Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Generative Model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

Recovering Topology of Nested Volumes Represented by Single Closed Surfaces

As scientific computing abilities continue to advance, so too have the efforts to model and simulate highly complex geometries in radiation environments. Modeling has advanced from primitive constructive solid geometry (CSG) to voxelized models, and now to high fidelity polygon mesh models. While polygon mesh surface models are very accurate, most Monte Carlo codes do not allow for their direct use. Often they are converted to voxel or tetrahedral mesh models and then used with the physics codes. The Direct Accelerated Geometry Monte Carlo (DAGMC) software package has the ability to efficiently run transport calculations directly on tessellated surface models. Typically the surface meshes used for DAGMC calculations come from CAD-based geometry models generated by solid modeling software. In some cases geometries of interest, like human phantoms, are generated by other means and may not contain all of the necessary information for particle transport. For example, mesh geometries in the OBJ file format contain vertex and connectivity data for each surface, but do not have any information about surface topology. These types of file formats necessitate a tool that can build a hierarchy of surfaces and reconstruct the topological information. The generate hierarchy tool was developed for this purpose. The following summary will explain the algorithm behind the tool, describe a test case, and finally demonstrate a real-world application of the tool with an MCNP5 calculation that directly uses a polygon mesh human phantom.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2018

Model for Generation of Neutrons in a Compact Diode with Laser-Plasma Anode and Suppression of Electron Conduction Using a Permanent Cylindrical Magnet

A model for acceleration of deuterons and generation of neutrons in a compact laser-plasma diode with electron isolation using magnetic field generated by a hollow cylindrical permanent magnet is presented. Experimental and computer-simulated neutron yields are compared for the diode structure under study. An accelerating neutron tube with a relatively high neutron generation efficiency can be constructed using suppression of electron conduction with the aid of a magnet placed in the vacuum volume.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation

We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

Godoy, William↗
DOE OSTI2023

De novo design of protein structure and function with RFdiffusion

Abstract There has been considerable recent progress in designing new proteins using deep-learning methods 1–9 . Despite this progress, a general deep-learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher-order symmetric architectures, has yet to be described. Diffusion models 10,11 have had considerable success in image and language generative modelling but limited success when applied to protein modelling, probably due to the complexity of protein backbone geometry and sequence–structure relationships. Here we show that by fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of designed symmetric assemblies, metal-binding proteins and protein binders. The accuracy of RFdiffusion is confirmed by the cryogenic electron microscopy structure of a designed binder in complex with influenza haemagglutinin that is nearly identical to the design model. In a manner analogous to networks that produce images from user-specified inputs, RFdiffusion enables the design of diverse functional proteins from simple molecular specifications.

Science & Technology - Other Topics↗
DOE OSTI2025

A comparison of probabilistic generative frameworks for molecular simulations

Generative artificial intelligence is now a widely used tool in molecular science. Despite the popularity of probabilistic generative models, numerical experiments benchmarking their performance on molecular data are lacking. Here, in this work, we introduce and explain several classes of generative models, broadly sorted into two categories: flow-based models and diffusion models. We select three representative models: neural spline flows, conditional flow matching, and denoising diffusion probabilistic models, and examine their accuracy, computational cost, and generation speed across datasets with tunable dimensionality, complexity, and modal asymmetry. Our findings are varied, with no one framework being the best for all purposes. In a nutshell, (i) neural spline flows do best at capturing mode asymmetry present in low-dimensional data, (ii) conditional flow matching outperforms other models for high-dimensional data with low complexity, and (iii) denoising diffusion probabilistic models appear the best for low-dimensional data with high complexity. Our datasets include a Gaussian mixture model and the dihedral torsion angle distribution of the Aib9 peptide, generated via a molecular dynamics simulation. We hope our taxonomy of probabilistic generative frameworks and numerical results may guide model selection for a wide range of molecular tasks.

Artificial intelligence↗
DOE OSTI2016

A kinetic model for stress generation in thin films grown from energetic vapor fluxes

We have developed a kinetic model for residual stress generation in thin films grown from energetic vapor fluxes, encountered, e.g., during sputter deposition. The new analytical model considers sub-surface point defects created by atomic peening, along with processes treated in already existing stress models for non-energetic deposition, i.e., thermally activated diffusion processes at the surface and the grain boundary. According to the new model, ballistically induced sub-surface defects can get incorporated as excess atoms at the grain boundary, remain trapped in the bulk, or annihilate at the free surface, resulting in a complex dependence of the steady-state stress on the grain size, the growth rate, as well as the energetics of the incoming particle flux. We compare calculations from the model with in situ stress measurements performed on a series of Mo films sputter-deposited at different conditions and having different grain sizes. The model is able to reproduce the observed increase of compressive stress with increasing growth rate, behavior that is the opposite of what is typically seen under non-energetic growth conditions. On a grander scale, this study is a step towards obtaining a comprehensive understanding of stress generation and evolution in vapor deposited polycrystalline thin films.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2016

