Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “modal 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Scalable foundation models for numerical simulations on HPC platforms

In recent years, foundation models (FMs) have begun to reshape numerical simulations on high-performance computing (HPC) platforms. These large, pre-trained AI models enable rapid predictions across a broad range of physical domains, including Earth system modeling, fluid dynamics, materials science, as well as complex multi-modal simulations in aerospace engineering and fusion research. By training on diverse datasets, FMs learn intricate relationships and underlying physical behavior while also enabling the quantification of uncertainty in their predictions. This capability allows simulations that once required days of numerical calculation to be completed in minutes (FM inference), supporting real-time design optimization, uncertainty-aware decision making, and more comprehensive exploration of complex scenarios.

AI↗
DOE OSTI2024

Validating a microphysical prognostic stratospheric aerosol implementation in E3SMv2 using observations after the Mount Pinatubo eruption

Abstract. This paper describes the addition of a stratospheric prognostic aerosol (SPA) capability – developed with the goal of accurately simulating sulfate aerosol formation and evolution in the stratosphere – in the Department of Energy (DOE) Energy Exascale Earth System Model, version 2 (E3SMv2). The implementation includes changes to the four-mode Modal Aerosol Module microphysics in the stratosphere to allow for larger particle growth and more accurate stratospheric aerosol lifetime following the Pinatubo eruption. E3SMv2-SPA reasonably reproduces stratospheric aerosol lifetime, burden, aerosol optical depth, and top-of-atmosphere flux when compared to remote sensing observations. E3SMv2-SPA also has close agreement with the interactive chemistry–climate model CESM2-WACCM (Community Earth System Model version 2–Whole Atmosphere Community Climate Model) – which has a more complete chemical treatment – and the observationally constrained, prescribed volcanic aerosol treatment in E3SMv2. Global stratospheric aerosol size distributions identify the nucleation and growth of sulfate aerosol from volcanically injected SO2 from both major and minor volcanic eruptions from 1991 to 1993. The modeled aerosol effective radius is consistently lower than satellite and in situ measurements (max differences of ∼ 30 %). Comparisons with in situ size distribution samples indicate that this simulated underestimation in both E3SMv2-SPA and CESM2-WACCM is due to overly small accumulation and coarse-mode aerosols 6–18 months post-eruption, with E3SMv2-SPA simulating ∼ 50 % of the coarse-mode geometric mean diameters of observations 11 months post-eruption. Effective radii from the models and observations are used to calculate offline scattering and absorption efficiencies to explore the implications of smaller simulated aerosol size for the Pinatubo climate impacts. Scattering efficiencies at wavelengths of peak solar irradiance (∼ 0.5 µm) are 10 %–80 % higher for daily samples in models relative to observations through 1993, suggesting higher diffuse radiation at the surface and a larger cooling effect in the models due to the smaller simulated aerosol; absorption efficiencies at the peak wavelengths of outgoing terrestrial radiation (∼ 10 µm) are 15 %–40 % lower for daily samples in models relative to observations, suggesting an underestimation in stratospheric heating in the models due to the smaller simulated aerosol. These potential biases are based on aerosol size alone and do not take into account differences in the aerosol number. The overall agreement of E3SMv2-SPA with observations and its similar performance to the well-validated CESM2-WACCM makes E3SMv2-SPA a viable alternative to simulating climate impacts from stratospheric sulfate aerosols.

Brown, Hunter York (ORCID:0000000218147874)↗
DOE OSTI2021

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models

Source code for Brain Attend and Decode paper. Functional magnetic resonance imaging (fMRI) is a neuroimaging modality that captures the blood oxygen level in a subject's brain while the subject either rests or performs a variety of functional tasks under different conditions. Given fMRI data, the problem of inferring the task, known as task state decoding, is challenging due to the high dimensionality (hundreds of million sampling points per datum) and complex spatio-temporal blood flow patterns inherent in the data. In this work, we propose to tackle the fMRI task state decoding problem by casting it as a 4D spatiotemporal classification problem. We present a novel architecture called Brain Attend and Decode (BAnD), that uses residual convolutional neural networks for spatial feature extraction and self-attention mechanisms for temporal modeling. We achieve significant performance gain compared to previous works on a 7-task benchmark from the large-scale Human Connectome Project-Young Adult (HCP-YA) dataset. We also investigate the transferability of BAnD's extracted features on unseen HCP tasks, either by freezing the spatial feature extraction layers and retraining the temporal model, or finetuning the entire model. The pre-trained features from BAnD are useful on similar tasks while finetuning them yields competitive results on unseen tasks/conditions.

