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 1,063 records · Page 59

Toward Physics-informed Neural Networks for 3D Multi-layer Cloud Mask Reconstruction

Three-dimensional (3D) cloud retrievals are critical for understanding their impact on climate and other applications such as aviation safety, weather prediction, and remote sensing. However, obtaining high-resolution and accurate vertical representation of clouds remains unsolved due to the limitations imposed by satellite instrumentation, viewing conditions, and the complexity of cloud dynamics. Cloud masks are essential for comprehending various cloud vertical properties, but deriving accurate 3D cloud masks from 2D satellite imagery data is a challenging task. To tackle these challenges, we introduce a physics-informed loss function for training deep learning models that can extend 2D cloud images into 3D cloud masks. The proposed loss, called CloudMask Loss, is composed of two domain knowledge-informed loss terms: one for evaluating cloud position and thickness, and the other for measuring the number of layers. By combining these loss terms, we improve the trainability of the deep learning models for more accurate and meaningful results. We apply the proposed loss function to different neural networks and demonstrate significant improvements in multi-layer cloud mask reconstruction. Utilizing the same neural network architecture, our proposed loss outperforms standard binary crossentropy loss in terms of multi-layer cloud classification accuracy, number of layers accuracy, and thickness mean absolute error (MAE). The proposed loss function can be readily integrated into various neural network architectures, resulting in substantial performance gains in 3D cloud mask generation.

multi-layer clouds↗

Reduced‐Order Modeling of Energetic Materials Using Physics‐Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)

Physics-aware deep learning (PADL) has gained popularity for use in spatiotemporal dynamics simulations, such as those in computational modeling of energetic materials (EM). We show that the challenge PADL methods face while learning complex field evolution problems can be simplified and accelerated by decoupling it into two tasks: learning complex geometric features in evolving fields and modeling dynamics over these features in a lower-dimensional feature space. We build upon our previous work on physics-aware recurrent convolutional neural networks (PARC). PARC embeds knowledge of underlying physics into its neural network architecture for more robust and accurate prediction of evolving physical fields. PARC was shown to effectively learn complex nonlinear features such as the formation of hotspots and coupled shock fronts in various initiation scenarios of EMs, as a function of microstructures, serving effectively as a microstructure-aware burn model. Here, we further accelerate PARC and reduce its computational cost by projecting the original dynamics onto a lower-dimensional invariant manifold, or “latent space.” The projected latent representation encodes the complex geometry of evolving fields (e.g., temperature and pressure) in a set of data-driven features. The reduced dimension of this latent space allows us to learn the dynamics during the initiation of EM with a lighter and more efficient model. We observe a significant decrease in training and inference time while maintaining results comparable to PARC at inference. This work takes steps towards enabling rapid prediction of EM thermomechanics at larger scales and characterization of EM structure–property–performance linkages at a full application scale.

Mathematics and Computing↗

Architecture-Preserving Provable Repair of Deep Neural Networks

Deep neural networks (DNNs) are becoming increasingly important components of software, and are considered the state-of-the-art solution for a number of problems, such as image recognition. However, DNNs are far from infallible, and incorrect behavior of DNNs can have disastrous real-world consequences. This paper addresses the problem of architecture-preserving V-polytope provable repair of DNNs. A V-polytope defines a convex bounded polytope using its vertex representation. V-polytope provable repair guarantees that the repaired DNN satisfies the given specification on the infinite set of points in the given V-polytope. An architecture-preserving repair only modifies the parameters of the DNN, without modifying its architecture. The repair has the flexibility to modify multiple layers of the DNN, and runs in polynomial time. It supports DNNs with activation functions that have some linear pieces, as well as fully-connected, convolutional, pooling and residual layers. To the best our knowledge, this is the first provable repair approach that has all of these features. We implement our approach in a tool called APRNN. Using MNIST, ImageNet, and ACAS Xu DNNs, we show that it has better efficiency, scalability, and generalization compared to PRDNN and REASSURE, prior provable repair methods that are not architecture preserving.

