Search NASA⌕ Search

SEARCH · Search NASA

Results for “domain 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.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

Software design as a problem in learning theory (a research overview)

Our interest in automating software design has come out of our research in automated reasoning, inductive inference, learnability, and algebraic machine theory. We have investigated these areas extensively, in connection with specific problems of language representation, acquisition, processing, and design. In the case of formal context-free (CF) languages we established existence of finite learnable models ('behavioral realizations') and procedures for constructing them effectively. We also determined techniques for automatic construction of the models, inductively inferring them from finite examples of how they should 'behave'. These results were obtainable due to appropriate representation of domain knowledge, and constraints on the domain that the representation defined. It was when we sought to generalize our results, and adapt or apply them, that we began investigating the possibility of determining similar procedures for constructing correct software. Discussions with other researchers led us to examine testing and verification processes, as they are related to inference, and due to their considerable importance in correct software design. Motivating papers by other researchers, led us to examine these processes in some depth. Here we present our approach to those software design issues raised by other researchers, within our own theoretical context. We describe our results, relative to those of the other researchers, and conclude that they do not compare unfavorably.

Fass, Leona F.↗

Solar soft cost ontology: a review of solar soft costs

The continued deployment of renewable energy is critical to the energy transition necessary for climate change mitigation. Since cost is one of the primary drivers of solar adoption, we must continue to reduce the cost of solar to hasten the transition to clean energy. Currently, solar soft costs account for 52%–70% of the cost of an installed residential solar photovoltaic (PV) system in the U.S. These costs are persistent and an increasing share of the costs, since hardware costs continue to decline. The consensus on a definition of soft costs is 'non-hardware costs', but defining something by what it is not does not tell us what it is, which makes it difficult to study and understand. To this end, we developed the solar soft cost ontology (SSCO) to provide a comprehensive view of the complex and variable knowledge domain of solar soft costs. In this work, we identify the main categories of solar soft costs, how they relate to each other, how that knowledge is created, shared, and acquired, and the relevant actors in the solar soft cost knowledge ecosystem. Developed by coding a corpus of nearly 130 academic articles, the resulting ontology in web ontology language (OWL) includes 136 classes and 87 properties. The SSCO can facilitate and enhance knowledge transfer of research findings and best practices within and between stakeholder communities, including researchers, practitioners, and policy makers, that seek to address solar soft costs. We conclude with a discussion of potential applications and use cases for the SSCO among this diverse stakeholder community.

14 SOLAR ENERGY↗

Physics-informed, empirically constrained machine learning for designing Fe-9Cr alloys

<span style="font-family: Calibri, sans-serif; font-size: 12pt;">Materials data analytics can be used to significantly shorten development time of specialized alloys needed for next generation energy applications. Incorporation of the domain knowledge into deep-learning graph structure via fuzzy pre-training and causal process imitation presents a viable approach to developing accurate data-driven models and reliable alloy design tools, with limited datasets. It was demonstrated that the domain knowledge-based empirical constraints not only inhibit overfitting but also allow training more accurate and reliable ML models with improved transparency of the output interpretation. In this study, alloy tensile properties were interpreted with three competing virtual-microstructure models.</span>

Romanov, Vyacheslav↗

A prototype case-based reasoning human assistant for space crew assessment and mission management

We present a prototype human assistant system for space crew assessment and mission management. Our system is based on case episodes from American and Russian space missions and analog environments such as polar stations and undersea habitats. The general domain of small groups in isolated and confined environments represents a near ideal application area for case-based reasoning (CBR) - there are few reliable rules to follow, and most domain knowledge is in the form of cases. We define the problem domain and outline a unique knowledge representation system driven by conflict and communication triggers. The prototype system is able to represent, index, and retrieve case studies of human performance. We index by social, behavioral, and environmental factors. We present the problem domain, our current implementation, our research approach for an operational system, and prototype performance and results.

