Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 1,027 records · Page 57
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Dynamic Topology Reconfiguration of Boltzmann Machines on Quantum Annealers

Boltzmann machines have useful roles in deep learning applications, such as generative data modeling, initializing weights for other types of networks, or extracting efficient representations from high-dimensional data. Most Boltzmann machines use restricted topologies that exclude looping connectivity, as such connectivity creates complex distributions that are difficult to sample. We have used an open-system quantum annealer to sample from complex distributions and implement Boltzmann machines with looping connectivity. Further, we have created policies mapping Boltzmann machine variables to the quantum bits of an annealer. These policies, based on correlation and entropy metrics, dynamically reconfigure the topology of Boltzmann machines during training and improve performance.

Liu, Jeremy (ORCID:0000000172299417)↗
DOE OSTI2023

Oracle-Preserving Latent Flows

A fundamental task in data science is the discovery, description, and identification of any symmetries present in the data. We developed a deep learning methodology for the simultaneous discovery of multiple non-trivial continuous symmetries across an entire labeled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function, ensuring the desired symmetry properties. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to invariant transformations with respect to high-dimensional oracles. The method is demonstrated with several examples on the MNIST digit dataset, where the oracle is provided by the 10-dimensional vector of logits of a trained classifier. We find classes of symmetries that transform each image from the dataset into new synthetic images while conserving the values of the logits. We illustrate these transformations as lines of equal probability (“flows”) in the reduced latent space. These results show that symmetries in the data can be successfully searched for and identified as interpretable non-trivial transformations in the equivalent latent space.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

New Subgrouping of Multiple Stellar Populations in NGC 2808 Based on Low-resolution Spectroscopy

We performed low-resolution spectroscopy for the red giant branch stars in an intriguing globular cluster (GC) NGC 2808, which hosts subpopulations with extreme helium and light-element abundances. In order to trace N, C, and Ca abundance differences among subpopulations, we measured CN, CH, and Ca ii H&K spectral indices, respectively. We identified four subpopulations (G1, G2, G3, and G4) from CN and CH strength, with CN-weak/CH-strong G1, CN-intermediate/CH-strong G2, CN-strong/CH-intermediate G3, and CN-strong/CH-weak G4. Compared to [Na/O] from high-resolution spectroscopy, we show that CN index can more clearly separate G1 and G2. Since CN traces N abundance in a GC, it implies that G1 and G2 would show a larger difference in [N/Fe] compared to [Na/Fe], as predicted by chemical evolution models. Later generation stars G3 and G4, however, are better separated with high-resolution spectroscopy. We also found that G4 shows a stronger Ca ii H&K line strength compared to that of G1, but we suspect this to be a result of unusually strong He enhancement and/or Mg depletion in G4 of this GC. This work illustrates that combining low- and high-resolution spectroscopic studies can improve the separation of subpopulations in GCs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

A New Constraint on the Nuclear Equation of State from Statistical Distributions of Compact Remnants of Supernovae

Abstract Understanding how matter behaves at the highest densities and temperatures is a major open problem in both nuclear physics and relativistic astrophysics. Our understanding of such behavior is often encapsulated in the so-called high-temperature nuclear equation of state (EOS), which influences compact binary mergers, core-collapse supernovae, and other phenomena. Our focus is on the type (either black hole or neutron star) and mass of the remnant of the core collapse of a massive star. For each six candidates of equations of state, we use a very large suite of spherically symmetric supernova models to generate a sample of synthetic populations of such remnants. We then compare these synthetic populations to the observed remnant population. Our study provides a novel constraint on the high-temperature nuclear EOS and describes which EOS candidates are more or less favored by an information-theoretic metric.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

DSCOVR/EPIC-derived global hourly and daily downward shortwave and photosynthetically active radiation data at 0.1° × 0.1° resolution