97 MATHEMATICS AND COMPUTING↗

Aerosol Hygroscopic Growth, Mixing State, and Cloud Condensation Nuclei Activity during TRACER (Field Campaign Report)

Convective clouds play a critical role in the Earth’s climate system. Recent research has shown that a realistic representation of convective processes is critical to constraining climate sensitivity in global climate models. Theoretical and modeling studies showed that aerosols could have strong dynamic feedback to convection in warm and humid environments through enhancing ice-related processes and condensational growth. A few observation-based studies also suggested the influence of aerosols on convective cloud and precipitation properties. However, robust observational quantification of an aerosol effect on convective clouds isolated from other factors remains elusive. Understanding the impact of aerosol on convective clouds requires knowledge of the cloud condensation nuclei (CCN) spectrum, which represents the number of particles that uptake water and form cloud droplets as a function of supersaturation. The water uptake by aerosol is also of critical importance for the direct interaction of aerosol with radiation (i.e., aerosol direct effect) due to light scattering and absorption by aerosol. While both droplet activation under supersaturated conditions (i.e., relative humidity RH > 100%) and the hygroscopic growth under sub-saturated conditions (i.e., RH < 100%) are strongly influenced by particle hygroscopicity, the thermodynamic regimes and measurement methods are quite different. Aerosol particles, especially organic particles, can exhibit higher hygroscopicity for droplet activation than that for hygroscopic growth. In the subsaturated regime, the hygroscopicity of organic particles can also vary strongly with RH. However, global climate models usually treat organic species in aerosols with a constant hygroscopicity, potentially introducing substantial uncertainties in the quantification of aerosol radiative effects.

54 ENVIRONMENTAL SCIENCES↗

Development of a Convolutional Neural Network Classifier for Data Starved Spectra - 20199

The Institute for Clean Energy Technology (ICET) at Mississippi State University is exploring the utility of machine learning in augmenting its mobile radiation surveying platforms, which are currently being developed as means to survey depleted uranium contaminated areas in support of remediation and decommissioning efforts. Mobile survey platforms provide a means to efficiently scan large areas of interest while reducing human exposure to radiation and other hazards. The survey platforms can also be used for scanning for any gamma emitting isotope in addition to depleted uranium. The spectral data that the platforms collect may be data starved with relatively low counts and poorly defined spectral features depending on the speed of the platforms and scintillation detector selection. Such data-starved spectra are difficult to use for isotope identification, requiring advanced knowledge of the possible radionuclides that could be present and environmental factors that could attenuate signals or introduce background noise. These factors in combination with the volume of survey data increases the time it takes to perform analysis of survey data when the source type is unknown. There are a number of algorithms in the field of machine learning that can be used to classify data that would be challenging and time-consuming for a human to identify. Supervised machine learning algorithms train models based on extensive amounts of human-labeled training data. Once sufficiently trained, these models can be used to quickly make high-fidelity predictions on new data. Convolutional neural networks are machine learning algorithms that excel in learning representations of 'shapes'. They do this by taking numerical input data and convolving them with spatial feature detectors referred to as filters. These filters are incrementally adjusted to reduce the prediction error on the data during the backpropagation step of training. Discussed in this paper is the development of a convolutional neural network classifier (CNNC) that can utilize spectral survey data for source discrimination and isotope identification. Bench-top laboratory experiments data using LaBr{sub 3}(Ce) scintillation detectors were used to train and evaluate the performance of the developed CNNC. The CNNC is capable of discriminating a variety of gamma emitting source types, differentiating different forms of uranium (depleted vs. natural), and estimating the amount of uranium for a known geometry. The discussed CNNC may be useful in scenarios where survey systems are deployed in situations where hazardous radioactive material maybe present, but the type is unknown. When used in remediation applications the CNNC can be used to screen-out false positives, helping reduce remediation costs. (authors)

