SEARCH · Search NASA

Results for “Natural language processing”

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 271 records · Page 15

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Control And Optimization Modular Modeling Application For Nuclear Deployment

The purpose of the COMMAND code is to provide a flexible, scalable tool for use in developing, integrating, and testing the technologies necessary for achieving autonomous operations of advanced nuclear reactors. The code enables users to efficiently implement custom simulations and experiments by combining key methods from different software modules. These modules are focused on: modeling and simulation tools, such as nuclear simulation tools used for high-fidelity modeling (e.g., Reactor Excursion and Leak Analysis Program [RELAP5-3D] and Monte Carlo N-Particle [MCNP]); machine learning and optimization tools (e.g., anomaly detection and data-driven modeling techniques); advanced control in its digital, high-performance, and supervisory control forms (e.g., proportional integral derivative (PID) control and model predictive control (MPC); and integration with hardware through industrial communication protocols. To ensure flexibility and scalability, COMMAND was designed to be both modular—the software “pieces” all inherit from generic building blocks and can be combined and connected to create complicated simulations—and high performing—designed for parallel processing, enabling simulations and experiments to take advantage of multi-core computers, servers, and nodes. The code is written in the Python programming language due to the language's popularity, active community, and open-source and cross-platform nature. Maintaining consistency with other simulation tools used within the nuclear energy community, users implement simulations and experiments through text input files, which define components, parameters, connections, etc., through lines of text. Given that COMMAND is written in Python, these input files are native Python scripts, and so use the standard Python structure and formatting. This also enables users to take advantage of Python's extensive package library to develop custom capabilities for their specific use cases.

Faber, Jacob [Idaho National Laboratory (INL), Ida↗

NASA NTRS1983

Databases as an information service

The relationship of databases to information services, and the range of information services users and their needs for information is explored and discussed. It is argued that for database information to be valuable to a broad range of users, it is essential that access methods be provided that are relatively unstructured and natural to information services users who are interested in the information contained in databases, but who are not willing to learn and use traditional structured query languages. Unless this ease of use of databases is considered in the design and application process, the potential benefits from using database systems may not be realized.

Vincent, D. A.↗

NASA NTRS1991

Neural network technologies

A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.

Villarreal, James A.↗

NASA NTRS1994

Learning procedures from interactive natural language instructions

Despite its ubiquity in human learning, very little work has been done in artificial intelligence on agents that learn from interactive natural language instructions. In this paper, the problem of learning procedures from interactive, situated instruction is examined in which the student is attempting to perform tasks within the instructional domain, and asks for instruction when it is needed. Presented is Instructo-Soar, a system that behaves and learns in response to interactive natural language instructions. Instructo-Soar learns completely new procedures from sequences of instruction, and also learns how to extend its knowledge of previously known procedures to new situations. These learning tasks require both inductive and analytic learning. Instructo-Soar exhibits a multiple execution learning process in which initial learning has a rote, episodic flavor, and later executions allow the initially learned knowledge to be generalized properly.

Huffman, Scott B.↗

DOE OSTI2025

PDF Entity Annotation Tool (PEAT)

While different text mining approaches – including the use of Artificial Intelligence (AI) and other machine based methods - continue to expand at a rapid pace, the tools used by researchers to create the labeled datasets required for training, modeling, and evaluation remain rudimentary. Labeled datasets contain the target attributes the machine is going to learn; for example, training an algorithm to delineate between images of a car or truck would generally require a set of images with a quantitative description of the underlying features of each vehicle type. Development of labeled textual data that can be used to build natural language machine learning models for scientific literature is not currently integrated into existing manual workflows used by domain experts. Published literature is rich with important information, such as different types of embedded text, plots, and tables that can all be used as inputs to train ML/natural language processing (NLP) models, when extracted and prepared in machine readable formats. Currently, both normalized data extraction of use to domain experts and extraction to support development of ML/NLP models are labor intensive and cumbersome manual processes. Automatic extraction of data and information from formats such as PDFs that are optimized for layout and human readability, not machine readability. The PDF (Portable Document Format) Entity Annotation Tool (PEAT) was developed with the goal of allowing users to annotate publications within their current print format, while also allowing those annotations to be captured in a machine-readable format. One of the main issues with traditional annotation tools is that they require transforming the PDF into plain text to facilitate the annotation process. While doing so lessens the technical challenges of annotating data, the user loses all structure and provenance that was inherent in the underlying PDF. Also, textual data extraction from PDFs can be an error prone process. Challenges include identifying sequential blocks of text and a multitude of document formats (multiple columns, font encodings, etc.). As a result of these challenges, using existing tools for development of NLP/ML models directly from PDFs is difficult because the generated outputs are not interoperable. We created a system that allows annotations to be completed on the original PDF document structure, with no plain text extraction. The result is an application that allows for easier and more accurate annotations. In addition, by including a feature that grants the user the ability to easily create a schema, we have developed a system that can be used to annotate text for different domain-centric schemas of relevance to subject matter experts. Different knowledge domains require distinct schemas and annotation tags to support machine learning.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1987