Owen, Robert B.↗

'Big Data' Collaboration: Exploring, Recording and Sharing Enterprise Knowledge

As data sources and data size proliferate, knowledge discovery from "Big Data" is starting to pose several challenges. In this paper, we address a specific challenge in the practice of enterprise knowledge management while extracting actionable nuggets from diverse data sources of seemingly-related information. In particular, we address the challenge of archiving knowledge gained through collaboration, dissemination and visualization as part of the data analysis, inference and decision-making lifecycle. We motivate the implementation of an enterprise data-discovery and knowledge recorder tool, called SEEKER based on real world case-study. We demonstrate SEEKER capturing schema and data-element relationships, tracking the data elements of value based on the queries and the analytical artifacts that are being created by analysts as they use the data. We show how the tool serves as digital record of institutional domain knowledge and a documentation for the evolution of data elements, queries and schemas over time. As a knowledge management service, a tool like SEEKER saves enterprise resources and time by avoiding analytic silos, expediting the process of multi-source data integration and intelligently documenting discoveries from fellow analysts.

Big Data↗

An expert system for setting time steps in dynamic finite element programs

An expert system, ETUDES - Expert Time integration control Using Deep and Surface Knowledge System, which addresses the determination of the timestep for time integration of linear structural dynamic equations is described. This timestep may also be applicable for a moderately nonlinear simulation of the same structure. The program also determines whether an explicit or implicit method is most efficient for the particular simulation. A production rule programming system written in OPS5 is used for the implementation of this prototype expert system. Issues relating to the expert system architecture for this application, such as knowledge representation and structure, as well as domain knowledge are discussed. The prototype is evaluated by measuring its performance in various benchmark model problems.

Ramirez, Martin R.↗

The Planning Execution Monitoring Architecture

The Planning Execution Monitoring (PEM) architecture is a design concept for developing autonomous cockpit command and control software. The PEM architecture is designed to reduce the operations costs in the space transportation system through the use of automation while improving safety and operability of the system. Specifically, the PEM autonomous framework enables automatic performance of many vehicle operations that would typically be performed by a human. Also, this framework supports varying levels of autonomous control, ranging from fully automatic to fully manual control. The PEM autonomous framework interfaces with the core flight software to perform flight procedures. It can either assist human operators in performing procedures or autonomously execute routine cockpit procedures based on the operational context. Most importantly, the PEM autonomous framework promotes and simplifies the capture, verification, and validation of the flight operations knowledge. Through a hierarchical decomposition of the domain knowledge, the vehicle command and control capabilities are divided into manageable functional "chunks" that can be captured and verified separately. These functional units, each of which has the responsibility to manage part of the vehicle command and control, are modular, re-usable, and extensible. Also, the functional units are self-contained and have the ability to plan and execute the necessary steps for accomplishing a task based upon the current mission state and available resources. The PEM architecture has potential for application outside the realm of spaceflight, including management of complex industrial processes, nuclear control, and control of complex vehicles such as submarines or unmanned air vehicles.

Wang, Lui↗

Data Science and the Knowledge Discovery Adventure

This talk will cover the important steps involved in the data science and knowledge discovery process: • Initial fact gathering (interview domain experts, review reports, articles, state-of-the-art) • Identify the problem (prediction, classification, statistical analysis, etc.) • Survey supporting data sources • Understand the data (numerical, categorical, text, sampling rate, data quality issues, etc.) • Selecting relevant features and sources • Acquire the data (set up agreements with the data stewards, APIs to download, etc.) • Merge data sources (temporal, spatial, common key, other ontologies...) • Feature Engineering (non linear domain knowledge or physics-based relationships) • Build data processing pipeline (may need to tap into data stream, develop parallel processing algorithm, federated learning etc.) • Build model and test (tune hyper-parameters, cross validation.) • Analyze/Validate results (do the results make sense. Does it answer the original question). • Deploy/Publish (Monitor and assess benefits)

Data science↗

Social Network and Content Analysis of the North American Carbon Program as a Scientific Community of Practice

