Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “foundation 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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Implementation of a SysML Model-Based Concept of Operations for Level of Care IV: Long-Duration Lunar Orbital and Surface Operations

One goal of the Human Research Program (HRP) Exploration Medical Capability (ExMC) Element Systems Engineering (SE) team is to define the technical system needed to support crew medical system capabilities for future exploration missions, including orbital and surface operations for long duration lunar missions. This is accomplished through the development of a Medical System Foundation, which communicates medical system requirements, capabilities, conditions, and resources that define a starting point for a medical system that meets the specification for design reference missions and associated Levels of Care (as defined by NASA-STD-3001). The starting point for creating this Medical System Foundation Model is the development of a Concept of Operations (ConOps) that describes the operation of the system from the point of view of the users. It includes a comprehensive and thoroughly vetted list of the users, their specific needs, the goals of the system, key assumptions about the system, and definitions of the system’s operational environments. The use case scenarios included in the ConOps illustrate required medical system capabilities for Level of Care IV and enable the ExMC SE team to develop integrated medical system requirements and identify capabilities required to meet those requirements. For this “Long Duration” Medical System Foundation development effort, ExMC replaced the traditional document-based ConOps with a model-based ConOps using model-based systems engineering. This approach has several advantages, including the facilitation of more efficient understanding of the material through information-dense images with less opportunity for misinterpretation than text alone, the roll-out of changes to the ConOps to stakeholders in real-time as they are approved, and the consolidation of all salient information into one centralized location. This discussion will focus on both how the model represents the ConOps content and how the SE team utilized lessons learned in an agile environment to improve the way this information was created and presented to stakeholders.

Mary Susan Kaetzer↗
DOE OSTI2024

Agent-based modeling for multimodal transportation of CO 2 for carbon capture, utilization, and storage: CCUS-agent

Here, to understand the system-level interactions between the entities in Carbon Capture, Utilization, and Storage (CCUS), an agent-based foundational modeling tool, CCUS-Agent, is developed for a large-scale study of transportation flows and infrastructure in the United States. Key features of the tool include (i) modular design, (ii) multiple transportation modes, (iii) capabilities for extension, and (iv) testing against various system components and networks of small and large sizes. Five matching algorithms for CO 2 supply agents (e.g., powerplants and industrial facilities) and demand agents (e.g., storage and utilization sites) are explored: Most Profitable First Year (MPFY), Most Profitable All Years (MPAY), Shortest Total Distance First Year (SDFY), Shortest Total Distance All Years (SDAY), and Shortest distance to long-haul transport All Years (ACAY). Before matching, the supply agent, demand agent, and route must be available, and the connection must be profitable. A profitable connection means the supply agent portion of revenue from the 45Q tax credit must cover the supply agent costs and all transportation costs, while the demand agent revenue portion must cover all demand agent costs. A case study employing over 5500 supply and demand agents and multimodal CCUS transportation infrastructure in the contiguous United States is conducted. The results suggest that it is possible to capture over 9 billion tonnes (GT) of CO 2 from 2025 to 2043, which will increase significantly to 22 GT if the capture costs are reduced by 40 %. The MPFY and SDFY algorithms capture more CO 2 earlier in the time horizon, while the MPAY and SDAY algorithms capture more later in the time horizon.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Uncertainty quantification of fireball features extracted from nuclear test films using computer vision

Films from the US’s historic nuclear testing era comprise the only extensive collection of imagery depicting high-yield detonations. These films offer unique insights into the characteristics of flows occurring on scales that are difficult to replicate experimentally, and they are a valuable source of data for the validation of models used to describe nuclear detonations. In recent work, we implemented modern computer vision and machine learning techniques to extract features of the fireball following nuclear detonation. With a training dataset of fireball films, we fine-tuned a You Only Look Once 11 (YOLO11) model to detect and track the fireball. Applied to a video, the outer bounding box produced in each frame by YOLO11 is used as an input prompt to Meta’s Segment Anything Model 2 (SAM2), which is shown to accurately predict the boundary of the fireball over time with high resolution. These state-of-the-art computer vision foundation models exhibit impressive visual accuracy in their results but lack an output of values that robustly quantify uncertainty in scientific applications. In this paper, we develop procedures for uncertainty quantification of extracted fireball features. We outline the application of a parallel attention mechanism to calculate uncertainty ranges that complement and better pose model validation data. This higher quality fireball validation data may serve to improve prognostic models describing nuclear detonations in support of nuclear forensic and emergency response activities.

