Search NASA⌕ Search

SEARCH · Search NASA

Results for “knowledge discovery”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Technical Track on Biomass Carbon Removal and Storage (BiCRS): Mapping bioresources, phase 1 - Consistency check comparing Mission Innovation’s Data Visualization Tool for Bioresources and the Clean Energy Ministerial Biofuture Initiative Global Biomass data accessible via the US Department of Energy’s Bioenergy Knowledge Discovery Framework (KDF)

The Mission Innovation (MI) Carbon Dioxide Removal (CDR) Mission, Technical Track on Biomass Carbon Dioxide Removal and Storage (BiCRS), has produced a biomass resource database for its members. In parallel, Oak Ridge National Laboratory (ORNL) developed the International Feedstock Reporting data portal—herein referred to as the CEM Biofuture-KDF data—on behalf of the Clean Energy Ministerial Biofuture Initiative (CEM Biofuture), as a specific task under Biofuture’s 2024–25 Action Plan. This work was conducted at the request of CEM Biofuture and funded by the U.S. Department of Energy in support of that initiative, and it is hosted within DOE’s Knowledge Discovery Framework (KDF).

09 BIOMASS FUELS↗
DOE OSTI2025

MuSIKAL: Multiphysics Simulations and Knowledge Discovery through AI/ML Technologies

Under the MuSiKAL project, we developed a framework for a coastal digital twin (DT) platform capable of integrating diverse data resources, configuring multiscale model simulations, performing SciML‐accelerated predictions, with applications primarily driven by storm surge and heavily rainfall events impacting the Gulf Coast of the U.S.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

SEED: Semantic Energy Exploration and Discovery

The Bioenergy Knowledge Discovery Framework (KDF) hosts a vast repository of specialized data, yet traditional keyword-based search methods often struggle to provide direct answers, requiring significant domain expertise and manual effort to filter through raw documents. To overcome these barriers, this software introduces a semantic search engine that enables both specialists and non-specialists to query the KDF using natural language. By shifting from rigid keyword matching to intent-based retrieval, the tool automatically identifies and ranks the most relevant sources within the database. The system functions by processing natural language queries to extract the most pertinent information, delivering an AI-generated plain-language summary alongside exact supporting quotes from retrieved documents. This integrated approach provides users with immediate, evidence-based answers while eliminating the need for exhaustive manual review. By surfacing direct insights and contextual evidence, the software enhances the usability of existing KDF resources and democratizes access to complex bioenergy data. Ultimately, this semantic search solution accelerates the discovery process and supports faster, more informed decision-making across the bioenergy sector.

Pan, Meiyu (Melrose) [Oak Ridge National Laborator↗
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↗
DOE OSTI2025

A Scientist-in-the-Loop Data Analytics Framework for Intelligent Simulation Model Tuning and Validation

This project developed a scientist-in-the-loop data analytics framework for intelligent simulation model tuning and validation, targeting the Weather Research and Forecasting (WRF) model and its solar energy variant, WRF-Solar-BNL. Domain experts, such as climate scientists, depend on large-scale numerical simulations for knowledge discovery and decision-making, yet the complexity of parameter tuning and the disconnect between automated optimization and domain expertise pose significant challenges. We extended an interactive visual analytics framework that enables domain experts to observe and intervene in the computational steering process by identifying disagreements between the simulation model, surrogate model, and the expert’s domain knowledge. Using Bayesian Optimization with Gaussian Process Regression as the surrogate model, our system allows users to probe parameter relationships, analyze correlation patterns, and adjust tuning parameters in real time. We developed use cases for solar irradiance forecasting through sustained collaboration with Brookhaven National Laboratory, resolving critical model configuration challenges and achieving meaningful reductions in prediction error. The project supported one PhD student, one MS student, and eight undergraduate students across three Data Science Capstone projects, resulting in one master’s thesis.