The North American Carbon Program (NACP) was formed to further the scientific understanding of sources, sinks, and stocks of carbon in Earth's environment. Carbon cycle science integrates multidisciplinary research, providing decision-support information for managing climate and carbon-related change across multiple sectors of society. This investigation uses the conceptual framework of com-munities of practice (CoP) to explore the role that the NACP has played in connecting researchers into a carbon cycle knowledge network, and in enabling them to conduct physical science that includes ideas from social science. A CoP describes the communities formed when people consistently engage in shared communication and activities toward a common passion or learning goal. We apply the CoP model by using keyword analysis of abstracts from scientific publications to analyze the research outputs of the NACP in terms of its knowledge domain. We also construct a co-authorship network from the publications of core NACP members, describe the structure and social pathways within the community. Results of the content analysis indicate that the NACP community of practice has substantially expanded its research on human and social impacts on the carbon cycle, contributing to a better understanding of how human and physical processes interact with one another. Results of the co-authorship social network analysis demonstrate that the NACP has formed a tightly connected community with many social pathways through which knowledge may flow, and that it has also expanded its network of institutions involved in carbon cycle research over the past seven years.

Knowledge domain↗

Domain adaptation techniques for improved cross-domain study of galaxy mergers

In astronomy, neural networks are often trained on simulated data with the prospect of being applied to real observations. Unfortunately, simply training a deep neural network on images from one domain does not guarantee satisfactory performance on new images from a different domain. The ability to share cross-domain knowledge is the main advantage of modern deep domain adaptation techniques. Here we demonstrate the use of two techniques - Maximum Mean Discrepancy (MMD) and adversarial training with Domain Adversarial Neural Networks (DANN) - for the classification of distant galaxy mergers from the Illustris-1 simulation, where the two domains presented differ only due to inclusion of observational noise. We show how the addition of either MMD or adversarial training greatly improves the performance of the classifier on the target domain when compared to conventional machine learning algorithms, thereby demonstrating great promise for their use in astronomy.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

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↗

The Integrated Medical Model: Statistical Forecasting of Risks to Crew Health and Mission Success

The Integrated Medical Model (IMM) helps capture and use organizational knowledge across the space medicine, training, operations, engineering, and research domains. The IMM uses this domain knowledge in the context of a mission and crew profile to forecast crew health and mission success risks. The IMM is most helpful in comparing the risk of two or more mission profiles, not as a tool for predicting absolute risk. The process of building the IMM adheres to Probability Risk Assessment (PRA) techniques described in NASA Procedural Requirement (NPR) 8705.5, and uses current evidence-based information to establish a defensible position for making decisions that help ensure crew health and mission success. The IMM quantitatively describes the following input parameters: 1) medical conditions and likelihood, 2) mission duration, 3) vehicle environment, 4) crew attributes (e.g. age, sex), 5) crew activities (e.g. EVA's, Lunar excursions), 6) diagnosis and treatment protocols (e.g. medical equipment, consumables pharmaceuticals), and 7) Crew Medical Officer (CMO) training effectiveness. It is worth reiterating that the IMM uses the data sets above as inputs. Many other risk management efforts stop at determining only likelihood. The IMM is unique in that it models not only likelihood, but risk mitigations, as well as subsequent clinical outcomes based on those mitigations. Once the mathematical relationships among the above parameters are established, the IMM uses a Monte Carlo simulation technique (a random sampling of the inputs as described by their statistical distribution) to determine the probable outcomes. Because the IMM is a stochastic model (i.e. the input parameters are represented by various statistical distributions depending on the data type), when the mission is simulated 10-50,000 times with a given set of medical capabilities (risk mitigations), a prediction of the most probable outcomes can be generated. For each mission, the IMM tracks which conditions occurred and decrements the pharmaceuticals and supplies required to diagnose and treat these medical conditions. If supplies are depleted, then the medical condition goes untreated, and crew and mission risk increase. The IMM currently models approximately 30 medical conditions. By the end of FY2008, the IMM will be modeling over 100 medical conditions, approximately 60 of which have been recorded to have occurred during short and long space missions.

