SEARCH · Search NASA

Results for “knowledge extraction”

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 19 records

All sources NASA NTRS DOE OSTI

NASA NTRS1990

Using decision-tree classifier systems to extract knowledge from databases

One difficulty in applying artificial intelligence techniques to the solution of real world problems is that the development and maintenance of many AI systems, such as those used in diagnostics, require large amounts of human resources. At the same time, databases frequently exist which contain information about the process(es) of interest. Recently, efforts to reduce development and maintenance costs of AI systems have focused on using machine learning techniques to extract knowledge from existing databases. Research is described in the area of knowledge extraction using a class of machine learning techniques called decision-tree classifier systems. Results of this research suggest ways of performing knowledge extraction which may be applied in numerous situations. In addition, a measurement called the concept strength metric (CSM) is described which can be used to determine how well the resulting decision tree can differentiate between the concepts it has learned. The CSM can be used to determine whether or not additional knowledge needs to be extracted from the database. An experiment involving real world data is presented to illustrate the concepts described.

St.clair, D. C.↗

NASA NTRS2016

Earth Science Data Analytics: Preparing for Extracting Knowledge from Information

Data analytics is the process of examining large amounts of data of a variety of types to uncover hidden patterns, unknown correlations and other useful information. Data analytics is a broad term that includes data analysis, as well as an understanding of the cognitive processes an analyst uses to understand problems and explore data in meaningful ways. Analytics also include data extraction, transformation, and reduction, utilizing specific tools, techniques, and methods. Turning to data science, definitions of data science sound very similar to those of data analytics (which leads to a lot of the confusion between the two). But the skills needed for both, co-analyzing large amounts of heterogeneous data, understanding and utilizing relevant tools and techniques, and subject matter expertise, although similar, serve different purposes. Data Analytics takes on a practitioners approach to applying expertise and skills to solve issues and gain subject knowledge. Data Science, is more theoretical (research in itself) in nature, providing strategic actionable insights and new innovative methodologies. Earth Science Data Analytics (ESDA) is the process of examining, preparing, reducing, and analyzing large amounts of spatial (multi-dimensional), temporal, or spectral data using a variety of data types to uncover patterns, correlations and other information, to better understand our Earth. The large variety of datasets (temporal spatial differences, data types, formats, etc.) invite the need for data analytics skills that understand the science domain, and data preparation, reduction, and analysis techniques, from a practitioners point of view. The application of these skills to ESDA is the focus of this presentation. The Earth Science Information Partners (ESIP) Federation Earth Science Data Analytics (ESDA) Cluster was created in recognition of the practical need to facilitate the co-analysis of large amounts of data and information for Earth science. Thus, from a to advance science point of view: On the continuum of ever evolving data management systems, we need to understand and develop ways that allow for the variety of data relationships to be examined, and information to be manipulated, such that knowledge can be enhanced, to facilitate science. Recognizing the importance and potential impacts of the unlimited ways to co-analyze heterogeneous datasets, now and especially in the future, one of the objectives of the ESDA cluster is to facilitate the preparation of individuals to understand and apply needed skills to Earth science data analytics. Pinpointing and communicating the needed skills and expertise is new, and not easy. Information technology is just beginning to provide the tools for advancing the analysis of heterogeneous datasets in a big way, thus, providing opportunity to discover unobvious scientific relationships, previously invisible to the science eye. And it is not easy It takes individuals, or teams of individuals, with just the right combination of skills to understand the data and develop the methods to glean knowledge out of data and information. In addition, whereas definitions of data science and big data are (more or less) available (summarized in Reference 5), Earth science data analytics is virtually ignored in the literature, (barring a few excellent sources).

data analytics↗

DOE OSTI2024

Model-Based Approaches to Generate Knowledge from Data in a Plant Reliability Context

One challenge that nuclear power plant system engineers are facing is that the amount of equipment reliability (ER) data being continuously generated are extremely large. These data elements come in different forms: textual (e.g., condition reports) and numeric (e.g., generated by monitoring systems) and they provide system engineers with valuable insights and information regarding the discovery of anomalous behaviors or degradation trends, the identification of the possible causes behind such behaviors and trends, and the prediction of their direct consequences. This paper directly targets the generation of knowledge from ER data by putting “data into context”. Here, we employ model-based system engineering (MBSE) models of systems and assets to represent and capture their architecture and functional (i.e., cause-effect) relations. ER data elements are processed by identifying first which elements of the developed MBSE elements they are referring to. This task is much harder for textual data since the information contained in issue or maintenance reports needs to “be understood” by a computational tool. Here we called this process “knowledge extraction” where our methods to extract knowledge from textual data. Lastly, once numeric and textual ER data elements have been processed and “understood”, we discover possible cause-effect relations among them. This is performed by observing if a logical connection through the MBSE models exists, and if there is a temporal relation among them. The logic and temporal are the two main ingredients to perform “machine reasoning” from ER data.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Model-Based Approaches to Generate Knowledge from Data in a Plant Reliability Context

