Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Conditional diffusion 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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Advancing set-conditional set generation: Diffusion models for fast simulation of reconstructed particles

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve as efficient surrogate models. We propose a fast emulation approach that combines simulation and reconstruction. In other words, a neural network generates a set of reconstructed objects conditioned on input particle sets. To make this possible, we advance set-conditional set generation with diffusion models. Using a realistic, generic, and public detector simulation and reconstruction package (COCOA), we show how diffusion models can accurately model the complex spectrum of reconstructed particles inside jets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

SurFE-XD (Surface curvature-driven Finite Elements model for Diffusion under eXtreme conditions)

SurFE-XD is a mesoscale finite element framework to model surface diffusion under mutliphysics environments. The code uses legacy C++ library dolphin wrapped with python in a FEniCS driven unified form language and just-in-time (JIT) compilation setting. The purpose of the release is to attract wide-ranging usage of the code along with publication supplementation to support reproducibility of scientific data. SurFE-XD has been originally conceived under the LDRD-DR funding for “High-Gradient (C-BAND) Breakdown tolerant accelerator materials project. Currently SrFE-XD support electrostatics and Thermo-elasticity driven surface diffusion kernels. Releasing the code will also enable to include contributions from other physical regimes e.g., plasticity and electrodynamics etc as well portability to GPU-based platforms.

Bagchi, Soumendu↗
DOE OSTI2020

Dirichlet absorbing boundary conditions for classical and peridynamic diffusion-type models

Diffusion-type problems in (nearly) unbounded domains play important roles in various fields of fluid dynamics, biology, and materials science. The aim of this paper is to construct accurate absorbing boundary conditions (ABCs) suitable for classical (local) as well as nonlocal peridynamic (PD) diffusion models. The main focus of the present study is on the PD diffusion formulation. The majority of the PD diffusion models proposed so far are applied to bounded domains only. In this study, we propose an effective way to handle unbounded domains both with PD and classical diffusion models. For the former, we employ a meshfree discretization, whereas for the latter the finite element method (FEM) is employed. The proposed ABCs are time-dependent and Dirichlet-type, making the approach easy to implement in the available models. The performance of the approach, in terms of accuracy and stability, is illustrated by numerical examples in 1D, 2D, and 3D.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Stability Analysis of Coupled Advection-Diffusion Models with Bulk Interface Condition

Numerical stability is of critical importance in general circulation models because it affects the design of algorithms, time to solution, and computational costs associated with the simulations, which are very expensive in practice. In this paper we extend the stability analysis for ocean-atmosphere coupling proposed in [Zhang et al., J. Sci. Comput. 84, 44(2020)] to a more realistic model that includes horizontal advection. We analyze various time-stepping strategies. We find that advection has a stabilizing effect in scenarios common to climate models when bulk interface condition and explicit flux coupling are used. We also show that our method can be used to study the stability impact of advection for other interface conditions such as Dirichlet-Neumann conditions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Using convolutional neural networks to accelerate three-dimensional coherent synchrotron radiation computations

Calculating the effects of coherent synchrotron radiation (CSR) is one of the most computationally expensive tasks in accelerator physics. Here, we use convolutional neural networks (CNNs), along with a latent conditional diffusion (LCD) model, trained on physics-based simulations to speed up calculations. Specifically, we produce the 3D CSR wakefields generated by electron bunches in circular orbit in the steady-state condition. Two datasets are used for training and testing the models: wakefields generated by three-dimensional Gaussian electron distributions and wakefields from a sum of up to 25 three-dimensional Gaussian distributions. The CNNs are able to accurately produce the 3D wakefields ∼250–1000 times faster than the numerical calculations, while the LCD achieves a gain of a factor of ∼34. We also test the extrapolation and out-of-distribution generalization ability of the models. They generalize well on distributions with larger spreads than what they were trained on but struggle with smaller spreads.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2018

