SEARCH · Search NASA

Results for “Knowledge”

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 109 records · Page 6

All sources NASA NTRS DOE OSTI

NASA NTRS2019

Orbital Debris Ontology, Terminology, and Knowledge Modeling

The looming threat orbital debris poses to assets in orbit demands solutions. As the orbital population grows, so does this hazard, but so does the sea of data. The problem is also an opportunity for interdisciplinary innovation and cooperation. This paper focuses on the data and information management aspect of developing solutions for a sustainable and safe orbital space environment. The corresponding author’s in-progress work to develop an orbital debris domain ontology is summarized in order to discuss knowledge modeling for this domain. Methodological approaches of this effort can also contribute to standards efforts and address terminological and policy questions. Leveraging the growing volumes of orbital debris and space situational awareness (SSA) data will create a more complete picture of the orbital space environment. Part of the solution will be: consistent and correct data interpretation, sharing orbital debris and SSA data in one form or another, terminology development & harmonization, and knowledge or domain modeling. To facilitate this, [Rovetto, 2015/16] discussed ontology development for the orbital debris domain. This paper lists concepts from that paper, and subsequently developed concepts [2-9]. Ontology engineering is an interdisciplinary field related to knowledge representation and reasoning in artificial intelligence, semantic technologies and the so-called semantic web. An ontology is effectively a computable and semantically rich terminology that presents a knowledge or domain model for a topic area. Expressions of knowledge or assertions are stored using formally defined term. This knowledge base is reasoned over to yield answers to queries, among other things. Ontologies have been developed in knowledge-based projects across various disciplines, and used for such things as search engines, chatbots, enterprise knowledge graphs, etc. Ontologies support: interoperability, automated reasoning, data sharing and integration, data search and retrieval, and communicating the meaning of data. The Orbital Debris Ontology (ODO), and related ontologies [Rovetto & Kelso 2016] [Rovetto 2016, 2017], were proposed to help achieve this. ODO, for instance, is intended as a domain ontology that can be used across federated databases, offering an explicitly specified set of concepts describing the orbital debris domain. Its meaning-rich taxonomy will provide a sharable semantics for orbital debris data to, in part, consistently communicate the meaning of data to both humans and machines, and tag data elements in space object catalogs to help afford inference tasks, decision support, knowledge discovery, and information integration. ODO and the SSA ontology (SSAO) is part of the overall Orbital Space Domain Ontology concept, which is conceived as a broader domain reference ontology. It aims to provide a knowledge representation structure of the orbital space environment, a common semantic model, and develop a sharable terminology. Collectively this will provide common meaning for datasets, a high-level taxonomy or classification for orbital space objects, and thus means to characterize space objects. Ongoing efforts have included using visualizations, R, JSON-LD, and contemporary semantic technologies. Potential applications and interdisciplinary partnerships include web-based platforms, web apps, visualizations, and academia projects. Community input and participation may yield a more widely understood domain model as well as facilitate terminological standards. For example, the proposed conceptual, terminological and ontological analysis may contribute to such efforts as the Space Debris Mitigation Requirements in the International Standards Organization by developing more precise, consistent and coherent terms and definitions. Projects that seek to develop in-house ontologies can use ODO and related ontologies as domain reference ontologies. This paper was developed independent of author affiliations. Readers are encouraged to contact corresponding author(1) with general interest and potential opportunities to support or realize the described project.