Ng, BrendaM.↗
DOE OSTI2025

A Data-Agnostic, Continuous Machine Learning Framework for Application in High Energy Physics and Beyond: Phase 1 Final Scientific/Technical Report

This Phase 1 effort has focused on the development of continual learning frameworks for use in machine learning, specifically in the applied context of High Energy Physics (HEP). Machine learning (ML) is a transformative technology by which computers, typically through the use of neural networks, are able to perform tasks with proficiency that rivals or surpasses that of human users. Model Degradation & Catastrophic Forgetting are two undesired phenomena which can occur in ML where the performance of a model degrades when either deployed on novel data streams, or trained on novel data which are sufficiently different than the data the models were initially trained on. A natural example where these sorts of effects can be observed is in the performance of detectors in harsh environments, where the detector signature may change over the lifetime of the detector as it ages and deteriorates — precisely what occurs in the experiments conducted in HEP. Real world HEP data is therefore an excellent test-ground and use-case for Continual Learning paradigms, which are techniques used in ML to counteract these problems. Ensemble learning is one such technique, where multiple smaller models are trained on subsets of the overall data and are ensembled together during inference. The intuition behind this technique is that, although there are shifts in the distributions which govern the incoming data streams, these shifts are not expected to be homogeneous or global. If a sufficient diversity in solutions within the various sub-models has been achieved, then at least one sub-model is expected to retain its performance within the overall ensemble. One further strength of this approach is that the architectures of the various models do not need to be identical, and in fact even different modalities of data can naturally be combined in this way. This work focused on applying ensemble learning techniques to derive results using two main datasets, anomaly detection in HEP data & time-series forecasting in semiconductor manufacturing data. Semiconductor manufacturing involves data with surprising similarity to that of HEP (e.g. wafer maps look very similar to digi-occupancy maps) and Cerium Lab’s prominence within the semiconductor industry makes semiconductor manufacturing a natural opportunity for commercialization of this work. Our efforts have led to two strong results. The first is that we evaluated the proposed ensembling techniques using previously proposed machine learning architectures for use in anomaly detection, namely AutoEncoder based models and their derivatives. We also developed new architectures which have not been evaluated in this context before. In fact, this work marks the first use of Vision Transformers for anomaly detection in HEP. Second, we demonstrated that ensemble learning significantly improves model performance in scenarios prone to degradation, validating its effectiveness across both HEP and semiconductor datasets. These results further support ensemble learning as a powerful strategy for mitigating catastrophic forgetting and maintaining robust performance in evolving data environments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models

Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone.

58 GEOSCIENCES↗
DOE OSTI2026

Towards Secure Autonomous Vehicles: An Integrated Edge and Multi-Modal Machine Learning Framework for Intrusion Detection

Autonomous vehicles (AVs) are vulnerable to cyberattacks targeting both internal communication networks and external perception sensors. While edge-based intrusion de- tection for Controller Area Network (CAN) buses offers real-time protection, it cannot detect cross-modal threats. Conversely, multi-modal fusion approaches improve coverage but often lack efficiency for in-vehicle deployment. This thesis integrates two complemen- tary solutions: (1) a lightweight, edge-deployable machine learning framework for CAN bus intrusion detection, and (2) a late-fusion system combining CAN FD and LiDAR data. Together, they form a hierarchical defense capable of handling single-modality and coordi- nated attacks. Simulations show that CAN-only models reach 93% accuracy on simulated DoS, spoofing, replay, and fuzzy attacks, while the fusion system achieves 0.87 AUC and 0.82 F1-score at 2 ms latency. This unified framework establishes a scalable, explainable, and field-ready strategy for AV cybersecurity.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A fast multi-fidelity method with uncertainty quantification for complex data correlations: Application to vortex-induced vibrations of marine risers