A numerical hybrid model for outdoor sound propagation in complex urban environments

Noise mapping in large and dense urban areas is computationally challenging, if not impossible, with the use of conventional numerical techniques. Recently, promising results have shown the potential of energy-based models to compete with conventional numerical techniques. In this study, a hybrid full-wave/diffusion propagation model is proposed to address some of the flaws of the traditional diffusion model. The full-wave model is used for predicting sound propagation (i) near the source, where interactions between waves are important, and (ii) outside the cluttered environment, where free-field-like conditions apply. Finally, the diffusion model is used in regions where diffusion conditions are met.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Hybrid learning techniques for scientific data reduction with performance guarantees

The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Final report- UFL - RAPIDS2: A SciDAC Institute for Computer Science, Data, and Artificial Intelligence

The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics

Abstract Background The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain‐relevant assessments via the analysis of relevant image statistics. Methods As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512 512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM‐generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results Fifty‐eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top‐ranked submission employed a conditional latent diffusion model, whereas the joint runners‐up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID‐based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions This Grand Challenge highlighted the need for domain‐specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Radiology, Nuclear Medicine & Medical Imaging↗
DOE OSTI2025

Latent diffusion can map beam loss to two-dimensional phase-space projections

Beam loss monitors (BLMs) and beam current monitors (BCMs) are ubiquitous at particle accelerators around the world. These simple devices provide noninvasive high-level beam measurements but give no insight into the detailed 6D (𝑥,𝑦,𝑧,𝑝 𝑥 ,𝑝 𝑦 ,𝑝 𝑧 ) beam phase-space distributions or dynamics. We show that generative conditional latent diffusion models can learn intricate patterns to solve the extreme inverse problem of mapping waveforms of tens of BLMs or BCMs along an accelerator to detailed 2D projections of a charged particle beam’s 6D phase-space density. This transformational method can be used at any particle accelerator to transform simple noninvasive devices into detailed beam phase-space diagnostics. We demonstrate this concept via multiparticle simulations of the high-intensity beam in the kilometer-long Los Alamos Neutron Science Center linear proton accelerator.

43 PARTICLE ACCELERATORS↗
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 OSTI2025

ClimGen: Learning the Forcing-Response Relationship in Climate System

Solar Radiation Management (SRM) is emerging as a potential geoengineering strategy to address the anthropogenic impact on climate, but its effective implementation requires an iterative and large ensemble of highly accurate and efficient climate projections. Traditional climate projections rely on executing computationally demanding and time-consuming numerical climate models. Recent advances in machine learning (ML) aim to enhance these approaches by emulating traditional methods. In this work, we propose a novel framework for directly learning the relationship between solar radiation flux at the top of the atmosphere and the corresponding surface temperature response. To evaluate the feasibility of this direct ML-based projection, we developed a dataset using an intermediate complexity model, incorporating a comprehensive suite of different forcing patterns and evaluation metrics to rigorously assess the ML model’s performance. We introduce a Conditional Denoising Diffusion Probabilistic Model (cDDPM) for this task, which demonstrates encouraging skill in representing climate statistics under previously unseen forcing patterns. This approach provides a promising pathway for direct climate projections by accurately learning the forcing-response relationship, with a wide range of applications in impact mitigation, emissions policy design, and SRM strategies.

