Search NASA⌕ Search

SEARCH · Search NASA

Results for “knowledge representation”

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 289 records · Page 16

A survey on the design of multiprocessing systems for artificial intelligence applications

Some issues in designing computers for artificial intelligence (AI) processing are discussed. These issues are divided into three levels: the representation level, the control level, and the processor level. The representation level deals with the knowledge and methods used to solve the problem and the means to represent it. The control level is concerned with the detection of dependencies and parallelism in the algorithmic and program representations of the problem, and with the synchronization and sheduling of concurrent tasks. The processor level addresses the hardware and architectural components needed to evaluate the algorithmic and program representations. Solutions for the problems of each level are illustrated by a number of representative systems. Design decisions in existing projects on AI computers are classed into top-down, bottom-up, and middle-out approaches.

Wah, Benjamin W.↗

Chemical reaction enhanced graph learning for molecule representation

Abstract Motivation Molecular representation learning (MRL) models molecules with low-dimensional vectors to support biological and chemical applications. Current methods primarily rely on intrinsic molecular information to learn molecular representations, but they often overlook effectively integrating domain knowledge into MRL. Results In this article, we develop a reaction-enhanced graph learning (RXGL) framework for MRL, utilizing chemical reactions as domain knowledge. RXGL introduces dual graph learning modules to model molecule representation. One module employs graph convolutions on molecular graphs to capture molecule structures. The other module constructs a reaction-aware graph from chemical reactions and designs a novel graph attention network on this graph to integrate reaction-level relations into molecular modeling. To refine molecule representations, we design a reaction-based relation learning task, which considers the relations between the reactant and product sides in reactions. In addition, we introduce a cross-view contrastive task to strengthen the cooperative associations between molecular and reaction-aware graph learning. Experiment results show that our RXGL achieves strong performance in various downstream tasks, including product prediction, reaction classification, and molecular property prediction. Availability and implementation The code is publicly available at https://github.com/coder-ACAC/RLM.

Biochemistry & Molecular Biology↗

Leveraging Large Language Models for Understanding Fundamental Principles of Catalysis

Heterogeneous catalysis presents a distinct challenge for artificial intelligence (AI). Data sets are often small and inconsistently reported, catalyst representations are not standardized, and extracting fundamental knowledge requires integrating performance data, spectroscopic characterizations, and mechanistic models across multiple scales. Language offers a unifying representation across these modalities, making catalysis well suited for leveraging large language models (LLMs). By standardizing how catalytic data is represented, LLMs make dispersed experimental results more accessible to downstream statistical modeling. In this perspective, we focus our discussion around three opportunities where LLMs can significantly contribute to catalysis: (1) text to properties; (2) text to structure; and (3) text to mechanistic models. The discussion is followed by a perspective section on LLM-readiness of data, aligning LLM outputs with scientific correctness, and bridging lab-scale discovery to industrial deployment. Across each area, the most productive applications couple dispersed chemical knowledge with physics-grounded validation to produce verifiable hypotheses and actionable representations.

Catalysts↗

CLIPS: A tool for corn disease diagnostic system and an aid to neural network for automated knowledge acquisition

This paper describes the building of a corn disease diagnostic expert system using CLIPS, and the development of a neural expert system using the fact representation method of CLIPS for automated knowledge acquisition. The CLIPS corn expert system diagnoses 21 diseases from 52 symptoms and signs with certainty factors. CLIPS has several unique features. It allows the facts in rules to be broken down to object-attribute-value (OAV) triples, allows rule-grouping, and fires rules based on pattern-matching. These features combined with the chained inference engine result to a natural user query system and speedy execution. In order to develop a method for automated knowledge acquisition, an Artificial Neural Expert System (ANES) is developed by a direct mapping from the CLIPS system. The ANES corn expert system uses the same OAV triples in the CLIPS system for its facts. The LHS and RHS facts of the CLIPS rules are mapped into the input and output layers of the ANES, respectively; and the inference engine of the rules is imbedded in the hidden layer. The fact representation by OAC triples gives a natural grouping of the rules. These features allow the ANES system to automate rule-generation, and make it efficient to execute and easy to expand for a large and complex domain.

