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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Wet scavenging of soluble gases in DC3 deep convective storms using WRF-Chem simulations and aircraft observations

In this work, we examine wet scavenging of soluble trace gases in storms observed during the Deep Convective Clouds and Chemistry (DC3) field campaign. We conduct high-resolution simulations with the Weather Research and Forecasting model with Chemistry (WRF-Chem) of a severe storm in Oklahoma. The model represents well the storm location, size, and structure as compared with Next Generation Weather Radar reflectivity, and simulated CO transport is consistent with aircraft observations. Scavenging efficiencies (SEs) between inflow and outflow of soluble species are calculated from aircraft measurements and model simulations. Using a simple wet scavenging scheme, we simulate the SE of each soluble species within the error bars of the observations. The simulated SEs of all species except nitric acid (HNO 3 ) are highly sensitive to the values specified for the fractions retained in ice when cloud water freezes. To reproduce the observations, we must assume zero ice retention for formaldehyde (CH 2 O) and hydrogen peroxide (H 2 O 2 ) and complete retention for methyl hydrogen peroxide (CH 3 OOH) and sulfur dioxide (SO 2 ), likely to compensate for the lack of aqueous chemistry in the model. We then compare scavenging efficiencies among storms that formed in Alabama and northeast Colorado and the Oklahoma storm. Significant differences in SEs are seen among storms and species. More scavenging of HNO 3 and less removal of CH 3 OOH are seen in storms with higher maximum flash rates, an indication of more graupel mass. Graupel is associated with mixed-phase scavenging and lightning production of nitrogen oxides (NOx ), processes that may explain the observed differences in HNO 3 and CH 3 OOH scavenging.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

Hierarchical modeling of molecular energies using a deep neural network

In this work, we introduce the Hierarchically Interacting Particle Neural Network (HIP-NN) to model molecular properties from datasets of quantum calculations. Inspired by a many-body expansion, HIP-NN decomposes properties, such as energy, as a sum over hierarchical terms. These terms are generated from a neural network—a composition of many nonlinear transformations—acting on a representation of the molecule. HIP-NN achieves the state-of-the-art performance on a dataset of 131k ground state organic molecules and predicts energies with 0.26 kcal/mol mean absolute error. Finally, with minimal tuning, our model is also competitive on a dataset of molecular dynamics trajectories. In addition to enabling accurate energy predictions, the hierarchical structure of HIP-NN helps to identify regions of model uncertainty.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2003

Subgrid Scale Modeling in Solar Convection Simulations using the ASH Code

The turbulent solar convection zone has remained one of the most challenging and important subjects in physics. Understanding the complex dynamics in the solar con- vection zone is crucial for gaining insight into the solar dynamo problem. Many solar observatories have generated revealing data with great details of large scale motions in the solar convection zone. For example, a strong di erential rotation is observed: the angular rotation is observed to be faster at the equator than near the poles not only near the solar surface, but also deep in the convection zone. On the other hand, due to the wide range of dynamical scales of turbulence in the solar convection zone, both theory and simulation have limited success. Thus, cutting edge solar models and numerical simulations of the solar convection zone have focused more narrowly on a few key features of the solar convection zone, such as the time-averaged di erential rotation. For example, Brun & Toomre (2002) report computational finding of differential rotation in an anelastic model for solar convection. A critical shortcoming in this model is that the viscous dissipation is based on application of mixing length theory to stellar dynamics with some ad hoc parameter tuning. The goal of our work is to implement the subgrid scale model developed at CTR into the solar simulation code and examine how the differential rotation will be a affected as a result. Specifically, we implement a Smagorinsky-Lilly subgrid scale model into the ASH (anelastic spherical harmonic) code developed over the years by various authors. This paper is organized as follows. In x2 we briefly formulate the anelastic system that describes the solar convection. In x3 we formulate the Smagorinsky-Lilly subgrid scale model for unstably stratifed convection. We then present some preliminary results in x4, where we also provide some conclusions and future directions.