Dasgupta, Aritra [New Jersey Institute of Technolo↗
DOE OSTI2025

Comparative Performance Evaluation of Large Language Models for Extracting Molecular Interactions and Pathway Knowledge

Understanding the interactions and regulatory relationships among biomolecules is essential for deciphering complex biological systems and elucidating the mechanisms behind diverse biological functions. Traditionally, the collection of such molecular interaction data has relied on expert curation, a process that is both time-consuming and labor-intensive. To address these limitations, this study explores the use of large language models (LLMs) to automate the genome-scale extraction of molecular interaction knowledge. Here, we evaluate the performance of various LLMs on key biological tasks, including the identification of protein-protein interactions, detection of genes associated with pathways influenced by low-dose radiation, and inference of gene regulatory relationships. Our findings demonstrate that larger LLMs tend to perform better, particularly in extracting intricate gene and protein interactions. Despite their strengths, these models face challenges in recognizing functionally diverse gene groups and highly correlated regulatory relationships. Through a comprehensive analysis using established molecular interaction and pathway databases, we show that LLMs possess the potential to identify relevant biomolecules and predict their interactions, offering valuable insights and marking a significant step toward AI-driven biological knowledge discovery.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2025

Domain-specific text embedding model for accelerator physics

Accelerator physics presents unique challenges for natural language processing (NLP) due to its specialized terminology and complex concepts. A key component in overcoming these challenges is the development of robust text embedding models that transform textual data into dense vector representations, facilitating efficient information retrieval and semantic understanding. In this work, we introduce AccPhysBERT, a sentence embedding model fine-tuned specifically for accelerator physics. Our model demonstrates superior performance across a range of downstream NLP tasks, surpassing existing models in capturing the domain-specific nuances of the field. We further showcase its practical applications, including semantic paper-reviewer matching and integration into retrieval-augmented generation systems, highlighting its potential to enhance information retrieval and knowledge discovery in accelerator physics. Published by the American Physical Society 2025

Hellert, Thorsten (ORCID:0000000227970926)↗
DOE OSTI2025

pnnl/HypoGen

An innovative workflow for automatic knowledge discovery in material science, combining experimental automation with advanced machine learning and artificial intelligence techniques

Yin, Tim [Pacific Northwest National Laboratory (P↗
DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗
DOE OSTI2026

Visualization for Insight and Data Analysis in Energy Research

This talk explores how advanced visualization technologies are transforming analytical reasoning and knowledge discovery in energy research, drawing on recent work at the National Laboratory of the Rockies' Computational Science Center. Through a series of scientific case studies, we demonstrate how immersive and high-resolution visualization environments enable scientists and engineers to identify previously unseen patterns and features - insights that often remain hidden in traditional desktop-based analysis. By embedding richer information into interactive analytics tools, these approaches support the exploration of complex, multivariate parameter spaces, where interaction itself catalyzes understanding. Beyond capability, we emphasize the critical role of visualization design grounded in perception and cognition, showing how visual encodings directly influence analytical outcomes. Spanning applications from materials science to integrated energy systems, these visualization approaches accelerate innovation and improve decision-making by enabling deeper, more reliable insight into increasingly complex energy data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Causal discovery from data assisted by large language models

Knowledge-driven discovery of novel materials necessitates the development of causal models for property emergence. While in the classical physical paradigm, the causal relationships are deduced based on physical principles or via experiment, the rapid accumulation of observational data necessitates learning causal relationships between dissimilar aspects of material structure and functionalities based on observations. For this, it is essential to integrate experimental data with prior domain knowledge. Here, we demonstrate this approach by combining high-resolution scanning transmission electron microscopy data with insights derived from large language models (LLMs). By applying ChatGPT to domain-specific literature, such as arXiv papers on ferroelectrics, and combining the obtained information with data-driven causal discovery, we construct adjacency matrices for directed acyclic graphs that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO 3 . This approach enables us to hypothesize how synthesis conditions influence material properties and guides experimental validation. Furthermore, the ultimate objective of this work is to develop a unified framework that integrates LLM-driven literature analysis with data-driven discovery, facilitating the precise engineering of ferroelectric materials by establishing clear connections between synthesis conditions and their resulting material properties.

Causal inference↗
DOE OSTI2026

Transformative Impacts of Laser-Induced Breakdown Spectroscopy on Environmental and Biological Research at Oak Ridge National Laboratory

