Search NASA⌕ Search

SEARCH · Search NASA

Results for “conditional 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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Conditioned quantum-assisted deep generative surrogate for particle-calorimeter interactions

Particle collisions at accelerators like the Large Hadron Collider (LHC), recorded by experiments such as ATLAS and CMS, enable precise standard model measurements and searches for new phenomena. Simulating these collisions significantly influences experiment design and analysis but incurs immense computational costs, projected at millions of CPU-years annually during the high luminosity LHC (HL-LHC) phase. Currently, simulating a single event with Geant4 consumes around 1000 CPU seconds, with calorimeter simulations especially demanding. To address this, we propose a conditioned quantum-assisted generative model, integrating a conditioned variational autoencoder (VAE) and a conditioned restricted Boltzmann machine (RBM). Our RBM architecture is tailored for D-Wave’s Pegasus-structured advantage quantum annealer for sampling, leveraging the flux bias for conditioning. This approach combines classical RBMs as universal approximators for discrete distributions with quantum annealing’s speed and scalability. We also introduce an adaptive method for efficiently estimating effective inverse temperature, and validate our framework on Dataset 2 of CaloChallenge.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1981

The effect of surface boundary conditions on the climate generated by a coarse-mesh general circulation model

A hierarchy of experiments was run, starting with an all water planet with zonally symmetric sea surface temperatures, then adding, one at a time, flat continents, mountains, surface physics, and realistic sea surface temperatures. The model was run with the sun fixed at a perpetual January. Ensemble means and standard deviations were computed and the t-test was used to determine the statistical significance of the results. The addition of realistic surface physics does not affect the model climatology to as large as extent as does the addition of mountains. Departures from zonal symmetry of the SST field result in a better simulation of the real atmosphere.

Cohen, C.↗
DOE OSTI2025

Second-generation downscaled earth system model data using generative machine learning

The second-generation Sup3rCC dataset provides high-resolution meteorological data generated through the downscaling of multiple earth system models (ESMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6). This downscaling is performed through application of a generative machine learning approach called Super-Resolution for Renewable Resource Data (sup3r). This dataset builds on the first-generation Sup3rCC data by applying improved bias correction methods and adding downscaled precipitation to the output variables. As with the first Sup3rCC version, the data still include temperature, wind speed and direction at multiple heights, pressure, three components of downwelling solar radiation, and relative humidity—all at 4-kilometer (km) hourly resolution over the contiguous United States. This is a 25x spatial enhancement and 24x temporal enhancement of the source 100-km daily-average ESM data. This extension of the Sup3rCC dataset includes data from six ESMs from two shared socioeconomic pathways (SSPs) totaling 400 years of data with multiple future projections of changing meteorological conditions. The scenario selection was based on a structured evaluation of historical ESM skill and comprehensive representation of possible trajectories of future climate change in temperature, humidity, precipitation, solar irradiance, and near-surface wind speeds. The inclusion of multiple future projections is intended to enable users to assess key drivers of un 36 certainty and variability. All data are double-bias corrected, resulting in a product that can be used out-of-the-box for energy system analysis with minimal historical bias. The potential applications of Sup3rCC data extend to various topics in renewable energy resource assessment, energy systems modeling, and grid resilience studies. High-resolution future meteorological projections are critical for evaluating the effects of changing meteorological conditions on renewable energy generation, energy demand, and for optimizing energy storage and grid infrastructure. The 4-km hourly resolution of the downscaled data enables understanding of spatial and temporal variability at the scales necessary for energy system operational planning. In addition, the dataset can support risk assessments by providing detailed information on possible future extreme weather events and long-term meteorological variability at scales relevant to energy infrastructure. By offering an enhanced representation of possible future meteorological conditions, the second-generation Sup3rCC dataset enables more precise modeling of energy resilience and adaptation strategies in response to changing meteorological conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