Khristy, Joel [ORNL] (ORCID:0000000209963060)↗
NASA NTRSDate not supplied

Concept-based Analysis of Neural Networks via Vision-Language Models

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this paper, we propose to leverage emerging multimodal, vision-language, foundation models (VLMs) as a lens through which we can reason about vision models. VLMs have been trained on a large body of images accompanied by their textual description, and are thus implicitly aware of high-level, human-understandable concepts describing the images. We describe a logical specification language Con spec designed to facilitate writing specifications in terms of these concepts. To define and formally check Con spec specifications, we build a map between the internal representations of a given vision model and a VLM, leading to an efficient verification procedure of natural-language properties for vision models. We demonstrate our techniques on a ResNet-based classifier trained on the RIVAL-10 dataset using CLIP as the multimodal model.

Large Vision Language Models↗
DOE OSTI2026

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Towards Anomaly Detection at the CMS High-Level Trigger System

Traditional trigger strategies in CMS typically rely on model-dependent selections or rigid kinematic cuts, risking the omission of unexpected exotic signatures. To address this, we propose a novel anomaly detection (AD) algorithm for the High-Level Trigger (HLT), designed to serve as a complementary second layer of filtering to the Level-1 AXOL1TL AD algorithm. We employ a transformer-based foundation model trained on a diverse ensemble of Standard Model processes. By combining a joint contrastive and classification objective, and using particle kinematics as inputs, the model learns to map events to a physics-informed latent space where anomalous events are isolated from dominant backgrounds. Preliminary results show that this strategy enhances the signal-to-background ratio across a range of rare SM and BSM scenarios. Furthermore, this work constitutes foundational R&D for the potential implementation of an analogous AD algorithm in the Level-1 trigger system for Phase-2.

Cruz, Roy [U. Wisconsin, Madison (main)] (ORCID:00↗
DOE OSTI2025

Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders

We demonstrate transfer learning capabilities in a machine-learned algorithm trained for particle-flow reconstruction in high energy particle colliders. This paper presents a cross-detector fine-tuning study, where we initially pretrain the model on a large full simulation dataset from one detector design, and subsequently fine-tune the model on a sample with a different collider and detector design. Specifically, we use the Compact Linear Collider detector (CLICdet) model for the initial training set and demonstrate successful knowledge transfer to the CLIC-like detector (CLD) proposed for the Future Circular Collider in electron-positron mode. We show that with an order of magnitude less samples from the second dataset, we can achieve the same performance as a costly training from scratch, across particle-level and event-level performance metrics, including jet and missing transverse momentum resolution. Furthermore, we find that the fine-tuned model achieves comparable performance to the traditional rule-based particle-flow approach on event-level metrics after training on 100,000 CLD events, whereas a model trained from scratch requires at least 1 million CLD events to achieve similar reconstruction performance. To our knowledge, this represents the first full-simulation cross-detector transfer learning study for particle-flow reconstruction. These findings offer valuable insights towards building large foundation models that can be fine-tuned across different detector designs and geometries, helping to accelerate the development cycle for new detectors and opening the door to rapid detector design and optimization using machine learning.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗
DOE OSTI2025

A Perspective on Data and Privacy for AI in Healthcare [Industrial and Governmental Activities]

As large language models continue to push the bounds of AI model size, they are also being trained on unprecedented volumes of data. While individual hospitals are estimated to produce petabytes of data per year, only a small fraction is currently being used for developing AI models. Additionally, with such data resources available, healthcare is well-positioned to benefit from the current trends in AI. Moreover, the inherently multi-modal and longitudinal nature of clinical data – from omics to imaging to unstructured notes – provides a fertile ground for the development and application of cutting-edge architectures like foundation models.

Gounley, John [Oak Ridge National Laboratory (ORNL↗
DOE OSTI2026

Low-latency Jet Tagging for HL-LHC Using Transformer Architectures

Transformers are the state-of-the-art model architectures and widely used in application areas of machine learning. However the performance of such architectures is less well explored in the ultra-low latency domains where deployment on FPGAs or ASICs is required. Such domains include the trigger and data acquisition systems of the LHC experiments. We present a transformer-based algorithm for jet tagging built with the HGQ2 framework, which is able to produce a model with heterogeneous bitwidths for fast inference on FPGAs, as required in the trigger systems at the LHC experiments. The bitwidths are acquired during training by minimizing the total bit operations as an additional parameter. By allowing a bitwidth of zero, the model is pruned in-situ during training. Using this quantization-aware approach, our algorithm achieves state-of-the-art performance while also retaining permutation invariance which is a key property for particle physics applications. Due to the strength of transformers in representation learning, our work also serves as a stepping stone for the development of a larger foundation model for trigger applications.