One challenge that nuclear power plant system engineers are facing is continuous generation of an extremely large amount of equipment reliability (ER) data. These data elements come in textual (e.g., condition reports) and numeric (e.g., generated by monitoring systems) forms. They provide system engineers with valuable insights and information by discovering anomalous behaviors or degradation trends, identifying possible causes behind such behaviors and trends, and predicting their direct consequences. This paper directly targets the knowledge generation from ER data by putting “data into context.” We employ model-based system engineering (MBSE) of systems and assets to represent and capture their architecture and functional (i.e., cause-effect) relations. ER data elements are processed by first identifying which of the developed MBSE elements they are referring to. This task is harder for textual data since the information contained in issue or maintenance reports needs to be “understood” by a computational tool. We called this process “knowledge extraction” since our methods extract knowledge from textual data. Last, once numeric and textual ER data elements have been processed and “understood,” we discover possible cause-effect relations among them. This is performed by observing whether a logical connection through the MBSE models exists, and if there is a temporal relationship among them. The logic and temporal are the two main ingredients to perform “machine reasoning” from ER data.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2024

A Data Processing Pipeline To Extract A Knowledge Graph From Sec Documents For Socio-technical Analysis Of Critical Infrastructure Influence

Weaver, GabrielA.↗

NASA NTRS1990

Automated extraction of knowledge for model-based diagnostics

The concept of accessing computer aided design (CAD) design databases and extracting a process model automatically is investigated as a possible source for the generation of knowledge bases for model-based reasoning systems. The resulting system, referred to as automated knowledge generation (AKG), uses an object-oriented programming structure and constraint techniques as well as internal database of component descriptions to generate a frame-based structure that describes the model. The procedure has been designed to be general enough to be easily coupled to CAD systems that feature a database capable of providing label and connectivity data from the drawn system. The AKG system is capable of defining knowledge bases in formats required by various model-based reasoning tools.

Gonzalez, Avelino J.↗

DOE OSTI2025

A Data Processing Pipeline To Extract A Knowledge Graph From Heterogeneous Data For Socio-technical Analysis Of Critical Infrastructure Influence

The code is written in Python and consists of the following pipeline that is implemented in Apache Airflow. This pipeline intends to understand the companies that are directly or indirectly involved with a type of critical infrastructure system at some point in that system's lifecycle. The pipeline takes a configuration file that specifies a list of initial companies to consider, a geographic region of interest, and a set of SEC form types as well as other data sources (e.g. CrunchBase) from which to extract entities and relations. There are four main components to this pipeline as currently implemented: Entity Extraction, Network Construction, Analysis, and Visualization. First, Entity Extraction, is implemented as the `topear-extract_organizations` Apache Airflow workflow. Given an initial query that specifies a geographic region of interest and a time interval, the software will extract CI facilities of interest and organizations that have a direct influence relationship to those facilities (e.g. ownership). During the course of the LDRD, we focused on Electric Vehicle charging stations and this information is available via the Department of Energy (DOE) database on fueling stations maintained by NREL. Within the context of the DOE CESER project, we have focused on Battery Energy Storage Systems (BESS). Second, the Network Extraction component will iteratively construct a social network graph given the set of organizations and people extracted in the previous step. Organizations (and eventually People if desired) are then fed as a query to the `topgear-construct_social_network` Apache Airflow workflow which given a set of initial companies and data sets (e.g. SEC EDGAR form types, OpenCorporates, Crunchbase). This Airflow workflow will iteratively query such data sources to discover relationships with new organizations and people. For example, this module can iteratively query SEC EDGAR for metadata that documents the number of each type of form for the given set of companies and their location. This forms metadata represents a catalog of data sources from SEC EDGAR for the extracted social network knowledge graph. The pipeline then downloads these forms from the website and saves them in a build directory for further processing. These documents are then parsed for entities and relations. Again, we note that in additional to SEC data sources, this step can also pull in information on organizations via API services such as CrunchBase and OpenCorporates or bulk data sources. At the end of this step, the resultant social network, the Critical Infrastructure network, and the edges that encode relationships between organizations and CI facilities, form the Adversarial Socio-Technical Network (ASTN) that informs the analysis. Third, the Analysis component processes these generated ASTN. Previously, that has included the ability to compare prevalence of different vendors for a given infrastructure component type across different regions as well as identify common public and private investors across those vendors. This was demonstrated for EV Charging Stations across several different metropolitan areas within an IEEE PES GridEdge publication. More recently, we have looked at ways to identify infrastructure owners and operators of BESS with the most nameplate capacity across different states as well as other indictors of risk resulting from changes in ownership over time. Finally, the Visualization component consists of an HTML/CSS/JS framework by which users can interact geospatial, operational, and organizational relationships across a given portfolio of Critical Infrastructure facilities. The objective is to provide a library of UI/UX modules that can be repurposed for stakeholder-specific dashboards. All of the modules are related via a common event model that enables UI actions in one view to percolate across the other views.