Here we develop a fast multi-fidelity modeling method for very complex correlations between high- and low-fidelity data by working in modal space to extract the proper correlation function. We apply this method to infer the amplitude of motion of a flexible marine riser in cross-flow, subject to vortex-induced vibrations (VIV). VIV are driven by an absolute instability in the flow, which imposes a frequency (Strouhal) law that requires a matching with the impedance of the structure; this matching is easily achieved because of the rapid parametric variation of the added mass force. As a result, the wavenumber of the riser spatial response is within narrow bands of uncertainty. Hence, an error in wavenumber prediction can cause significant phase-related errors in the shape of the amplitude of response along the riser, rendering correlation between low- and high-fidelity data very complex. Working in modal space as outlined herein, dense data from low-fidelity data, provided by the semi-empirical computer code VIVA, can correlate in modal space with few high-fidelity data, obtained from experiments or fully-resolved CFD simulations, to correct both phase and amplitude and provide predictions that agree very well overall with the correct shape of the amplitude response. We also quantify the uncertainty in the prediction using Bayesian modeling and exploit this uncertainty to formulate an active learning strategy for the best possible location of the sensors providing the high fidelity measurements.

42 ENGINEERING↗
DOE OSTI2021

Sandia NRT Blade-0 Laboratory Modal Survey

Modal testing was performed on the Sandia NRT Blade-0 in building A-60 at NREL/NWTC. Modal testing was intended to identify the fundamental frequencies of the blade. The blade was cantilevered to the A-60 test stand. Fundamental frequencies were identified using impact modal testing. Additional tests included free-decay testing to quantify damping at small displacements. Small-displacement modal testing aims to minimize the influence of aerodynamic damping; roaming accelerometer impact testing with the development of a dynamic frame model enabled visualization of mode shapes.

17 WIND ENERGY↗
DOE OSTI2023

Understanding and Improving Energy Efficiency of Regional Mobility Systems Leveraging System-Level Data

Increased congestion required urban Americans to travel 6.8 billion hours more and purchase 3.1 billion gallons of fuel for a congestion cost of $\$$153 billion, according to the 2019 Urban Mobility Report. How to effectively manage the regional mobility system and improve the energy efficiency presents a big challenge to public agencies. Recent years have witnessed massive multi-jurisdictional multi-modal system-level data from various sources, which provides an unprecedented opportunity to improve the mobility system and its energy efficiency. However, implications of system-level data for mobility and energy efficiency are unclear. Those system-level data sets are siloed, spatially and temporally sparse, biased, not unified, and lacking of insights for system management. Consequently, there is a real need to acquire, fuse, mine and learn from multi-source system-level data to prepare public agencies to deal more effectively with large-scale energy efficiency modeling, management and planning. This project proposes to intensively review inexpensive, replicable and openly-accessible data from multi-modal systems, develop a data-driven system-level modeling framework enabled and validated by data, identify the energy inefficiencies of mobility systems from infrastructure, vehicles, passenger systems, and quantify the benefits of system-level strategies to improve mobility/energy efficiency. In addition, this research develops models to effectively estimate energy consumption and emissions from various types of vehicles on the roadway networks, with high granularity and high fidelity. Traditional models often heavily rely on aggregated infrastructure or vehicle/passenger data, for example, the census survey, land-use, and traffic counts of one or several classes, which may lead to research gaps considering the emerging vehicle technologies. Those models do not contain individual vehicular information. We propose an integrated data-driven method that combines multiple network modeling components, featuring the utilization of state-wide vehicle registration data. The additional vehicle registration data improve the model performance, and produce high-resolution vehicle-specific estimates of emissions and network performance metrics. Two case studies on the Pittsburgh and Philadelphia regional network show that the proposed method can efficiently and effectively estimate the emissions of a large-scale network, and provide valuable information for evaluating common management strategies.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Understanding the Stability of Manganese Chromium Antimonate Electrocatalysts through Multimodal In Situ and Operando Measurements

