SEARCH · Search NASA

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.

SourceResearch connectionFrom yearThrough year

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

At least 145 records · Page 8

All sources NASA NTRS DOE OSTI

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↗

DOE OSTI2026

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipelines ability to ingest several modalities of information. We present (1) a curated dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, multimodal data, and cross-document multimodal data; (2) a phrase-level recall metric for correctness; (3) a nearest-neighbor embedding classifier in an attempt to classify pipeline hallucinations; (4) a comparative evaluation of 2 pipelines built with open-source retrieval mechanisms and 4 closed-source foundational models; and (5) a third-party human evaluation of the alignment of our correctness and hallucination metrics. We find that closed-source pipelines significantly outperform open-source pipelines in both the correctness and halucination metrics, with a wider performance gap in questions relying on multimodal and cross-document information. We also find after a human evaluation of our correctness and hallucination metric compared with our questions and pipeline responses, average agreement was 4.62 for correctness 4.53 for hallucination detection on a 1-5 Likert scale with 5 being strongly agree with our determination.

Hildebrand, Samuel [ORNL] (ORCID:0009000465963104)↗

NASA NTRSDate not supplied

Implementing Artificial Thinking Autonomy with Model-Based System Engineering

Complex autonomous systems capable of successfully operating independently under ‘known unknowns’ and harsh conditions require paradigm innovation in modern development strategies. In the field of autonomy, developing a system-of-systems which can ostensibly think for itself in the face of ‘unknown unknowns’ is still a field of ongoing research. Maturing the systems architecting and modeling methodologies for developing henceforth named Thinking Autonomous Systems, which are verified with digital mission simulation, can potentially usher in the next generation of artificial intelligence for space exploration. The concept presented in this paper incorporates multiple Model-Based Systems Engineering and simulation methodologies combined as a new paradigm to design a novel, biomimetic thinking autonomy strategy. Anachronistic concepts from classical Kantian philosophy will be leveraged to inspire architectural designs that could be used for complex distributed systems in deep space. To accomplish this, digital transformation of a document-based implementation plan for Thinking Autonomous Systems, generated by experienced NASA software engineers, is implemented for NASA’s Platform for Autonomous Systems by creating descriptive and executable software models in SysML to prototype real-time operating capabilities. This conceptual implementation has been developed by incorporating model-based digital simulations to theorize how a cyberphysical thinking system would achieve specific strategies without crew reliance, while simultaneously being resilient to all operating conditions and remaining functional when devoid of ground communication. Additionally, ensuring that an autonomous system framework is an ethical Artificial Intelligence requires careful consideration of system behavior and accountability, human factors for teaming with a thinking autonomous system, and comparison to other modern approaches used for implementing true autonomy. This paper presents the first steps in formalizing the metacognition required for instantiating a truly Thinking Autonomous System; the approach described symphonizes autonomy characteristics from classical philosophical into a unified software architecture describing human thought. In the future, the foundational models described in this paper can be further leveraged to help advance research into thinking autonomy requirements for future deep space missions as well as for current near-term applications, i.e., living aboard crewed spacecraft like a NASA Gateway cislunar habitat.

Artificial Thought↗

DOE OSTI2025

LLMs for Mfg.—On the State of Large Language Models and Applications to Manufacturing

Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.

