Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative model”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Full-wave modeling of RF waves in fusion plasmas with finite element method: Progress in past decades and its future role

This paper reviews the progress in computing radio frequency (RF) wave fields in fusion plasmas, specifically focusing on simulations utilizing the finite element method (FEM) over the past few decades. Computing RF wave fields in fusion plasmas presents unique challenges due to large simulation domains, complex antenna structures, non-local dielectric properties, and wide ranges of spatial scales. It highlights key developments and outlines future directions, primarily addressing waves in the ion cyclotron (IC) to lower hybrid (LH) frequency range. We begin with briefly revisiting earlier developments before the widespread availability of modern computer-aided engineering (CAE) software based on FEM. This historical perspective illuminates early progress and the physics difficulties that motivated ongoing work within the community. Modern wave simulations for RF antennas based on FEM are characterized by the use of detailed 3D antenna model geometry generated from engineering CAD software and localized wave dielectric model. Significant advancements have also been made in improving physics models to include phenomena such as RF sheath rectification and wave scattering. FEM-based RF simulations have also been applied to compute wave propagation in the core region, where the inclusion of non-local dielectric response is crucial. This is a challenging goal, and several promising approaches have been proposed in this area. Additionally, RF simulation development initiatives based on open-source libraries have gained popularity, demonstrating scalability and flexibility in extending physics models. This paper will discuss the advantages and disadvantages of using such a publicly available FEM library.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
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 OSTI2024

SCIMON: Scientific Inspiration Machines Optimized for Novelty

We explore and enhance the ability of neu- ral language models to generate novel scien- tific directions grounded in literature. Work on literature-based hypothesis generation has traditionally focused on binary link prediction— severely limiting the expressivity of hypothe- ses. This line of work also does not focus on optimizing novelty. We take a dramatic depar- ture with a novel setting in which models use as input background contexts (e.g., problems, experimental settings, goals), and output natu- ral language ideas grounded in literature. We present SCIMON, a modeling framework that uses retrieval of “inspirations” from past scien- tific papers, and explicitly optimizes for novelty by iteratively comparing to prior papers and up- dating idea suggestions until sufficient novelty is achieved. Comprehensive evaluations reveal that GPT-4 tends to generate ideas with over- all low technical depth and novelty, while our methods partially mitigate this issue. Our work represents a first step toward evaluating and developing language models that generate new ideas derived from the scientific literature.

Ji, Heng↗
DOE OSTI2024

Understanding Generative AI Content with Embedding Models

The construction of high-quality numerical features is critical to any quantitative data analysis. Feature engineering has been historically addressed by carefully hand-crafting data representations based on domain expertise. This work views the internal representations of modern deep neural networks (DNNs), called embeddings, as an implicit form of traditional feature engineering. For trained DNNs, we show that these embeddings can reveal interpretable, high-level concepts in unstructured sample data. We use these embeddings in natural language and computer vision tasks to uncover both inherent heterogeneity in the underlying data and human-understandable explanations for it. In particular, we find empirical evidence that there is inherent separability between real data and those generated from AI models.

Vargas, Max↗
DOE OSTI2026

A curated benchmark for cofolding models on kinase conformational states

Abstract Protein kinases are critical drug targets, requiring therapeutics that can modulate their active and inactive conformational states. While cofolding models can generate global folds directly from kinase sequences and ligand SMILES strings, these models have not yet been tested on their ability to recover ligand-induced-fit conformational states of the kinase proteins. Here, we introduce KinConfBench, a curated benchmark of 2225 high-quality human kinase chains to evaluate the ability of four state-of-the-art cofolding models—Boltz-2, Chai-1, Protenix, and RoseTTAFold-All-Atom—to recover both canonical and rare conformational states. We show that geometric success metrics of a ligand pose in the active site do not correlate strongly with the correct kinase conformational state, motivating a new set of dynamical benchmarks for assessing cofolding models. While all four cofolding models achieve ~60–80% prediction accuracy for kinase conformational classification, they exhibit severe mode collapse when performing multiple inferences, show negligible structural diversity in sampling induced-fit motions, and display a prevalent “apo-drift” in which most cofolding models predominantly predict the kinase to be in its ligand-free state. Our results highlight that capturing ligand-induced protein conformational diversity, not just geometric fit, is critical for next-generation structure-based drug discovery.

