Theoretical studies predict that unusual quasiparticle excitations across the correlated gap between upper and lower Hubbard bands can arise due to long-range Coulomb interactions in generalized Wigner crystal states. However, the microscopic proof of such quasiparticle excitations is challenging because of the low excitation energy of the Wigner crystal. Here, in this study, we describe a scanning single-electron charging spectroscopy technique with nanometre spatial resolution and single-electron charge resolution that enables us to directly image electron and hole wavefunctions and to determine the thermodynamic gap of generalized Wigner crystal states in twisted WS 2 moiré heterostructures. High-resolution scanning single-electron charging spectroscopy combines scanning tunnelling microscopy with a monolayer graphene sensing layer, thus enabling the generation of individual electron and hole quasiparticles in generalized Wigner crystals. We show that electron and hole quasiparticles have complementary wavefunction distributions and that thermodynamic gaps of ~50 meV exist for the 1/3 and 2/3 generalized Wigner crystal states in twisted WS 2 .

36 MATERIALS SCIENCE↗
DOE OSTI2024

Dual blockade of IL-10 and PD-1 leads to control of SIV viral rebound following analytical treatment interruption

Human immunodeficiency virus (HIV) persistence during antiretroviral therapy (ART) is associated with heightened plasma interleukin-10 (IL-10) levels and PD-1 expression. We hypothesized that IL-10 and PD-1 blockade would lead to control of viral rebound following analytical treatment interruption (ATI). Twenty-eight ART-treated, simian immunodeficiency virus (SIV)mac 239 -infected rhesus macaques (RMs) were treated with anti-IL-10, anti-IL-10 plus anti-PD-1 (combo) or vehicle. ART was interrupted 12 weeks after introduction of immunotherapy. Durable control of viral rebound was observed in nine out of ten combo-treated RMs for >24 weeks post-ATI. Induction of inflammatory cytokines, proliferation of effector CD8 + T cells in lymph nodes and reduced expression of BCL-2 in CD4 + T cells pre-ATI predicted control of viral rebound. Twenty-four weeks post-ATI, lower viral load was associated with higher frequencies of memory T cells expressing TCF-1 and of SIV-specific CD4 + and CD8 + T cells in blood and lymph nodes of combo-treated RMs. These results map a path to achieve long-lasting control of HIV and/or SIV following discontinuation of ART.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Predicting the chemical reactivity of organic materials using a machine-learning approach

Stability and compatibility between chemical components are essential parameters that need to be considered in the selection of functional materials in configuring a system. In configuring devices such as batteries or solar cells, not only the functionality of individual constituting materials such as electrodes or electrolyte but also an appropriate combination of materials which do not undergo unwanted side reactions is critical in ensuring their reliable performance in long-term operation. While the universal theory that can predict the general chemical reactivity between materials is long awaited and has been the subject of studies with a rich history, traditional ways proposed to date have been mostly based on simple electronic properties of materials such as electronegativity, ionization energy, electron affinity and hardness/softness, and could be applied to only a small group of materials. Moreover, prediction has often been far from accurate and has failed to offer general implications; thus it was practically inadequate as a selection criterion from a large material database, i.e. data-driven material discovery. Herein, we propose a new model for predicting the general reactivity and chemical compatibility among a large number of organic materials, realized by a machine-learning approach. As a showcase, we demonstrate that our new implemented model successfully reproduces previous experimental results reported on side-reactions occurring in lithium–oxygen electrochemical cells. Furthermore, the mapping of chemical stability among more than 90 available electrolyte solvents and the representative redox mediators is realized by this approach, presenting an important guideline in the development of stable electrolyte/redox mediator couples for lithium–oxygen batteries.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Development and Use of an Ultra-High Resolution Electron Scattering Apparatus

In this LDRD project, we developed a versatile capability for high-resolution measurements of electron scattering processes in gas-phase molecules, such as ionization, dissociation, and electron attachment/detachment. This apparatus is designed to advance fundamental understanding of these processes and to inform predictions of plasmas associated with applications such as plasma-assisted combustion, neutron generation, re-entry vehicles, and arcing that are critical to national security. We use innovative coupling of electron-generation and electron-imaging techniques that leverages Sandia’s expertise in ion/electron imaging methods. Velocity map imaging provides a measure of the kinetic energies of electrons or ion products from electron scattering in an atomic or molecular beam. We designed, constructed, and tested the apparatus. Tests include dissociative electron attachment to O2 and SO2, as well as a new method for studying laser-initiated plasmas. This capability sets the stage for new studies in dynamics of electron scattering processes, including scattering from excited-state atoms and molecules.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Forecasting [C II ] Line-intensity Mapping Measurements between the End of Reionization and the Epoch of Galaxy Assembly