Chen, Tse-Chun [BATTELLE (PACIFIC NW LAB)] (ORCID:↗
DOE OSTI2016

An a priori DNS study of the shadow-position mixing model

In this study, the modeling of mixing by molecular diffusion is a central aspect for transported probability density function (tPDF) methods. In this paper, the newly-proposed shadow position mixing model (SPMM) is examined, using a DNS database for a temporally evolving di-methyl ether slot jet flame. Two methods that invoke different levels of approximation are proposed to extract the shadow displacement (equivalent to shadow position) from the DNS database. An approach for a priori analysis of the mixing-model performance is developed. The shadow displacement is highly correlated with both mixture fraction and velocity, and the peak correlation coefficient of the shadow displacement and mixture fraction is higher than that of the shadow displacement and velocity. This suggests that the composition-space localness is reasonably well enforced by the model, with appropriate choices of model constants. The conditional diffusion of mixture fraction and major species from DNS and from SPMM are then compared, using mixing rates that are derived by matching the mixture fraction scalar dissipation rates. Good qualitative agreement is found, for the prediction of the locations of zero and maximum/minimum conditional diffusion locations for mixture fraction and individual species. Similar comparisons are performed for DNS and the IECM (interaction by exchange with the conditional mean) model. The agreement between SPMM and DNS is better than that between IECM and DNS, in terms of conditional diffusion iso-contour similarities and global normalized residual levels. It is found that a suitable value for the model constant c that controls the mixing frequency can be derived using the local normalized scalar variance, and that the model constant a controls the localness of the model. A higher-Reynolds-number test case is anticipated to be more appropriate to evaluate the mixing models, and stand-alone transported PDF simulations are required to more fully enforce localness and to assess model performance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2017

Development of a diffusive wave shallow water model with a novel stability condition and other new features

Traditionally, one of the approaches to flood modelling is numerical simulation of the diffusive wave approximation of the shallow water equations. Improving these models in various aspects is still an open area of research. In this study, a new diffusive wave model with explicit time integration was developed which includes some novel features: (1) time steps are determined using a novel stability criterion which resulted in more dynamic time steps (i.e., broader range) compared to the conventional Courant-Friedrichs-Lewy stability condition; (2) stability constraints are reduced, considering the flow processes within surface ponds; (3) besides Manning's formula, which is the common equation for computing velocities in diffusive wave models, the free fall velocity and a new equation for wave-front velocity are employed; and (4) the influence of upstream surface ponds on downstream flow is considered. This paper introduces the enhanced diffusive wave model, the socalled Overland Flow Simulator Cellular Automata (OFS-CA), and its results for five test cases. Available analytical solutions and an experimental study were used for verification. Two other shallow water models were used for comparison and benchmarking. Overall, good agreements were observed and OFS-CA was computationally less expensive compared to the other two shallow water models.

42 ENGINEERING↗
DOE OSTI2016

Moisture ingress into electronics enclosures under isothermal conditions

The number of electronics used in outdoor environment is constantly growing. The humidity causes about 19 % of all electronics failures and, especially, moisture increases these problems due to the ongoing process of miniaturization and lower power consumption of electronic components. Moisture loads are still not understood well by design engineers, therefore this field has become one of the bottlenecks in the electronics system design. The objective of this paper is to model moisture ingress into an electronics enclosure under isothermal conditions. The moisture diffusion model is based on a 1D quasi-steady state (QSS) approximation for Fick’s second law. This QSS approach is also described with an electrical analogy which gives a fast tool in modelling of the moisture response. The same QSS method is applied to ambient water vapour variations. The obtained results are compared to an analytical solution and very good agreement is found.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Towards universal unfolding of detector effects in high-energy physics using denoising diffusion probabilistic models

Correcting for detector effects in experimental data, particularly through unfolding, is critical for enabling precision measurements in high-energy physics. However, traditional unfolding methods face challenges in scalability, flexibility, and dependence on simulations. We introduce a novel approach to multidimensional object-wise unfolding using conditional Denoising Diffusion Probabilistic Models (cDDPM). Our method utilizes the cDDPM for a non-iterative, flexible posterior sampling approach, incorporating distribution moments as conditioning information, which exhibits a strong inductive bias that allows it to generalize to unseen physics processes without explicitly assuming the underlying distribution. Our results highlight the potential of this method as a step towards a "universal" unfolding tool that reduces dependence on truth-level assumptions, while enabling the unfolding of a wide range of measured distributions with improved adaptability and accuracy.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