Sun, Kunyang↗
DOE OSTI2024

Statistical data analysis of x-ray spectroscopy data enabled by neural network accelerated Bayesian inference

Bayesian inference applied to x-ray spectroscopy data analysis enables uncertainty quantification necessary to rigorously test theoretical models. However, when comparing to data, detailed atomic physics and radiation transfer calculations of x-ray emission from non-uniform plasma conditions are typically too slow to be performed in line with statistical sampling methods, such as Markov Chain Monte Carlo sampling. Furthermore, differences in transition energies and x-ray opacities often make direct comparisons between simulated and measured spectra unreliable. Here, we present a spectral decomposition method that allows for corrections to line positions and bound–bound opacities to best fit experimental data, with the goal of providing quantitative feedback to improve the underlying theoretical models and guide future experiments. In this work, we use a neural network (NN) surrogate model to replace spectral calculations of isobaric hot-spots created in Kr-doped implosions at the National Ignition Facility. The NN was trained on calculations of x-ray spectra using an isobaric hot-spot model post-processed with Cretin, a multi-species atomic kinetics and radiation code. The speedup provided by the NN model to generate x-ray emission spectra enables statistical analysis of parameterized models with sufficient detail to accurately represent the physical system and extract the plasma parameters of interest.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Convolutional L2LFlows: generating accurate showers in highly granular calorimeters using convolutional normalizing flows

Abstract In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been among the models with the best fidelity. However, as the latent space in such models is required to have the same dimensionality as the data space, scaling up normalizing flows to high dimensional datasets is not straightforward. The prior L2LFlows approach successfully used a series of separate normalizing flows and sequence of conditioning steps to circumvent this problem. In this work, we extend L2LFlows to simulate showers with a 9-times larger profile in the lateral direction. To achieve this, we introduce convolutional layers and U-Net-type connections, move from masked autoregressive flows to coupling layers, and demonstrate the successful modelling of showers in the ILD Electromagnetic Calorimeter as well as Dataset 3 from the public CaloChallenge dataset.

Instruments & Instrumentation↗
DOE OSTI2024

Using Co-Simulation to Model Interconnect-Scale Power Systems from Loads to Generators

Co-simulation is a modeling technique that allows analysts to combine simulation tools and their corresponding models to exchange data during run-time, allowing the creation of larger and more complex models across heterogeneous domains. HELICS is a co-simulation platform developed over the past six years that has been shown to be effective for these multi-domain analysis. Recently, a HELICS-based analysis was completed where the ERCOT electrical interconnect in the United States was modeled in high detail from bulk power system generation to individual customer loads. This model was used to evaluate a flat-rate and transactive energy tariff with integrated wholesale and retail real-time and day-ahead energy markets. This modeling allows detailed analysis showing how the operations of the power system under these tariffs impact all actors in the power system, from individual customers to bulk power system operators.

co-simulation, HELICS, transactive energy system, ↗
DOE OSTI2025

Selection of Global Climate Model Data for Downscaling With Generative Machine Learning and Use in the Power Planning for Alignment of Climate and Energy Systems Project

The range of results from climate models and scenarios is important to the understanding of uncertainty in power planning analysis. A U.S. Department of Energy-funded analytic project called Power Planning for Alignment of Climate and Energy Systems is developing data and analytic methods to reflect the effects of climate change on key variables for power system planning, as part of the Grid Modernization Lab Consortium. This project will select and prepare global climate model results for use in power system planning models. A related report (Evaluation of Global Climate Models for Use in Energy Analysis) assesses the performance of various global climate models from the Coupled Model Intercomparison Project Phase 6 data archive for their historical skill with respect to energy system performance and for their future projections under multiple climate change scenarios. Building from that report, we describe the selection of a climate scenario (Shared Socioeconomic Pathway [SSP] 2-4.5) and five climate models: TaiESM1, EC-Earth3-CC, GFDL-CM4, EC-Earth3-Veg, and MPI-ESM1-2-HR. We describe the model selection criteria, which were based on the quality of the match between model results under historical conditions and on the representation of the range of future values for several variables. These results will be downscaled via an open-source generative machine learning method called Super-Resolution for Renewable Energy Resource Data with Climate Change Impacts.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2024

DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models With 3D Diffusion Models

Earth system models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low-cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low-cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio-temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Addressing Low-Cost Methane Sensor Calibration Shortcomings with Machine Learning

Quantifying methane emissions is essential for meeting near-term climate goals and is typically carried out using methane concentrations measured downwind of the source. One major source of methane that is important to observe and promptly remediate is fugitive emissions from oil and gas production sites but installing methane sensors at the thousands of sites within a production basin is expensive. In recent years, relatively inexpensive metal oxide sensors have been used to measure methane concentrations at production sites. Current methods used to calibrate metal oxide sensors have been shown to have significant shortcomings, resulting in limited confidence in methane concentrations generated by these sensors. To address this, we investigate using machine learning (ML) to generate a model that converts metal oxide sensor output to methane mixing ratios. To generate test data, two metal oxide sensors, TGS2600 and TGS2611, were collocated with a trace methane analyzer downwind of controlled methane releases. Over the duration of the measurements, the trace gas analyzer’s average methane mixing ratio was 2.40 ppm with a maximum of 147.6 ppm. The average calculated methane mixing ratios for the TGS2600 and TGS2611 using the ML algorithm were 2.42 ppm and 2.40 ppm, with maximum values of 117.5 ppm and 106.3 ppm, respectively. A comparison of histograms generated using the analyzer and metal oxide sensors mixing ratios shows overlap coefficients of 0.95 and 0.94 for the TGS2600 and TGS2611, respectively. Overall, our results showed there was a good agreement between the ML-derived metal oxide sensors’ mixing ratios and those generated using the more accurate trace gas analyzer. This suggests that the response of lower-cost sensors calibrated using ML could be used to generate mixing ratios with precision and accuracy comparable to higher priced trace methane analyzers. This would improve confidence in low-cost sensors’ response, reduce the cost of sensor deployment, and allow for timely and accurate tracking of methane emissions.

03 NATURAL GAS↗
DOE OSTI2025

Diffusion Model-Guided Inverse Design of Bimetallic Catalysts for Ammonia Decomposition

In the past decade, artificial intelligence and deep learning have played increasingly prominent roles in materials design and discovery. Among these, generative AI models, known for their ability to create unique and complex structures, have emerged as state-of-the-art tools for materials screening due to their high efficiency and low computational cost. In catalysis, one of the major challenges is identifying promising material candidates within an immense chemical space. This challenge can be addressed using generative approaches, such as diffusion-based inverse design models. In this study, we present a machine learning-guided workflow that employed a diffusion model for the inverse design of bimetallic alloy catalysts for low-carbon ammonia decomposition, a key reaction for ammonia emission control and sustainable hydrogen production. Catalyst candidates were evaluated using nitrogen adsorption energy as the key descriptor, inspired by multiscale modeling. The proposed workflow identified low-cost, environmentally friendly catalysts with excellent catalytic performance, which have been validated theoretically and experimentally. Our framework decoupled the generative and property-prediction components, enhancing both flexibility and accuracy in the catalytic material design process.

Adsorption↗
DOE OSTI2024

Powering Data Centers with Clean Energy: A Techno-Economic Case Study of Nuclear and Renewable Energy Dependability