07 ISOTOPE AND RADIATION SOURCES↗

An Assessment of the Ability of Potential Space-Borne Instruments to Resolve Spatial and Temporal Variability of Atmospheric Carbon Dioxide

Mounting concern regarding the possibility that increasing carbon dioxide concentrations will initiate climate change has stimulated interest in the feasibility of measuring CO2 mixing ratios from satellites. Currently, the most comprehensive set of atmospheric CO2 data is from the NOAA CMDL cooperative air sampling network, consisting of more than 40 sites where flasks of air are collected approximately weekly. Sporadic observations in the troposphere and stratosphere from airborne in situ and flask samplers are also available. Although the surface network is extensive, there is a dearth of data in the Southern Hemisphere and most of the stations were intentionally placed in remote areas, far from major sources. Sufficiently precise satellite observations with adequate spatial and temporal resolution would substantially increase our knowledge of the atmospheric CO2 distribution and would undoubtedly lead to improved understanding of the global carbon budget. We use a 3-D chemical transport model to investigate the ability of potential satellite instruments with a variety of orbits, horizontal resolution and vertical weighting functions to capture the variation in the modeled CO2 fields. The model is driven by analyzed winds from the Goddard Data Assimilation Office. Simulated CO2 fields are compared with existing surface and aircraft data, and the effects of the model convection scheme and representation of the planetary boundary layer are considered.

Andrews, Arlyn E.↗

An Assessment of the Ability of Potential Spaceborne Instruments to Resolve Spatial and Temporal Variability of Atmospheric Carbon Dioxide

Mounting concern regarding the possibility that increasing carbon dioxide concentrations will initiate climate change has stimulated interest in the feasibility of measuring CO2 mixing ratios from satellites. Currently, the most comprehensive set of atmospheric CO2 data is from the NOAA CMDL cooperative air sampling network, consisting of more than 40 sites where flasks of air are collected approximately weekly. Sporadic observations in the troposphere and stratosphere from airborne in situ and flask samplers are also available. Although the surface network is extensive, there is a dearth of data in the Southern Hemisphere and most of the stations were intentionally placed in remote areas, far from major sources. Sufficiently precise satellite observations with adequate spatial and temporal resolution would substantially increase our knowledge of the atmospheric CO2 distribution and would undoubtedly lead to improved understanding of the global carbon budget. We use a 3-D chemical transport model to investigate the ability of potential satellite instruments with a variety of orbits, horizontal resolution and vertical weighting functions to capture the variation in the modeled CO2 fields. The model is driven by analyzed winds from the Goddard Data Assimilation Office. Simulated CO2 fields are compared with existing surface and aircraft data, and the effects of the model convection scheme and representation of the planetary boundary layer are considered.

Andrews, Arlyn E.↗

Analytic Result for the Two-loop Six-point NMHV Amplitude in N = 4 Super Yang-Mills Theory

We provide a simple analytic formula for the two-loop six-point ratio function of planar N = 4 super Yang-Mills theory. This result extends the analytic knowledge of multi-loop six-point amplitudes beyond those with maximal helicity violation. We make a natural ansatz for the symbols of the relevant functions appearing in the two-loop amplitude, and impose various consistency conditions, including symmetry, the absence of spurious poles, the correct collinear behavior, and agreement with the operator product expansion for light-like (super) Wilson loops. This information reduces the ansatz to a small number of relatively simple functions. In order to fix these parameters uniquely, we utilize an explicit representation of the amplitude in terms of loop integrals that can be evaluated analytically in various kinematic limits. The final compact analytic result is expressed in terms of classical polylogarithms, whose arguments are rational functions of the dual conformal cross-ratios, plus precisely two functions that are not of this type. One of the functions, the loop integral {Omega}{sup (2)}, also plays a key role in a new representation of the remainder function R{sub 6}{sup (2)} in the maximally helicity violating sector. Another interesting feature at two loops is the appearance of a new (parity odd) x (parity odd) sector of the amplitude, which is absent at one loop, and which is uniquely determined in a natural way in terms of the more familiar (parity even) x (parity even) part. The second non-polylogarithmic function, the loop integral {tilde {Omega}}{sup (2)}, characterizes this sector. Both {Omega}{sup (2)} and {tilde {Omega}}{sup (2)} can be expressed as one-dimensional integrals over classical polylogarithms with rational arguments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Samish Climate Resilience Planning Project

