Search NASA⌕ Search

SEARCH · Search NASA

Results for “language”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
NASA NTRS2019

Simplifying NASA Earth Science Data and Information Access Through Natural Language Processing Based Data Analysis and Visualization

NASA Earth science data collected from satellites, model assimilation, airborne missions, and field campaigns, are large, complex and evolving. Such characteristics pose great challenges for end users (e.g., Earth science and applied science users, students, citizen scientists), particularly for those who are unfamiliar with NASA's EOSDIS and thus unable to access and utilize datasets effectively. For example, a novice user may simply ask: what is the total rainfall for a flooding event in my county yesterday? For an experienced user (e.g., algorithm developer), a question can be: how did my rainfall product perform, compared to ground observations, during a flooding event? Nonetheless, with rapid information technology development such as natural language processing, it is possible to develop simplified Web interfaces and back-end processing components to handle such questions and deliver answers in terms of text, data, or graphic results directly to users.In this presentation, we describe the main challenges for end users with different levels of expertise in accessing and utilizing NASA Earth science data. Surveys reveal that most non-professional users normally do not want to download and handle raw data as well as conduct heavy-duty data processing tasks. Often they just want some simple graphics or data for various purposes. To them, simple and intuitive user interfaces are sufficient because complicated ones can be difficult and time-consuming to learn. Professionals also want such interfaces to answer many questions from datasets. One solution is to develop a natural language based search box like Google and the search results can be text, data, graphics and more. Now the challenge is, with natural language processing, can we design a system to process a scientific question typed in by a user? In this presentation, we describe our plan for such a prototype. The workflow is: 1) extract needed information (e.g., variables, spatial and temporal information, processing methods, etc.) from the input, 2) process the data in the backend, and 3) deliver the results (data or graphics) to the user.

Liu, Zhong↗
NASA NTRS2020

Julia Language 1.1 Ephemeris Reader and Gravitational Modeling Program for Solar System Bodies

This paper analyzes the advancements to the Julia Language 1.1 Ephemeris and Physical constants Reader including the addition of gravitational modeling. Originally written in MATLAB, this Julia Language program is intended to be used in for trajectory design. Written in an open-source coding language, this ephemeris reader can output the state of planetary bodies including asteroids as well as other constants such as gravitational parameters. Two primary methods were chosen to calculate the gravitational potentials which include polyhedral modeling and spherical harmonics.

Gray, Brennan↗
NASA NTRS2021

A Short Glossary of Inclusive Language

Words matter—that old adage that many of us may have heard as children, Sticks and stones may break my bones, but words will never hurt me, is a harmful fallacy. In reality, the language we use has tremendous power to alienate, exclude, deride, humiliate, and wound. On the other hand, thoughtful use of language can signal openness, inclusivity, admiration, and celebration, or simply be an expression of empathy and care for our fellow humans. As part of The Oceanography Society (TOS) Justice, Equity, Diversity, and Inclusion Committee’s series of columns in Oceanography, here we provide a glossary of terms that are often used while discussing topics such as race, ethnicity, gender, sexual orientation, and gender identity. It should be explicitly stated that this list is neither definitive nor exhaustive. Indeed, the terms included here are likely heavily influenced by the authors’ own lived experiences and the lenses through which we see the world. Language is a living entity, a fluid social construct subject to rapid changes and overlaid with regional nuances. Indeed, what may be accurate and acceptable terminology for one person may be entirely unacceptable for another. Keeping this in mind, the following glossary is an attempt to group together some of the acronyms and phrases that are most commonly used today in social justice studies and bodies of work and that may have particular relevance to our community of ocean-related scientists, technologists, and stakeholders. We have borrowed heavily from a wide range of excellent existing scholarship and activism and have cited all sources used. We encourage the reader to follow the links to these multimedia resources and, perhaps, use them as teaching and discussion materials with your students, colleagues, and mentees. Finally, it is our hope that this glossary, along with the links provided to more comprehensive definitions and discussions, helps to define terms that you may have heard used, but not understood, and that it will serve to remind us of the power of the words we use in our everyday professional and personal lives. We begin by defining the very words that form the name of our committee: Justice, Equity, Diversity, and Inclusion (JEDI)

Susanne E. Craig↗
NASA NTRS2024

Hierarchical Semantic Frames for Grounding Language in Robot Control Primitives

As robots become increasingly present in human environments, we need robots to be intuitively commanded by and effectively communicate with humans. In particular, non-expert users should be able to communicate task goals with robots. Language emerges as a logical mode of interaction due to its ubiquity in human environments and, more importantly, as the way humans naturally express tasks. Natural language commands present challenges in that robots must reason over ambiguous language probabilistically and reason over commands they may not be able to execute. We present hierarchical semantic frames , which ground commands in robot control primitives through hierarchies that construct high-level commands from lower-level commands. We demonstrate that hierarchical semantic frames allow robots to understand and execute a variety of commands, such as those involving multiple verb meanings, command variations, and compound nouns. The robot quickly processes hierarchical semantic frames and accurately grounds and executes the commanded tasks, demonstrating the power of hierarchical semantic frames for allowing users to intuitively interact with robots.