Weaver, Gabriel [Idaho National Laboratory (INL), ↗

DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗

DOE OSTI2025

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Abstract Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Computer Science↗

NASA NTRS2004

ViDI: Virtual Diagnostics Interface: The Future of Wind Tunnel Testing - Volume 1

The quality of data acquired in a given test facility ultimately resides within the fidelity and implementation of the instrumentation systems. Over the last decade, the emergence of robust optical techniques has vastly expanded the envelope of measurement possibilities. At the same time the capabilities for data processing, data archiving and data visualization required to extract the highest level of knowledge from these global, on and off body measurement techniques have equally expanded. Yet today, while the instrumentation has matured to the production stage, an optimized solution for gaining knowledge from the gigabytes of data acquired per test (or even per test point) is lacking. A technological void has to be filled in order to possess a mechanism for near-real time knowledge extraction during wind tunnel experiments. Under these auspices, the Virtual Diagnostics Interface, or ViDI, was developed.

Fleming, Gary A.↗

NASA NTRS1986

Development of a knowledge acquisition tool for an expert system flight status monitor

Two of the main issues in artificial intelligence today are knowledge acquisition dion and knowledge representation. The Dryden Flight Research Facility of NASA's Ames Research Center is presently involved in the design and implementation of an expert system flight status monitor that will provide expertise and knowledge to aid the flight systems engineer in monitoring today's advanced high-performance aircraft. The flight status monitor can be divided into two sections: the expert system itself and the knowledge acquisition tool. The knowledge acquisition tool, the means it uses to extract knowledge from the domain expert, and how that knowledge is represented for computer use is discussed. An actual aircraft system has been codified by this tool with great success. Future real-time use of the expert system has been facilitated by using the knowledge acquisition tool to easily generate a logically consistent and complete knowledge base.

Disbrow, J. D.↗

NASA NTRS1986

Development of a knowledge acquisition tool for an expert system flight status monitor

Two of the main issues in artificial intelligence today are knowledge acquisition and knowledge representation. The Dryden Flight Research Facility of NASA's Ames Research Center is presently involved in the design and implementation of an expert system flight status monitor that will provide expertise and knowledge to aid the flight systems engineer in monitoring today's advanced high-performance aircraft. The flight status monitor can be divided into two sections: the expert system itself and the knowledge acquisition tool. This paper discusses the knowledge acquisition tool, the means it uses to extract knowledge from the domain expert, and how that knowledge is represented for computer use. An actual aircraft system has been codified by this tool with great success. Future real-time use of the expert system has been facilitated by using the knowledge acquisition tool to easily generate a logically consistent and complete knowledge base.

Disbrow, J. D.↗

NASA NTRS1988

Psychological tools for knowledge acquisition

Knowledge acquisition is said to be the biggest bottleneck in the development of expert systems. The problem is getting the knowledge out of the expert's head and into a computer. In cognitive psychology, characterizing metal structures and why experts are good at what they do is an important research area. Is there some way that the tools that psychologists have developed to uncover mental structure can be used to benefit knowledge engineers? We think that the way to find out is to browse through the psychologist's toolbox to see what there is in it that might be of use to knowledge engineers. Expert system developers have relied on two standard methods for extracting knowledge from the expert: (1) the knowledge engineer engages in an intense bout of interviews with the expert or experts, or (2) the knowledge engineer becomes an expert himself, relying on introspection to uncover the basis of his own expertise. Unfortunately, these techniques have the difficulty that often the expert himself isn't consciously aware of the basis of his expertise. If the expert himself isn't conscious of how he solves problems, introspection is useless. Cognitive psychology has faced similar problems for many years and has developed exploratory methods that can be used to discover cognitive structure from simple data.

Rueter, Henry H.↗

NASA NTRS2014

Data-Intensive Science meets Inquiry-Driven Pedagogy: Interactive Big Data Exploration, Threshold Concepts, and Liminality