Young, Y.-N.↗
DOE OSTI2019

Non-Intrusive Inference Reduced Order Model for Fluids Using Deep Multistep Neural Network

In this effort we propose a data-driven learning framework for reduced order modeling of fluid dynamics. Designing accurate and efficient reduced order models for nonlinear fluid dynamic problems is challenging for many practical engineering applications. Classical projection-based model reduction methods generate reduced systems by projecting full-order differential operators into low-dimensional subspaces. However, these techniques usually lead to severe instabilities in the presence of highly nonlinear dynamics, which dramatically deteriorates the accuracy of the reduced-order models. In contrast, our new framework exploits linear multistep networks, based on implicit Adams–Moulton schemes, to construct the reduced system. The advantage is that the method optimally approximates the full order model in the low-dimensional space with a given supervised learning task. Moreover, our approach is non-intrusive, such that it can be applied to other complex nonlinear dynamical systems with sophisticated legacy codes. We demonstrate the performance of our method through the numerical simulation of a two-dimensional flow past a circular cylinder with Reynolds number Re = 100. The results reveal that the new data-driven model is significantly more accurate than standard projection-based approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices

Quantum computing presents a promising approach for machine learning with its capability for extremely parallel computation in high-dimension through superposition and entanglement. Despite its potential, existing quantum learning algorithms, such as Variational Quantum Circuits (VQCs), face challenges in handling more complex datasets, particularly those that are not linearly separable. What’s more, it encounters the deployability issue, making the learning models suffer a drastic accuracy drop after deploying them to the actual quantum devices. To overcome these limitations, this paper proposes a novel spatial-temporal design, namely “ST-VQC”, to integrate nonlinearity in quantum learning and improve the robustness of the learning model to noise. Specifically, ST-VQC can extract spatial features via a novel block-based encoding quantum sub-circuit coupled with a layer-wise computation quantum sub-circuit to enable temporal-wise deep learning. Additionally, a SWAP-Free physical circuit design is devised to improve robustness. These designs bring a number of hyperparameters. After a systematic analysis of the design space for each design component, an automated optimization framework is proposed to generate the ST-VQC quantum circuit. The proposed ST-VQC has been evaluated on two IBM quantum processors, ibm-cairo with 27 qubits and ibmq-lima with 7 qubits to assess its effectiveness. The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers. Moreover, on a non-linear synthetic dataset, the STVQC outperforms a linear classifier by 27.9%, while the linear classifier using classical computing outperforms the existing VQC by 15.58%.

Li, Jinyang↗
DOE OSTI2025

Machine-Learned Force Field for Molecular Dynamics Simulations of Nonequilibrium Ammonia Synthesis on Iron Catalysts

Ammonia (NH 3 ) is one of the most important industrial chemicals. The conventional NH 3 synthesis method-the Haber–Bosch process-converts atmospheric nitrogen (N 2 ) into NH 3 using H 2 with an iron (Fe) catalyst. However, this process requires high pressures (100–200 atm) and temperatures (700–800 K) near thermal equilibrium. Recently, Fe-based nanocatalysts have been reported to produce promising NH 3 yields under atmospheric pressures and temperature-modulated nonequilibrium conditions. Understanding the mechanism of nonequilibrium catalysis with programmed temperature variation could help to optimize this fully electrified and less energy-intensive process. Although reactive molecular dynamics (RMD) simulations can be a useful tool to model nonequilibrium catalytic processes, they require the development of accurate force fields (i.e., interatomic potentials). Here, we present a machine-learned (ML) force field within the Deep Potential MD (DPMD) framework, trained using periodic density functional theory (DFT) calculations, to model NH 3 synthesis on Fe catalysts with various surface adsorbates such as *N, *H, *N 2 , *H 2 , *NH, *NH 2 , and *NH 3 . Here, we generated the DFT data from static models of elementary reactions on the most stable (110) surface of body-centered cubic Fe, which then were augmented by data from constant number of particles–volume–temperature (NVT) DFT-MD trajectories at various temperatures. Finally, we utilized the fully optimized ML force field to investigate reaction dynamics at an Fe(110) surface at linearly increasing temperatures using NVT-DPMD simulations. Our simulations indicate that pulsed temperature ramping could prove favorable for NH3 synthesis. For example, we conducted ramping under multiple sets of conditions: (i) from 900 to 1200 K over periods of 0.1–0.3 ns for Fe surfaces precovered with N or NH along with H; and (ii) from 300 to 600 K over 0.1–0.3 ns for Fe surfaces precovered with NH 3 . While our simulations so far are limited to short time scales (very rapid heating), these observations shed light on the mechanism of the high NH 3 synthesis rate achieved in a novel temperature-modulated nonequilibrium catalytic reactor using pulsed heating and cooling.