We combine recent simulation work on the SFR–[C II ] correlation at high redshift with empirical modeling of the galaxy–halo connection (via UniverseMachine) to forecast [C ii] auto power spectra from z ~ 4 to z ~ 8. We compare these to sensitivities realistically expected from various instruments expected to come online in the next decade. If the predictions of our model are correct, [C II ] should be detectable up to z ~ 6 in this generation of surveys, but detecting [C II ] past the end of reionization will require a generational leap in line-intensity survey capabilities.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Nondestructive Evaluation of Concrete: Elastic Property Imaging Through Full Waveform Inversion

Concrete is a major construction material worldwide and plays a crucial role in the nuclear industry. The elastic properties of concrete are prone to change and degrade while in service, as it is often subjected to extreme operational and environmental conditions. An accurate evaluation of concrete's elastic properties is thus essential to ensure structural integrity and safety. This is especially true for concrete in nuclear power plants, where irradiation effects significantly impact concrete mechanical properties. There are various methods to assess these properties, with ultrasound-based techniques showing high potential due to their nondestructive nature, cost-effectiveness, and safety. While several nondestructive evaluation methods exist, most rely on idealizations such as assuming homogeneous material and plane wavefronts. In this work, we address these issues by introducing an ultrasound-based nondestructive method aimed at reconstructing spatially varying images of concrete mechanical properties. By accurately modeling wave physics, including scattering and reflection, we overcome several of the aforementioned idealizations and aim to utilize the full waveform for imaging material properties through depth, resulting in more reliable images. Full waveform inversion (FWI) was first introduced by geophysicists to reconstruct subsurface elastic property images. The goal is to minimize the difference between simulated and recorded wavefield signals, often through gradient-based optimization algorithms. While FWI is primarily conducted using the acoustic approximation of the wave equation, few works focus on elastic FWI, where the goal is to reconstruct images of not only the pressure wave speed but also the shear wave speed and density (or their equivalents). This work explores the potential of using elastic FWI to predict concrete mechanical properties as an initial effort for a more accurate monitoring of concrete conditions in service. Reconstructing images of different elastic parameters enables more specificity and accurate condition diagnosis. This paper will detail this approach and provide examples demonstrating the effectiveness of elastic FWI in reconstructing comprehensive maps of concrete mechanical properties.

42 - ENGINEERING↗
DOE OSTI2021

Revealing causes of macroscale heterogeneity in lithium ion pouch cells via synchrotron X-ray diffraction

Heterogeneous battery performance is a critical issue for maximization of cell lifetime capacity and safety. Using high energy synchrotron X-ray diffraction, the influence of charge rate, voltage limit, uneven stack pressure, and gas generation on the lithium transport properties was quantified in single-layer graphite/LiNi 0.5 Mn 0.3 Co 0.2 O 2 pouch cells. A freshly formatted cell tracked in operando during initial fast charge cycles indicated variable position-dependent performances, while lateral mapping showed a significant fast charge (6C) heterogeneity compared to slow charge (C/2). Pressure effects were non-dominant compared to charge rate. Maps of previously aged and rested cells indicate that lateral heterogeneity slowly equilibrates at rest, but regenerates upon further cycling at fast charge rate. Furthermore, an unformatted cell was mapped at charge and discharge during its first formation cycle to analyze the effect of byproduct gases on the heterogeneous lithium transport. Gas was observed as randomly interspersed “bubbles” which locally hindered lithium intercalation and caused significant heterogeneity. Electrode architectures and charging protocols that promote homogeneous intercalation are critical for predictable high-performance and long-life batteries.

25 ENERGY STORAGE↗
DOE OSTI2025

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have been developed to understand the mechanisms leading to complex morphologies. However, the LMD governing equations in these models often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, numerical stiffness in the PDEs requires an extremely refined time step size (on the order of 10 -12 s or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose a U-shaped adaptive Fourier neural operator (U-AFNO), a machine learning (ML) based model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics of mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g., the deformation of the liquid-metal interface, lost metal, etc.) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in spite of the chaotic nature of LMD. Most notably, our model reproduces the key microstructure statistics and QoIs with a level of accuracy on par with the high-fidelity numerical solver, while achieving a significant 11, 200 × speed-up on a high-resolution grid when comparing the computational expense per time step. Finally, we also investigate the opportunity of using hybrid simulations, in which we alternate forward leaps in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Spatial top-down proteomics for the functional characterization of human kidney