Rising data demands from artificial intelligence (AI) and large language models (LLMs) generating images, videos, and text have prompted increased need for larger and more robust data centers in the United States. Major companies interested in these larger data centers face the choice of linking them to existing regional grids, building stand-alone power supplies onsite, or a combination of both. The request, review, and approval process for new transmission lines to grids in the United States, however, has grown in recent years to times spans rivaling those of new construction for nuclear power plants. Building an islanded power supply for each data center is therefore becoming a prominent option. In this case study, several technologies are modeled in techno-economic simulations for long-term system costs subject to fixed electricity demand from a singular data center. A 250 MWe data center is assumed with additional 50 MWe for resiliency. Techno-economic simulations are conducted using the Holistic Energy Resource Optimization Network (HERON) software, which is a part of the Framework for Optimization of Resources and Economics (FORCE) tool suite. Technologies considered include solar, wind, lithium-ion batteries, and several types of nuclear reactors: large-scale reactors, small modular reactors, and microreactors. A low- and high-cost estimate for each technology is assumed to develop a range of expected economic performance. Low-cost estimates included several clean energy production tax credits. Different combinations of renewable energy generators with nuclear reactors are considered, ranging from a fully renewable-powered data center to a fully nuclear-powered data center. Historic time series of wind and solar availability from the Texas grid are used to train a reduced order model; this model then generates unique time series with similar characteristics of the training dataset. Multiple scenarios of weather and subsequent operations are simulated for each renewable-nuclear combination to determine total costs throughout the project lifetime. Fully renewable-powered configurations required large amounts of installed capacity (GW scale) in the simulations to meet the fixed demand of the data center. This is due to some scenarios in the historical dataset which captured low-wind and low-solar days, requiring over-building of these technologies as well as batteries to compensate for the low amounts of electricity generation. Fully nuclear-powered configurations outperformed the fully renewable and mixed renewable-nuclear configurations in terms of cost, with ranges between $1B and $10B in 2023 USDs compared to $40B+ for fully renewable configurations. Of the nuclear technologies, small modular reactors performed better economically than large-scale nuclear models due to lower projected capital costs, and both performed better than the microreactor models. These results demonstrate the applicability of firm, dispatchable electricity resources from baseload generators like nuclear power plants for operating facilities that run at constant power without daily variability.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Metabolic skinflint or spendthrift? Insights into ground sloth integument and thermophysiology revealed by biophysical modeling and clumped isotope paleothermometry

Abstract Remains of megatheres have been known since the 18th -century and were among the first megafaunal vertebrates to be studied. While several examples of preserved integument show a thick coverage of fur for smaller ground sloths living in cold climates such as Mylodon and Nothrotheriops , comparatively very little is known about megathere skin. Assuming a typical placental mammal metabolism, it was previously hypothesized that megatheres would have had little-to-no fur as they achieved giant body sizes. Here the “hairless model of integument” is tested using geochemical analyses to estimate body temperature to generate novel models of ground sloth metabolism, fur coverage, and paleoclimate with Niche Mapper software. The simulations assuming metabolic activity akin to those of modern xenarthrans suggest that sparse fur coverage would have resulted in cold stress across most latitudinal ranges inhabited by extinct ground sloths. Specifically, Eremotherium predominantly required dense 10 mm fur with implications for seasonal changes of coat depth in northernmost latitudes and sparse fur in the tropics; Megatherium required dense 30 mm fur year-round in its exclusive range of cooler, drier climates; Mylodon and Nothrotheriops required dense 10–50 mm fur to avoid thermal stress, matching the integument remains of both genera, and further implying the use of behavioral thermoregulation. Moreover, clumped isotope paleothermometry data from the preserved teeth of four genera of ground sloth yielded reconstructed body temperatures lower than those previously reported for large terrestrial mammals (29 ± 2°–32 ± 3° C). This combination of low metabolisms and thick fur allowed ground sloths to inhabit various environments.