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

Deep Factorization Machine Learning for Disaggregation of Transmission Load Profiles with High Penetration of Behind-The-Meter Solar

The ever-growing integration of distributed energy resources (DERs), especially behind-the-meter (BTM) solar generations, poses imperative operational challenges to system operators such as regional transmission organizations (RTOs). It is important for RTOs to effectively and accurately extract actual load profiles at the transmission level for a single node with significant BTM solar injection. This paper first illustrates the necessity of disaggregating the daily actual load profile of a single node. Furthermore, by segmenting nodes with selected timeseries features, nodes with significant BTM solar generation are identified. Lastly, a bi-level framework is proposed, comprising reference node disaggregation and DeepFM nodal disaggregation, aimed at disaggregating the nodal load profiles from which system operators require more information. By adopting a hybrid Deep Factorization Machine (DeepFM) model, the model achieve accurate results by extracting both linear and nonlinear relations between nodes in the same region and the zonal load and nodal load profile. To overcome the lack of ground truth, this paper segments the load profile into daytime, nighttime, and zero-crossing points and utilizes the latter two for evaluation purposes. The proposed disaggregation procedure is validated using real world, minute-level, normalized, and anonymized nodal data in the PJM service territory.

42 ENGINEERING↗
DOE OSTI2017

Novel Geothermal Development of Deep Sedimentary Systems in the United States

Economic and reservoir engineering models show that stratigraphic reservoirs have the potential to contribute significant geothermal power in the U.S. If the reservoir temperature exceeds about 150 – 200 °C at 2 – 4 km depth, respectively, and there is good permeability, then these resources can generate power with a levelized cost of electricity (LCOE) of close to 10 ¢/kWh (without subsidies) on a 100 MW power plant scale. There is considerable evidence from both groundwater geology and petroleum reservoir geology that relatively clean carbonates and sandstones have, and can sustain, the required high permeability to depths of at least 5 km. This paper identifies four attractive stratigraphic reservoir prospects which are all located in the eastern Great Basin, and have temperatures of 160 – 230 °C at 3 – 3.5 km depth. They are the Elko basins (Nevada), North Steptoe Valley (Nevada), Pavant Butte (Utah), and the Idaho Thrust Belt. The reservoir lithologies are Paleozoic carbonates in the first three, and Jurassic sandstone and carbonate in the Idaho Thrust Belt. All reservoir lithologies are known to have high permeability characteristics. At North Steptoe Valley and Pavant Butte, nearby transmission line options allow interconnection to the California power market. Modern techniques for drilling and developing tight oil and gas reservoirs are expected to have application to geothermal development of these reservoirs.

15 GEOTHERMAL ENERGY↗
NASA NTRS2018

Automatic Speech Recognition for Launch Control Center Communication Using Recurrent Neural Networks with Data Augmentation and Custom Language Model

Transcribing voice communications in NASA’s launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.