Background: The Human Proteome Project has credibly detected nearly 93% of the roughly 20,000 proteins which are predicted by the human genome. However, the proteome is enigmatic, where alterations in amino acid sequences from polymorphisms and alternative splicing, errors in translation, and post-translational modifications result in a proteome depth estimated at several million unique proteoforms. Recently mass spectrometry has been demonstrated in several landmark efforts mapping the human proteoform landscape in bulk analyses. Herein, we developed an integrated workflow for characterizing proteoforms from human tissue in a spatially resolved manner by coupling laser capture microdissection, nanoliter-scale sample preparation, and mass spectrometry imaging. Results: Using healthy human kidney sections as the case study, we focused our analyses on the major functional tissue units including glomeruli, tubules, and medullary rays. After laser capture microdissection, these isolated functional tissue units were processed with microPOTS (microdroplet processing in one-pot for trace samples) for sensitive top-down proteomics measurement. This provided a quantitative database of 616 proteoforms that was further leveraged as a library for mass spectrometry imaging with near-cellular spatial resolution over the entire section. Notably, several mitochondrial proteoforms were found to be differentially abundant between glomeruli and convoluted tubules, and further spatial contextualization was provided by mass spectrometry imaging confirming unique differences identified by microPOTS, and further expanding the field-of-view for unique distributions such as enhanced abundance of a truncated form (1-74) of ubiquitin within cortical regions. Conclusions: We developed an integrated workflow to directly identify proteoforms and reveal their spatial distributions. Where of the 20 differentially abundant proteoforms identified as discriminate between tubules and glomeruli by microPOTS, the vast majority of tubular proteoforms were of mitochondrial origin (8 of 10) where discriminate proteoforms in glomeruli were primarily hemoglobin subunits (9 of 10). These trends were also identified within ion images demonstrating spatially resolved characterization of proteoforms that has the potential to reshape discovery-based proteomics because the proteoforms are the ultimate effector of cellular functions. Applications of this technology have the potential to unravel etiology and pathophysiology of disease states, informing on biologically active proteoforms, which remodel the proteomic landscape in chronic and acute disorders.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Insights into cosmological structure formation with machine learning.

Our modern understanding of cosmological structure formation posits that small matter density fluctuations present in the early Universe, as traced by the cosmic microwave background, grow via gravitational instability to form extended haloes of dark matter. A theoretical understanding of the structure, evolution and formation of dark matter haloes is an essential step towards unravelling the intricate connection between halo and galaxy formation, needed to test our cosmological model against data from upcoming galaxy surveys. Physical understanding of the process of dark matter halo formation is made difficult by the highly non-linear nature of the haloes' evolution. I describe a new approach to gain physical insight into cosmological structure formation based on machine learning. This approach combines the ability of machine learning algorithms to learn non-linear relationships, with techniques that enable us to physically interpret the learnt mapping. I describe applicatio ns of th e method, with the aim of investigating which aspects of the early universe density field impact the later formation of dark matter haloes. First I present a case where the process of halo formation is turned into a binary classification problem; the algorithm predicts whether or not dark matter `particles' in the initial conditions of a simulation will collapse into haloes of a given mass range. Second, I present its generalization to regression, where the algorithm infers the final mass of the halo to which each particle will later belong. I show that the initial tidal shear does not play a significant role compared to the initial density field in establishing final halo masses. Finally, I demonstrate that extending the framework to deep learning algorithms such as convolutional neural networks allows us to explore connections between the early universe and late time haloes beyond those studied by existing analytic approximations of halo collapse.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Skeletal Kinetics Reduction for Astrophysical Reaction Networks

A novel methodology is developed to extract accurate skeletal reaction models for nuclear combustion. Local sensitivities of isotope mass fractions with respect to reaction rates are modeled based on the forced optimally time-dependent (f-OTD) scheme. These sensitivities are then analyzed temporally to generate skeletal models. The methodology is demonstrated by conducting skeletal reduction of constant density and temperature burning of carbon and oxygen relevant to Type Ia supernovae (SNe Ia). The 495-isotopes Torch model is chosen as the detailed reaction network. A map of maximum production of 56 Ni in SNe Ia is produced for different temperatures, densities, and proton-to-neutron ratios. The f-OTD simulations and the sensitivity analyses are then performed with initial conditions from this map. A series of skeletal models are derived and their performances are assessed by comparison against currently existing skeletal models. Previous models have been constructed intuitively by assuming the dominance of α-chain reactions. The comparison of the newly generated skeletal models against previous models is based on the predicted energy release and 44 Ti and 56 Ni abundances by each model. The consequences of ye ≠ 0.5 in the initial composition are also explored where ye is the electron fraction. The simulated results show that 56 Ni production decreases by decreasing ye as expected, and that the 43 Sc is a key isotope in proton and neutron channels toward 56 Ni production. It is shown that an f-OTD skeletal model with 150 isotopes can accurately predict the 56Ni abundance in SNe Ia for ye ≲ 0.5 initial conditions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Raptor

