Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Reduced-Order Modeling of Multigroup Neutron Cross Sections for High-Temperature Gas-cooled Reactors

Abstract – Deterministic neutronics calculations rely on multigroup neutron cross section libraries, which consist of databases of tabulated values, used to calculate the neutron cross sections through multivariate linear interpolation. However, interpolation of the multidimensional cross section data becomes memory inefficient and time consuming as the number of tabulations increases, significantly slowing down the neutronics calculation, especially in the case of microscopic cross section libraries where every isotope (on the order of hundreds) has its own set of specific reactions and cross sections. In order to address this challenge, this work constructs efficient and robust reduced-order models (ROMs) of the multi-group cross sections to support the Griffin simulation of high-temperature gas-cooled reactors (HTGRs). The first part of the study investigates the linearity of the multigroup cross section data across isotopes, reaction types, and energy groups on pre-generated datasets for the purpose of dimensionality reduction. Secondly, a down-selection of ROM techniques is presented on representative classical machine learning (ML) techniques, including variants of linear regression, kernel-based methods, tree-based algorithms, and artificial neural networks. The selection criteria jointly consider the memory efficiency, predictive accuracy, prediction speed, and scalability in comparison to the multidimensional interpolation. Among all the ML techniques, deep neural networks (DNNs) have proven to be the best selection with sufficient accuracy, high robustness, good memory efficiency, great scalability, and superior flexibility. DNNs have been trained for all isotopes in this work and systematic Griffin testing is ongoing to ensure the feasibility of this ROM technique for predicting cross section and reducing memory requirements without a significant sacrifice in computational performance.

42 - ENGINEERING↗
DOE OSTI2022

Non‐Linear Dimensionality Reduction With a Variational Encoder Decoder to Understand Convective Processes in Climate Models

Abstract Deep learning can accurately represent sub‐grid‐scale convective processes in climate models, learning from high resolution simulations. However, deep learning methods usually lack interpretability due to large internal dimensionality, resulting in reduced trustworthiness in these methods. Here, we use Variational Encoder Decoder structures (VED), a non‐linear dimensionality reduction technique, to learn and understand convective processes in an aquaplanet superparameterized climate model simulation, where deep convective processes are simulated explicitly. We show that similar to previous deep learning studies based on feed‐forward neural nets, the VED is capable of learning and accurately reproducing convective processes. In contrast to past work, we show this can be achieved by compressing the original information into only five latent nodes. As a result, the VED can be used to understand convective processes and delineate modes of convection through the exploration of its latent dimensions. A close investigation of the latent space enables the identification of different convective regimes: (a) stable conditions are clearly distinguished from deep convection with low outgoing longwave radiation and strong precipitation; (b) high optically thin cirrus‐like clouds are separated from low optically thick cumulus clouds; and (c) shallow convective processes are associated with large‐scale moisture content and surface diabatic heating. Our results demonstrate that VEDs can accurately represent convective processes in climate models, while enabling interpretability and better understanding of sub‐grid‐scale physical processes, paving the way to increasingly interpretable machine learning parameterizations with promising generative properties.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Surrogate Model of Flexible Research Platform EnergyPlus Models to Enable Sensitivity Analysis

This letter report describes the surrogate models developed from the EnergyPlus model of Oak Ridge National Laboratory’s Flexible Research Platform. Two data-driven black-box models were developed, and the outputs of the surrogate models were compared with the EnergyPlus model. The two models developed are a multilayer perceptron deep learning model, and a long short-term memory (LSTM) neural network model. The three factors for selecting the black-box models are scalability, computation time, and accuracy. A total of 107 input variables were the dominant variables in determining the outputs of building energy consumptions and thermal comfort. A total of 54 output variables were identified as the prediction targets, including the system- and zone-level outputs. The large set of the simulation cases were generated by integrating sensor errors into an emulator based on EnergyPlus and Python EMS, which includes advanced control sequences from ASHRAE Guideline 36-2018: High-Performance Sequences of Operation. The surrogate models were developed based on a set of large-scale simulation runs (i.e., 4,000 runs) on a cloud platform. The comparison analysis shows that the two black-box models had good accuracy for predicting new outputs for sensitivity analysis using the root mean square error metric. As a next step, the developed surrogate models will be used to perform sensitivity analysis for different sensor impacts (e.g., sensor types, sensor locations).