Wu, Cathy↗

The Synthetic Biology Open Language (SBOL) Version 3: Simplified Data Exchange for Bioengineering

The Synthetic Biology Open Language (SBOL) is a community-developed data standard that allows knowledge about biological designs to be captured using a machine-tractable, ontology-backed representation that is built using Semantic Web technologies. While early versions of SBOL focused only on the description of DNA-based components and their sub-components, SBOL can now be used to represent knowledge across multiple scales and throughout the entire synthetic biology workflow, from the specification of a single molecule or DNA fragment through to multicellular systems containing multiple interacting genetic circuits. The third major iteration of the SBOL standard, SBOL3, is an effort to streamline and simplify the underlying data model with a focus on real-world applications, based on experience from the deployment of SBOL in a variety of scientific and industrial settings. Here, we introduce the SBOL3 specification both in comparison to previous versions of SBOL and through practical examples of its use.

59 BASIC BIOLOGICAL SCIENCES↗

PVDaCS - A prototype knowledge-based expert system for certification of spacecraft data

On-line data management techniques to certify spacecraft information are mandated by increasing telemetry rates. Knowledge-based expert systems offer the ability to certify data electronically without the need for time-consuming human interaction. Issues of automatic certification are explored by designing a knowledge-based expert system to certify data from a scientific instrument, the Orbiter Ultraviolet Spectrometer, on an operating NASA planetary spacecraft, Pioneer Venus. The resulting rule-based system, called PVDaCS (Pioneer Venus Data Certification System), is a functional prototype demonstrating the concepts of a larger system design. A key element of the system design is the representation of an expert's knowledge through the usage of well ordered sequences. PVDaCS produces a certification value derived from expert knowledge and an analysis of the instrument's operation. Results of system performance are presented.

Wharton, Cathleen↗

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes (NLP). The complexity of EHR presents challenges in feature representation, information extraction, and uncertainty quantification. Here, to address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: Using data from 12.5 million Veterans Affairs patients, ARCH first derives embedding vectors and generates similarities along with associated p-values to measure the strength of relatedness between clinical features with statistical certainty quantification. Next, ARCH performs a sparse embedding regression to remove indirect linkage between features to build a sparse KG. Finally, ARCH was validated on various clinical tasks, including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer’s disease patients. Results: ARCH produces high-quality clinical embeddings and KG for over 60,000 codified and narrative EHR concepts. The KG and embeddings are visualized in the R-shiny powered web-API.3 ARCH achieved high accuracy in detecting EHR concept relationships, with AUCs of 0.926 (codified) and 0.861 (NLP) for similar EHR concepts, and 0.810 (codified) and 0.843 (NLP) for related pairs. It detected drug side effects with a 0.723 AUC, which improved to 0.826 after fine-tuning. Using both codified and NLP features, the detection power increased significantly. Compared to other methods, ARCH has superior accuracy and enhances weakly supervised phenotyping algorithms’ performance. Notably, it successfully categorized Alzheimer’s patients into two subgroups with varying mortality rates. Conclusion: The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

Electronic health records↗

TARGET's role in knowledge acquisition, engineering, validation, and documentation

We investigate the use of the TARGET task analysis tool for use in the development of rule-based expert systems. We found TARGET to be very helpful in the knowledge acquisition process. It enabled us to perform knowledge acquisition with one knowledge engineer rather than two. In addition, it improved communication between the domain expert and knowledge engineer. We also found it to be useful for both the rule development and refinement phases of the knowledge engineering process. Using the network in these phases required us to develop guidelines that enabled us to easily translate the network into production rules. A significant requirement for TARGET remaining useful throughout the knowledge engineering process was the need to carefully maintain consistency between the network and the rule representations. Maintaining consistency not only benefited the knowledge engineering process, but also has significant payoffs in the areas of validation of the expert system and documentation of the knowledge in the system.