Laatu, Lauri [Imperial Coll., London]↗
DOE OSTI2025

Data and Code for Understanding Generative AI Content with Embedding Models

This repository contains code for the experiments in the paper "Understanding Generative AI Content with Embedding Models". Constructing high-quality features is critical to any quantitative data analysis. While feature engineering was historically addressed by carefully hand-crafting data representations based on domain expertise, deep neural networks (DNNs) now offer a radically different approach. DNNs implicitly engineer features by transforming their input data into hidden feature vectors called embeddings. For embedding vectors produced by foundation models -- which are trained to be useful across many contexts -- we demonstrate that simple and well-studied dimensionality-reduction techniques such as Principal Component Analysis uncover inherent heterogeneity in input data concordant with human-understandable explanations. Of the many applications for this framework, we find empirical evidence that there is intrinsic separability between real samples and those generated by artificial intelligence (AI).

Vargas, Max [Pacific Northwest National Laboratory↗
NASA NTRS1994

TEXCAD: Textile Composite Analysis for Design. Version 1.0: User's manual

The Textile Composite Analysis for Design (TEXCAD) code provides the materials/design engineer with a user-friendly desktop computer (IBM PC compatible or Apple Macintosh) tool for the analysis of a wide variety of fabric reinforced woven and braided composites. It can be used to calculate overall thermal and mechanical properties along with engineering estimates of damage progression and strength. TEXCAD also calculates laminate properties for stacked, oriented fabric constructions. It discretely models the yarn centerline paths within the textile repeating unit cell (RUC) by assuming sinusoidal undulations at yarn cross-over points and uses a yarn discretization scheme (which subdivides each yarn not smaller, piecewise straight yarn slices) together with a 3-D stress averaging procedure to compute overall stiffness properties. In the calculations for strength, it uses a curved beam-on-elastic foundation model for yarn undulating regions together with an incremental approach in which stiffness properties for the failed yarn slices are reduced based on the predicted yarn slice failure mode. Nonlinear shear effects and nonlinear geometric effects can be simulated. Input to TEXCAD consists of: (1) materials parameters like impregnated yarn and resin properties such moduli, Poisson's ratios, coefficients of thermal expansion, nonlinear parameters, axial failure strains and in-plane failure stresses; and (2) fabric parameters like yarn sizes, braid angle, yarn packing density, filament diameter and overall fiber volume fraction. Output consists of overall thermoelastic constants, yarn slice strains/stresses, yarn slice failure history, in-plane stress-strain response and ultimate failure strength. Strength can be computed under the combined action of thermal and mechanical loading (tension, compression and shear).

Naik, Rajiv A.↗
NASA NTRS1995

TEXCAD: TEXile Composite Analysis for Design

The Textile Composite Analysis for Design (TEXCAD) code provides the materials/design engineer with a user-friendly, desktop computer based tool for the analysis of a wide variety of fabric reinforced woven and braided composites. It can be used to calculate overall thermal and mechanical properties along with engineering estimates of damage progression and strength. TEXCAD also calculates laminate properties for stacked, oriented fabric constructions. It discretely models the yarn centerline paths within the textile repeating unit cell (RUC) by assuming sinusoidal undulations at yarn cross-over points and uses a year discretization scheme (which subdivides each yarn into smaller, piecewise straight yarn slices) together with a 3-D stress averaging procedure to compute overall stiffness properties. In the calculations for strength, it uses a curved beam-on-elastic foundation model for yarn undulating regions together with incremental approach in which stiffness properties for the failed yarn slices are reduced based on the predicted yarn slice failure mode. Nonlinear shear effects and nonlinear geometric effects can be stimulated. Input to TEXCAD consists of: (1) material parameters like impregnated yarn and resin properties such as moduli, Poisson's ratios, coefficients of thermal expansion, nonlinear shear parameters, axial failure strains, and in-plane failure stresses; and (2) fabric parameters like yarn sizes, braid angle, yarn packing density, filament diameter, and overall fiber volume fraction. Output consists of overall thermoelastic constants, yarn slice strains/stresses, yarn slice failure history, in-plane strain response, and ultimate failure strength. Strength can be computed under the combined action of thermal and mechanical loading (tension, compression, and shear). A brief overview of the analytical capabilities, program organization, and modules, input and output parameters, computer platforms, distribution, and modifications/extensions of the TEXCAD code are presented here.