42 ENGINEERING↗
DOE OSTI2021

Artificial Intelligence for Autonomous Molecular Design: A Perspective

Domain-aware artificial intelligence has been increasingly adopted in recent years to expedite molecular design in various applications, including drug design and discovery. Recent advances in areas such as physics-informed machine learning and reasoning, software engineering, high-end hardware development, and computing infrastructures are providing opportunities to build scalable and explainable AI molecular discovery systems. This could improve a design hypothesis through feedback analysis, data integration that can provide a basis for the introduction of end-to-end automation for compound discovery and optimization, and enable more intelligent searches of chemical space. Several state-of-the-art ML architectures are predominantly and independently used for predicting the properties of small molecules, their high throughput synthesis, and screening, iteratively identifying and optimizing lead therapeutic candidates. However, such deep learning and ML approaches also raise considerable conceptual, technical, scalability, and end-to-end error quantification challenges, as well as skepticism about the current AI hype to build automated tools. To this end, synergistically and intelligently using these individual components along with robust quantum physics-based molecular representation and data generation tools in a closed-loop holds enormous promise for accelerated therapeutic design to critically analyze the opportunities and challenges for their more widespread application. This article aims to identify the most recent technology and breakthrough achieved by each of the components and discusses how such autonomous AI and ML workflows can be integrated to radically accelerate the protein target or disease model-based probe design that can be iteratively validated experimentally. Taken together, this could significantly reduce the timeline for end-to-end therapeutic discovery and optimization upon the arrival of any novel zoonotic transmission event. Our article serves as a guide for medicinal, computational chemistry and biology, analytical chemistry, and the ML community to practice autonomous molecular design in precision medicine and drug discovery.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

DuctGPT: A Generative Transformer for Forward Screening of Ductile Refractory Multi-Principal Element Alloys

Designing ductile materials for extreme environments such as fusion reactors requires a deep understanding of the complex interplay between electronic structure, mechanical stability, and wide compositional space. Here, in this work, we introduce DuctGPT, a physics-informed, GPT-powered machine learning platform that enables rapid and accurate prediction of ductility across a wide range of refractory multi-principal element alloys (MPEAs). Trained on both experimental and high-fidelity computational data, DuctGPT integrates descriptors such as density of states at the Fermi level, elastic constants, and valence electron concentration to capture the fundamental mechanisms governing ductile versus brittle behavior. Using this framework, we screen over 1000 compositions in of body-centered cubic (BCC) MPEAs, including two new alloy classes, i.e., NbTa-rich (NbTa $>$ 50 at.%) NbTa-Ti-V and W-rich ($>$ 50 at.%) W-Ti-V MPEAs, to rapidly identify promising alloy compositions with enhanced ductility. Validation against experimental data confirms the model's ability to predict ductility with high fidelity and low uncertainty. By leveraging conversational AI and robust physical modeling, DuctGPT provides a blueprint for the next generation of alloy design assistants, enabling human-AI collaboration in the accelerated discovery of ductile, high-performance materials for fusion, aerospace, and advanced manufacturing.

AI/ML↗
DOE OSTI2022

Platform for probing radiation transport properties of hydrogen at conditions found in the deep interiors of red dwarfs

We describe an experimental concept at the National Ignition Facility for specifically tailored spherical implosions to compress hydrogen to extreme densities (up to ∼800× solid density, electron number density ne∼4×1025 cm−3) at moderate temperatures (T∼200 eV), i.e., to conditions, which are relevant to the interiors of red dwarf stars. The dense plasma will be probed by laser-generated x-ray radiation of different photon energy to determine the plasma opacity due to collisional (free–free) absorption and Thomson scattering. The obtained results will benchmark radiation transport models, which in the case for free–free absorption show strong deviations at conditions relevant to red dwarfs. This very first experimental test of free–free opacity models at these extreme states will help to constrain where inside those celestial objects energy transport is dominated by radiation or convection. Moreover, our study will inform models for other important processes in dense plasmas, which are based on electron–ion collisions, e.g., stopping of swift ions or electron–ion temperature relaxation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Deciphering the Scattering of Mechanically Driven Polymers Using Deep Learning