Measuring and Modeling Bipartite Graphs with Community Structure

Network science is a powerful tool for analyzing complex systems in fields ranging from sociology to engineering to biology. This paper is focused on generative models of bipartite graphs, also known as two-way graphs. We propose two generative models that can be easily tuned to reproduce the characteristics of real-world networks, not just qualitatively, but quantitatively. The measurements we consider are the degree distributions and the bipartite clustering coefficient, which we refer to as the metamorphosis coefficient. We define edge, node, and degreewise metamorphosis coefficients, enabling a more detailed understand of the bipartite community structure. Our proposed bipartite Chung-Lu model is able to reproduce real-world degree distributions, and our proposed bipartite “BTER” model reproduces both the degree distributions as well as the degreewise metamorphosis coefficients. We demonstrate the effectiveness of these models on several real-world data sets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

Methods and Results for Standard Model Event Generation at $\sqrt{s}$ = 14 TeV, 33 TeV and 100 TeV Proton Colliders (A Snowmass Whitepaper)

This document describes the novel techniques used to simulate the common Snowmass 2013 En- ergy Frontier Standard Model backgrounds for future hadron colliders. The purpose of many Energy Frontier studies is to explore the reach of high luminosity data sets at a variety of high energy collid- ers. The generation of high statistics samples which accurately model large integrated luminosities for multiple center-of-mass energies and pile-up environments is not possible using an unweighted event generation strategy | an approach which relies on event weighting was necessary. Even with these improvements in e ciency, extensive computing resources were required. This document de- scribes the speci c approach to event generation using Madgraph5 to produce parton-level processes, followed by parton showering and hadronization with Pythia6, and pile-up and detector simulation with Delphes3. The majority of Standard Model processes for pp interactions at √s = 14, 33, and 100 TeV with 0, 50, and 140 additional pile-up interactions are publicly available.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2010

Cost and Performance Assumptions for Modeling Electricity Generation Technologies

The goal of this project was to compare and contrast utility scale power plant characteristics used in data sets that support energy market models. Characteristics include both technology cost and technology performance projections to the year 2050. Cost parameters include installed capital costs and operation and maintenance (O&M) costs. Performance parameters include plant size, heat rate, capacity factor or availability factor, and plant lifetime. Conventional, renewable, and emerging electricity generating technologies were considered. Six data sets, each associated with a different model, were selected. Two of the data sets represent modeled results, not direct model inputs. These two data sets include cost and performance improvements that result from increased deployment as well as resulting capacity factors estimated from particular model runs; other data sets represent model input data. For the technologies contained in each data set, the levelized cost of energy (LCOE) was also evaluated, according to published cost, performance, and fuel assumptions.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2019

Broadband (0–5 Hz) Fully Deterministic 3D Ground‐Motion Simulations of a Magnitude 7.0 Hayward Fault Earthquake: Comparison with Empirical Ground‐Motion Models and 3D Path and Site Effects from Source Normalized Intensities

We report on high‐performance computing (HPC) fully deterministic simulation of ground motions for a moment magnitude (⁠Mw⁠) 7.0 scenario earthquake on the Hayward fault resolved to 5 Hz using the SW4 finite‐difference code. We computed motions obeying physics‐based 3D wave propagation at a regional scale with an Mw 7.0 kinematic rupture model generated following Graves and Pitarka (2016). Both plane‐layered (1D) and 3D Earth models were considered, with 3D subsurface material properties and topography interpolated from a model of the U.S. Geological Survey (USGS). The resulting ground‐motion intensities cover a broader frequency range than typically considered in regional‐scale simulations, including higher frequencies relevant for engineering analysis of structures. Median intensities for sites across the domain are within the reported between‐event uncertainties (⁠τ⁠) of ground‐motion models (GMMs) across spectral periods 0.2–10 s (frequencies 0.1–5 Hz). The within‐event standard deviation ϕ of ground‐motion intensity measurement residuals range 0.2–0.5 natural log units with values consistently larger for the 3D model. Source‐normalized ratios of intensities (3D/1D) reveal patterns of path and site effects that are correlated with known geologic structure. These results demonstrate that earthquake simulations with fully deterministic wave propagation in 3D Earth models on HPC platforms produce broadband ground motions with median and within‐event aleatory variability consistent with empirical models. Systematic intensity variations for the 3D model caused by path and site effects suggest that these epistemic effects can be estimated and removed to reduce variation in site‐specific hazard estimates. This study motivates future work to evaluate the validity of the USGS 3D model and investigate the development of path and site corrections by running more scenarios.