Machine-aided indexing for NASA STI

One of the major components of the NASA/STI processing system is machine-aided indexing (MAI). MAI is a computer process that generates a set of indexing terms selected from NASA's thesaurus, is used for indexing technical reports, is based on text, and is reviewed by indexers. This paper summarizes the MAI objectives and discusses the NASA Lexical Dictionary, subject switching, and phrase matching or natural languages. The benefits of using MAI are mentioned, and MAI production improvement and the future of MAI are briefly addressed.

Wilson, John↗

NASA NTRS1989

Knowledge acquisition from natural language for expert systems based on classification problem-solving methods

It is shown how certain kinds of domain independent expert systems based on classification problem-solving methods can be constructed directly from natural language descriptions by a human expert. The expert knowledge is not translated into production rules. Rather, it is mapped into conceptual structures which are integrated into long-term memory (LTM). The resulting system is one in which problem-solving, retrieval and memory organization are integrated processes. In other words, the same algorithm and knowledge representation structures are shared by these processes. As a result of this, the system can answer questions, solve problems or reorganize LTM.

Gomez, Fernando↗

DOE OSTI2026

Bayesian Optimization of Catalysis with In-Context Learning

Large language models (LLMs) can perform accurate classification with zero or few examples through in-context learning (ICL), allowing the model to observe query-relevant examples at inference time and eliminating the need for additional weight updates to generalize beyond its original training data. We extend this capability to regression with uncertainty estimation using frozen LLMs (e.g., GPT-4o, Gemini), enabling Bayesian optimization (BO) in natural language without explicit model training or feature engineering. We apply this to materials discovery by representing materials as synthesis and testing procedures for use in natural language prompts. This Bayesian, design-first approach prioritizes optimization toward target material properties before detailed characterization, in contrast to conventional experimental workflows that often emphasize characterization of suboptimal materials. On benchmarks like aqueous solubility and oxidative coupling of methane (OCM), BO-ICL matches or outperforms Gaussian processes. In live experiments on the reverse water–gas shift (RWGS) reaction, BO-ICL identifies multimetallic catalysts that approach equilibrium CO yield within 6 and 10 iterations from a pool of 3,700 and 360,000 candidates, respectively. Our method redefines materials representation and accelerates discovery, with broad applications across catalysis, materials science, and AI.

Calibration↗

DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗

NASA NTRSDate not supplied

Information Extraction on an Earth Science Knowledge Graphs with Semantic Parsing

Knowledge graphs are an important tool, both for representing knowledge and for retrieving information. Fundamentally, they are semantic networks that represent entities and relationships in the form of nodes and edges. A large corpus of natural language text can bebroken down into discrete entities and relationships to form a useful knowledge graph. Existing research breaks down text into a subject, object, and verb relationship triple. Although this is a useful first step, it loses much of the original contextual information encoded within the text. Our process uses a novel 7-tuple approach, in which elements of sentences are programmatically parsed into seven categories: initiator, impacted, receiver, beneficiary, result, and context. In this presentation, we show a knowledge graph built using this 7-tupleprocessing of an Earth science corpus. We explain the techniques used to create the graph and analyze its information retrieval capability while assessing the accuracy and limitations of the results.

Carson Davis↗

NASA NTRS1972

Natural Resource Information System, design analysis

The computer-based system stores, processes, and displays map data relating to natural resources. The system was designed on the basis of requirements established in a user survey and an analysis of decision flow. The design analysis effort is described, and the rationale behind major design decisions, including map processing, cell vs. polygon, choice of classification systems, mapping accuracy, system hardware, and software language is summarized.