Emily Sheetz↗
NASA NTRSDate not supplied

A Natural Language Understanding Approach for Digitizing Aircraft Ground Taxi Instructions

Advancements in natural language processing (NLP) technologies offer a unique opportunity to furnish aircraft crews, primarily pilots, with digital instructions for taxiing operations. Digital taxi instructions, delivered either as text or graphics, can streamline taxiing procedures, thereby reducing radio congestion, minimizing communication errors, and enhancing aircraft monitoring. Techniques used for natural language understanding (NLU), a subset of NLP focused on machine comprehension of natural language, can extract taxi instructions directly from verbal radio communications. This capability paves the way for implementing a digital taxi communication framework with minimal adjustments to the existing air traffic controller operations. This paper delves into a novel application of NLU: the automated generation of digital taxi instructions from air traffic controller speech. We detail the development of an annotation scheme to represent aircraft ground traffic communications within the US National Airspace System (NAS), employing intent classification (IC) and slot filling (SF) to extract taxi instructions using NLU models. Several neural network models were trained on a dataset annotated with our scheme, achieving notable accuracy and F1 scores. Our research demonstrates the feasibility of using NLU to automatically generate digital taxi instructions, showcasing its potential to streamline the implementation of digital taxi communications.

LSTM↗
NASA NTRSDate not supplied

A Natural Language Understanding Approach for Digitizing Aircraft Ground Taxi Instructions

Advancements in natural language processing (NLP) technologies offer a unique opportunity to furnish aircraft crews, primarily pilots, with digital instructions for taxiing operations. Digital taxi instructions, delivered either as text or graphics, can streamline taxiing procedures, thereby reducing radio congestion, minimizing communication errors, and enhancing aircraft monitoring. Techniques used for natural language understanding (NLU), a subset of NLP focused on machine comprehension of natural language, can extract taxi instructions directly from verbal radio communications. This capability paves the way for implementing a digital taxi communication framework with minimal adjustments to the existing air traffic controller operations. This paper delves into a novel application of NLU: the automated generation of digital taxi instructions from air traffic controller speech. We detail the development of an annotation scheme to represent aircraft ground traffic communications within the US National Airspace System (NAS), employing intent classification (IC) and slot filling (SF) to extract taxi instructions using NLU models. Several neural network models were trained on a dataset annotated with our scheme, achieving notable accuracy and 𝐹1 scores. Our research demonstrates the feasibility of using NLU to automatically generate digital taxi instructions, showcasing its potential to streamline the implementation of digital taxi communications.

ATC↗
DOE OSTI2025

Demystifying the Resilience of Large Language Models: An End-to-End Perspective

Deep neural networks are known to be resilient to random bit-wise faults in their parameters. However, this resilience has primarily been established through evaluations of classification models. The extent to which this claim holds for large-language models remains underexplored. In this work, we conduct an extensive measurement study on the impact of random bitwise faults in commercial-scale language models. We perform an in-depth analysis of the resulting generation outputs. We first expose that these language models are not truly resilient to random bit-flips. While aggregate metrics such as accuracy may suggest resilience, an in-depth inspection of the generated outputs shows significant degradation in text quality. Our analysis also shows that tasks requiring more complex reasoning suffer more from performance and quality degradation. Moreover, we extend our analysis to models with augmented reasoning capabilities, such as Chain-of-Thought or Mixture of Experts architectures, and characterize their failure scenarios under random bit-flips.