Here, we present a deep learning approach for analyzing two-dimensional scattering data of semiflexible polymers under external forces. In our framework, scattering functions are compressed into a three-dimensional latent space using a Variational Autoencoder (VAE), and two converter networks establish a bidirectional mapping between the polymer parameters (bending modulus, stretching force, and steady shear) and the scattering functions. The training data are generated using off-lattice Monte Carlo simulations to avoid the orientational bias inherent in lattice models, ensuring robust sampling of polymer conformations. The feasibility of this bidirectional mapping is demonstrated by the organized distribution of polymer parameters in the latent space. By integrating the converter networks with the VAE, we obtain a generator that produces scattering functions from given polymer parameters and an inferrer that directly extracts polymer parameters from scattering data. While the generator can be utilized in a traditional least-squares fitting procedure, the inferrer produces comparable results in a single pass and operates 3 orders of magnitude faster. This approach offers a scalable automated tool for polymer scattering analysis and provides a promising foundation for extending the method to other scattering models, experimental validation, and the study of time-dependent scattering data.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗
DOE OSTI2021

A HPC Theory-Guided Machine Learning Cyberinfrastructure for Communicating Hydrometeorological Data Across Scales

High-resolution predictions of hydrometeorological variables are critical for supporting hydropower generation decisions and flood control at hydroelectric power plants. Traditional climate and hydrologic models rely on the numerical simulation of detailed physical processes. Therefore, running these simulations is time-, labor-, and computation-intensive. Improving the spatial and temporal resolution in these modeling outputs could lead to cubic increases in both the simulation time and computational demands, rendering high-resolution hydrometeorological predictions expensive and impractical. Many past studies apply the super resolution (SR) technique to downscale climate models using deep learners. However, deep learners are deemed “black-boxes,” as their derivation processes from low-resolution outputs to high-resolution outputs are often hidden. Their results are difficult for domain scientists to interpret and validate. Thus, there is a need for an exploratory machine learning approach that can partially integrate domain-specific theory and knowledge into the data-driven mapping process between simulation outputs of different spatial scales. The domain-specific theory and knowledge can be incorporated into the data model through an inductive approach in which process-related environmental variables are used and analyzed as key drivers (i.e., environmental surrogates) to reflect the complex physical processes. Many of these variables, such as land use land cover, soil types, topography, digital elevation, air temperature, and various watershed characteristics, can be directly measured through sensors or remote sensing techniques. Additionally, SR applications that can downscale hydrological and hydrodynamics models to efficiently produce high-resolution (1 m) flood depth grids are still rare. Since the flood depth grid can be used to support critical decisions for flood control operation at hydroelectric power plants, it is crucial to enable an SR-based capability for interpolating high-resolution flood inundation maps.

13 HYDRO ENERGY↗
DOE OSTI2024

Using AI for Wave-front Estimation with the Rubin Observatory Active Optics System

Abstract The Vera C. Rubin Observatory will, over a period of 10 yr, repeatedly survey the southern sky. To ensure that images generated by Rubin meet the quality requirements for precision science, the observatory will use an active-optics system (AOS) to correct for alignment and mirror surface perturbations introduced by gravity and temperature gradients in the optical system. To accomplish this, Rubin will use out-of-focus images from sensors located at the edge of the focal plane to learn and correct for perturbations to the wave front. We have designed and integrated a deep-learning (DL) model for wave-front estimation into the AOS pipeline. In this paper, we compare the performance of this DL approach to Rubin’s baseline algorithm when applied to images from two different simulations of the Rubin optical system. We show the DL approach is faster and more accurate, achieving the atmospheric error floor both for high-quality images and low-quality images with heavy blending and vignetting. Compared to the baseline algorithm, the DL model is 40× faster, the median error 2× better under ideal conditions, 5× better in the presence of vignetting by the Rubin camera, and 14× better in the presence of blending in crowded fields. In addition, the DL model surpasses the required optical quality in simulations of the AOS closed loop. This system promises to increase the survey area useful for precision science by up to 8%. We discuss how this system might be deployed when commissioning and operating Rubin.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1987