Chow, Edward↗
DOE OSTI2019

Augmenting C. elegans Microscopic Dataset for Accelerated Pattern Recognition

The detection of cell shape changes in 3D time-lapse images of complex tissues is an important task. However, it is a challenging and tedious task to establish a comprehensive dataset to improve the performance of deep learning models. In the paper, we present a deep learning approach to augment 3D live images of the Caenorhabditis elegans embryo, so that we can further speed up the specific structure pattern recognition. We use an unsupervised training over unlabeled images to generate supplementary datasets for further pattern recognition. Technically, we used Alex-style neural networks in a generative adversarial network framework to generate new datasets that have common features of the C. elegans membrane structure. We also made the dataset available for a broad scientific community.

Lu, Zheng↗
DOE OSTI2022

Toward designing effective exascale scientific computing workflows: experiences and best practices

Many fields within scientific computing have embraced advances in big-data analysis and machine learning, which often requires the deployment of large, distributed and complicated workflows that may combine training neural networks, performing simulations, running inference, and performing database queries and data analysis in asynchronous, parallel and pipelined execution frameworks. Such a shift has brought into focus the need for scalable, efficient workflow management solutions with reproducibility, error and provenance handling, traceability, and checkpoint-restart capabilities, among other needs. Here, we discuss challenges and best-practices for deploying exascale-generation computational science workflows on resources at the Oak Ridge Leadership Computing Facility (OLCF). We present our experiences with large-scale deployment of distributed workflows on the Summit supercomputer, including for bioinformatics and computational biophysics, materials science, and deep learning model optimization. We also present problems and solutions created by working within a Python-centric software base on traditional HPC systems, and discuss steps that will be required before the convergence of HPC, AI, and data science can be fully realized. Our results point to a wealth of exciting new possibilities for harnessing this convergence to tackle new scientific challenges.

Coletti, Mark↗
DOE OSTI2023

Application of Quantum Machine Learning to High Energy Physics Analysis at LHC using IBM Quantum Computer Simulators and IBM Quantum Computer Hardware

Our group pioneers the use of Quantum Machine Learning (QML) on High Energy Physics analysis at LHC. We have successfully employed several QML classification algorithms in the ttH (Higgs production in association with a top quark pair) and Higgs to two muons (Higgs coupling to second generation fermions), two recent LHC flagship physics analysis, on gate-model quantum computer simulators and hardware. The simulation studies have been performed with the IBM Quantum Framework, Google Tensorflow Quantum Framework, and Amazon Braket Framework, and we have achieved good classification performance that is similar to the performances of the classical machine learning methods currently used in LHC physics analyses, classical SVM, classical BDT, and classical deep neural network for example. We have also performed our studies using IBM superconducting quantum computer hardware and the performance is promising and is approaching the performance from IBM quantum simulators. Moreover, we extend our studies to other QML areas such as quantum anomaly detection and quantum generative adversarial, and some preliminary results have been obtained. Also, we have overcome the challenges of intensive computing resources in the cases of large qubits (25 qubits or more) and large numbers of events using NVIDIA cuQuantum with NERSC Perlmutter HPC. Our studies give an example that Quantum Machine Learning performs as well as its classical counterpart for realistic High Energy Physics analysis datasets. Furthermore, our result on noisy quantum hardware provides important validation for the result on noiseless quantum simulators.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks

Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5 m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ~343 km 2 area, and a high-resolution (5 m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

HYPHY: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics

Generating large-volume hydrodynamical simulations for cosmological observables is a computationally demanding task necessary for next-generation observations. In this work, we construct a novel fully convolutional variational autoencoder (VAE) to synthesize hydrodynamic fields conditioned on dark matter fields from N -body simulations. After training the model on a single hydrodynamical simulation, we are able to probabilistically map new dark-matter-only simulations to corresponding full hydrodynamical outputs. By sampling over the latent space of our VAE, we can generate posterior samples and study the variance of the mapping. We find that our reconstructed field provides an accurate representation of the target hydrodynamical fields as well as reasonable variance estimates. This approach has promise for the rapid generation of mocks as well as for implementation in a full inverse model of observed data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2013