Sun, Yu↗
DOE OSTI2026

HARMONY: Large-Scale Architecture Search for Efficient Hybrid Language Models

As large language models scale to trillions of parameters, their computational and memory requirements present critical challenges for efficient training and deployment. While Mixture of Experts (MoE) architectures enable efficient scaling through sparse parameter activation, and state-space models like Mamba offer linear-time complexity, principled methods for combining these paradigms remain undeveloped. We introduce HARMONY (Hybrid Architecture Research for Mamba, Optimized with Neural efficiencY), a multi-objective evolutionary neural architecture search framework for discovering efficient hybrid language models that integrate Transformer attention mechanisms, Mixture-of-Experts routing, and Mamba state-space components. Through large-scale distributed search using 16,384 MI250X GPUs on the Frontier supercomputer, HARMONY explores a comprehensive design space encompassing six attention variants (MHA, MQA, GQA, MLA, SWA, and Mamba-2), variable MoE configurations with both routed and shared experts, and extensive Mamba hyperparameters. Our framework discovers heterogeneous architectures that balance training performance with computational efficiency through multi-objective optimization incorporating latency penalties and fitness-based selection. Analysis of discovered architectures reveals that optimal hybrid designs favor heterogeneous component mixing rather than homogeneous patterns, with Mamba-2 and Multi-Head Latent Attention (MLA) emerging as preferred mechanisms. Discovered architectures demonstrate superior training efficiency: our best configuration achieves a final perplexity of 1.0874 with 2.38B parameters while processing 4,320 tokens/second, outperforming significantly larger manually designed models. Full-scale evaluation shows HARMONY's top architectures achieve better loss trajectories than equivalently-sized models using state-of-the-art configurations including Mixtral, Jamba, and Samba. Additionally, we demonstrate 91% weak scaling efficiency when training discovered 36B-parameter models across 1,024 GPUs. HARMONY is released as an open framework with comprehensive tools for building and training hybrid models using expert-data-pipeline parallelism, democratizing access to automated architecture design for next-generation language models.

Herron, Emily [ORNL] (ORCID:0000000273008172)↗
DOE OSTI2025

Large language models for batteries

Large Language Models (LLMs) are advanced artificial intelligence systems capable of solving diverse tasks using language, reasoning, and external tools. Despite their growing deployment in academia and industry, their potential remains underexplored in battery research. This review presents a comprehensive overview of existing and emerging applications of LLMs in batterie field, addressing two critical questions: What can LLMs offer to support battery-related tasks, and how to develop more effective models for this purpose. We begin by outlining the principles of LLMs and criteria for selecting appropriate models and tools for battery research and development. We then explore their roles in text-mining, data interpretation, and the development of intelligent battery systems. In parallel, we discuss technical challenges, such as data standardizing and sharing, model evaluation, and tool integration. Lastly, we propose future research directions with short-, medium-, and long-term goals and highlight more broad perspectives for connecting experts and cross-disciplinary collaborations.

SoC↗
DOE OSTI2025

Language models for materials discovery and sustainability: Progress, challenges, and opportunities

Significant advancements have been made in one of the most critical branches of artificial intelligence: natural language processing (NLP). These advancements are exemplified by the remarkable success of OpenAI’s GPT-3.5/4 and the recent release of GPT-4.5, which have sparked a global surge of interest akin to an NLP gold rush. Here, in this article, we offer our perspective on the development and application of NLP and large language models (LLMs) in materials science. We begin by presenting an overview of recent advancements in NLP within the broader scientific landscape, with a particular focus on their relevance to materials science. Next, we examine how NLP can facilitate the understanding and design of novel materials and its potential integration with other methodologies. To highlight key challenges and opportunities, we delve into three specific topics: (i) the limitations of LLMs and their implications for materials science applications, (ii) the creation of a fully automated materials discovery pipeline, and (iii) the potential of GPT-like tools to synthesize existing knowledge and aid in the design of sustainable materials.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Protein–Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools

The study of protein-protein interactions (PPIs) provides insight into various biological mechanisms, including the binding of antibodies to antigens, enzymes to inhibitors or promoters, and receptors to ligands. Recent studies of PPIs have led to significant biological breakthroughs. For example, the study of PPIs involved in the human:SARS-CoV-2 viral infection mechanism aided in the development of the SARS-CoV-2 vaccines. Though several databases exist for the manual curation of PPI networks, text mining methods have been routinely demonstrated as useful alternatives for newly studied or understudied species where databases are incomplete. Here, the relationship extraction (RE) performance of several open-source classical text processing, machine learning (ML)-based natural language processing (NLP), and large language model (LLM)-based NLP tools were compared. Overall, our results indicated that networks derived from classical methods tend to have high true positive rates at the expense of having overconnected-networks, ML-based NLP methods have lower true positive rates but networks with the closest structures to the target network, and LLM-based NLP methods tend to exist in-between the two other approaches, with variable performances. Finally, the selection of a specific NLP approach should be tied to the needs of a study and text availability, as models varied in performance due to the amount of text provided.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

From natural language to control signals: a conceptual framework for semantic channel finding in complex experimental infrastructure

Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels, accumulated over decades of hardware evolution. Operators and AI systems alike depend on informal expert knowledge, inconsistent naming conventions, and scattered documentation to locate the signals required for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and emerging language-model-driven interfaces. We formalize semantic channel finding, the task of mapping natural-language intent to concrete control-system signals, as a general problem in complex experimental infrastructure, and introduce a four-paradigm conceptual framework to guide architecture selection based on facility-specific data regimes. The paradigms span (i) direct in-context lookup over small, curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate the practical feasibility of each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale: from compact free-electron lasers to large synchrotron light sources, operating under diverse control-system architectures ranging from clean hierarchical naming schemes to legacy environments with decades of heterogeneous conventions. Where evaluated against expert-curated operational queries, these instantiations achieve 90%–97% accuracy, validating the framework’s applicability across real-world deployment scenarios. To accelerate adoption across the broader scientific and industrial control-system community, we release open-source, plug-and-play implementations of all three interactive paradigms-direct lookup, hierarchical navigation, and middle-layer exploration-within the Osprey framework, together with tools for channel database generation, interactive testing, and minimal-configuration deployment. This work establishes semantic channel finding as a foundational capability for human-centric and agentic AI interfaces at large-scale facilities, providing both a systematic framework for architecture design and practical resources to enable adoption without building custom infrastructure from scratch.

channel finding↗
DOE OSTI2025

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Leveraging Natural Language Processing and Generative Models in Molecular Chemistry: Property Prediction and Novel Compound Generation

The accurate prediction of molecular properties is important for the rational design and the advancement of green chemistry and sustainable materials research. However, the predictive power of traditional computational chemistry methods is limited due to computational restrictions. Here, in this study, we examine an alternative approach to the accurate prediction of properties of organic compounds: natural language processing (NLP)-based molecular embedding. Using viscosity, partition coefficient (log P), and enthalpy of vaporization as test properties through a survey of comprehensive datasets comprising 5695 data points for viscosity, 25 870 data points for log P, and 2296 data points for enthalpy of vaporization. These are important properties for the design of greener, safer, and sustainable chemical processes. Models were trained using NLP methods such as Mol2vec and fine-tuned ChemBERTa, and results were compared with traditional input featurization techniques such as Morgan fingerprints and quantum chemistry derived sigma profiles and DFT features. Among the various machine learning models, Mol2vec demonstrated superior predictive capabilities, achieving the highest correlation coefficient (R 2 = 0.945) and lowest RMSE (0.106 mPa s) for viscosity, as well as high accuracy for log P and enthalpy of vaporization predictions. These findings establish the Mol2vec featurization technique, graph-convolutional neural networks (GCNN), and fine-tuned ChemBERTa model as powerful tools for predictive modeling of organic compounds properties, offering a significant improvement over previously used featurization techniques and opening up strategies for very-high-throughput computational screening. Finally, we integrated ML models with hybrid language-model-based generative adversarial networks (LM-GAN) to generate novel molecular sequences with desirable properties for different research applications. The ability to computationally design solvents with lower viscosity, lower log P, and lower enthalpy of vaporization offers a data-driven route to accelerating the discovery of sustainable alternatives to traditionally toxic solvents.

ChemBERTa↗
DOE OSTI2026

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

Debiasing Watermarks for Large Language Models via Maximal Coupling

Watermarking language models is essential for distinguishing between human and machine-generated text and thus maintaining the integrity and trustworthiness of digital communication. Here, we present a novel green/red list watermarking approach that partitions the token set into “green” and “red” lists, subtly increasing the generation probability for green tokens. To correct token distribution bias, our method employs maximal coupling, using a uniform coin flip to decide whether to apply bias correction, with the result embedded as a pseudorandom watermark signal. Theoretical analysis confirms this approach’s unbiased nature and robust detection capabilities. Experimental results show that it outperforms prior techniques by preserving text quality while maintaining high detectability, and it demonstrates resilience to targeted modifications aimed at improving text quality. This research provides a promising watermarking solution for language models, balancing effective detection with minimal impact on text quality.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Synergizing human expertise and AI efficiency with language model for microscopy operation and automated experiment design

With the advent of large language models (LLMs), in both the open source and proprietary domains, attention is turning to how to exploit such artificial intelligence (AI) systems in assisting complex scientific tasks, such as material synthesis, characterization, analysis and discovery. Here, we explore the utility of LLMs, particularly ChatGPT4, in combination with application program interfaces (APIs) in tasks of experimental design, programming workflows, and data analysis in scanning probe microscopy, using both in-house developed APIs and APIs given by a commercial vendor for instrument control. We find that the LLM can be especially useful in converting ideations of experimental workflows to executable code on microscope APIs. Beyond code generation, we find that the GPT4 is capable of analyzing microscopy images in a generic sense. At the same time, we find that GPT4 suffers from an inability to extend beyond basic analyses for more in-depth technical experimental design. We argue that an LLM specifically fine-tuned for individual scientific domains can potentially be a better language interface for converting scientific ideations from human experts to executable workflows. Such a synergy between human expertise and LLM efficiency in experimentation can open new doors for accelerating scientific research, enabling effective experimental protocols sharing in the scientific community.

97 MATHEMATICS AND COMPUTING↗