Levi, Keith R.↗

Graphic simualtion test bed for robotics applications in a workstation environment

Graphical simulation is a cost-effective solution for developing and testing robots and their control systems. The availability of various high-performance workstations makes these systems feasible. Simulation offers preliminary testing of systems before their actual realizations, and it provides a framework for developing new control and planning algorithms. On the other hand, these simulation systems have to have the capability of incorporating various knowledge-based system components, e.g., task planners, representation formalisms, etc. They also should have an appropriate user interface, which makes possible the creation and control of simulation models. ROBOSIM was developed jointly by MSFC and Vanderbilt University, first in a VAX environment. Recently, the system has been ported to an HP-9000 workstation equipped with an SRX graphics accelerator. The user interface of the system now contains a menu- and icon-based facility, as well as the original ROBOSIM language. The system is also coupled to a symbolic computing system based on Common Lisp, where knowledge-based functionalities are implemented. The knowledge-based layer uses various representation and reasoning facilities for programming and testing the control systems of robots.

Springfield, J.↗

Microbially mediated climate feedbacks from wetland ecosystems

Wetlands are crucial nodes in the carbon cycle, emitting approximately 20% of global CH4 while also sequestering 20%–30% of all soil carbon. Both greenhouse gas fluxes and carbon storage are driven by microbial communities in wetland soils. However, these key players are often overlooked or overly simplified in current global climate models. Here, we first integrate microbial metabolisms with biological, chemical, and physical processes occurring at scales from individual microbial cells to ecosystems. This conceptual scale-bridging framework guides the development of feedback loops describing how wetland-specific climate impacts (i.e., sea level rise in estuarine wetlands, droughts and floods in inland wetlands) will affect future climate trajectories. Furthermore, these feedback loops highlight knowledge gaps that need to be addressed to develop predictive models of future climates capturing microbial contributions. We propose a roadmap connecting environmental scientific disciplines to address these knowledge gaps and improve the representation of microbial processes in climate models. Together, this paves the way to understand how microbially mediated climate feedbacks from wetlands will impact future climate change.

54 ENVIRONMENTAL SCIENCES↗

Techniques for modeling the reliability of fault-tolerant systems with the Markov state-space approach

This paper presents a step-by-step tutorial of the methods and the tools that were used for the reliability analysis of fault-tolerant systems. The approach used in this paper is the Markov (or semi-Markov) state-space method. The paper is intended for design engineers with a basic understanding of computer architecture and fault tolerance, but little knowledge of reliability modeling. The representation of architectural features in mathematical models is emphasized. This paper does not present details of the mathematical solution of complex reliability models. Instead, it describes the use of several recently developed computer programs SURE, ASSIST, STEM, and PAWS that automate the generation and the solution of these models.

Butler, Ricky W.↗

Earth Science Informatics Comes of Age

The volume and complexity of Earth science data have steadily increased, placing ever-greater demands on researchers, software developers and data managers tasked with handling such data. Additional demands arise from requirements being levied by funding agencies and governments to better manage, preserve and provide open access to data. Fortunately, over the past 10-15 years significant advances in information technology, such as increased processing power, advanced programming languages, more sophisticated and practical standards, and near-ubiquitous internet access have made the jobs of those acquiring, processing, distributing and archiving data easier. These advances have also led to an increasing number of individuals entering the field of informatics as it applies to Geoscience and Remote Sensing. Informatics is the science and technology of applying computers and computational methods to the systematic analysis, management, interchange, and representation of data, information, and knowledge. Informatics also encompasses the use of computers and computational methods to support decisionmaking and other applications for societal benefits.

Jodha, Siri↗

Understanding the Physics Representation of Deep Learning Models in Environmental Applications