CaloChallenge 2022: a community challenge for fast calorimeter simulation

Here, we present the results of the ‘Fast Calorimeter Simulation Challenge 2022’—the CaloChallenge. We study state-of-the-art generative models on four calorimeter shower datasets of increasing dimensionality, ranging from a few hundred voxels to a few tens of thousand voxels. The 31 individual submissions span a wide range of current popular generative architectures, including variational autoencoders (VAEs), generative adversarial networks (GANs), normalizing flows, diffusion models, and models based on conditional flow matching. We compare all submissions in terms of quality of generated calorimeter showers, as well as shower generation time and model size. To assess the quality we use a broad range of different metrics including differences in one-dimensional histograms of observables, KPD/FPD scores, AUCs of binary classifiers, and the log-posterior of a multiclass classifier. The results of the CaloChallenge provide the most complete and comprehensive survey of cutting-edge approaches to calorimeter fast simulation to date. In addition, our work provides a uniquely detailed perspective on the important problem of how to evaluate generative models. As such, the results presented here should be applicable for other domains that use generative AI and require fast and faithful generation of samples in a large phase space.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1995

A Simulated Geochemical Rover Mission to the Taurus-Littrow Valley of the Moon

We test the effectiveness of using an alpha backscatter, alpha-proton, X ray spectrometer on a remotely operated rover to analyze soils and provide geologically useful information about the Moon during a simulated mission to a hypothetical site resembling the Apollo 17 landing site. On the mission, 100 soil samples are "analyzed" for major elements at moderate analytical precision (e.g., typical relative sample standard deviation from counting statistics: Si[11%], Al[18%], Fe[6%], Mg[20%], Ca[5%]). Simulated compositions of soils are generated by combining compositions of components representing the major lithologies occurring at the site in known proportions. Simulated analyses are generated by degrading the simulated compositions according to the expected analytical precision of the analyzer. Compositions obtained from the simulated analyses are modeled by least squares mass balance as mixtures of the components, and the relative proportions of those components as predicted by the model are compared with the actual proportions used to generate the simulated composition. Boundary conditions of the modeling exercise are that all important lithologic components of the regolith are known and are represented by model components, and that the compositions of these components are well known. The effect of having the capability of determining one incompatible element at moderate precision (25%) is compared with the effect of the lack of this capability. We discuss likely limitations and ambiguities that would be encountered, but conclude that much of our knowledge about the Apollo 17 site (based on the return samples) regarding the distribution and relative abundances of lithologies in the regolith could be obtained. This success requires, however, that at least one incompatible element be determined.

Korotev, Randy L.↗
DOE OSTI2026

Parallel-in-Time Solution of Allen-Cahn Equations by Integrating Operator Learning into the Parareal Method

While recent advances in deep learning have shown promising efficiency gains in solving time-dependent partial differential equations (PDEs), matching the accuracy of conventional numerical solvers still remains a challenge. One strategy to improve the accuracy of deep learning-based solutions for time-dependent PDEs is to use the learned model as the coarse propagator in the Parareal method and a traditional numerical method as the fine solver. However, successful integration of deep learning into the Parareal method requires consistency between the coarse and fine solvers, particularly for PDEs exhibiting rapid changes such as sharp transitions. Here, to ensure this consistency, we propose using convolutional neural networks (CNNs) to learn the fully discrete time-stepping operator defined by the same numerical scheme employed as the fine solver. We demonstrate the effectiveness of the proposed method in solving the classical and mass-conservative Allen–Cahn (AC) equations. Through iterative updates in the Parareal algorithm, our approach achieves a significant computational speedup compared to traditional fine solvers while converging to high-accuracy solutions. Our results highlight that the proposed hybrid Parareal algorithm effectively accelerates simulations, particularly when implemented on multiple GPUs, and converges to the desired accuracy in only a few iterations. Another advantage of our method is that the CNN model is trained on trajectory-based data generated from random initial conditions, such that the trained model can be used to solve the AC equations with various initial conditions without retraining. This work demonstrates the potential of integrating neural network methods into parallel-in-time frameworks for efficient and accurate simulations of time-dependent PDEs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Development of a UO2 Densification Model in the MARMOT Tool