Herein, we utilize an on-line electrochemical flow cell coupled with an inductively coupled plasma-mass spectrometer (ICP-MS) to characterize the impact of composition and reactant gas on the multielement dissolution of Mn(-Cr)-Sb-O electrocatalysts. Compared to Mn 2 O 3 and Cr 2 O 3 oxides, we find that the antimonate framework stabilizes Mn at OER potentials and Cr at both ORR and OER potentials. Furthermore, dissolution of Mn and Cr from Mn(-Cr)-Sb-O is found to be driven by ORR reaction rate, with minimal dissolution under N 2 . We observe preferential dissolution of Cr totaling 13% over 10 minutes at 0.3, 0.6, and 0.9 V vs RHE, with only 1.5% loss of Mn, indicating an enrichment of Mn at the surface of the particles. Despite this asymmetric dissolution, in situ X-ray absorption spectroscopy (XAS) showed no measurable changes in the Mn K-edge at comparable potentials. This lack of change could suggest that modification to the Mn oxidation state in the surface layer is too small or that layer is too thin to be measured with the bulk XAS measurement. Lastly, on-line ICP-MS was used to assess the effects of applied potential, scan rate, and current of Mn-Cr-Sb-O during cyclic voltammetry and accelerated stress tests. With this deeper understanding of the interplay between oxygen reduction and dissolution, testing procedures were identified to maximize both activity and stability. This work highlights the use of multi-modal in situ characterization techniques in tandem to build a more complete model of stability and develop protocols for optimizing catalyst performance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Selective permeation up a chemical potential gradient to enable an unusual solvent purification modality

The need for energy-efficient recovery of organic solutes from aqueous streams is becoming more urgent as chemical manufacturing transitions toward nonconventional and bio-based feedstocks and processes. In addition to this, many aqueous waste streams contain recalcitrant organic contaminants, such as pharmaceuticals, industrial solvents, and personal care products, that must be removed prior to reuse. We observe that rigid carbon membrane materials can remove and concentrate organic contaminants via an unusual liquid-phase membrane permeation modality. Surprisingly, detailed thermodynamic calculations on the chemical potential of the organic contaminant reveal that the organic species has a higher chemical potential on the permeate side of the membrane than on the feed side of the membrane. This unusual observation challenges conventional membrane transport theory that posits that all permeating species move from high chemical potential states to lower chemical potential states. Based on experimental measurements, we hypothesize that the organic is concentrated in the membrane relative to water via favorable binding interactions between the organic and the carbon membrane. The concentrated organic is then swept through the membrane via the bulk flow of water in a modality known as “sorp-vection.” We highlight via simplified nonequilibrium thermodynamic models that this “uphill” chemical potential permeation of the organic does not result in second-law violations and can be deduced via measurements of the organic and water sorption and diffusion rates into the carbon membrane. Moreover, this work identifies the need to consider such nonidealities when incorporating unique, rigid materials for the separations of aqueous waste streams.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Computational and Systems Biology Advances to Enable Bioagent Agnostic Signatures

Enumerated threat agent lists have long driven biodefense priorities. The global SARS-CoV-2 pandemic demonstrated the limitations of searching for known threat agents as compared to a more agnostic approach. Recent technological advances are enabling agent-agnostic biodefense, especially through the integration of multi-modal observations of host-pathogen interactions directed by a human immunological model. Although well-developed technical assays exist for many aspects of human-pathogen interaction, the analytic methods and pipelines to combine and holistically interpret the results of such assays are immature and require further investments to exploit new technologies. In this manuscript, we discuss potential immunologically based bioagent-agnostic approaches and the computational tool gaps the community should prioritize filling.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Estimation of Participation Factors Using the Synchrosqueezed Wavelet Transform

This paper proposes a data-driven approach for estimating participation factors for a power system using only simulation results on selected disturbances. The approach is purely response-based and does not need a linearized system model for eigen-analysis, which makes it applicable to systems whose detailed, complete mathematical models are not available. Considering the unavoidable nonlinearity as exhibited in the transient period of a system response, the Synchrosqueezed Wavelet Transform is applied to simulated responses for modal analysis to obtain participation factors. Based on simulations of Kundur's two-area system using both the electromagnetic transient model and phasor model, the participation factors estimated by the proposed approach are compared with two other signal processing tools, the Prony analysis and continuous wavelet transform, and are also benchmarked with conventional model-based participation factors.

participation factor↗
DOE OSTI2021

An Intelligent Garbage Sorting System Based on Edge Computing and Visual Understanding of Social Internet of Vehicles