This manuscript will present an advancement of transformative research that has been conducted at Oak Ridge National Laboratory (ORNL) over a 25-year period (2000–2025) on a variety of environmental and biological matrices. These investigations derived a fundamental understanding of how elemental detection and analysis of these matrices led to the knowledge and discovery of natural processes in plants and the environment. Each project led to the initiation of a new research area which unearthed awesome and novel breakthroughs. Highlights are listed below: 1. The preliminary research at ORNL centered on the detection of aerosols utilizing Laser-induced Breakdown Spectroscopy (LIBS) technology. The Clean Air Act Amendment (CAAA) of 1990 highlighted the importance of identifying hazardous air pollutants (HAPs) due to their impact on environmental and human health, thereby underscoring the need to detect various toxic elements. Research in aerosol chemistry aimed to identify these harmful elements released by factories during periods of increased emissions in their manufacturing processes. LIBS emerged as the most effective method for real-time, in situ measurements of metal species in both gaseous and aerosol phases. 2. An understanding of the presence of total carbon in soils gives perspective on how to develop carbon sequestration strategies. The recognition that carbon sinks can evolve back to carbon sources to emit back to the atmosphere was an important consideration. Also, the concentration of carbon in soil indicates the health of land areas for growing crops successfully. 3. The direct detection of most of the elements in a wood sample in a single emission spectrum, without sample preparation, encouraged the research to use the LIBS technique for preservative treated wood coupled with use of multivariate statistical methodology. Additionally, it encouraged the researchers to try to differentiate natural woods from different parts of the country, and it was successfully demonstrated that LIBS coupled with MVA analysis could differentiate wood of different species from each other and of similar species grown in different environments based on their elemental spectra. This was a breakthrough since it revealed a systematic approach to connect elemental scarcity and abundance to either drought or typical rainfall conditions for the hardwood trees grown in specific areas. 4. Furthermore, the research progressed to reveal physiological and developmental processes contributing to biomass production such that the variation in leaf elemental composition increases our understanding of terrestrial nutrient cycles, as well as tracking the transfer of toxic elements from soils to living organisms. 5. Recently another breakthrough viz., ionomics initiated the correlation of elements to specific genes, uncovering the function that the element performed in the plant. More recently, this has been extended from plants to fungi as well as fungi growing in symbiotic relations with plants.

09 BIOMASS FUELS↗
DOE OSTI2024

K–Co–Mo–S x chalcogel: high-capacity removal of Pb 2+ and Ag + and the underlying mechanisms

Chalcogenide-based aerogels, known as chalcogels, represent a novel class of nanoparticle-based porous amorphous materials characterized by high surface polarizability and Lewis base properties, exhibiting promising applications in clean energy and separation science. This work presents a K–Co–Mo–S x (KCMS) chalcogel as a highly efficient sorbent for heavy metal ions and details its sorption mechanisms. Its incoherent structure comprises Mo 2 V (S 2 ) 6 and Mo 3 IV S(S 6 ) 2 anion-like clusters with four- and six-coordinated Co–S polyhedra, forming a Co–Mo–S covalent network that hosts K + ions through electrostatic attraction. The interactions of KCMS with heavy metal ions, particularly Pb 2+ and Ag + , reveal that KCMS is exceptionally effective in removing these ions from ppm concentrations down to trace levels (≤5 ppb). KCMS rapidly removes Ag + (≈81.7%) and Pb 2+ (≈99.5%) within five minutes, achieving >99.9% removal within an hour, with a distribution constant K d ≥10 8 mL g -1 . KCMS exhibits an impressive removal capacity of 1378 mg g -1 for Ag + and 1146 mg g -1 for Pb 2+ , establishing it as one of the most effective materials known to date for heavy metal removal. This material is also effective for the removal of Ag + and Pb 2+ along with Hg 2+ , Ni 2+ , Cu 2+ , and Cd 2+ from various water sources even in the presence of highly concentrated and chemically diverse cations, anions, and organic species. Analysis of the post-interacted KCMS by synchrotron X-ray pair distribution function (PDF), X-ray photoelectron spectroscopy (XPS) and energy dispersive X-ray spectroscopy (EDS) revealed that the sorption of Pb 2+ , Ag + , and Hg 2+ mainly occurs by the exchange of K + and Co 2+ . Despite being amorphous, this material exhibits unprecedented ion-exchange mechanisms both for the ionically and covalently bound K + and Co 2+ , respectively. In conclusion, this discovery advances our knowledge of amorphous gels and guides material synthesis principles for the highly selective and efficient removal of heavy metal ions from water.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

A roadmap toward scaling, reasoning and self-evolving foundation models for nuclear and particle physics