A phase-field model for irradiation-enhanced densification is currently under development in the NEAMS code MARMOT. To begin, a simplified model of sintering without irradiation effects is developed. This model requires a method to generate sintering initial conditions, and the accepted phase-field rigid-body motion sintering model must either be fully implemented in MARMOT or shown to be unnecessary. It is shown to be unnecessary. Sintering simulation results without rigid body motion are shown. Shortcomings in the results are discussed and plans on how to address them are presented.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

CFD-trained ANN Model for Approximating Near-occupant Condition in Real-time Simulations

The main drawback of Computational Fluid Dynamics (CFD) simulations has been the time and resource consuming nature which is not suitable for real-time applications. In this work, we first generated numerous CFD models of a given indoor space to obtain airspeed, temperature, and mean radiant temperature near an occupant as training data. Several artificial neural networks (ANN) models were trained using this CFD simulated data to approximate near real-time environmental conditions for a given occupant. This trained ANN model approach is a part of a real-time simulation of building operations using a combination of software and real hardware (HVAC equipment) approaches. The preliminary results suggest that the CFD- generated training data and the trained ANN model can accurately approximate such conditions in a real-time application, a method that has great potential in building simulation and building digital twin areas of research.

Zhang, Yun↗
DOE OSTI2025

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

An evaluation of in-line component process modules

The purpose of this paper is to discuss the analysis of abnormal configurations of in-line components, tanks and pumps in support of the integration of Criticality Safety into the Uranium Processing Facility (UPF) at Y-12 National Security Complex (Y-12). In-line components are components that are used in solution piping systems, including instrumentation, valves, pumps, and other general-use equipment. Mounted on self-contained skids/modules, in-line components (instruments, seal pots, level switches, etc.), tanks, and pumps are associated with a wide variety of the UPF processes. Using computer generated models expected to bound abnormal conditions for process module configurations, this report evaluates the impact of loss of spacing between in-line components in in-line component arrays and the effects of abnormal events. All fissile materials are considered to have a {sup 235}U enrichment of 100% and full theoretical density of 18.81 g/cm{sup 3} to conservatively represent the maximum credible enrichment available. Water and concrete were utilized to account for the construction materials associated with the skids and other reflective surfaces. Uranyl nitrate, was evaluated over the range of 0 to 550 g U/L for various normal and abnormal configurations of components mounted on skids. Abnormal events included fissile spills, sprinkler activation, and loss of spacing due to a seismic event. The results from this analysis provide a basis that supports development of nuclear safety design criteria, which generates standardized volume limits expected to bound the actual internal volume of the planned components. The results also provide a basis for consistent Nuclear Criticality Safety (NCS) control of in-line components, pumps, and tanks, for the ultimate development of Criticality Safety Process Studies in the UPF. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2016

The effects of the small-scale DM power on the cosmological neutral hydrogen (HI) distribution at high redshifts