36 MATERIALS SCIENCE↗

NASA NTRSDate not supplied

GeoAI advances in specific landform mapping

Landform mapping (also referred to as geomorphology or geomorphometry) can be divided into two domains: general and specific (Evans 2012). Whereas general landform mapping categorizes all elements of the study area into landform classes, such as ridges, valleys, peaks, and depressions, the mapping of specific landforms requires the delineation (even if fuzzy) of individual landforms. The former is mainly driven by physical properties such as elevation, slope, and curvature. The latter, however, must consider the cognitive (human) reasoning that discriminates individual landforms in addition to these physical properties (Arundel and Sinha 2018). Both mapping forms are important. General geomorphometry is needed to understand geological and ecological processes and as boundary layer input to climate and environmental models. Specific geomorphometry supports such activities as disaster management and recovery, emergency response, transportation, and navigation. In the United States, individual landforms of interest are named in the U.S. Geological Survey (USGS) Geographic Names Information System, a point dataset captured specifically to digitize geographic names from the USGS Historical Topographic Map Collection (HTMC). Named landform extent is represented only by the name placement in the HTMC. Recent work has investigated CNN-based deep learning methods to capture these extents in machine-readable form. These studies first relied on physical properties (Arundel et al. 2020) and then included the HTMC as a band in RGB images in limited testing (Arundel et al. 2023). Results from the HTMC dataset surpassed those using just physical properties and using the HTMC alone performed best due to the hillshading and elevation (contour) data incorporated into the topographic maps. However, results fell short of an operational capacity to map all named landforms in the United States. Thus, our current work expands upon past research by focusing on the HTMC and physical information as inputs and the named landform label extents. Specifically, we propose to leverage pre-trained foundation models for segmentation and optical character recognition (OCR) models to jointly map landforms in the United States. Our approach aims to bridge the disparities among the independent information sources to facilitate informed decision-making. The modeling pipeline performs (1) segmentation using the physical information and (2) information extraction using OCR, in parallel. Then a computer vision approach merges the two branches into a labeled segmentation. References: Arundel, Samantha T., Wenwen Li, and Sizhe Wang. 2020. “GeoNat v1.0: A Dataset for Natural Feature Mapping with Artificial Intelligence and Supervised Learning.” Transactions in GIS 24 (3): 556–72. https://doi.org/10.1111/tgis.12633. Arundel, Samantha T, and Gaurav Sinha. 2018. “Validating GEOBIA Based Terrain Segmentation and Classification for Automated Delineation of Cognitively Salient Landforms BT - Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017).” In Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017), Lecture Notes in Geoinformation and Cartography, edited by Paolo Fogliaroni, Andrea Ballatore, and Eliseo Clementini, 9–14. Cham: Springer International Publishing. Arundel, Samantha T., Gaurav Sinha, Wenwen Li, David P. Martin, Kevin G. McKeehan, and Philip T. Thiem. 2023. “Historical Maps Inform Landform Cognition in Machine Learning.” Abstracts of the ICA 6 (August): 1–2. https://doi.org/10.5194/ica-abs-6-10-2023. Evans, Ian S. 2012. “Geomorphometry and Landform Mapping: What Is a Landform?” Geomorphology 137 (1): 94–106. https://doi.org/10.1016/j.geomorph.2010.09.029.

machine learning↗

NASA NTRSDate not supplied

GeoAI Advances in Specific Landform Mapping

machine learning↗

DOE OSTI2026

Data readiness pipeline patterns for scientific AI at scale: Insights from climate, fusion, life sciences, and materials

This article examines how data readiness for AI principles apply to large scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains—climate, nuclear fusion, life sciences, and materials—to identify common preprocessing patterns and domain‐specific constraints. We introduce a two‐dimensional readiness model that combines canonical preprocessing patterns with a five‐level operational readiness scale, both tailored to high‐performance computing (HPC) environments. This construct helps outline key challenges in transforming large‐scale scientific data into formats suitable for scalable AI training. Together, these dimensions form a conceptual maturity matrix that characterizes scientific data readiness and guides infrastructure development toward standardized, cross‐domain support for scalable and reproducible AI for science. Finally, we evaluate this maturity matrix in the context of case studies including ClimaX (climate), AFLOW (materials), OpenFold (proteomics), and DIII‐D fusion disruption‐prediction workflows, from which we distill lessons learned and provide recommendations to guide practitioners in developing robust AI‐readiness pipelines. Finally, we discuss remaining cross‐cutting challenges that persist across scientific domains.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

yProv4ML: Effortless provenance tracking for machine learning systems

The rapid growth in interest in deep learning and foundation models (FMs) in particular, has attracted the attention of a diverse range of researchers thanks to their generalization ability. However, the advent of these techniques has also brought to light the lack of transparency and rigor in the way development is pursued. In particular, the inability to determine the number of epochs and other hyperparameters in advance presents challenges in identifying the best model. To address this challenge, machine learning frameworks such as MLFlow can automate the collection of this type of information. However, these tools capture data using proprietary formats and pose little attention to lineage. This paper proposes yProv4ML, a framework that captures provenance information generated during machine learning processes in PROV-JSON format, with minimal code modification.