Geochemical Impacts of Leaking CO 2 from Subsurface Storage Reservoirs to Unconfined and Confined Aquifers

Experimental research work has been conducted and is undergoing at Pacific Northwest National Laboratory (PNNL) to address a variety of scientific issues related with the potential leaks of the carbon dioxide (CO 2 ) gas from deep storage reservoirs. The main objectives of this work are as follows: • Develop a systematic understanding of how CO 2 leakage is likely to influence pertinent geochemical processes (e.g., dissolution/precipitation, sorption/desorption and redox reactions) in the aquifer sediments. • Identify prevailing environmental conditions that would dictate one geochemical outcome over another. • Gather useful information to support site selection, risk assessment, policy-making, and public education efforts associated with geological carbon sequestration. In this report, we present results from experiments conducted at PNNL to address research issues related to the main objectives of this effort. A series of batch and column experiments and solid phase characterization studies (quantitative x-ray diffraction and wet chemical extractions with a concentrated acid) were conducted with representative rocks and sediments from an unconfined, oxidizing carbonate aquifer, i.e., Edwards aquifer in Texas, and a confined aquifer, i.e., the High Plains aquifer in Kansas. These materials were exposed to a CO 2 gas stream simulating CO 2 gas leaking scenarios, and changes in aqueous phase pH and chemical composition were measured in liquid and effluent samples collected at pre-determined experimental times. Additional research to be conducted during the current fiscal year will further validate these results and will address other important remaining issues. Results from these experimental efforts will provide valuable insights for the development of site-specific, generation III reduced order models. In addition, results will initially serve as input parameters during model calibration runs and, ultimately, will be used to test model predictive capability and competency. The results from these investigations will provide useful information to support site selection, risk assessment, and public education efforts associated with geological, deep subsurface CO 2 storage and sequestration.

Qafoku, Nikolla P.↗
DOE OSTI2025

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm 2 aqueous organic redox flow battery

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low capacity degradation in 10 cm2 cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier for commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm 2 DHP-based AORFB by combining physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical quantities and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. These combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks the first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗
DOE OSTI2024

Spin squeezing with itinerant dipoles: A case for shallow lattices

Entangled spin squeezed states generated via dipolar interactions in lattice models provide unique opportunities for quantum enhanced sensing and are now within reach of current experiments. A critical question in this context is which parameter regimes offer the best prospects under realistic conditions. Light scattering in deep lattices can induce significant decoherence and strong Stark shifts, while shallow lattices face motional decoherence as a fundamental obstacle. Here we analyze the interplay between motion and spin squeezing in itinerant fermionic dipoles in one dimensional chains using exact matrix product state simulations. We demonstrate that shallow lattices can achieve more than 5 dB of squeezing, outperforming deep lattices by up to more than 3 dB, even in the presence of low filling, loss, and decoherence. We relate this finding to SU(2)-symmetric superexchange interactions, which keep spins aligned and protect collective correlations. We show that the optimal regime is achieved for small repulsive off-site interactions, with a trade-off between maximal squeezing and optimal squeezing time. Published by the American Physical Society 2024

Wellnitz, David (ORCID:0000000349788938)↗
DOE OSTI2019

LEMD

Deep neural network-based force field enables researchers to study materials systems of large size and/or time scale efficiently with comparable accuracy to DFT-based methods. However, such force fields, if improperly trained or mistakenly selected, could result in ill-conditioned results. This SBIR Phase I project has explored the possibility to characterize and index force fields in Deep potential theme by quantizing local atomic environments of atoms in a simulation system. This project has also demonstrated the feasibility of building a public accessible web infrastructure providing high quality machine learning algorithm-based force field for next generation materials modeling and simulation to accelerate the study and discovery of new energy-related materials.

Su, Ninghai↗