The Samish Indian Nation recognizes that climate change is indeed occurring and that even the most conservative climate projections threaten Samish members, culture, and natural resources. This report is a representation of the Samish Indian Nation’s commitment to providing a bright, sustainable future for the Seventh Generation and beyond by developing an institutional understanding of how climate change may impact the Tribe, determining what is most vulnerable to future changes, and creating strategies to mitigate these impacts and protect our resources. This report is the product of over a year of collaboration between Samish Indian Nation staff and Tribal community members, led by the Samish Climate Change Working Group (hereafter referred to as Working Group). This sharing of knowledge built a list of over 200 planning areas, including infrastructure, human health, and culturally important species, all of which were evaluated in this vulnerability assessment using up to date climate projections, recent reports, and internal expertise. This vulnerability assessment is the foundation for upcoming climate adaptation planning. It will provide staff with a knowledge base that can be used to develop effective climate adaptation strategies and foster a climate resilient community. This work will help ensure that Samish People can continue utilizing the bountiful natural resources of the Salish Sea that is such an important part of the Samish cultural identity. This document and associated web links within it represent the work and deliverables accomplished during the course of this project. It summarizes the last 2 years of effort by the Samish Tribe to understand, plan for and adapt to our changing climate and will provide planning guidance to the Tribe moving forward.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Assimilating Scanning Radar Data into Cloud-Scale Models

The aim of this project is to improve the initial conditions of large eddy simulations (LES) of deep convective storms by assimilating scanning radar reflectivity and radial velocity data as well as local environmental observations. Accomplishing this goal often results in more accurate numerical forecasts of clouds and precipitation than if the background initial meteorological conditions are solely relied upon for convection initiation and intensification, as is typical of most operational and research models. Conducted in a storm-scale LES framework, these more accurate numerical analyses can serve as tool to better understand and parameterize land-atmosphere coupling, boundary layer turbulence, and cloud processes, each used for model parameterization development of convection. Our work examined the sensitivity of the numerical representation of cloud-scale wind and microphysical structures to: i) the assimilation of radiosonde observations characterizing the near-storm inflow, ii) the assimilation of radar data of varying resolution for model simulations with grid spacings of 1-km and 0.25-km, and iii) to the assimilation of three-dimensional plan-projection-indicator (PPI) and range-height indicator (RHI) radar volumes. Few studies have explored deep convective storm analyses and forecasts produced by assimilation of radar observations to cloud-scale LES. Furthermore, to our knowledge, no storm-scale DA study has explored the value of assimilating high-resolution sector RHI volumes to determine if they can improve the retrieval of the vertical kinematic and microphysical storm structure aloft over the use of traditionally utilized PPI scans.

54 ENVIRONMENTAL SCIENCES↗

Functional reasoning in diagnostic problem solving

This work is one facet of an integrated approach to diagnostic problem solving for aircraft and space systems currently under development. The authors are applying a method of modeling and reasoning about deep knowledge based on a functional viewpoint. The approach recognizes a level of device understanding which is intermediate between a compiled level of typical Expert Systems, and a deep level at which large-scale device behavior is derived from known properties of device structure and component behavior. At this intermediate functional level, a device is modeled in three steps. First, a component decomposition of the device is defined. Second, the functionality of each device/subdevice is abstractly identified. Third, the state sequences which implement each function are specified. Given a functional representation and a set of initial conditions, the functional reasoner acts as a consequence finder. The output of the consequence finder can be utilized in diagnostic problem solving. The paper also discussed ways in which this functional approach may find application in the aerospace field.