Machine learning↗

DOE OSTI2025

A Representation Fusion Framework for Decoupling Diagnostic Information in Multimodal Learning

Modern medicine increasingly relies on multimodal data, ranging from clinical notes to imaging and genomics, to guide diagnosis and treatment. However, integrating these heterogeneous data sources in a principled and interpretable manner remains a major challenge. We present MODES (Multi-mOdal Disentangled Embedding Space), a representation fusion framework that explicitly separates shared and modality-specific factors of variation, offering a structured latent space for multimodal information that improves both prediction and interpretability. By leveraging pre-trained unimodal foundation models, MODES mitigates the dependency on extensive paired datasets, crucial in data-scarce clinical settings. We introduce a masking strategy that optimizes representation dimensionality by eliminating low-information dimensions, to achieve compact, information-rich representations. Our framework demonstrates superior performance in predicting diagnoses and phenotypes compared to unimodal and conventional fusion models. MODES also enables robust diagnostic inference in missing data scenarios, offering an opportunity toward interpretable and efficient multimodal diagnostics in personalized healthcare.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2026

Roadmap for transforming heterogeneous catalysis with artificial intelligence

Artificial intelligence (AI) is poised to transform heterogeneous catalysis, opening avenues for catalytic materials discovery. By uncovering intricate patterns in high-dimensional data, AI has been reshaping our pursuit of sustainable catalytic processes across the energy, environmental and chemical sectors. This promise, however, hinges on overcoming fundamental barriers, including limitations in data availability and quality, challenges in the generalizability and interpretability of data-augmented decisions, and the persistent gap between in silico predictions and experiments. Furthermore, we outline a forward-looking roadmap for deeply integrating AI into heterogeneous catalysis with an AI-ready data ecosystem, multimodal foundation models, and ultimately autonomous laboratories to accelerate the development of next-generation catalytic technologies via AI-empowered human–machine collaboration.

Computational methods↗

DOE OSTI2026

ChemGraph as an agentic framework for computational chemistry workflows

Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered by artificial intelligence and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows. ChemGraph leverages graph neural network-based foundation models for accurate yet computationally efficient calculations and large language models (LLMs) for natural language understanding, task planning, and scientific reasoning to provide an intuitive and interactive interface. We evaluate ChemGraph across 13 benchmark tasks and demonstrate that smaller LLMs (GPT-4o-mini, Claude-3.5-haiku, Qwen-2.5-14B) perform well on simple workflows, while more complex tasks benefit from using larger models. Importantly, we show that decomposing complex tasks into smaller subtasks through a multi-agent framework enables GPT-4o to reach perfect accuracy and smaller LLMs to match or exceed single-agent GPT-4o's performance in these benchmarks.

Computational chemistry↗

DOE OSTI2025

Spin-informed universal graph neural networks for simulating magnetic ordering

The screening and discovery of magnetic materials are hindered by the computational cost of first-principles density-functional theory (DFT) calculations required to find the ground state magnetic ordering. Although universal machine-learning interatomic potentials (uMLIPs), also known as atomistic foundation models, offer high-fidelity models of many atomistic systems with significant speedup, they currently lack the inputs required for predicting magnetic ordering. In this work, we present a data-efficient, spin-informed graph neural network framework that incorporates spin degrees of freedom as inputs and preserves physical symmetries, extending the functionality of uMLIPs to simulate magnetic orderings. This framework speeds up DFT calculations through better initial guesses for magnetic moments, determines the ground-state ordering of bulk materials and even generalizes to magnetic ordering in surfaces. Furthermore, we implement a closed-loop anomaly detection approach that effectively addresses the classic "chicken-and-egg" problem of creating a high-quality dataset while developing a uMLIP, unearthing anomalies in large benchmark datasets and boosting model accuracy.