Robert J. Rovetto↗

NASA NTRS2023

U.S. Spacesuit Knowledge Capture – Expanding Our Future

NASA is going to the Moon. And it will don a new spacesuit when it reaches its destination. NASA is partnering with industry to build the spacesuit and supporting systems (i.e., surface mobility tools) that astronauts will use on the Moon, starting with Artemis III. The Johnson Space Center’s (JSC) Extravehicular Activity and Human Surface Mobility Program (EHP) is managing this effort, and the U.S. Spacesuit Knowledge Capture (SKC) Program is expanding its scope to help. For 15 years, the SKC Program has collected, archived, and disseminated decades of spacesuit-related knowledge, as appropriate, to help NASA scientists, technicians, and engineers support space exploration. The SKC Program captures its knowledge by hosting and recording subject-matter expert (SME) lectures, interviews, and workshops. It also collects retired SMEs’ reports, drawings, and schematics containing legacy spacesuit knowledge. To build a technically capable spacesuit essential for future lunar exploration, spacesuit professionals borrowed much of their knowledge from legacy Extravehicular Activity (EVA) spacesuits. Most of the SKC Program’s captured knowledge has focused on legacy and current spacesuits. To support EHP, the SKC Program is expanding its knowledge capture focus beyond the spacesuit and will seek to collect knowledge from other pertinent topics (e.g., Lunar Terrain Vehicle and EVA tools). In 2007, the SKC Program began as an independent source, without funding. As demand for capturing essential spacesuit knowledge increased, consequently, the SKC Program’s funding increased. Expansion of the SKC Program was evident in 2019, when it seized the opportunity to capture the Exploration Extravehicular Mobility Unit (xEMU) buildup at JSC. In 2021, its collaboration with the xEMU Technical Community of Practice facilitated training and knowledge sharing with the xEMU team. In 2022, the SKC Program began supporting EHP. This paper describes the SKC Program’s expansive evolution, plans to support EHP, and more.

Cinda Chullen↗

DOE OSTI2019

Integration of Local Knowledge is a Key for the Remediation Success of Legacy Uranium Mine Sites - 19564

A key to success, during all aspects of the remediation process on legacy uranium sites, and easily transferable between countries and projects, is the integration of local knowledge. However, before this knowledge can be integrated, local trust and project understanding must be developed. Local trust and project understanding can only be developed through a principle-centred approach to a shared project vision, two-way communication of knowledge, alignment of project goals, and understanding the local needs early in the remediation process. Once public confidence is obtained, local trust and project understanding must be maintained throughout the entirety of the remediation process. Project understanding is an ongoing endeavor that needs continuous communication and varied methods to succeed. During the management of assessment, remediation, and post remediation monitoring on the Saskatchewan Research Council's CLEANS project (remediation of 37 legacy uranium mine sites in Northern Saskatchewan, Canada), integration of local knowledge has been an instrumental tool attributing to success. During site assessment, integration of local knowledge has included the development and implementation of land use surveys to determine realistic travel and occupancy on and adjacent to these legacy sites, and site specific traditional knowledge and land use studies that have contributed to the development of a detailed knowledge of local land use, resource utilization, country food intake, and human history of the sites. The local knowledge gained during the assessment process is invaluable as it provides information required to support remediation planning, such as: valued ecosystem components, human trophic utilization, length of site occupancy, cultural value assessment, and future land use considerations. During remediation planning, local and traditional knowledge can also be incorporated through determination of plant species suitability for revegetation, development and selection of remediation options, and setting realistic sustainable development targets for local project inclusion. During site remediation operations, local involvement can be utilized through direct labour and equipment, cultural resource monitoring (i.e. archaeological and heritage protection), local logistics and historic information transfer, and stakeholder communications and engagement support. Post remediation, local involvement is an efficient mechanism for long-term monitoring, and care and maintenance activities. Although there may be differences between countries, regions and sites, the remediation process on legacy uranium mines can universally be more successful through the integration of local knowledge; while developing rights/stakeholder engagement and capacity building. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2026

Knowledge-guided learning with curated prior genetic biomarkers for robust model interpretation

Abstract Motivation Knowledge-guided learning offers effective and robust model training strategies in data-scarce settings by incorporating established domain knowledge, thereby enhancing generalization, robustness, and interpretability. By contrast, conventional deep learning approaches rely purely on data-driven learning, which can limit robust model interpretability, particularly in high-dimensional settings with limited size samples. In computational biology, knowledge-guided learning has primarily leveraged network- and structural-based knowledge, leading to biologically interpretable representations and enhanced predictive performance compared to conventional approaches. However, curated biomarkers, one of the most accessible forms of biological knowledge, remain largely unexplored within knowledge-guided paradigms. Results In this study, we propose a model-agnostic training paradigm, Biomarker-driven Explainable Prior-guided Learning (BioExPL), that can be applied to any neural networks that incorporates curated prior knowledge. BioExPL enforces neural networks to reflect curated biomarker priors in their latent representations through a novel knowledge-alignment loss. BioExPL consistently demonstrated significantly improved predictive performance and enhanced model interpretability with minimized computational overhead in simulation studies and intensive experiments on multiple cancer datasets. BioExPL not only integrates prior curated knowledge into the model but also accurately identifies unknown associated signals additionally. BioExPL is model-agnostic and domain-independent, enabling its integration into diverse neural network architectures. Availability and implementation The open-source is publicly available at: https://github.com/datax-lab/BioExPL.