The particle nature of dark matter remains a mystery. In this paper, we consider two dark matter models—Late Forming Dark Matter (LFDM) and Ultra-Light Axion (ULA) models—where the matter power spectra show novel effects on small scales. The high redshift universe offers a powerful probe of their parameters. In particular, we study two cosmological observables: the neutral hydrogen (HI) redshifted 21-cm signal from the epoch of reionization, and the evolution of the collapsed fraction of HI in the redshift range 2 < z < 5. We model the theoretical predictions of the models using CDM-like N-body simulations with modified initial conditions, and generate reionization fields using an excursion set model. The N-body approximation is valid on the length and halo mass scales studied. We show that LFDM and ULA models predict an increase in the HI power spectrum from the epoch of reionization by a factor between 2–10 for a range of scales 0.1 < k < 4 Mpc{sup −1}. Assuming a fiducial model where a neutral hydrogen fraction x-bar {sub HI} = 0.5 must be achieved by z = 8, the reionization process allows us to put approximate bounds on the redshift of dark matter formation z{sub f} > 4 × 10{sup 5} (for LFDM) and the axion mass m{sub a} > 2.6 × 10{sup −23} eV (for ULA). The comparison of the collapsed mass fraction inferred from damped Lyman-α observations to the theoretical predictions of our models lead to the weaker bounds: z{sub f} > 2 × 10{sup 5} and m{sub a} > 10{sup −23} eV. These bounds are consistent with other constraints in the literature using different observables; we briefly discuss how these bounds compare with possible constraints from the observation of luminosity function of galaxies at high redshifts. In the case of ULAs, these constraints are also consistent with a solution to the cusp-core problem of CDM.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2016

An Assessment of Multimodel Simulations for the Variability of Western North Pacific Tropical Cyclones and Its Association with ENSO

An assessment of simulations of the interannual variability of tropical cyclones (TCs) over the western North Pacific (WNP) and its association with El Niño-Southern Oscillation (ENSO), as well as a subsequent diagnosis for possible causes of model biases generated from simulated large-scale climate conditions, are documented in the paper. The model experiments are carried out by the Hurricane Work Group under the U.S. Climate Variability and Predictability Research Program (CLIVAR) using five global climate models (GCMs) with a total of 16 ensemble members forced by the observed sea surface temperature and spanning the 28-yr period from 1982 to 2009. The results show GISS and GFDL model ensemble means best simulate the interannual variability of TCs, and the multimodel ensemble mean (MME) follows. Also, the MME has the closest climate mean annual number of WNP TCs and the smallest root-mean-square error to the observation. Most GCMs can simulate the interannual variability of WNP TCs well, with stronger TC activities during two types of El Niño-namely, eastern Pacific (EP) and central Pacific (CP) El Niño-and weaker activity during La Niña. However, none of the models capture the differences in TC activity between EP and CP El Niño as are shown in observations. The inability of models to distinguish the differences in TC activities between the two types of El Niño events may be due to the bias of the models in response to the shift of tropical heating associated with CP El Niño.

climate models↗
DOE OSTI2026

AI-Based Analytics and Energy Modeling Framework for Characterizing Urban Energy Systems

Developing location-specific district energy models is essential for understanding energy patterns and supporting efficient management and planning decisions. However, accurately characterizing these models remains challenging due to gaps in building characteristics and labor-intensive traditional modeling workflows. To address these challenges, we develop an AI-based framework that integrates top-down and bottom-up building energy data to automate urban energy model characterization. The framework trains multimodal deep learning models using heterogeneous ResStockTM datasets to infer missing building characteristics from varying levels of known information and generate simulation-ready inputs for district-scale energy modeling. It also employs a conditioning-based injection approach to generate ”what-if” scenarios, enabling users to explore retrofit, efficiency, and technology-upgrade pathways. Integrated within URBANoptTM, a bottom-up district energy modeling platform for simulating co-located buildings, the framework infers detailed building-level inputs required for bottom-up simulations. Both localized and generalized AI models are developed to learn relationships across categorical, numerical, and time-series data, enabling reconstruction of missing attributes and generation of targeted upgrade scenarios. We demonstrate this methodology on a residential neighborhood in Baltimore, MD, assessing internal consistency against ResStock reference data and URBANopt simulation, and comparing selected attributes against real-world building characteristics. Results show strong overall predictive accuracy in data completion and scenario generation, with localized and generalized models offering complementary trade-offs between precision and scalability. Overall, our automated framework streamlines energy modeling and provides a reliable framework for urban building energy characterization.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS1992