Interseismic deformation for normal fault earthquakes

Comparison between the coseismic vertical deformation associated with normal fault earthquakes and permanent deformation indicated by geologic structure indicates that large deformation must occur during the period between earthquakes. When sufficient geodetic and geologic information is available it is possible to estimate the spatial character of this interseismic deformation. A case in point is the 1983 Borah Peak, Idaho earthquake. This normal fault earthquake produced roughly 5 times as much basin subsidence as it did uplift of the adjacent mountain ranges. In contrast, geophysical and geological observations show that the basin is roughly as deep as the bounding range is high. A similar normal fault event in the Basin and Range, the 1959 Hebgen Lake earthquake, was also accompanied by substantially larger subsidence than uplift. In this case, postseismic geodetic measurements show broad regional uplift with a spatial pattern which is roughly consistent with that proposed for the Borah Peak event. Modeling suggests that postseismic viscoelastic relaxation and strain accumulation in an elastic lithosphere overlying a viscoelastic asthenosphere are possible physical mechanisms to generate interseismic uplift. These mechanisms may be the contemporary expression of those processes responsible for the high elevation of the Basin and Range Province.

Reilinger, Robert↗
NASA NTRS1992

Miniature X-band GaAs MMIC analog and bi-phase modulators for spaceborne communications applications

The design concepts, analyses, and the development of GaAs monolithic microwave integrated circuit (MMIC) linear-phase and digital modulators for the next generation of spaceborne communications systems are summarized. The design approach uses a very compact lumped-element, quadrature hybrid, and MESFET-varactors to provide low-loss and well-controlled phase performance for deep-space transponder (DST) applications. The measured results of the MESFET-diode show a capacitance range of 2:1 under reverse bias, and a Q of 38 at 10 GHz. Three cascaded sections of hybrid-coupled reflection phase shifters have been modeled and simulations performed to provide an X-band (8415 +/- 50 MHz) DST phase modulator with +/-2.5 radians of peak phase deviation.

Mysoor, Narayan R.↗
NASA NTRS1997

Evolution of Nonlinear Internal Waves in China Seas

Synthetic Aperture Radar (SAR) images from ERS-I have been used to study the characteristics of internal waves of Taiwan in the East China Sea, and east of Hainan Island in the South China Sea. Rank-ordered packets of internal solitons propagating shoreward from the edge of the continental shelf were observed in the SAR images. Based on the assumption of a semidiurnal tidal origin, the wave speed can be estimated and is consistent with the internal wave theory. By using the SAR images and hydrographic data, internal waves of elevation have been identified in shallow water due to a thicker mixed layer as compared with the bottom layer on the continental shelf. The generation mechanism includes the influences of the tide and the Kuroshio intrusion across the continental shelf for the formations of elevation internal waves. The effects of water depth on the evolution of solitons and wave packets are modeled by nonlinear Kortweg-deVries (KdV) type equation and linked to satellite image observations. The numerical calculations of internal wave evolution on the continental shelf have been performed and compared with the SAR observations. For a case of depression waves in deep water, the solitons first disintegrate into dispersive wave trains and then evolve to a packet of elevation waves in the shallow water area after they pass through a turning point of approximately equal layer depths has been observed in the SAR image and simulated by numerical model.