Baek, Beomsu [Department of Computer Science, Univ↗

DOE OSTI2025

Knowledge Oriented Graph Unified Transformer (KOGUT) v0.1

KOGUT — Knowledge Oriented Graph Unified Transformer KOGUT implements the Relational Graph Transformer (RelGT) architecture for knowledge graph link prediction in biological domains, with a primary focus on microbial growth media prediction. While the original RelGT (arXiv:2505.10960) targets relational tables, time series, and multi-table databases, KOGUT adapts this architecture for heterogeneous biological knowledge graphs, providing first-in-class AI predictive models for microbial cultivation. Key Adaptations Beyond Original RelGT: - Knowledge Graph Focus: Applied to biological KGs with semantic node types (taxa, chemicals, media, phenotypes, environments) versus generic relational database tables, trained on the KG-Microbe knowledge graph (1.3M entities, 2.9M edges, 24 relation types). - Multimodal Node Encoding: Integrates node labels, categories, descriptions, and synonyms from KG metadata through learned embedding layers—adapting relational column features to graph node attributes with textual semantics. - Extended K-Hop Subgraph Strategy: Optimized neighborhood sampling (3-hop default, configurable up to 200 nodes) tuned for sparse biological networks, building on the original local-global attention framework with biological relation preservation. - Biolink Predicate Preservation: Type-specific transformations for 24 biological edge semantics (occurs_in, consumes, produces, has_phenotype, subclass_of) beyond standard relational foreign keys, enabling multi-relation link prediction. - Inductive Learning Support: Enables zero-shot predictions for novel taxa through feature-based embeddings (temperature, oxygen requirements, gram stain, cell shape), extending the original transductive relational benchmark scope to uncultured microorganisms. CheapSOTA Performance Optimizations (This Distribution): - VQ-EMA Centroid Attention: Vector quantization with exponential moving average for improved global context modeling (+5-10% MRR improvement). - HDF5 Precomputed Data Loading: One-time preprocessing of k-hop subgraphs to eliminate redundant graph traversals (2-5× training speedup). - Distributed Data Parallel Training: Multi-GPU support for scaling to larger knowledge graphs (tested on 4× NVIDIA A100 GPUs at NERSC Perlmutter). - Mixed Precision Training: Automatic mixed precision (AMP) for memory efficiency and faster training. Advantages Over Standard Knowledge Graph Embedding Models: Combines RelGT's proven multi-element tokenization (features, type, hop, structure) with graph-native biological representations, enabling interpretable link prediction across heterogeneous entities that standard embedding models (TransE, RotatE, ComplEx) and table-based transformers cannot directly model. Achieves near-perfect performance on microbial growth media prediction (MRR: 0.9966, Precision@1: 0.9932, Hit@10: 1.0000) while maintaining explainability through attention-based reasoning over biological pathways. Training Data: - KG-Microbe merged knowledge graph: 1,379,337 nodes, 2,960,472 edges - 24 biological relation types including taxonomic hierarchies, metabolic interactions, phenotype associations, and environmental relationships - Primary prediction task: Growth media suitability for microbial taxa (biolink:occurs_in, 50K edges) - Multi-relation capability: Predicts links for any of the 24 relation types, including chemical consumption/production, phenotype associations, and taxonomic classification Citation: Original RelGT Architecture: Dwivedi et al., "Relational Graph Transformer", arXiv:2505.10960, 2025 KOGUT Implementation: Knowledge Oriented Graph Unified Transformer for Microbial Growth Media Prediction Developed at Lawrence Berkeley National Laboratory (LBNL) Trained on NERSC Perlmutter supercomputer

Joachimiak, Marcin [Lawrence Berkeley National Lab↗

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 NTRS1985

Perspectives on knowledge in engineering design

Various perspectives are given of the knowledge currently used in engineering design, specifically dealing with knowledge-based expert systems (KBES). Constructing an expert system often reveals inconsistencies in domain knowledge while formalizing it. The types of domain knowledge (facts, procedures, judgments, and control) differ from the classes of that knowledge (creative, innovative, and routine). The feasible tasks for expert systems can be determined based on these types and classes of knowledge. Interpretive tasks require reasoning about a task in light of the knowledge available, where generative tasks create potential solutions to be tested against constraints. Only after classifying the domain by type and level can the engineer select a knowledge-engineering tool for the domain being considered. The critical features to be weighed after classification are knowledge representation techniques, control strategies, interface requirements, compatibility with traditional systems, and economic considerations.