Deak, Michael D.↗
DOE OSTI2024

Processing MCNP Elemental Edit Outputs

The Monte Carlo N-Particle (MCNP) transport code version 6 (also known as MCNP6) has the capability for tracking particles on unstructured mesh (UM) geometry models embedded into constructive solid geometry (CSG) cells. A UM geometry is a collection of elements representing a solid geometry. The first step of MCNP UM modeling is using other software packages to create a finite element mesh representation of a solid 3D geometry. Computer-aided design (CAD) or computer-aided manufacturing (CAM) software is typically used to create a solid geometry model, which is later imported into mesh generation software to create a UM model. The MCNP UM feature was originally designed for models generated by the Abaqus/CAE software. The MCNP code version 6.0 and later can process UM models formatted as Abaqus input files. MCNP can process a UM model consisting of several different element types including linear tetrahedral or hexahedral elements and calculate quantities of interest such as flux and energy deposition at elements. An MCNP UM simulation provides high-fidelity elemental edit (i.e., tally) outputs, which can be further used in multiphysics calculations. The MCNP UM feature was used for multiphysics simulations where quantities of interest calculated by MCNP are used as inputs for heat transfer calculations in Abaqus. MCNP6.3 can produce two types of elemental edit output (EEOUT) file formats: ASCII and HDF5. An EEOUT file type must be requested on an EMBED card while output type (flux or energy deposition) must be requested on an EMBEE card. We wrote Python3 scripts to extract energy deposition values in an ASCII or HDF5 EEOUT file and compute a heat flux profile for an Abaqus heat transfer calculation.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still face key limitations: some become computationally infeasible for large messages, while others suffer from a poor trade-off between text quality and decoding accuracy. Moreover, the decoding accuracy of existing methods drops significantly when the number of tokens in the generated text is limited, a condition that frequently arises in practical usage. To address these challenges, we propose XMark, a novel method for encoding and decoding binary messages in LLM-generated texts. The unique design of XMark’s encoder produces a less distorted logit distribution for watermarked token generation, preserving text quality, and also enables its tailored decoder to reliably recover the encoded message with limited tokens. Extensive experiments across diverse downstream tasks show that XMark significantly improves decoding accuracy while preserving the quality of watermarked text, outperforming prior methods. The code will be made publicly available upon acceptance.

Xu, Jiahao [University of Nevada, Reno]↗
DOE OSTI2026

Deployment Pathways for Long Duration Energy Storage

We apply a least-cost generation expansion model of the continental United States to assess how optimal investments in long-duration energy storage (LDES) technologies are impacted by changes in system generation portfolios and technology costs, assessing 369 capacity expansion scenarios in total. The expansion model considers 8,760 h of chronological operations for the entire target year, 2040. We find that low-cost LDES technologies can reduce generation investments and system costs. Specifically, once the costs for 24- and 100-h storage reach $38/kWh and $14/kWh, respectively, substantial deployments are observed. The distribution of storage investments across durations is strongly influenced by the system generation portfolio. We also demonstrate that a high-fidelity temporal representation is required to capture the value of LDES in generation expansion. Finally, we conduct a regression analysis of our capacity expansion results and find that LDES deployments are positively correlated with the combined wind and solar capacity share and negatively correlated with peaking and baseload shares.

Levin, Todd↗
DOE OSTI2026

Simulation of wind and solar energy generation over California with E3SM SCREAM regionally refined models at 3.25 km and 800 m resolutions

This study presents wind and solar power generation estimates derived from the US Department of Energy’s Simple Cloud-Resolving E3SM Atmosphere Model (SCREAM) Regionally Refined Models (RRM) over California at 3.25 km and 800 m horizontal resolutions, using the Python wrapper for the System Advisor Model (PySAM). The resulting wind and solar generation estimates are compared to monthly capacity factors reported to the Energy Information Administration (EIA), High-Resolution Rapid Refresh (HRRR, 3 km resolution) forecast model, and E3SM North American regionally refined model (NARRM, 25 km resolution). We systematically assess the impacts of generation modeling assumptions, meteorological models, and horizontal resolution. Results show that resolution plays a dominant role for wind energy: increasing from 25 to 3.25 km brings qualitative and quantitative improvements, most notably by resolving the phase error in the seasonal cycle found in coarser simulations. However, further refinement to 800 m offers minimal gains. SCREAM performs better than HRRR for solar power generation in single- and dual-axis tracking systems, likely due to more accurate surface radiation. The sensitivity of PySAM to system configuration, particularly for axis-tracking modeling in photovoltaics, is also highlighted. Overall, SCREAM-RRM shows strong potential for high-resolution energy assessments, with future progress depending on more in situ observations and clearer quantification of uncertainties in generation modeling.

Geosciences↗