Liu, Antony K.↗
DOE OSTI2021

xSDK: Building an ecosystem of highly efficient math libraries for exascale

Current efforts to build increasingly powerful computer architectures are opening up new avenues for more complex and higher fidelity simulations coupled with data analytics and learning, leading to new scientific insights and deeper understanding. At one extreme, exascale computers will be much faster than previous computer generations (performing 10 18 operations per second—that is, 1,000 times faster than petascale). To achieve these performance improvements, computer architectures are becoming increasingly complex, with deep memory hierarchies, very high node and core counts, and heterogeneous features such as graphics processing units (GPUs). Such architectural changes impact the full breadth of computing scales, as heterogeneity pervades even current-generation laptops, workstations, and moderate-sized clusters. While emerging advanced architectures provide unprecedented opportunities, they also present significant challenges for developers of scientific applications, such as multiphysics and multiscale codes, who must adapt their software to handle disruptive changes in architectures and new programming models that have not yet stabilized. Developers must consider increasing concurrency while reducing communication and synchronization, and other complexities such as the potential for using mixed precision to leverage the compute power available in low-precision tensor cores. On one hand, developers must implement new scientific capabilities, which in turn increase code complexity. On the other hand, the codes must be ported to new architectures, requiring the inclusion of new programming models and the restructuring of code to achieve good performance. Addressing these issues is beyond the capability of any single person or team—leading to the need for collaboration among many teams, who encapsulate their expertise in reusable software and work together to create sustainable software ecosystems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Deep learning-enabled probing of irradiation-induced defects in time-series micrographs

Modeling time-series data with convolutional neural networks (CNNs) requires building a model to learn in batches as opposed to training sequentially. Coupling CNNs with in situ or operando techniques opens the possibility of accurately segmenting dynamic reactions and mass transport phenomena to understand how materials behave under the conditions in which they are used. In this article, in situ ion irradiation transmission electron microscopy (TEM) images are used as inputs into the CNN to assess the defect generation rate, defect cluster density, and saturation of defects. We then use the output segmentation maps to correlate with conventional TEM micrographs to assess the model’s ability to detail nanoscale interactions. Next, we discuss the implications of preprocessing and hyperparameters on model variability, accuracy when expanded to other datasets, and the role of regularization when controlling model variance. Ultimately, we eliminate human bias when extrapolating physical metrics, speed up analysis time, decouple reactions that happen at 100 ms intervals, and deploy models that are both accurate and transferable to similar experiments.

Burns, Kory (ORCID:0000000158019909)↗
DOE OSTI2023

Building an EPA Class VI Permit Application

Summary To accelerate the commercialization of carbon capture and storage (CCS), the US Department of Energy (US DOE) is building on decades of characterization efforts and pilot-scale projects through their CarbonSAFE program. Administered through their National Energy Technology Laboratory, this program seeks to bring fully integrated projects to the sector that can store more than 50 million tonnes of CO2 over a 30-year period. The program, which was enacted before the enhancement of Internal Revenue Code Section 45Q, is in the capture assessment, characterization, and permitting phase. The objectives of this paper are to discuss (a) the injection permitting requirements of the CarbonSAFE projects; (b) information gathering in support of the permit; (c) the timelines of field development and permit-related activities; (d) the major technical components of the field development plan; and (e) early feedback from the regulators toward acceptance of the permit. In Mississippi, more than 30,000 acres have been characterized by six deep characterization wells, a deep groundwater well, and 92 line miles of 2D seismic as part of the CarbonSAFE Project ECO2S. During the acquisition of seismic data, all receiver lines were live, which resulted in the generation of a pseudo-3D seismic design. The incorporation of a 3D seismic survey was not included as part of this project due to logistical difficulties presented by the undulating, wooded surface terrain. A suite of openhole geophysical logs was taken from each well, allowing for a detailed interpretation of prospective storage reservoirs and confining intervals to complement the analysis carried out on the 290 ft of a whole core that was cut through the prospective confining zone and storage reservoir. The detailed geologic and reservoir data were assembled and entered into a 3D model to assess the injection capacity and the area of review (AoR). This information fed into the detailed corrective action, monitoring, testing, and postinjection site care (PISC) modeling. The results have been exceptional. The geologic assessment has revealed three primary storage targets, ranging in depth from 3,500 ft to 6,000 ft. These storage reservoirs net 1,300 ft of sandstone, with mean porosity and permeability of 29% and 3.6 darcies, respectively. Together, these reservoirs have storage capacities that may exceed 20 million tonnes per square mile, making this a gigatonne prospect. Forward modeling of the project resulted in an AoR of 16 sq miles, injecting about 8000 t/d, for 30 years, via two deep injection wells. The excellent confining characteristics of the caprock, relatively simple geologic structure, and lack of historical well drilling activity in this area provide excellent containment of the injected CO2. Based on this work, the project has proposed 20 years of PISC. To date, only two US CO2 injection permits have been granted. These projects relied on a singular capture point feeding a singular sequestration point (source to sink), and considerations have not been made to garner CO2 emissions from other industrial sources. The Kemper County Storage Complex is a first-of-its-kind storage hub concept that looks to develop an area capable of storing significant quantities of CO2 from the region. Also, this work will show how characterization efforts, geological and numerical modeling efforts, and plan development were constructed in support of permit and incentives acceptance.