Rasdorf, W. J.↗

NASA NTRS1990

Computer-assisted knowledge acquisition for hypermedia systems

The usage of procedural and declarative knowledge to set up the structure or 'web' of a hypermedia environment is described. An automated knowledge acquisition tool was developed that helps a knowledge engineer elicit and represent an expert's knowledge involved in performing procedural tasks. The tool represents both procedural and prerequisite, declarative knowledge that supports each activity performed by the expert. This knowledge is output and subsequently read by a hypertext scripting language to generate the link between blank, but labeled cards. Each step of the expert's activity and each piece of supporting declarative knowledge is set up as an empty node. An instructional developer can then enter detailed instructional material concerning each step and declarative knowledge into these empty nodes. Other research is also described that facilitates the translation of knowledge from one form into a form more readily useable by computerized systems.

Steuck, Kurt↗

NASA NTRS1993

Autonomously acquiring declarative and procedural knowledge for ICAT systems

The construction of Intelligent Computer Aided Training (ICAT) systems is critically dependent on the ability to define and encode knowledge. This knowledge engineering effort can be broadly divided into two categories: domain knowledge and expert or task knowledge. Domain knowledge refers to the physical environment or system with which the expert interacts. Expert knowledge consists of the set of procedures and heuristics employed by the expert in performing their task. Both these areas are a significant bottleneck in the acquisition of knowledge for ICAT systems. This paper presents a research project in the area of autonomous knowledge acquisition using a passive observation concept. The system observes an expert and then generalizes the observations into production rules representing the domain expert's knowledge.

Kovarik, Vincent J., Jr.↗

NASA NTRS2002

A Survey of Knowledge Management Research & Development at NASA Ames Research Center

This chapter catalogs knowledge management research and development activities at NASA Ames Research Center as of April 2002. A general categorization scheme for knowledge management systems is first introduced. This categorization scheme divides knowledge management capabilities into five broad categories: knowledge capture, knowledge preservation, knowledge augmentation, knowledge dissemination, and knowledge infrastructure. Each of nearly 30 knowledge management systems developed at Ames is then classified according to this system. Finally, a capsule description of each system is presented along with information on deployment status, funding sources, contact information, and both published and internet-based references.

Keller, Richard M.↗

NASA NTRSDate not supplied

U.S. Spacesuit Knowledge Capture – Creation, Curation, and Dissemination

The U.S. spacesuit is a special system that has intrigued and fascinated the world since Neil Armstrong set foot on the Moon in 1969. With over 50 years since that momentous achievement, NASA is planning to land the first woman and next man on the Moon in the near future. This goal begets the need to build a new spacesuit, a spacesuit created from the legacy knowledge of the Extravehicular Mobility Unit (EMU), combined with knowledge gained from technology development over the decades. As NASA transitions to its new horizon, the U.S. Spacesuit Knowledge Capture (SKC) Program is poised to help. The SKC Program’s primary function has been to capture, curate, and disseminate spacesuit-related knowledge among scientists, engineers, and technicians. The SKC Program was created in 2007 to capture knowledge primarily from spacesuit subject-matter experts (SMEs) who were retiring from NASA. These SMEs had 30 to 50 years of spacesuit knowledge. Over the years, the SKC Program has evolved and expanded its scope with a current focus on complementing the buildup of the Exploration EMU (xEMU) at the Johnson Space Center. As part of this focus, the SKC Program recently teamed with the xEMU Community of Practice (CoP) for knowledge sharing. The xEMU CoP provides a forum where early career engineers, professionals new to human spaceflight, and the xEMU community can come together regularly to seek guidance, share knowledge, meet their peers, discover resources, and ask questions. The CoP created an environment where the knowledge can be easily and routinely captured and recorded. The recorded events are archived and curated in an SKC Program library and disseminated as appropriate. This paper details the roles that the SKC Program and CoP play in the xEMU buildup, along with the navigation of the creation, curation, and dissemination processes.