Source record↗

NASA NTRS2014

VARED: Verification and Analysis of Requirements and Early Designs

Requirements are a part of every project life cycle; everything going forward in a project depends on them. Good requirements are hard to write, there are few useful tools to test, verify, or check them, and it is difficult to properly marry them to the subsequent design, especially if the requirements are written in natural language. In fact, the inconsistencies and errors in the requirements along with the difficulty in finding these errors contribute greatly to the cost of the testing and verification stage of flight software projects [1]. Large projects tend to have several thousand requirements written at various levels by different groups of people. The design process is distributed and a lack of widely accepted standards for requirements often results in a product that varies widely in style and quality. A simple way to improve this would be to standardize the design process using a set of tools and widely accepted requirements design constraints. The difficulty with this approach is finding the appropriate constraints and tools. Common complaints against the tools available include ease of use, functionality, and available features. Also, although preferable, it is rare that these tools are capable of testing the quality of the requirements.

Badger, Julia↗

NASA NTRS2005

Use of Field Programmable Gate Array Technology in Future Space Avionics

Fulfilling NASA's new vision for space exploration requires the development of sustainable, flexible and fault tolerant spacecraft control systems. The traditional development paradigm consists of the purchase or fabrication of hardware boards with fixed processor and/or Digital Signal Processing (DSP) components interconnected via a standardized bus system. This is followed by the purchase and/or development of software. This paradigm has several disadvantages for the development of systems to support NASA's new vision. Building a system to be fault tolerant increases the complexity and decreases the performance of included software. Standard bus design and conventional implementation produces natural bottlenecks. Configuring hardware components in systems containing common processors and DSPs is difficult initially and expensive or impossible to change later. The existence of Hardware Description Languages (HDLs), the recent increase in performance, density and radiation tolerance of Field Programmable Gate Arrays (FPGAs), and Intellectual Property (IP) Cores provides the technology for reprogrammable Systems on a Chip (SOC). This technology supports a paradigm better suited for NASA's vision. Hardware and software production are melded for more effective development; they can both evolve together over time. Designers incorporating this technology into future avionics can benefit from its flexibility. Systems can be designed with improved fault isolation and tolerance using hardware instead of software. Also, these designs can be protected from obsolescence problems where maintenance is compromised via component and vendor availability.To investigate the flexibility of this technology, the core of the Central Processing Unit and Input/Output Processor of the Space Shuttle AP101S Computer were prototyped in Verilog HDL and synthesized into an Altera Stratix FPGA.

Ferguson, Roscoe C.↗

NASA NTRS1993

Reactive system verification case study: Fault-tolerant transputer communication

A reactive program is one which engages in an ongoing interaction with its environment. A system which is controlled by an embedded reactive program is called a reactive system. Examples of reactive systems are aircraft flight management systems, bank automatic teller machine (ATM) networks, airline reservation systems, and computer operating systems. Reactive systems are often naturally modeled (for logical design purposes) as a composition of autonomous processes which progress concurrently and which communicate to share information and/or to coordinate activities. Formal (i.e., mathematical) frameworks for system verification are tools used to increase the users' confidence that a system design satisfies its specification. A framework for reactive system verification includes formal languages for system modeling and for behavior specification and decision procedures and/or proof-systems for verifying that the system model satisfies the system specifications. Using the Ostroff framework for reactive system verification, an approach to achieving fault-tolerant communication between transputers was shown to be effective. The key components of the design, the decoupler processes, may be viewed as discrete-event-controllers introduced to constrain system behavior such that system specifications are satisfied. The Ostroff framework was also effective. The expressiveness of the modeling language permitted construction of a faithful model of the transputer network. The relevant specifications were readily expressed in the specification language. The set of decision procedures provided was adequate to verify the specifications of interest. The need for improved support for system behavior visualization is emphasized.

Crane, D. Francis↗

NASA NTRS1992

GATOR: Requirements capturing of telephony features

We are developing a natural language-based, requirements gathering system called GATOR (for the GATherer Of Requirements). GATOR assists in the development of more accurate and complete specifications of new telephony features. GATOR interacts with a feature designer who describes a new feature, set of features, or capability to be implemented. The system aids this individual in the specification process by asking for clarifications when potential ambiguities are present, by identifying potential conflicts with other existing features, and by presenting its understanding of the feature to the designer. Through user interaction with a model of the existing telephony feature set, GATOR constructs a formal representation of the new, 'to be implemented' feature. Ultimately GATOR will produce a requirements document and will maintain an internal representation of this feature to aid in future design and specification. This paper consists of three sections that describe (1) the structure of GATOR, (2) POND, GATOR's internal knowledge representation language, and (3) current research issues.