Deep learning (DL) models have been popular in earth and environmental modeling and analysis, which exhibit huge potential in capturing and reconstructing the non-linearity of relevant environmental processes. They are extensively used as analytical tools or emulators for multiple domains (atmosphere, land surface, ocean, and biogeochemistry). Despite their success, their internal working mechanism remains largely unknown. Such a lack of knowledge hinders the identification of physically consistent models that are fully adaptive to non-stationary climate, as well as the development of physics-informed machine learning such as physics-informed neural network (PINN). To establish preliminary knowledge and framework of such physics representation evaluation, this project focuses on an improved understanding of DL models in the environmental applications. DL models are increasingly applied to environmental modeling and prediction. However, they have been evaluated mostly from a performance perspective, and there is a gap in understanding how they represent the known physics internally. Such knowledge is especially critical when applying DL models under climate change conditions, where new inputs are likely outside the ranges of the training datasets. In this project, we reveal how the known physical processes are represented within DL models from both statistical and mechanistic perspectives. Leveraging the traditional model evaluations that focus more on the accuracies of predictions, we establish a framework that examines both the accuracy and physics representation of DL models. This analysis framework can identify DL models that make the correct predictions based on correct physics, thus enhancing the existing explainable artificial intelligence (explainable-AI) portfolio. It lays a foundation for developing novel metrics to evaluate the emerging DL models in environmental applications. This knowledge also informs the development of physics-informed DL models by revealing the direct connections between the known physical processes and specific model components or structures.

54 ENVIRONMENTAL SCIENCES↗

A Knowledge Graph Framework for Organizing Heterogeneous Datasets for Utilization in Classical and Quantum Computing: Current Challenges and Future Directions

"The escalating impact of climate change induced extreme weather events in urban, suburban, and rural environments demands a rethink of how we have been using the single event-based or use-case-based knowledge graph models. The lack of representation in interaction within environmental variables found in literature led to the development of a novel framework that reflects the true nature of the interconnectedness in our environment. We propose an Environmental Interaction Knowledge Graph (EIKG) framework. This general EIKG framework works as the basis for interconnected environmental events by knitting interrelated events such as hurricanes leading to storm surges, which lead to flood events that could cause mudslides, landslides, etc., The cascading nature of one event leading to another related event in the environment requires an adequate understanding of each event using contextual information before conducting any data-driven analytics. This vision paper showcases how the EIKG:floods, EIKG:wildfire EIKG:landslides, etc, can be derived from a base case framework of EIKG as those individual events are interconnected with some common denominator variables. As an example, the precipitation variable is used in the flood case study as well as in the wildfire case study, as excessive precipitation levels lead to floods, and lack of precipitation leads to droughts and wildfires. We identify the precipitation variable as a “common-denominator-variable” in extreme weather events that play a key role in modeling the environment leading to different extreme weather events based on the variability of that variable (varying values where low precipitation leads to drought, and high values lead to floods). We use the insights gained from EIKG to conduct classical and Quantum Machine Learning (QML) based data analysis on the research questions developed. Our preliminary study shows how the Variational Quantum Classifier (VQC) and Quantum Support Vector Classifier (QSVC) are used along with the classical machine learning models to compare the model accuracies. Our study elaborates on how a quantitative analysis uses state-of-the-art machine learning techniques that include implementing both classical and quantum machine learning models and developing the knowledge graph. The EIKG is used to organize heterogeneous datasets and integrate the relations to case-specific extreme weather events such as floods. The study uses datasets such as county-to-country residential mobility data, socioeconomic datasets from the US Census Bureau, climate and weather-related Earth Observational data from NASA, and critical infrastructure data from the Homeland Infrastructure datasets."

Knowledge Graphs, Quantum Computing, Heterogenous ↗

Algebraic model to study the internal structure of pseudoscalar mesons with heavy-light quark content

The internal structure of all lowest-lying pseudoscalar mesons with heavy-light quark content is studied in detail using an algebraic model that has been applied recently, and successfully, to the same physical observables of pseudoscalar and vector mesons with hidden-flavor quark content, from light to heavy quark sectors. The algebraic model consists on constructing simple and evidence-based of the meson’s Bethe-Salpeter amplitude (BSA) and quark’s propagator in such a way that the Bethe-Salpeter wave function (BSWF) can then be readily computed algebraically. Its subsequent projection onto the light front yields the light front wave function (LFWF) whose form allows us a simple access to the valence-quark parton distribution amplitude (PDA) by integrating over the transverse momentum squared. We exploit our current knowledge of the PDAs of lowest-lying pseudoscalar heavy-light mesons to compute their generalized parton distributions (GPDs) through the overlap representation of LFWFs. From these three dimensional knowledge, different limits/projections lead us to deduce the related parton distribution functions (PDFs), electromagnetic form factors (EFFs), and impact parameter space GPDs (IPS-GPDs). When possible, we make explicit comparisons with available experimental results and earlier theoretical predictions. Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Strategies to improve reference databases for soil microbiomes