Naik, Rajiv A.↗
NASA NTRSDate not supplied

Fast Machine Learning Lidar Surrogate Simulator: Pristine Clear Sky

The simulations of lidar signals and retrievals rely on a range of optic-physical models, such as radiative transfer models, particle scattering and absorption models, along with the output data from atmospheric physical models. Integrating these different models to represent signals of a lidar system is computationally expensive, and performing backward retrievals can be complex and ambiguous. However, with the advantages of Machine Learning, there is a new potential for building effective lidar signal database linked to corresponding atmospheric profiles. For this project, we are developing a fast pre-trained neural network as the lidar surrogate simulator using simulated data for a CALIPSO-like lidar (355 nm, 532nm, and 1064nm), and a CO2 differential absorption lidar (DIAL) near 1571nm. Specifically, we utilize a long short-term memory (LSTM) model to map the relationships between atmospheric profiles (pressure, temperature, air density and CO2 mixing ratio) and lidar signals. This approach allows us to build machine learning based simulators that can reconstruct lidar signals at specific bands from MERRA reanalysis data, and perform retrievals of atmospheric profiles using lidar signals at various wavelengths. As a first step, the results show the potential of this method to establish a foundational model for sensor signals. This model offers the promise of enabling both accurate predictions and rapid retrievals, providing a more efficient approach to signal processing and analysis.

Shan Zeng↗
DOE OSTI2025

DNABERT-S: pioneering species differentiation with species-aware DNA embeddings

SUMMARY: We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. AVAILABILITY AND IMPLEMENTATION: Model, codes, and data are publically available at https://github.com/MAGICS-LAB/DNABERT_S.

Zhou, Zhihan↗
NASA NTRS1993

Nonlinear probabilistic finite element models of laminated composite shells

A probabilistic finite element analysis procedure for laminated composite shells has been developed. A total Lagrangian finite element formulation, employing a degenerated 3-D laminated composite shell with the full Green-Lagrange strains and first-order shear deformable kinematics, forms the modeling foundation. The first-order second-moment technique for probabilistic finite element analysis of random fields is employed and results are presented in the form of mean and variance of the structural response. The effects of material nonlinearity are included through the use of a rate-independent anisotropic plasticity formulation with the macroscopic point of view. Both ply-level and micromechanics-level random variables can be selected, the latter by means of the Aboudi micromechanics model. A number of sample problems are solved to verify the accuracy of the procedures developed and to quantify the variability of certain material type/structure combinations. Experimental data is compared in many cases, and the Monte Carlo simulation method is used to check the probabilistic results. In general, the procedure is quite effective in modeling the mean and variance response of the linear and nonlinear behavior of laminated composite shells.

Engelstad, S. P.↗
DOE OSTI2025

A machine-learning-driven data labeling pipeline for scientific analysis in MLExchange

This study introduces a novel labeling pipeline to accelerate the labeling process of scientific data sets by using artificial intelligence (AI)-guided tagging techniques. This pipeline includes a set of interconnected web-based graphical user interfaces (GUIs), where Data Clinic and MLCoach enable the preparation of machine learning (ML) models for data reduction and classification, respectively, while Label Maker is used for label assignment. Throughout this pipeline, data can be accessed through a direct connection to a file system or through Tiled for access through Hypertext Transfer Protocol (HTTP). Our experimental results present three use cases where this labeling pipeline has been instrumental for the study of large X-ray scattering data sets in the area of pattern recognition, the remote analysis of resonant soft X-ray scattering data and the fine-tuning process of foundation models. These use cases highlight the labeling capabilities of this pipeline, including the ability to label large data sets in a short period of time, to perform remote data analysis while minimizing data movement and to enhance the fine-tuning process of complex ML models with human involvement.

Chavez, Tanny (ORCID:0000000193172896)↗
DOE OSTI2026

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

Aubourg, Eric [APC, Paris] (ORCID:000000025592023X↗