Foundation models have revolutionized artificial intelligence, with Large Language Models demonstrating unprecedented capabilities in multimodal understanding, reasoning and tool use. Nuclear and particle physics stands at a critical juncture where similar transformative potential awaits realization. The field generates exabytes of experimental data, exascale simulations, and decades of theoretical insights — yet these remain largely disconnected from modern Artifical Intelligence (AI) capabilities, with most physics AI applications confined to narrow, task-specific models that suffer from domain shifting when applied to real experimental data. We present a roadmap for FM4NPP (Foundation Model for Nuclear and Particle Physics), systematically scaling from current proof-of-concept models to trillion-parameter architectures capable of autonomous discovery. Our approach advances three critical frontiers: unified data infrastructure integrating detector data, scientific knowledge and computational tools across global facilities; multi-facility foundation models enabling cross-experiment knowledge transfer and accelerated discovery; and agentic AI capabilities for reasoning and autonomous tool use. The resulting self-evolving FM4NPP will transform physics research by converting time-intensive data analysis, theory derivation and computational bottlenecks into rapid AI–human collaborative discovery. This paradigm shift promises to fundamentally accelerate scientific progress in nuclear and particle physics, enabling researchers to focus on high-level insights while AI handles routine analysis and explores vast parameter spaces beyond human capacity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Physical discovery in representation learning via conditioning on prior knowledge

Recent advances in electron, scanning probe, optical, and chemical imaging and spectroscopy yield bespoke data sets containing the information of structure and functionality of complex systems. In many cases, the resulting data sets are underpinned by low-dimensional simple representations encoding the factors of variability within the data. The representation learning methods seek to discover these factors of variability, ideally further connecting them with relevant physical mechanisms. However, generally, the task of identifying the latent variables corresponding to actual physical mechanisms is extremely complex. Here, we present an empirical study of an approach based on conditioning the data on the known (continuous) physical parameters and systematically compare it with the previously introduced approach based on the invariant variational autoencoders. The conditional variational autoencoder (cVAE) approach does not rely on the existence of the invariant transforms and hence allows for much greater flexibility and applicability. Interestingly, cVAE allows for limited extrapolation outside of the original domain of the conditional variable. However, this extrapolation is limited compared to the cases when true physical mechanisms are known, and the physical factor of variability can be disentangled in full. We further show that introducing the known conditioning results in the simplification of the latent distribution if the conditioning vector is correlated with the factor of variability in the data, thus allowing us to separate relevant physical factors. We initially demonstrate this approach using 1D and 2D examples on a synthetic data set and then extend it to the analysis of experimental data on ferroelectric domain dynamics visualized via piezoresponse force microscopy.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Geospatial Data Platform for All

Spatiotemporal data has evolved in scale due to augmented use in cross-domain applications. Simultaneously, there is substantial growth in the availability of Geographic Information Systems (GIS) data provided by the United States Geological Survey (USGS) along with other federal, state, county, or local agencies through open-data portals and public access APIs. However, data availability does not equate with accessibility. Large-scale analyses and applications require robust, performant data management with co-location of data storage and computing. The insufficiency of data management infrastructure compels researchers to adopt ad hoc project- specific GIS data storage solutions (e.g., copying data to High-Performance computer file systems). As an ad hoc storage strategy does not scale, it hampers cross-domain analyses causing difficulty in data reuse and utilizing existing code bases. Furthermore, GIS data is complex and requires expertise to analyze and manipulate due to its intricate data structures and data-specific projection transformations. Despite the challenges, we recognize that derived GIS data products, e.g., satellite or LIDAR-based images, can be used in downstream applications such as AI by domain, but non-GIS experts. To address the data needs and overcome the challenges, we are working towards a GIS Data Platform focused on efficient data storage, data discovery and access, and an API to enable common workflows. We propose a knowledge-graph (KG) approach for data discovery, whereby datasets are semantically linked to higher- level constructs such as projects and research areas. The semantic data links enable researchers to explore datasets in a top-down approach by specifying relevant and meaningful terms (assists in finding hidden data). An advantage is that the nodes and edges in a knowledge graph create built-in semantic documentation. Deeper spatiotemporal connections between data sources can be encoded via Graph Neural Networks (GNN) (Zhang et al., 2021). The KG approach can be extended to integrate the data itself in a Virtual KG (VKG). Our work will derive inspiration from large-scale VKG efforts that have been undertaken or are currently underway as part of the OpenStreetMap project (Ding et al., 2021). For DOE Data Days, we share the proposed geospatial data platform hybrid (cloud/on-prem) architecture, our work-to-date on storing, retrieving, and transforming LiDAR and raster data relevant to two important NREL use-cases, including the Renewable Energy Potential (reV) Model, and present our proposal for a KG based data discovery engine.

data platform↗