Fitts, M. A.↗

Detecting Unclassified Electromagnetic Signals for Secure Wireless Communication Using Open Set Recognition

We developed multiple machine learning methods for the detection and classification of new wireless communication waveforms, which is critical for targeted attacks in wireless networks and electronic warfare. Our machine learning models are capable of dynamically detecting security threats in near real time through our advanced open set recognition (OSR) approach. This model has demonstrated significant improvements in the detection of unknown waveforms, thereby enhancing the security and reliability of mission critical communications. Our approach to detecting uncertain security threats is novel; we advanced OSR techniques by incorporating domain knowledge of wireless signals. Specifically, we combined time and frequency domain model features to enhance the model’s performance. Utilizing an OSR approach eliminates the need for training data to be distributed similarly to the deployment environment and removes the requirement for the training set to contains all possible threat classes. This is crucial because it is often infeasible to determine and characterize all potential security threats in advance. Our model were trained on simulated data, generated in partnership with the University at Albany, State of New York. The data set contained a diverse array of wireless signals, including those with additive white Gaussian noise and multipath signals, with and without line of sight. This comprehensive training set allowed us to optimize our models to detect unknown waveforms under various challenging scenarios, such as low signal-to-noise ratios. By training on various waveforms, varying signal-to-noise ratio, and different sample sizes under normal conditions, our models were fine tuned to perform effectively in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗

Designing alloys with process-mapping AI pre-trained on empirical knowledge

<span style="font-family: Calibri, sans-serif; font-size: 12pt;">Accelerated materials design should match the recent trends in the product development cycles. Materials data analytics can be used to significantly shorten development time of specialized alloys needed for next generation energy applications. However, it faces a challenge of scarce data available for training ML models. Incorporation of the domain knowledge into deep-learning graph structure via fuzzy pre-training and causal process imitation presents a viable approach to developing accurate data-driven models and reliable alloy design tools, with limited datasets. Artificial Intelligence (AI) was used in this study to incorporate such knowledge in the domain-specific computational tool, pyroMind. The tool provides not only novel design ideas but also their interpretation via physics and engineering concepts.</span>

Romanov, Vyacheslav↗

C3F: Collaborative Container-based Model Coupling Framework

Solving complex real-world grand challenge problems requires in-depth collaboration of researchers from multiple disciplines. Such collaboration often involves harnessing multiscale and multi-dimensional data and combining models from different fields to simulate systems. However, the progress on this front has been limited mainly due to significant gaps in domain knowledge and tools that are typically employed in silos of the domains. Researchers from different fields face considerable barriers to understanding and reusing each other’s data/models in order to collaborate effectively. For example, in solving the global sustainability problems, researchers from hydrology, climate science, agriculture, and economics need to run their respective models to study different components of the global and local food, energy and water systems while, at the same time, need to interact with other researchers and integrate the results of one model with another. Developing this kind of model coupling workflow calls for (1) a large amount of data being processed and exchanged across domains and organizations, (2) identifying and processing the output of one model to make it ready for integration into another model, (3) controlling the workflow dynamically so that it runs until a certain convergence condition or other criteria is met, and (4) close collaboration among the modelers to explore, tune, and test the configuration and data transformation needed to link the models. We have developed C3F, a flexible collaborative model coupling framework to help researchers accelerate their model integration and linking efforts by leveraging advanced cyberinfrastructure such as high-performance computing and virtual containers. In this paper, we describe our experience and lessons learned in developing this cyberinfrastructure solution to support the linking of Water Balance Model (WBM) and SIMPLE-G agricultural economic model in an NSF funded INFEWS project and a DOE-funded Program on Coupled Human and Earth Systems (PCHES) to study the implications of groundwater scarcity for food-energy-water systems. The C3F model coupling framework can be extended to facilitate other model linkages as well.

containerization↗

A Benchmarking Framework for Evaluating Large Language Model Capabilities in Nuclear Reactor Safety Applications