Cinda Chullen↗

DOE OSTI2019

Soft costs and knowledge pathways in the US solar photovoltaic ecosystem

An enduring puzzle in the US solar industry is that despite substantial reductions in the cost of photovoltaic hardware, soft costs (defined here as all costs not directly driven by hardware) have not done the same (US DOE, 2012). In fact, soft costs now account for the majority of the cost of total cost of installed solar systems, despite decades of efforts by firms and policy-makers to reduce these costs. In this study, we address two questions: a) what drives soft costs within the US solar industry, and b) how do firms gain the knowledge required to address these costs? We address this question through an explorative inductive multiple-case study (e.g., Eisenhardt, 1989; Appleyard, 1996). Our sample consists of 15 actors from across various roles within the industry, including residential and commercial installers (8), distribution intermediaries (3), and business software vendors (4). We conducted extensive interviews with executives at each firm (76 interviews in total), and supplemented this information with archival resources such as press releases, news coverage, analyst reports, and internet articles. This data was synthesized into a comprehensive case for each actor, detailing the activities conducted within each firm, the drivers of soft costs within that firm, and knowledge flows (e.g., new technologies, best practices, etc) within and across firms. We then compared across these cases to identify common patterns in cost and knowledge dynamics. Our study contributes a nuanced perspective on the drivers of soft costs within the solar industry as well as the patterns and mechanisms of knowledge flows within the industry. We find for example that the majority of the soft costs occur at the interface between firms (e.g., utilities, suppliers). We also observe substantive variation in costs across different types of actors and even within firm types (e.g., small vs. large installers). We also provide insight into how firms acquire knowledge and when they are able to apply it in order to reduce these costs. Our data reveal heterogeneity in a) the types of knowledge, and b) the pathways of knowledge flow between the actors in the industry. For example, we observe that distributors and suppliers play a key role in the dissemination of new technologies as well as general management knowledge for smaller firms. In contrast, informal personal networks and internal experimentation appear to be more important for larger firms. We also reveal critical distinctions across markets – e.g., differences in organizational culture that facilitate learning and experimentation more readily in residential vs. commercial markets. Overall, these results contribute preliminary insights into the knowledge dynamics of the solar industry, the persistence of soft costs over time, heterogeneity across firm types and regions, and the effective design of policy to support the solar industry.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2019

A Knowledge Graph Approach for the Secondary Use of Cancer Registry Data

Population-based central cancer registries collect valuable structured and unstructured data primarily for cancer surveillance and research, enhancing insights into clinical features associated with cancer occurrence, cancer treatment, and cancer outcomes to guide interventions which reduce the cancer burden. Cancer registries primarily collect data on (1) cancer type (case or tumor); (2) patient demographics such as age, gender, and residential address at time of diagnosis; (3) planned first course of treatment; and (4) date of last contact, vital status, and cause of death. Cancer registry data is dynamic, structured data, which is extracted from many unstructured sources such as electronic healthcare records, and consolidated for reporting and other purposes. While available advanced analytic tools such as SEER*Stat have the ability to build SAS queries, we, however, explore an innovative knowledge graph approach to organizing cancer registry data for advanced analytics and visualization, which has unique advantages over approaches of existing tools. This innovative knowledge graph approach semantically enriches the data and easily enables linkage with third-party data, which can better explain variation in outcomes. We have developed a prototype knowledge graph based on data from the Louisiana Tumor Registry and other publicly available datasets including Behavioral Risk Factor Surveillance System, Clinical Trials, DBpedia, GeoNames, Rural-Urban Continuum Codes, and Semantic MEDLINE. The resource description framework (RDF) data model was selected to represent our knowledge graph, which contains more than 25 billion triples and is ~4TB in storage size. To exhibit the benefits of the knowledge graph approach, we used scenario specific queries, which find the relationships between cancer treatment sequences and outcomes. To illustrate its ease of use in iterative analysis, the knowledge graph was linked to external datasets for performing complex queries across multiple datasets. In addition, we used knowledge graphs to identify data discrepancies and to handle schema changes. Finally, we visualized the knowledge graph to discover data patterns. Our results demonstrate this graph-based solution enables cancer researchers to execute complex queries and more easily perform iterative analyses to improve understanding of cancer registry data. In the future, we would like to use high-performance computing (HPC) resources for faster-generating hypotheses with clinical potential from our knowledge graph.