Energy & Fuels↗
DOE OSTI2023

Machine learning the spectral function of a hole in a quantum antiferromagnet

Understanding charge motion in a background of interacting quantum spins is a fundamental problem in quantum many-body physics. The most extensively studied model for this problem is the so-called t-t'-t''-J model, where the determination of the parameter t' in the context of cuprate superconductors is challenging. Here we present a theoretical study of the spectral functions of a mobile hole in the t-t'-t''-J model using two machine-learning techniques: K-nearest neighbor regression (KNN) and a feed-forward neural network (FFNN). We employ the self-consistent Born approximation to generate a dataset of about 1.3 x 10 5 spectral functions. Here we show that, for the forward problem, both methods allow for the accurate and efficient prediction of spectral functions, allowing, e.g., rapid searches through parameter space. Furthermore, we find that for the inverse problem (inferring Hamiltonian parameters from spectra), the FFNN can, but the KNN cannot, accurately predict the model parameters using merely the density of states. Our results suggest that it may be possible to use deep-learning methods to predict materials parameters from experimentally measured spectral functions.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

Improving neutrino oscillation measurements through event classification

Precise neutrino energy reconstruction is essential for next-generation long-baseline oscillation experiments, yet current methods remain limited by large uncertainties in neutrino-nucleus interaction modeling. Even so, it is well established that different interaction channels produce systematically varying amounts of missing energy and therefore yield different reconstruction performance–information that standard calorimetric approaches do not exploit. We introduce a strategy that incorporates this structure by classifying events according to their underlying interaction type prior to energy reconstruction. Using supervised machine-learning techniques trained on labeled generator events, we leverage intrinsic kinematic differences among quasielastic scattering, meson-exchange current, resonance production, and deep-inelastic scattering processes. A cross-generator testing framework demonstrates that this classification approach is robust to microphysics mismodeling and, when applied to a simulated DUNE 𝜈 𝜇 disappearance analysis, yields improved accuracy and sensitivity at the 10%–20% level. These results highlight a practical path toward reducing reconstruction-driven systematics in future oscillation measurements.

Ellis, Sebastian A. R. [King's College, London (Un↗
DOE OSTI2020

Status and Plan of DUNE at Fermilab

The discovery and the solid confirmation of neutrino flavor oscillation have been made throughout late 1990 to 2000s. Such oscillation is the clear proof of non-zero neutrino mass since this is caused by the fact that the neutrino mass eigenstates differ from that of the flavor. The neutrinos in the Standard Model, however, are massless leptons, and thus the neutrino flavor oscillation necessitates either the Standard Model to be significantly modified or a new theoretical paradigm to describe the universe better. In order to provide experimental information, it is essential for the properties of the neutrino oscillation be well understood through precision measurements of oscillation parameters, including the mixing angles, determination of the mass hierarchy between the three mass eigenstates and determination of the CP phase (Delta_CP) between neutrino and anti-neutrino oscillations. Among the several next generation neutrino experiments, this presentation covers the Deep Underground Neutrino Experiment (DUNE) which, with the high intensity neutrino beam facility, will help accomplish these goals. In this report, I will discuss the current status and plan of the DUNE experiment, including the results of the detector performance studies from the large scale prototype detectors operating at CERN and the timeline for construction and data taking of the experiment, as well as its physics prospects.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