Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep generative 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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Aspen Open Jets: unlocking LHC data for foundation models in particle physics

Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrates how data collected by the CMS experiment at the Large Hadron Collider can be useful in pre-training foundation models for HEP. Specifically, we introduce the AspenOpenJets (AOJs) dataset, consisting of approximately 178 M high p T jets derived from CMS 2016 Open Data. We show how pre-training the OmniJet-α foundation model on AOJs improves performance on generative tasks with significant domain shift: generating boosted top and QCD jets from the simulated JetClass dataset. In addition to demonstrating the power of pre-training of a jet-based foundation model on actual proton–proton collision data, we provide the ML-ready derived AOJs dataset for further public use.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

A deep learning and finite element approach for exploration of inverse structure–property designs of lightweight hybrid composites

Hybrid composites have important applications, such as high-performance and lightweight materials in aerospace and automotive industries. Hybrid composites utilize the synergy of diverse fillers to achieve desired material properties, but usually have more complicated microstructures. While topology optimization can optimize a particular property, designing hybrid composites for customized mechanical performances, e.g. full-range stress–strain curve, remains challenging. Here, a computational framework that integrated finite element analysis (FEA) and artificial intelligence (AI) methods of Conditional Generative Adversarial Networks (cGAN) deep learning and transfer learning was developed to establish inverse structure–property relationships and design tailor-made hybrid composites. Based on FEA-generated datasets of hybrid fiber-particle–matrix microstructures and their corresponding full-range stress–strain curves, a cGAN architecture was trained to generate tailored microstructures and establish structure–property relationships. Similarity in microstructural features and well-matched stress–strain curves based on the AI-generated composites were achieved. In conclusion, transfer learning was used to expand the pre-trained model for designing different materials systems.

Hybrid composites↗
DOE OSTI2025

High precision monitoring of outgassing species in model EUV photoresists with a cavity ring-down spectrometer

Extreme ultraviolet (EUV) photoresists play a pivotal role in advancing nanopatterning technologies by balancing image quality and sensitivity. The outgassing behavior of photoresist thin films under EUV and deep ultraviolet (DUV) exposure reveals chemical details relevant to their performance. This study focuses on utilizing an analytical technique not previously used in photolithography, the tabletop cavity ring-down spectrometer, to investigate outgassing dynamics in EUV photoresists, enabling precise chemical identification and deeper insights into resist processing. The spectrometer’s enhanced laser path length (~20 km) and broadband absorption capabilities in the CH overtone region allow for sensitive and temporally resolved detection of outgassed species. Using a model resist comprising a polymer matrix with a photoacid generator and quencher, we analyzed the influence of time delays between exposure and Post-Exposure Bake (PEB) as well as storage under varying environmental conditions. Suppression of isobutylene outgassing and thickness loss was observed with extended delays between exposure and PEB, potentially linked to water absorption and acid deactivation. The technique proved highly effective in distinguishing subtle chemical differences between processing stages. Delay times and their environmental conditions, particularly humidity, reduce outgassing and thickness loss of photoresists during PEB, suggesting decreased acid-driven deprotection. This can potentially impact sensitivity, defectivity, and roughness of resist patterns, necessitating precise monitoring and control.

Lüttgenau, Bernhard↗
DOE OSTI2024

Deep Image Prior Enabled Full Waveform Inversion (Final Technical Report)

MS Student Naveen Gupta worked on the problem of full waveform inversion (FWI) using neural networks as shown in Figure 1. Our goal was to learn a neural network to represent the subsurface velocity model, which when fed into the FWI module (implemented using a numerical forward model of wave equations) produces amplitude estimates that match with ground-truth observations of amplitude. We used neural networks to solve the inverse problem of estimating velocity distributions for a given seismic amplitude data such that, once trained, our neural network model can generate a distribution of velocity profiles for different random vectors fed as inputs to the neural network model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