Xu, Wenbin↗

DOE OSTI2024

Convolutional Variational Autoencoder-based Unsupervised Learning for Power Systems Faults

Classification of power system event data is a growing need, particularly where non-protective relaying-based sensors are used to monitor grid performance. Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to obtain. This paper presents an unsupervised learning method to classify and label transients observed in the distribution grid. A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations. The simulation data is used to train the CVAE that identifies different faults as different clusters in the latent space. The clusters are then used as the foundation model to categorize the real-world data.

Alam, Maksudul↗

DOE OSTI2026

Atomistic Simulation of Glasses and Amorphous Materials: Challenges and Opportunities for the Next Decade

Atomistic simulations have become indispensable tools for understanding glass structure, dynamics, and properties, yet persistent challenges limit their predictive power. This perspective examines three interconnected issues, namely glass formation procedures, interatomic potential development, and machine learning applications, which emerged from the 5th International Workshop on Challenges of Atomistic Simulations of Glasses and Amorphous Materials. We identify convergent community priorities for (i) standardized validation protocols, (ii) curated benchmark datasets with complete metadata, and (iii) open repositories for glasses. A systematic was forward is provided by a hierarchical validation framework for assessing the structural fidelity, property prediction, and behavioral realism of simulation techniques. Looking ahead, transformative advances are promised by the fusion of classical techniques with machine learning based approaches, for instance, by integrating swap Monte Carlo with machine-learning (ML) potentials, leveraging foundation models through transfer learning, and finetuning ML potentials with experimental data. Progress depends on the community committing to validated models, reproducible protocols, and sustained data sharing.

Krishnan, N. M. Anoop↗

DOE OSTI2025

Data Readiness for Scientific AI at Scale

This paper examines how Data Readiness for AI (DRAI) principles apply to leadership-scale scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains—climate, nuclear fusion, bio/health, and materials—to identify common preprocessing patterns and domain-specific constraints. We introduce a two-dimensional readiness framework that combines canonical preprocessing patterns with a five-level operational readiness scale, both tailored to high-performance computing (HPC) environments. This framework helps outline key challenges in transforming large-scale scientific data into formats suitable for scalable AI training. Together, these dimensions form a conceptual maturity matrix that characterizes scientific data readiness and guides infrastructure development toward standardized, cross-domain support for scalable and reproducible AI for science.

Brewer, Wes [ORNL] (ORCID:0000000236393956)↗

DOE OSTI2024

SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97]

You've found the official code repository for the paper "SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems," presented at the Foundation Models for Science: Progress, Opportunities, and Challenges workshop at NeurIPS 2024. Our paper conjectures that interfaces (both text templates as well as conversational) makes interacting with simulation surrogate models for complex systems more intuitive and accessible for both non-experts and experts. "System captions", or SysCaps, are text-based descriptions of systems based on information contained in simulation metadata. Our paper's goal is to train multimodal regression models that take text inputs (SysCaps) and timeseries inputs (exogenous system conditions such as hourly weather) and regress timeseries simulation outputs (e.g. hourly building energy consumption). The experiments in our paper with building and wind farm simulators, which can be reproduced using this codebase, aim to help us understand whether a) accurate regression in this setting is possible and b) if so, how well can we do it. Paper: https://arxiv.org/abs/2405.19653

Emami, Patrick↗

DOE OSTI2025

ORBIT-2 Weather and Climate Downscaling Software Repository

ORBIT-2 is a scalable foundation model for global, hyper-resolution climate and weather downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 ExaFLOPS sustained throughput and 74–98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with 𝑅2 scores in range of 0.98–0.99 against observation data.

Wang, Xiao [Oak Ridge National Laboratory]↗