Rodgers, Arthur J.↗
DOE OSTI2020

Multiple-objective Reinforcement Learning for Inverse Design and Identification

The aim of inverse chemical design is to develop new molecules with given optimized molecular properties or objectives. Recently, generative deep learning (DL) networks are considered as the state-of-the-art in inverse chemical design and have achieved early success in generating molecular structures with desired properties in the pharmaceutical and material chemistry fields. However, satisfying a large number (> 10 objectives) of molecular objectives is a limitation of current generative models. To improve the model’s ability to handle a large number of molecule design objectives, we developed a Reinforcement Learning (RL) based generative framework to optimize chemical molecule generation. Our use of Curriculum Learning (CL) to fine-tune the pre-trained generative network allowed the model to satisfy up to 21 objectives and increase the generative network’s robustness. The experiments show that the proposed multiple-objective RL-based generative model can correctly identify unknown molecules with an 83% to 100% success rate, compared to the baseline approach of 0%. Additionally, this proposed generative model is not limited to just chemistry research challenges; we anticipate that problems that utilize RL with multiple objectives will benefit from this framework.

reinforcement learning, generative model, inverse ↗
DOE OSTI2015

Automatic building information model query generation

Energy efficient building design and construction calls for extensive collaboration between different subfields of the Architecture, Engineering and Construction (AEC) community. Performing building design and construction engineering raises challenges on data integration and software interoperability. Using Building Information Modeling (BIM) data hub to host and integrate building models is a promising solution to address those challenges, which can ease building design information management. However, the partial model query mechanism of current BIM data hub collaboration model has several limitations, which prevents designers and engineers to take advantage of BIM. To address this problem, we propose a general and effective approach to generate query code based on a Model View Definition (MVD). This approach is demonstrated through a software prototype called QueryGenerator. In conclusion, by demonstrating a case study using multi-zone air flow analysis, we show how our approach and tool can help domain experts to use BIM to drive building design with less labour and lower overhead cost.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2010

Cost and Performance Assumptions for Modeling Electricity Generation Technologies

The goal of this project was to compare and contrast utility scale power plant characteristics used in data sets that support energy market models. Characteristics include both technology cost and technology performance projections to the year 2050. Cost parameters include installed capital costs and operation and maintenance (O&M) costs. Performance parameters include plant size, heat rate,capacity factor or availability factor, and plant lifetime. Conventional, renewable, and emerging electricity generating technologies were considered. Six data sets, each associated with a different model, were selected. Two of the data sets represent modeled results, not direct model inputs. These two data sets include cost and performance improvements that result from increased deployment aswell as resulting capacity factors estimated from particular model runs; other data sets represent model input data. For the technologies contained in each data set, the levelized cost of energy (LCOE) was also evaluated, according to published cost, performance, and fuel assumptions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Artificial intelligence-driven approaches for materials design and discovery

Materials design is an important component of modern science and technology, yet traditional approaches rely heavily on trial and error and can be inefficient. Computational techniques, enhanced by modern artificial intelligence, have reshaped the landscape of designing new materials. Among these approaches, inverse design has shown great promise in designing materials that meet specific property requirements. Here, in this Review, we present key computational advances in materials design over the past few decades. We follow the evolution of relevant materials design techniques, from high-throughput forward machine learning methods and evolutionary algorithms, to advanced artificial intelligence strategies such as reinforcement learning and deep generative models. We highlight the paradigm shift from conventional screening approaches to inverse generation driven by deep generative models. Finally, we discuss current challenges and future perspectives of materials inverse design. This Review may serve as a brief guide to the approaches, progress and outlook of designing future functional materials with technological relevance.

computational methods↗
DOE OSTI2026

Generative Thermodynamic Computing

Here, we introduce a generative modeling framework for thermodynamic computing, in which structured data are synthesized from noise by the natural time evolution of a physical system governed by Langevin dynamics. While conventional diffusion models use neural networks to perform denoising, here the information needed to generate structure from noise is encoded by the dynamics of a thermodynamic system. Training proceeds by maximizing the probability with which the computer generates the reverse of a noising trajectory, which ensures that the computer generates data with minimal heat emission. We demonstrate this framework within a digital simulation of a thermodynamic computer. If realized in analog hardware, such a system would function as a generative model that produces structured samples without the need for artificially injected noise or active control of denoising.

Whitelam, Stephen [Lawrence Berkeley National Labo↗