The role of the droplet interface in controlling the multiphase oxidation of thiosulfate by ozone

Predicting reaction kinetics in aqueous microdroplets, including aerosols and cloud droplets, is challenging due to the probability that the underlying reaction mechanism can occur both at the surface and in the interior of the droplet. Additionally, few studies directly measure the surface activities of doubly charged anions, despite their prevalence in the atmosphere. Here, deep-UV second harmonic generation spectroscopy is used to probe surface affinities of the doubly charged anions thiosulfate, sulfate, and sulfite, key species in the thiosulfate ozonation reaction mechanism. Thiosulfate has an appreciable surface affinity with a measured Gibbs free energy of adsorption of -7.3 ± 2.5 kJ mol -1 in neutral solution, while sulfate and sulfite exhibit negligible surface propensity. The Gibbs free energy is combined with data from liquid flat jet ambient pressure X-ray photoelectron spectroscopy to constrain the concentration of thiosulfate at the surface in our model. Stochastic kinetic simulations leveraging these novel measurements show that the primary reaction between thiosulfate and ozone occurs at the interface and in the bulk, with the contribution of the interface decreasing from ~65% at pH 5 to ~45% at pH 13. Additionally, sulfate, the major product of thiosulfate ozonation and an important species in atmospheric processes, can be produced by two different pathways at pH 5, one with a contribution from the interface of >70% and the other occurring predominantly in the bulk (>98%). The observations in this work have implications for mining wastewater remediation, atmospheric chemistry, and understanding other complex reaction mechanisms in multiphase environments. Future interfacial or microdroplet/aerosol chemistry studies should carefully consider the role of both surface and bulk chemistry.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Micropolar deep material network

This study extends the Deep Material Network (DMN), a physics-informed machine learning framework, to predict the homogenized mechanical response of composite materials with micropolar (Cosserat-type) constitutive behavior. This extension incorporates microstructure-dependent size effects, enabling accurate, efficient, and size-aware predictions for composites with complex internal architectures. While traditional, direct numerical simulation micropolar models effectively capture size effects by introducing extra local degrees of freedom, they bring significant computational challenges, particularly for multiscale analyses relevant to engineering applications. The micropolar DMN developed in this paper achieves high accuracy while significantly reducing computation time compared to micropolar direct numerical simulations. This advancement enables multiscale analyses and parameter studies that were previously impractical, such as high-cycle fatigue simulations and comprehensive investigations of internal length scale effects notably in size-dependent plastic response and the optimization of lattice structures. By uniting microstructure-sensitive modeling, physics-driven learning, and scalable surrogate modeling, the micropolar DMN paves the way for accelerated material design, large-scale parametric studies, and the reliable incorporation of size-dependent effects across a wide range of engineering applications, including optimization and next-generation composite design.

36 MATERIALS SCIENCE↗
DOE OSTI2025

High-precision monitoring of outgassing species in model extreme ultraviolet photoresists with a cavity ring-down spectrometer

Background Extreme ultraviolet (EUV) photoresists play a pivotal role in advancing nanopatterning technologies by balancing image quality and sensitivity. The outgassing behavior of photoresist thin films under EUV and deep ultraviolet (DUV) exposure reveals chemical details relevant to their performance. Aim Here, we focus on utilizing an analytical technique not previously used in photolithography, the tabletop cavity ring-down spectrometer, to investigate outgassing dynamics in EUV photoresists, enabling precise chemical identification and deeper insights into resist processing. Approach The spectrometer’s enhanced laser path length (∼ 20 km) and broadband absorption capabilities in the C–H overtone region allow for sensitive and temporally resolved detection of mixtures of outgassed species. Using a model resist comprising a polymer matrix with a photoacid generator and quencher, we analyzed the influence of time delays between exposure and post-exposure bake (PEB) as well as storage under varying environmental conditions. Results Suppression of isobutylene outgassing and thickness loss was observed with extended delays between exposure and PEB, potentially linked to water absorption and acid deactivation. The technique proved highly effective in distinguishing subtle chemical differences between processing stages. Conclusions Delay times and their environmental conditions, particularly humidity, reduce outgassing and thickness loss of photoresists during PEB, suggesting decreased acid-driven deprotection. This can potentially impact sensitivity, defectivity, and roughness of resist patterns, necessitating precise monitoring and control.