Downward shortwave radiation (SW) and photosynthetically active radiation (PAR) play crucial roles in Earth system dynamics. Spaceborne remote sensing techniques provide a unique means for mapping accurate spatiotemporally continuous SW–PAR, globally. However, any individual polar-orbiting or geostationary satellite cannot satisfy the desired high temporal resolution (sub-daily) and global coverage simultaneously, while integrating and fusing multisource data from complementary satellites/sensors is challenging because of co-registration, intercalibration, near real-time data delivery and the effects of discrepancies in orbital geometry. The Earth Polychromatic Imaging Camera (EPIC) on board the Deep Space Climate Observatory (DSCOVR), launched in February 2015, offers an unprecedented possibility to bridge the gap between high temporal resolution and global coverage and characterize the diurnal cycles of SW–PAR globally. In this study, we adopted a suite of well-validated data-driven machine-learning models to generate the first global land products of SW–PAR, from June 2015 to June 2019, based on DSCOVR/EPIC data. The derived products have high temporal resolution (hourly) and medium spatial resolution (0.1°×0.1°), and they include estimates of the direct and diffuse components of SW–PAR. We used independently widely distributed ground station data from the Baseline Surface Radiation Network (BSRN), the Surface Radiation Budget Network (SURFRAD), NOAA's Global Monitoring Division and the U.S. Department of Energy's Atmospheric System Research (ASR) program to evaluate the performance of our products, and we further analyzed and compared the spatiotemporal characteristics of the derived products with the benchmarking Clouds and the Earth's Radiant Energy System Synoptic (CERES) data. We found both the hourly and daily products to be consistent with ground-based observations (e.g., hourly and daily total SWs have low biases of -3.96 and -0.71 W m -2 and root-mean-square errors (RMSEs) of 103.50 and 35.40 W m -2 , respectively). The developed products capture the complex spatiotemporal patterns well and accurately track substantial diurnal, monthly, and seasonal variations in SW–PAR when compared to CERES data. They provide a reliable and valuable alternative for solar photovoltaic applications worldwide and can be used to improve our understanding of the diurnal and seasonal variabilities of the terrestrial water, carbon and energy fluxes at various spatial scales.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Statistical emulation of a perturbed basal melt ensemble of an ice sheet model to better quantify Antarctic sea level rise uncertainties

Abstract. Antarctic ice shelves are vulnerable to warming ocean temperatures, and some have already begun thinning in response to increased basal melt rates. Sea level is therefore expected to rise due to Antarctic contributions, but uncertainties in its amount and timing remain largely unquantified. In particular, there is substantial uncertainty in future basal melt rates arising from multi-model differences in thermal forcing and how melt rates depend on that thermal forcing. To facilitate uncertainty quantification in sea level rise projections, we build, validate, and demonstrate projections from a computationally efficient statistical emulator of a high-resolution (4 km) Antarctic ice sheet model, the Community Ice Sheet Model version 2.1. The emulator is trained to a large (500-member) ensemble of 200-year-long 4 km resolution transient ice sheet simulations, whereby regional basal melt rates are perturbed by idealized (yet physically informed) trajectories. The main advantage of our emulation approach is that by sampling a wide range of possible basal melt trajectories, the emulator can be used to (1) produce probabilistic sea level rise projections over much larger Monte Carlo ensembles than are possible by direct numerical simulation alone, thereby providing better statistical characterization of uncertainties, and (2) predict the simulated ice sheet response under differing assumptions about basal melt characteristics as new oceanographic studies are published, without having to run additional numerical ice sheet simulations. As a proof of concept, we propagate uncertainties about future basal melt rate trajectories, derived from regional ocean models, to generate probabilistic sea level rise estimates for 100 and 200 years into the future.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Powered by dGen Webinar [Slides]

NLR's Powered By Webinar Series featuring NLR's dGen Modeling Tool. The Distributed Generation Market Demand (dGenTM) model simulates customer adoption of distributed energy resources for residential, commercial, and industrial entities in the United States or other countries through 2050. The model enables analysis at multiple geographic levels (national, state, and utility, or below) and offers sophistication in representation of decision-making regarding economic and behavioral considerations. Analysts have used dGen to answer questions about load forecasting and integrated resource planning, policy analysis, locational value of distributed energy resources, and more. dGen is open source, and various energy organizations - including independent system operators, regional transmission organizations, and the California Energy Commission - use the model internally.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2024

Neural Networks for Prediction of Complex Chemistry in Water Treatment Process Optimization

Water chemistry plays a critical role in the design and operation of water treatment processes. Detailed chemistry modeling tools use a combination of advanced thermodynamic models and extensive databases to predict phase equilibria and reaction phenomena. The complexity and formulation of these models preclude their direct integration in equation-oriented modeling platforms, making it difficult to use their capabilities for rigorous water treatment process optimization. Neural networks (NN) can provide a pathway for integrating the predictive capability of chemistry software into equation-oriented models and enable optimization of complex water treatment processes across a broad range of conditions and process designs. Herein, we assess how NN architecture and training data impact their accuracy and use in equation-oriented water treatment models. We generate training data using PhreeqC software and determine how data generation and sample size impact the accuracy of trained NNs. The effect of NN architecture on optimization is evaluated by optimizing hypothetical black-box desalination processes using a range of feed compositions from USGS brackish water data set, tracking the number of successful optimizations, and testing the impact of initial guess on the final solution. Our results clearly demonstrate that data generation and architecture impact NN accuracy and viability for use in equation-oriented optimization problems.

Dudchenko, Alexander V↗
DOE OSTI2020

SEASONAL PERFORMANCE SIMULATION OF A GAS-FIRED CHEMISORPTION HEAT PUMP FOR RESIDENTIAL HEATING IN COLD CLIMATE

The gas-fired chemisorption heat pump (CSHP) is a promising technology for high-efficiency cold-climate residential heating. The CSHP utilizes the heat of reversible chemical reactions between sorbent and refrigerant to extract heat from cold ambient and supply high-temperature heat to the indoors. The efficiency of CSHP depends on the ambient and heat rejection temperatures. This study evaluates the seasonal performance of a CSHP by first develop a dynamic system model to generate a performance map for various ambient and heat-supply temperatures; then the bin method is used to evaluate the CSHP seasonal performance in two cold-climate locations for space and water heating.