Hasan, S M Shamimul↗

DOE OSTI2019

Managing Knowledge Over Time for Supporting Radioactive Waste Geological Disposal Project Development - 19028

Projects designed to define, build, operate and monitor radioactive waste disposal solutions require the transmission of knowledge over several decades and the preservation of memory over several centuries. This is particularly acute for the geological disposal project 'Cigeo' led by the French national radioactive waste management agency (Andra) as far as the requirements in terms of reversibility lead to the choice of an incremental design that allows to integrate learning resulting from continuous improvement of knowledge. For instance, for robustness purposes, Cigeo is designed on the basis of currently proven technologies, but its step-by-step construction in successive stages must make it possible to integrate improvements derived from the scientific and technical progress as well as from experience feedback from its exploitation. In the field of industrial activity, a significant proportion of the knowledge and skills implemented by employees of a company are not known or even identified by the human resources organization or the mid-management staff. This is mainly due to the fact that (i) the organized knowledge-sharing is often based on documentary tools but little on social modalities and (ii) the organization of knowledge is mostly cross-cutting to the managerial lines. To overcome this bias, a global and integrated approach to knowledge management is currently the focus of Andra's specific efforts. Cross-disciplinary groups and close intergenerational links positioned throughout the life of the projects aim specifically at continuous and participative knowledge sharing, capitalization and transmission. Then, devices aiming at systematic dissemination of and access to knowledge support experience feedback and provide unified collaboration, traceability and decision-support at all scales. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2019

Unsupervised word embeddings capture latent knowledge from materials science literature

The overwhelming majority of scientific knowledge is published as text, which is difficult to analyse by either traditional statistical analysis or modern machine learning methods. By contrast, the main source of machine-interpretable data for the materials research community has come from structured property databases, which encompass only a small fraction of the knowledge present in the research literature. Beyond property values, publications contain valuable knowledge regarding the connections and relationships between data items as interpreted by the authors. To improve the identification and use of this knowledge, several studies have focused on the retrieval of information from scientific literature using supervised natural language processing, which requires large hand-labelled datasets for training. Here we show that materials science knowledge present in the published literature can be efficiently encoded as information-dense word embeddings (vector representations of words) without human labelling or supervision. Without any explicit insertion of chemical knowledge, these embeddings capture complex materials science concepts such as the underlying structure of the periodic table and structure-property relationships in materials. Furthermore, we demonstrate that an unsupervised method can recommend materials for functional applications several years before their discovery. This suggests that latent knowledge regarding future discoveries is to a large extent embedded in past publications. Lastly, our findings highlight the possibility of extracting knowledge and relationships from the massive body of scientific literature in a collective manner, and point towards a generalized approach to the mining of scientific literature.

36 MATERIALS SCIENCE↗

NASA NTRS1988

The elements of design knowledge capture

This paper will present the basic constituents of a design knowledge capture effort. This will include a discussion of the types of knowledge to be captured in such an effort and the difference between design knowledge capture and more traditional knowledge base construction. These differences include both knowledge base structure and knowledge acquisition approach. The motivation for establishing a design knowledge capture effort as an integral part of major NASA programs will be outlined, along with the current NASA position on that subject. Finally the approach taken in design knowledge capture for Space Station will be contrasted with that used in the HSTDEK project.

Freeman, Michael S.↗

NASA NTRS1990

Construction of dynamic stochastic simulation models using knowledge-based techniques

Over the past three decades, computer-based simulation models have proven themselves to be cost-effective alternatives to the more structured deterministic methods of systems analysis. During this time, many techniques, tools and languages for constructing computer-based simulation models have been developed. More recently, advances in knowledge-based system technology have led many researchers to note the similarities between knowledge-based programming and simulation technologies and to investigate the potential application of knowledge-based programming techniques to simulation modeling. The integration of conventional simulation techniques with knowledge-based programming techniques is discussed to provide a development environment for constructing knowledge-based simulation models. A comparison of the techniques used in the construction of dynamic stochastic simulation models and those used in the construction of knowledge-based systems provides the requirements for the environment. This leads to the design and implementation of a knowledge-based simulation development environment. These techniques were used in the construction of several knowledge-based simulation models including the Advanced Launch System Model (ALSYM).

Williams, M. Douglas↗