Extreme ultraviolet photoresists↗
DOE OSTI2024

3D-Reconstruction of Tau Neutrinos in LArTPC Detectors

The Deep Underground Neutrino Experiment (DUNE) is a next-generation neutrino experiment currently under construction. DUNE will consist of two high-resolution neutrino interaction imaging detectors exposed to the world’s most intense neutrino beam, with the Near Detector at Fermilab and the Far Detector 1,300 km away in the Sanford Underground Research Facility in South Dakota, US. The high statistics and excellent resolution capabilities of DUNE's $^{40}$Ar detector will allow us to make precision studies of oscillation parameters capable of searching for CP violation in the lepton sector, testing interaction models, and studying phenomena that have until now, seemed too complex to measure, like $\nu_\tau$ detection and therefore, providing the completion of the 3-flavor neutrino paradigm. Knowledge of the $\nu_\tau$ detection can impact a broad spectrum of open questions. These include searching for non-standard neutrino interactions, constraining the unitarity of the PMNS matrix, searching for sterile neutrinos, and studying neutrino interactions. In the case of LArTPC data, the detector hits can be considered nodes in a graph, and the edges represent the spatial and temporal relationships between them. By using graph neural networks, it is possible to exploit these relationships and improve the accuracy of particle identification and reconstruction. During my presentation and specifically for tau neutrino reconstruction, I will show the effectiveness and reliability of our in-house developed graph neural network (GNN), NuGraph. This GNN classifies detector hits based on the particle type responsible for their production, assuring that the system accurately identifies and categorizes information based on its unique characteristics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Optical potential uncertainties on exclusive tens-of-MeV Ar cross sections

Large liquid argon time projection chamber (LArTPC) neutrino detectors, such as those planned for the Deep Underground Neutrino Experiment (DUNE), show considerable promise as a platform for next-generation measurements of supernova neutrinos. Thanks to the neutron excess in $^{40}$Ar as well as the detailed tracking possible with LArTPCs, these detectors are expected to be uniquely capable of measuring supernova electron neutrinos with high statistics and minimal backgrounds. However, these technological advantages come at the price of complexities in data interpretation; reconstruction of the incident energies of supernova neutrinos in a future LArTPC-based analysis will be subject to a variety of systematic uncertainties related to nuclear interaction modeling. In this talk, we present a study of a subset of these uncertainties as implemented in the MARLEY event generator used by DUNE and other LArTPC neutrino experiments. Variations to the optical potential used in the MARLEY nuclear de-excitation model are applied to the calculation of exclusive tens-of-MeV neutrino-nucleus cross sections for the first time, and the impact on observables of interest for supernova neutrino detection is examined. We also discuss prospects for quantifying other sources of uncertainty on the MARLEY neutrino interaction model.

El-Haj, Luca Abu↗
DOE OSTI2026

Harnessing Ocean Thermal Gradients Using Thermoelectric Based Submersibles for Ocean Power Applications