Yang, Zhiyao↗
DOE OSTI2021

Design and Optimization of a Gas-Cooled, Airfoil Fin Microchannel Heat Exchanger

High-performance microchannel heat exchangers are needed to supply heat for power conversion for nuclear microreactors. An airfoil fin microchannel design, constructed of Alloy 617 with helium as the working fluid, was analyzed and optimized using a design of experiments with artificial intelligence and machine learning techniques. The use of airfoil fins offers the potential to reduce pressure drop across the heat exchanger, as compared to other types of channel configurations. A framework for topology optimization of airfoil fin PCHEs has been developed that can be readily extended to different fin sizes and shapes, as well as different inlet and operating conditions, materials of construction, and working fluids. An optimization procedure was developed that employs computational fluid dynamics for a set of design points identified using Latin hypercube sampling. STAR-CCM+ was used to analyze a simplified two-channel configuration where five parameters were varied – inlet angle, fin scale, extent of staggering, transverse and longitudinal pitches. Two methods were compared for generating surrogate models – a 5D polynomial and a regression neural network. A response surface approximation was created from the surrogate models and input to a genetic algorithm. The genetic algorithm identified a set of optimal points on the Pareto front. The optimal geometry was found across six channel Reynolds numbers ranging from 1000 to 5000 to analyze how varying inlet conditions affects the optimal design. A set of optimal designs that maximizes heat transfer and minimizes pressure drop was identified, and a thermal stress analysis was performed on the optimal design. This work has developed a digital framework for the expedient topology design and evaluation of PCHE designs for gas-cooled microreactor applications. Correlations for the Nusselt number and Darcy friction factor were developed that can be useful for thermal hydraulic analyses using system codes. A thermal stress analysis was conducted and a brief discussion of the status of code cases of PCHEs for nuclear applications is given. Testing and thermomechanical modeling is needed to facilitate future code compliance of PCHEs for high pressure and high temperature applications.

42 ENGINEERING↗
DOE OSTI2021

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. Here, the framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2022

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure --- this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2022

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2023

An Interpretable Index of Social Vulnerability to Environmental Hazards

Index-based measures of social vulnerability to environmental hazards are commonly modeled from composites of population-level risk factors. These models overlook individual context in communities' experiences of environmental hazards, producing metrics that may hinder spatial decision support for mitigating and responding to hazards. This paper introduces an interpretable, high-resolution model for generating an individual-oriented social vulnerability index (IOSVI) for the United States built on synthetic populations that couples individual and social determinants of vulnerability. The IOSVI combines an individual vulnerability index (IVI) that ranks individuals in an area’s synthetic population based on intersecting risk factors, with a social vulnerability index (SVI) based on the population’s cumulative distribution of IVI scores. Interpretability of the IOSVI procedure is demonstrated through examples of national, metropolitan, and neighborhood (census tract) level spatial variation in index scores and IVI themes, as well as an exploratory analysis examining risk factors affecting a specific sub-population (military veterans) in areas of high social and environmental vulnerability.

Tuccillo, Joe↗
DOE OSTI2022

SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY

We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure - this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

Wu, Y↗
DOE OSTI2022

The LLNL nuclear data infrastructure for the GNDS data format

The next generation of nuclear data infrastructure tools at the Livermore National Laboratory (LLNL) consists of pipeline of codes that read and process nuclear data from evaluated files saved in the new GNDS (Generalised Nuclear Data Structure) nuclear data format. The processing code FUDGE (For Updating Data and Generating Evaluations) is at the front-end of this pipeline as it reads and process the evaluated data for use in downstream transport codes. FUDGE is Python based with C and C++ extensions for computationally intensive tasks. As is the case for the evaluated data, the processed output is also saved in the GNDS format and the GIDI+ API is provided as the interface between the processed data and the transport codes. GIDI+ is a C++ based suite of codes and it includes GIDI (General Interaction Data Interface), a library for reading and writing GNDS data, and MCGIDI which is the cross section lookup, and reaction and product distribution sampling interface between Monte Carlo transport codes and the GNDS data. GIDI provides methods for easy access to the multi-group processed GNDS data and this is demonstrated through its implementation in ARDRA, the LLNL deterministic transport code. The evaluation and sampling methods in MCGIDI are available as both CPU and GPU methods which facilitates the use of MCGIDI in both traditional CPU-based as well as the next generation mixed model computational architectures. This is demonstrated through the GIDI+ implementation in MERCURY, the LLNL Monte Carlo transport code. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Towards Unlocking Insights from Logbooks Using AI

Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL, and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, enable macro-analysis for root cause analysis, and facilitate problem-solving automation.

43 PARTICLE ACCELERATORS↗