A database of curated genomes is needed to better assess soil microbial communities and their processes associated with differing land management and environmental impacts. Interpreting soil metagenomic datasets with existing sequence databases is challenging because these datasets are biased towards medical and biotechnology research and can result in misleading annotations. We have curated a database of 928 genomes of soil-associated organisms (888 bacteria, 34 archaea, and 6 fungi). Using this database as a representation of the current state of knowledge of soil microbes that are well-characterized, we evaluated its composition and compared it to broader microbial databases, specifically NCBI’s RefSeq, as well as 3,035 publicly available soil amplicon datasets. These comparisons identified phyla and functions that are enriched in soils as well as those that may be underrepresented in RefSoil. For example, RefSoil was observed to have increased representation of Firmicutes despite its low abundance in soil environments and also lacked representation of Acidobacteria and Verrucomicrobia, which are abundant in soils. Our comparison of RefSoil to soil amplicon datasets allowed us to identify targets that if cultured or sequenced would significantly increase the biodiversity represented within RefSoil. To demonstrate the opportunities to access these underrepresented targets, we employed single cell genomics in a pilot experiment to recover 14 genomes from the "most wanted" list, which improved RefSoil's representation of EMP sequences by 7% by abundance. This effort demonstrates the value of RefSoil in the guidance of future research efforts and the capability of single cell genomics as a practical means to fill the existing genomic data gaps.

59 BASIC BIOLOGICAL SCIENCES↗

Certainty grids for mobile robots

A numerical representation of uncertain and incomplete sensor knowledge called Certainty Grids has been used successfully in several mobile robot control programs, and has proven itself to be a powerful and efficient unifying solution for sensor fusion, motion planning, landmark identification, and many other central problems. Researchers propose to build a software framework running on processors onboard the new Uranus mobile robot that will maintain a probabilistic, geometric map of the robot's surroundings as it moves. The certainty grid representation will allow this map to be incrementally updated in a uniform way from various sources including sonar, stereo vision, proximity and contact sensors. The approach can correctly model the fuzziness of each reading, while at the same time combining multiple measurements to produce sharper map features, and it can deal correctly with uncertainties in the robot's motion. The map will be used by planning programs to choose clear paths, identify locations (by correlating maps), identify well-known and insufficiently sensed terrain, and perhaps identify objects by shape. The certainty grid representation can be extended in the same dimension and used to detect and track moving objects.

Moravec, H. P.↗

Wavelets as basis functions to represent the coarse-graining potential in multiscale coarse graining approach

In this paper, we apply Multiresolution Analysis (MRA) to develop sparse but accurate representations for the Multiscale Coarse-Graining (MSCG) approximation to the many-body potential of mean force. We rigorously framed the MSCG method into MRA so that all the instruments of this theory become available together with a multitude of new basis functions, namely the wavelets. The coarse-grained (CG) force field is hierarchically decomposed at different resolution levels enabling to choose the most appropriate wavelet family for each physical interaction without requiring an a priori knowledge of the details localization. The representation of the CG potential in this new efficient orthonormal basis leads to a compression of the signal information in few large expansion coefficients. The multiresolution property of the wavelet transform allows to isolate and remove the noise from the CG force-field reconstruction by thresholding the basis function coefficients from each frequency band independently. We discuss the implementation of our wavelet-based MSCG approach and demonstrate its accuracy using two different condensed-phase systems, i.e. liquid water and methanol. Simulations of liquid argon have also been performed using a one-to-one mapping between atomistic and CG sites. The latter model allows to verify the accuracy of the method and to test different choices of wavelet families. Furthermore, the results of the computer simulations show that the efficiency and sparsity of the representation of the CG force field can be traced back to the mathematical properties of the chosen family of wavelets. This result is in agreement with what is known from the theory of multiresolution analysis of signals.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