The urgent need for energy solutions in marine environments has accelerated the development of innovative technologies capable of leveraging natural resources for power generation. This study introduces a buoyancy-driven submersible system designed to harness ocean thermal gradients using thermoelectric generators (TEGs) and phase change materials (PCMs). The technology aims to provide autonomous power to offshore aquaculture farms, unmanned underwater vehicles (UUVs), offshore platform illumination, and ocean sensors, significantly reducing dependence on fossil fuels. Ocean thermal gradients, especially prevalent in mid-latitude regions, exhibit temperature differences between surface and deep waters ranging from 7 degrees Celsius to 30 degrees Celsius depending on seasonal variations. The proposed submersible technology utilizes TEGs to convert thermal energy from these gradients into electrical power, generating between 0.2 and 0.5 watts, while PCMs are employed to store and regulate this energy, ensuring a stable and continuous power supply. The buoyancy-driven mechanism of the submersible enhances its capability to navigate through varying depths, optimizing its exposure to different thermal gradients and maximizing energy harvesting. The performance of this submersible system is analyzed through detailed thermodynamic assessments and computational fluid dynamics (CFD) modeling focused on heat transfer. These analyzes consider real-world ocean temperature profiles and seek to refine the interaction between TEGs and PCMs to optimize energy extraction. The evaluation encompasses several key performance metrics, including power output and energy efficiency. Results confirm the potential of this innovative technology to provide a continuous and reliable power source for marine applications. By demonstrating the feasibility of using ocean thermal gradients for energy generation, this study contributes to the broader efforts of innovation in energy technologies for harsh, remote marine environments. The implementation of such promises is significant advancements in the autonomy of marine operations. The ongoing research will further investigate scalability ensuring that the system can be effectively adapted to various marine settings and operational demands.

16 TIDAL AND WAVE POWER↗
DOE OSTI2025

Vehicular Re-Identification from Uncontrolled Multiple Views

Vehicle re-identification (re-ID) across disparate sensing modalities remains a fundamental challenge for transportation research. In this work, we introduce a deep multi-view vehicle re-ID framework that leverages Siamese networks to compare pairs of vehicle images and produce matching scores, enabling robust association across drastically different viewpoints such as those from UAVs, surveillance cameras, and ground sensors. The model exploits convolutional neural networks to learn features that remain discriminative under changes in angle, distance, and illumination, supporting more generalizable re-ID performance. As part of this effort, we also developed an automated pipeline to synchronize roadside and UAV video streams, producing a multi-perspective dataset that complements preexisting real collections and a synthetic dataset generated in this study. Together, these contributions advance the capability to re-identify vehicles across wide viewing baselines; establish a foundation for scalable, reproducible research in vehicle re-ID; and open pathways for future applications, such as inferring routine behaviors, movement patterns, and daily habits of the individual associated with the vehicle.

convolutional neural networks↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2024

Deep learning-driven super-resolution in Raman hyperspectral imaging: Efficient high-resolution reconstruction from low-resolution data

Deep learning (DL) has become an indispensable tool in hyperspectral data analysis, automatically extracting valuable features from complex, high-dimensional datasets. Super-resolution reconstruction, an essential aspect of hyperspectral data, involves enhancing spatial resolution, particularly relevant to low-resolution hyperspectral data. Yet, the pursuit of super-resolution in hyperspectral analysis is fraught with challenges, including acquiring ground truth high-resolution data for training, generalization, and scalability. The pressing issue of extended spectral acquisition times, notably for high-resolution scans, is a significant roadblock in hyperspectral imaging. Super-resolution methods offer a promising solution by providing higher spatial resolution data to expedite data collection and yield more efficient outcomes. This paper delves into a practical application of these concepts using Raman imaging, where spectral acquisition times can be prohibitively long. In this context, DL-based super-resolution models demonstrate their efficacy by predicting and reconstructing high-resolution Raman data from low-resolution input, eliminating the need for resource-intensive high-resolution scans. While previous work often relied on substantial high-resolution datasets, this study showcases the ability to achieve similar outcomes even with limited data, presenting a more practical and cost-effective approach. In conclusion, the results offer a glimpse into the transformative potential of this technology to streamline hyperspectral imaging applications by saving valuable time and resources through the successful generation of high-resolution data from low-resolution inputs.