Raptor is an efficient Python-based tool for predicting the formation and morphology of stochastic lack of fusion defects in metal AM processes. A major obstacle for the qualification and certification of additively manufactured parts in critical applications continues to be performance variability caused in part by porosity-related defects. High-fidelity process models that could predict these defect features are currently too computationally expensive for component-level analysis. To address this, Raptor employs a high-performance geometric method to model the dynamic melt pool rather than relying on computationally intensive thermal fluid dynamics. This allows Raptor to rapidly identify regions of unmelted material that correspond to lack of fusion pores. The efficiency of this approach significantly reduces the time and resources needed for generating 3D defect predictions, which enables users to conduct large-scale parameter studies and evaluate how process variations affect part quality. The framework offers operational flexibility; users can execute simulations through a simple command line interface or integrate core functions as a library within larger computational workflows. Simulation outputs include 3D porosity maps for visualization and tools for quantitative morphological analysis. These results are suitable for direct comparison with experimental characterization data from methods such as X-ray computed tomography and can be used for statistical process optimization.

Subraveti, Vamsi [Vanderbilt Univ., Nashville, TN ↗
DOE OSTI2021

Field validation of an actuated convergent-beam acoustic Doppler profiler for high resolution flow mapping

Abstract Energetic river and tidal flow environments feature complex hydrodynamic conditions. Conventional acoustic Doppler profiling instrumentation typically requires assumptions of flow homogeneity over the spatial scales of the divergent beam separation. This removes the ability to measure spatio-temporal variability within the flow. However, velocity variability within these spatial scales is often important in the design of structures and devices exposed to such flow, informing dynamic and peak hydrodynamic load predictions. The research presented outlines the development and testing of a flow measurement instrument consisting of multiple spatially-separated single beam acoustic Doppler profilers converging on a remote focal point, the location of which can be programmatically adjusted through actuation. This increases the spatial resolution at which remote field measurements can be made in energetic flow environments. Field testing of the instrument was conducted in a tidal channel at Sequim Bay Inlet, WA, USA. Results are compared with independent reference measurements made by a co-located, motion-corrected acoustic Doppler velocimeter. This comparison, across tidal velocities of 0.4–0.7 m s −1 , showed a mean velocity error of 0.5%–13.2% across nine sample locations within a 3.00 m × 2.25 m plane. To the authors’ knowledge, this is the first publication of flow velocity results from non-intrusive acoustic measurements at an off-axis, focal point location that features 3D positional control.

13 HYDRO ENERGY↗
DOE OSTI2022

GenMod: A generative modeling approach for spectral representation of PDEs with random inputs

Here, we propose a method for quantifying uncertainty in high-dimensional PDE systems with random parameters, where the number of solution evaluations is small. Parametric PDE solutions are often approximated using a spectral decomposition based on polynomial chaos expansions. For the class of systems we consider (i.e., high dimensional with limited solution evaluations) the coefficients are given by an underdetermined linear system in a regression formulation. This implies additional assumptions, such as sparsity of the coefficient vector, are needed to approximate the solution. Here, we present an approach where we assume the coefficients are close to the range of a generative model that maps from a low to a high dimensional space of coefficients. Our approach is inspired be recent work examining how generative models can be used for compressed sensing in systems with random Gaussian measurement matrices. Using results from PDE theory on coefficient decay rates, we construct an explicit generative model that predicts the polynomial chaos coefficient magnitudes. The algorithm we developed to find the coefficients, which we call GenMod, is composed of two main steps. First, we predict the coefficient signs using Orthogonal Matching Pursuit. Then, we assume the coefficients are within a sparse deviation from the range of a sign-adjusted generative model. This allows us to find the coefficients by solving a nonconvex optimization problem, over the input space of the generative model and the space of sparse vectors. We obtain theoretical recovery results for a Lipschitz continuous generative model and for a more specific generative model, based on coefficient decay rate bounds. We examine three high-dimensional problems and show that, for all three examples, the generative model approach outperforms sparsity promoting methods at small sample sizes.

97 MATHEMATICS AND COMPUTING↗