Ship viscous flow: A report on the 1990 SSPA-IIHR Workshop

To assess the state of the art in ship viscous flow computation a Workshop was organized in 1990 by three organizations: SSPA Maritime Consulting AB, Chalmers University of Technology, and the Iowa Institute of Hydraulic Research. Two test cases were specified by the organizers and sent out to all interested research groups, which were asked to submit results in a prescribed format. In September 1990 a meeting was held at Chalmers University of Technology. All results had then been collected and presented in a common format, and the theories based on responses to a questionnaire sent out earlier. During the meeting, each research group was first given the opportunity to briefly introduce their method and results. Thereafter, a considerable time was spent on general discussions on the performance of the different methods considering the differences in the underlying theories. Specific items that were addressed were grid generation, governing equations, boundary conditions, turbulence modelling, and numerical methods. Practical aspects of the results, for instance from the point of view of propeller design, were also discussed. The Workshop Proceedings contain a description of the participating methods, and the results of both test cases. In the present paper, a summary of the Workshop and its results is presented.

Patel, Virendra C.↗
NASA NTRS1993

Assumed modes method and flexible multibody dynamics

The use of assumed modes in flexible multibody dynamics algorithms requires the evaluation of several domain dependent integrals that are affected by the type of modes used. The implications of these integrals - often called zeroth, first and second order terms - are investigated in this paper, for arbitrarily shaped bodies. Guidelines are developed for the use of appropriate boundary conditions while generating the component modal models. The issue of whether and which higher order terms must be retained is also addressed. Analytical results, and numerical results using the Shuttle Remote Manipulator System as the multibody system, are presented to qualitatively and quantitatively address these issues.

Tadikonda, S. S. K.↗
NASA NTRS2020

Supporting Information for ”The 2019-2020 Australian Drought and Bushfires Altered the Partitioning of Hydrological Fluxes

The model configuration employs the modified International Geosphere Biosphere Programme (IGBP) MODIS 20 category landcover data, soil parameters derived from the International Soil Reference and Information Centre, and the Shuttle Radar Topography Mission based elevation, slope, and aspect data. Statistical downscaling approaches are used to transform the coarse resolution MERRA2 meteorological inputs to 1km. The input meteorological fields of air temperature, humidity, surface pressure, wind, downward shortwave radiation, and downward longwave radiation are downscaled to 1km by adjusting for terrain differences in elevation, slope, and aspect. The high resolution monthly precipitation climatology from WorldClim is used to spatially disaggregate input MERRA2 precipitation to 1km. The initial conditions for the model simulations are generated from a long spinup of NoahMP starting from year 2000. All model integrations and evaluations are conducted using the NASA Land Information System and the Land surface Verification Toolkit.

Sujay V Kumar↗
DOE OSTI2022

Generating Ectropis obliqua axenic larvae in support of functional microbiome studies

Abstract Ectropis obliqua Prout (Lepidoptera: Geometridae) is a serious leaf‐eating pest in tea gardens throughout China, with rich bacterial communities in the larval gut. Few studies have investigated whether these bacteria play an important role in growth, development, and adaptability of E. obliqua . Axenic larval models are a useful tool for the study of interactions between gut bacteria and host insects. At present, artificial diet and antibiotics are typically used to remove larval gut bacteria for study; however, this method may change the natural food of insects and the habitat provided by their host plants, and cannot completely eliminate insect gut bacteria. Therefore, in order to establish an axenic insect feeding model, we first investigated the effects of egg age, different disinfectant concentration, and treatment time on the eggs of E. obliqua through orthogonal experiments. Next, we fed E. obliqua larvae tissue‐cultured tea seedlings under aseptic conditions. Thus, we successfully generated a feeding model of gut axenic larvae in the laboratory. Based on it, we then compared the mortality of axenic and non‐axenic E. obliqua larvae infected with the entomopathogenic fungus Beauveria bassiana (Balsamo) Vuill. These results demonstrated the feasibility of this axenic larval model and that B. bassiana is a broad‐spectrum entomogenous fungus with a toxic effect on E. obliqua .

Su, Qingqing↗