42 ENGINEERING↗
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Quantum fluctuations lead to glassy electron dynamics in the good metal regime of electron doped KTaO 3

One of the central challenges in condensed matter physics is to comprehend systems that have strong disorder and strong interactions. In the strongly localized regime, their subtle competition leads to glassy electron dynamics which ceases to exist well before the insulator-to-metal transition is approached as a function of doping. Here, we report on the discovery of glassy electron dynamics deep inside the good metal regime of an electron-doped quantum paraelectric system: KTaO 3 . We reveal that upon excitation of electrons from defect states to the conduction band, the excess injected carriers in the conduction band relax in a stretched exponential manner with a large relaxation time, and the system evinces simple aging phenomena—a telltale sign of glassy dynamics. Most significantly, we observe a critical slowing down of carrier dynamics below 35 K, concomitant with the onset of quantum paraelectricity in the undoped KTaO 3 . Our combined investigation using second harmonic generation technique, density functional theory and phenomenological modeling demonstrates quantum fluctuation-stabilized soft polar modes as the impetus for the glassy behavior. This study addresses one of the most fundamental questions regarding the potential promotion of glassiness by quantum fluctuations and opens a route for exploring glassy dynamics of electrons in a well-delocalized regime.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Event generator for jet tomography in electron-ion collisions

We develop the first event generator, the electron-heavy-ion-jet-interaction-generator (eHIJING), for the jet tomography study of electron-ion collisions. In this generator, energetic jet partons produced from the initial hard scattering undergo multiple collisions with the nuclear target. The collision rate is proportional to the transverse-momentum-dependent (TMD) gluon density in the nucleus, which is given by a simple model inspired by the physics of gluon saturation. Medium-modified QCD splitting functions within the higher-twist (HT) and generalized higher-twist (GHT) frameworks are utilized to simulate parton showering in the nuclear medium that takes into account the non-Abelian Landau-Pomeranchuck-Midgal interference effect. Employing eHIJING, we revisit hadron production in semi-inclusive deep inelastic scattering (SIDIS) as measured by EMC, HERMES, and recent CLAS experiments. eHIJING with both GT and GHT frameworks gives reasonably good descriptions of these experimental data. Predictions for experiments at the future electron-ion colliders are also provided. It is demonstrated that future measurements of the transverse momentum broadening of single hadron spectra can be used to map out the two-dimensional kinematic (Q 2 , x B ) dependence of the jet transport coefficient $\hat{q}$ in cold nuclear matter.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Digital Real-Time Simulation and Power Quality Analysis of a Hydrogen-Generating Nuclear-Renewable Integrated Energy System

This paper investigates the challenges and solutions associated with integrating a hydrogen-generating nuclear-renewable integrated energy system (NR-IES) under a transactive energy framework. The proposed system directs excess nuclear power to hydrogen production during periods of low grid demand while utilizing renewables to maintain grid stability. Using digital real-time simulation (DRTS) in the Typhoon HIL 404 model, the dynamic interactions between nuclear power plants, electrolyzers, and power grids are analyzed to mitigate issues such as harmonic distortion, power quality degradation, and low power factor caused by large non-linear loads. A three-phase power conversion system is modeled using the Typhoon HIL 404 model and includes a generator, a variable load, an electrolyzer, and power filters. Active harmonic filters (AHFs) and hybrid active power filters (HAPFs) are implemented to address harmonic mitigation and reactive power compensation. The results reveal that the HAPF topology effectively balances cost efficiency and performance and significantly reduces active filter current requirements compared to AHF-only systems. During maximum electrolyzer operation at 4 MW, the grid frequency dropped below 59.3 Hz without filtering; however, the implementation of power filters successfully restored the frequency to 59.9 Hz, demonstrating its effectiveness in maintaining grid stability. Future work will focus on integrating a deep reinforcement learning (DRL) framework with real-time simulation and optimizing real-time power dispatch, thus enabling a scalable, efficient NR-IES for sustainable energy markets.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