Threshold concepts in any discipline are the core concepts an individual must understand in order to master a discipline. By their very nature, these concepts are troublesome, irreversible, integrative, bounded, discursive, and reconstitutive. Although grasping threshold concepts can be extremely challenging for each learner as s/he moves through stages of cognitive development relative to a given discipline, the learner's grasp of these concepts determines the extent to which s/he is prepared to work competently and creatively within the field itself. The movement of individuals from a state of ignorance of these core concepts to one of mastery occurs not along a linear path but in iterative cycles of knowledge creation and adjustment in liminal spaces - conceptual spaces through which learners move from the vaguest awareness of concepts to mastery, accompanied by understanding of their relevance, connectivity, and usefulness relative to questions and constructs in a given discipline. For example, challenges in the teaching and learning of atmospheric science can be traced to threshold concepts in fluid dynamics. In particular, Dynamic Meteorology is one of the most challenging courses for graduate students and undergraduates majoring in Atmospheric Science. Dynamic Meteorology introduces threshold concepts - those that prove troublesome for the majority of students but that are essential, associated with fundamental relationships between forces and motion in the atmosphere and requiring the application of basic classical statics, dynamics, and thermodynamic principles to the three dimensionally varying atmospheric structure. With the explosive growth of data available in atmospheric science, driven largely by satellite Earth observations and high-resolution numerical simulations, paradigms such as that of dataintensive science have emerged. These paradigm shifts are based on the growing realization that current infrastructure, tools and processes will not allow us to analyze and fully utilize the complex and voluminous data that is being gathered. In this emerging paradigm, the scientific discovery process is driven by knowledge extracted from large volumes of data. In this presentation, we contend that this paradigm naturally lends to inquiry-driven pedagogy where knowledge is discovered through inductive engagement with large volumes of data rather than reached through traditional, deductive, hypothesis-driven analyses. In particular, data-intensive techniques married with an inductive methodology allow for exploration on a scale that is not possible in the traditional classroom with its typical problem sets and static, limited data samples. In addition, we identify existing gaps and possible solutions for addressing the infrastructure and tools as well as a pedagogical framework through which to implement this inductive approach.

Ramachandran, Rahul↗

NASA NTRS1988

Knowledge acquisition for autonomous systems

Knowledge-based capabilities for autonomous aerospace systems, such as the NASA Space Station, must encompass conflict-resolution functions comparable to those of human operators, with all elements of the system working toward system goals in a concurrent, asynchronous-but-coordinated fashion. Knowledge extracted from a design database will support robotic systems by furnishing geometric, structural, and causal descriptions required for repair, disassembly, and assembly. The factual knowledge for these databases will be obtained from a master database through a technical management information system, and it will in many cases have to be augmented by domain-specific heuristic knowledge acquired from domain experts.

Lum, Henry↗

DOE OSTI2025

Digital Twin for Chemical Science: a case study on water interactions on the Ag(111) surface

Directly visualizing chemical trajectories offers insights into catalysis, gas-phase reactions and photoinduced dynamics. Tracking the transformation of chemical species is best achieved by coupling theory and experiment. Here we developed Digital Twin for Chemical Science (DTCS) v.01, which integrates theory, experiment and their bidirectional feedback loops into a unified platform for chemical characterization. DTCS addresses a core question: given a set of experimental conditions, what is the expected outcome and why? It consists of a forward solver that takes a chemical reaction network and predicts spectra under experimental conditions, and an inverse solver that infers kinetics from measured spectra. We applied DTCS to ambient-pressure X-ray photoelectron spectroscopy measurements of the Ag–H2O interface as an example. This approach enables real-time knowledge extraction and guides experiments until a stopping condition is met based on accuracy and degeneracy. As a step toward autonomous chemical characterization, DTCS provides mechanistic knowledge in a verified, standardized manner.

Chemistry↗

NASA NTRS2006

Automated Knowledge Discovery from Simulators

In this paper, we explore one aspect of knowledge discovery from simulators, the landscape characterization problem, where the aim is to identify regions in the input/ parameter/model space that lead to a particular output behavior. Large-scale numerical simulators are in widespread use by scientists and engineers across a range of government agencies, academia, and industry; in many cases, simulators provide the only means to examine processes that are infeasible or impossible to study otherwise. However, the cost of simulation studies can be quite high, both in terms of the time and computational resources required to conduct the trials and the manpower needed to sift through the resulting output. Thus, there is strong motivation to develop automated methods that enable more efficient knowledge extraction.

landscapes↗

NASA NTRSDate not supplied

The Radiation Biology Ontology: A New Tool Supporting FAIR Principles Across Radiation Biology Facilitating Data Discovery and Integration

Development of the Radiation Biology Ontology (RBO) was motivated by the need for a comprehensive, well-structured ontology for encoding radiation biology metadata. The primary use-cases were archiving data in the STORE database (https://www.storedb.org/), the repository for the RadoNorm Project, and in GeneLab (https://genelab.nasa.gov), NASA’s ‘omics database. The scope of radiobiology research ranges from physics to radiation oncology to socio-legal studies; no existing ontology has the necessary breadth or depth. In addition, a formal ontology has the advantage of being usable for machine learning and, importantly, for tasks like data integration, knowledge extraction from the scientific literature and for query extension and data classification. Standardisation of metadata is one of the primary objectives of the FAIR principles for open data; RBO is an important landmark for FAIR radiation biology data.

ontology↗