Dankel, Douglas D., II↗

NASA NTRS1989

Applications of artificial intelligence to space station and automated software techniques: High level robot command language

The objective is to develop a system that will allow a person not necessarily skilled in the art of programming robots to quickly and naturally create the necessary data and commands to enable a robot to perform a desired task. The system will use a menu driven graphical user interface. This interface will allow the user to input data to select objects to be moved. There will be an imbedded expert system to process the knowledge about objects and the robot to determine how they are to be moved. There will be automatic path planning to avoid obstacles in the work space and to create a near optimum path. The system will contain the software to generate the required robot instructions.

Mckee, James W.↗

DOE OSTI2025

Arctic shrub expansion generates regional variation in litter decomposition by altering litter quality and the decomposition environment

Abstract The expansion of deciduous shrubs into the graminoid‐dominated arctic tundra is expected to alter litter decomposition by changing litter quality and local abiotic and biotic conditions. However, it remains unclear how shrub expansion will affect litter decomposition at regional scales, where macroclimate is expected to be the dominant regulator of decomposition. To determine the relative influence of macroclimate and local controls on regional patterns of litter mass loss and nitrogen release, we conducted two hierarchical litter decomposition experiments across spatial scales. We decomposed leaf and root litter from a prominent graminoid ( Eriophorum vaginatum ) and three genera of deciduous shrubs ( Betula , Alnus and Salix ) for 1 year within replicated plots at five sites spanning a 160 km latitudinal gradient in northern Alaska. Using Eriophorum litter as a substrate, we found that macroclimate was the primary regulator of mass loss but had opposing effects on leaf and root litter. As summer temperature increased along the latitudinal gradient (11.9 to 13.9°C), leaf litter mass loss increased by 20% whereas root litter mass loss decreased by 33%. Leaf nitrogen release also increased with summer temperature. Conversely, root nitrogen release was controlled by the vegetation type of the decomposition environment. Using different shrub litters as substrates, we found that litter quality and its interaction with soil microclimate and macroclimate controlled decomposition. Overall, shrub root litters decomposed faster than Eriophorum root litter, losing 53% more mass and 190% more nitrogen across all sites and decomposition environments. For leaf litter, however, patterns varied by litter genus, with Salix losing more mass and Betula and Alnus losing less mass than Eriophorum . Our findings demonstrate that shrub expansion in the Arctic can regulate leaf and root litter decomposition at the regional scale through its effects on local controls, primarily litter quality. Ongoing increases in shrub cover are likely to accelerate the turnover of root litter carbon and nitrogen pools in tundra ecosystems. Therefore, including shrub‐related processes in Earth system models will improve our ability to predict regional‐scale litter decomposition and its effects on carbon and nutrient cycling in a warming Arctic. Read the free Plain Language Summary for this article on the Journal blog.

Vozzo, Justin T. [Department of Natural Resources ↗

NASA NTRSDate not supplied

Language Model For Earth Science: Exploring Potential Downstream Applications As Well As Current Challenges

The use of deep learning techniques to build transformer language models such as SciBERT and GPT3 have transformed the natural language technology (NLT) landscape. These new NLTs are being used in speech to text and vice versa, auto-mated text classification, sentiment analysis, topic modeling, text summarization, and cognitive assistants. While Earth science has no shortage of unstructured data such as journal and conference papers, little efforts have focused on harnessing NLTs for knowledge extraction and supporting the scientific process. This paper surveys the use of language models in different science. BERT-E, a new Earth science-specific language model, is presented. BERT-E is generated using a transfer learning solution. A language model that has already been trained for general Science (SciBERT) is fine-tuned using abstracts and full text extracted from various Earth science-related articles. A downstream keywords classification application is used for evaluation, and the use of BERT-E shows improved performance. The need to develop a robust set of benchmarks in evaluating the language model such as BERT-E is discussed. Finally, example applications are presented to inspire additional ideas for applications using domain-specific language models.

R Ramachandran↗