In order to enable Social Internet of Vehicles devices to achieve the purpose of intelligent and autonomous garbage classification in a public environment, while avoiding network congestion caused by a large amount of data accessing the cloud at the same time, it is therefore considered to combine mobile edge computing with Social Internet of Vehicles to give full play to mobile edge computing features of high bandwidth and low latency. At the same time, based on cutting-edge technologies such as deep learning, knowledge graph, and 5G transmission, the paper builds an intelligent garbage sorting system based on edge computing and visual understanding of Social Internet of Vehicles. First of all, for the massive multisource heterogeneous Social Internet of Vehicles big data in the public environment, different item modal data adopts different processing methods, aiming to obtain a visual understanding model. Secondly, using the 5G network, the model is deployed on the edge device and the cloud for cloud-side collaborative management, aiming to avoid the waste of edge node resources, while ensuring the data privacy of the edge node. Finally, the Social Internet of Vehicles devices is used to make intelligent decision-making on the big data of the items. First, the items are judged as garbage, and then the category is judged, and finally the task of grabbing and sorting is realized. The experimental results show that the system proposed in this paper can efficiently process the big data of Social Internet of Vehicles and make valuable intelligent decisions. At the same time, it also has a certain role in promoting the promotion of Social Internet of Vehicles devices.

Shen, Xuehao↗
DOE OSTI2023

Machine Learning Enabled Sensor Fusion for In-Situ Defect Detection in Laser Powder Bed Fusion

Laser Powder Bed Fusion (L-PBF) Additive Manufacturing (AM) is among the metal 3D printing technologies most broadly adopted by the manufacturing industry. The current industry qualification paradigm for critical-application L-PBF parts relies heavily on expensive non-destructive inspection techniques such as X-Ray Computed Tomography (XCT), which significantly limits the use-cases of L-PBF. In situ monitoring of the process promises a less expensive alternative to ex situ testing, but existing sensor technologies and data analysis techniques struggle to detect sub-surface flaws (e.g., porosity and cracking) on production-scale L-PBF printers. RTX Technologies Research Center (RTRC) has licensed ORNL’s Peregrine software package – a printer- and camera-agnostic data analytics tool designed specifically for detecting process anomalies using in situ data collected during powder bed printing. The goal of this project was to feed temporally rich, multi-modal sensor data, including visible light, integrated near infrared (NIR), and spatially mapped co-axial melt pool thermal emission data into Peregrine to enable detection of subsurface flaws. XCT data was used as ground truth training data to allow Peregrine’s deep learning algorithms to recognize anomalies in these complex data streams in both test artifacts and industrially relevant geometries. Completion of this program has seen the successful implementation of multi-modal, multi-layer sensor data footprints for training of machine learning models in Peregrine. Flaws detected in XCT data have been successfully detected directly from this in situ data footprint, and initial analyses of the in situ probability-of-detection has been conducted, showing performance levels commensurate with traditional non-destructive evaluation (NDE) methods. The in situ monitoring methodology was then applied to an industrially relevant component that was using post-build NDE, highlighting the utility of the proposed method for hard-to-inspect AM components. As a direct result of this program, two journal manuscripts [1], [2] have been published in Additive Manufacturing, with additional manuscripts planned following program completion.

36 MATERIALS SCIENCE↗
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 OSTI2022

Revealing low-temperature plasma efficacy through a dose-rate assessment by DNA damage detection combined with machine learning models

Low-temperature plasmas have quickly emerged as alternative and unconventional types of radiation that offer great promise for various clinical modalities. As with other types of radiation, the therapeutic efficacy and safety of low-temperature plasmas are ubiquitous concerns, and assessing their dose rates is crucial in clinical settings. Unfortunately, assessing the dose rates by standard dosimetric techniques has been challenging. To overcome this difficulty, we proposed a dose-rate assessment framework that combined the predictive modeling of plasma-induced damage in DNA by machine learning with existing radiation dose-DNA damage correlations. Our results indicated that low-temperature plasmas have a remarkably high dose rate that can be tuned by various process parameters. This attribute is beneficial for inducing radiobiological effects in a more controllable manner.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Microscopy modality transfer of steel microstructures: Inferring scanning electron micrographs from optical microscopy using generative AI

Scanning electron microscopy (SEM) is resource intensive, which limits its throughput in some applications. As an alternative, we propose applying computer vision and machine learning to generate high-quality synthetic SEM micrographs from micrographs obtained using light optical microscopy (LOM). Working with a correlated LOM/SEM dataset of dual-phase steel images, we test generative models of various architectures, including encoder-decoder networks, generative adversarial networks (GANs), and diffusion-based models. We find that the diffusion models significantly outperform other methods on both qualitative and quantitative assessments, while preserving key metallurgical meaning. This work establishes diffusion as the state-of-the-art for microscopy modality transfer and demonstrates the potential of AI-powered microscopy to enhance LOM with micron scale structural recreation.

Computer vision↗