Large language models (LLMs) are increasingly capable of answering technical questions, synthesizing domain knowledge, and supporting engineering workflows. For nuclear science and engineering, these capabilities require careful, domain-specific evaluation before they can be credibly incorporated into safety-related activities, regulatory review, or technical decision support. This paper presents preliminary results from benchmarking framework for evaluating LLM capabilities in nuclear contexts. The framework is organized into three evaluation categories: nuclear fundamentals, general dual-use knowledge, and plant specific knowledge. These categories are intended to distinguish general nuclear engineering competence from broader technical reasoning and more context-dependent nuclear knowledge. Initial evaluations focus on nuclear fundamentals using questions representative of the knowledge expected of a nuclear professional engineer. Results indicate that contemporary frontier models perform at a high level and substantially exceed the performance of older model generations, with some models approaching saturation of the current benchmark. These findings suggest both the rapid improvement of LLM capabilities in specialized technical domains and the need for more discriminating evaluation methods. The paper presents the benchmark structure, preliminary model-comparison results, and ongoing work. This work supports development of verifiable, responsible, and safety-conscious methods for assessing AI systems in nuclear engineering applications.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

Simple explanations and reasoning: From philosophy of science to expert systems

A preliminary prototype of a simple explanation system was constructed. Although the system, based on the idea of storytelling, did not incorporate all of the principles of simple explanation, it did demonstrate the potential of the approach. The system incorporated a hypertext system, an inference engine, and facilities for constructing contrast type explanations. The continued development of such a system should prove to be valuable. By extending the resources of the expert system paradigm, the knowledge engineer is not forced to learn a new set of skills, and the domain knowledge already acquired by him is not lost. Further, both the beginning user and the more advanced user can be accommodated. For the beginning user, corrective explanations and ES explanations provide facilities for more clearly understanding the way in which the system is functioning. For the more advanced user, the instance and state explanations allow him to focus on the issues at hand. The simple model of explanation attempts to exploit and show how the why and how facilities of the expert system paradigm can be extended by attending to the pragmatics of explanation and adding texture to the ordinary pattern of reasoning in a rule based system.

Rochowiak, Daniel↗

A Visual Analytics Approach to Structured Data Analysis to Enhance Nonproliferation and Arms Control Verification Activities

Analysis activities for Nonproliferation and Arms Control verification require the use of many types of data. Tabular structured data, such as Excel spreadsheets and relational databases, have traditionally been used for data mining activities, where specific queries are issued against data to look for matching results. The application of visual analytics tools to structured data enables further exploration of datasets to promote discovery of previously unknown results. This paper discusses the application of a specific visual analytics tool to datasets related to the field of Arms Control and Nonproliferation to promote the use of visual analytics more broadly in this domain. Visual analytics focuses on analytical reasoning facilitated by interactive visual interfaces (Wong and Thomas 2004). It promotes exploratory analysis of data, and complements data mining technologies where known patterns can be mined for. Also with a human in the loop, they can bring in domain knowledge and subject matter expertise. Visual analytics has not widely been applied to this domain. In this paper, we will focus on one type of data: structured data, and show the results of applying a specific visual analytics tool to answer questions in the Arms Control and Nonproliferation domain. We chose to use the T.Rex tool, a visual analytics tool developed at PNNL, which uses a variety of visual exploration patterns to discover relationships in structured datasets, including a facet view, graph view, matrix view, and timeline view. The facet view enables discovery of relationships between categorical information, such as countries and locations. The graph tool visualizes node-link relationship patterns, such as the flow of materials being shipped between parties. The matrix visualization shows highly correlated categories of information. The timeline view shows temporal patterns in data. In this paper, we will use T.Rex with two different datasets to demonstrate how interactive exploration of the data can aid an analyst with arms control and nonproliferation verification activities. Using a dataset from PIERS (PIERS 2014), we will show how container shipment imports and exports can aid an analyst in understanding the shipping patterns between two countries. We will also use T.Rex to examine a collection of research publications from the IAEA International Nuclear Information System (IAEA 2014) to discover collaborations of concern. We hope this paper will encourage the use of visual analytics structured data analytics in the field of nonproliferation and arms control verification. Our paper outlines some of the challenges that exist before broad adoption of these kinds of tools can occur and offers next steps to overcome these challenges.

arms control↗