Sticklen, Jon↗

The Ontology of Biological Attributes (OBA)—computational traits for the life sciences

Abstract Existing phenotype ontologies were originally developed to represent phenotypes that manifest as a character state in relation to a wild-type or other reference. However, these do not include the phenotypic trait or attribute categories required for the annotation of genome-wide association studies (GWAS), Quantitative Trait Loci (QTL) mappings or any population-focussed measurable trait data. The integration of trait and biological attribute information with an ever increasing body of chemical, environmental and biological data greatly facilitates computational analyses and it is also highly relevant to biomedical and clinical applications. The Ontology of Biological Attributes (OBA) is a formalised, species-independent collection of interoperable phenotypic trait categories that is intended to fulfil a data integration role. OBA is a standardised representational framework for observable attributes that are characteristics of biological entities, organisms, or parts of organisms. OBA has a modular design which provides several benefits for users and data integrators, including an automated and meaningful classification of trait terms computed on the basis of logical inferences drawn from domain-specific ontologies for cells, anatomical and other relevant entities. The logical axioms in OBA also provide a previously missing bridge that can computationally link Mendelian phenotypes with GWAS and quantitative traits. The term components in OBA provide semantic links and enable knowledge and data integration across specialised research community boundaries, thereby breaking silos.

59 BASIC BIOLOGICAL SCIENCES↗

Development of a Knowledgebase (MetRxn) of Metabolites, Reactions and Atom Mappings to Accelerate Discovery and Redesign

With advances in DNA sequencing and genome annotation techniques, the breadth of metabolic knowledge across all kingdoms of life is increasing. The construction of genome-scale models (GSMs) facilitates this distillation of knowledge by systematically accounting for reaction stoichiometry and directionality, gene to protein to reaction relationships, reaction localization among cellular organelles, metabolite transport costs and routes, transcriptional regulation, and biomass composition. Genome-scale reconstructions available now span across all kingdoms of life, from microbes to whole-plant models, and have become indispensable for driving informed metabolic designs and interventions. A key barrier to the pace of this development is our inability to utilize metabolite/reaction information from databases such as BRENDA [1], KEGG [2], MetaCyc [3], etc. due to incompatibilities of representation, duplications, and errors. Duplicate entries constitute a major impediment, where the same metabolite is found with multiple names across databases and models, which significantly slows downs the collating of information from multiple data sources. This can also lead to serious modeling errors such as charge/mass imbalances [4,5] which can thwart model predictive abilities such as identifying synthetic lethal gene pairs and quantifying metabolic flows. Hence, we created the MetRxn database [6] that takes the next step in integrating data from multiple sources and formats to automatically create a standardized knowledgebase. We subsequently deployed this resource to bring about new paradigms in genome-scale metabolic model reconstruction, metabolic flux elucidation through MFA, modeling of microbial communities, and pathway prospecting. This research has enabled the PI’s group to continue building upon research milestones and reach new ones (see list of MetRxn-related publications below).

59 BASIC BIOLOGICAL SCIENCES↗

Vibration-Based Sensor Design: A Grey-Box Approach

Knowledge of the internal structure of an object or device under investigation proceeds from the basic idea of constructing its dynamic behavioral relations governed by a set of differential/algebraic equations that characterize its response. These equations can be partial differential equations leading to finite element or finite difference relations requiring a complex numerical solution on a super computer or ordinary differential equations requiring sophisticated numerical integration techniques to obtain the desired solution. Discrete dynamic systems evolving from digitized data acquisition are typically captured by sampled-data (continuous-to-discrete) representations characterized by a set of difference equations specifying the underlying system dynamics. In any case, with a mathematical description in hand, Grey-Box modeling techniques have evolved, concerned with the estimation of model parameters embedded in a prescribed set of equations (the system) governing its behavior, while capturing the underlying physical phenomenology of the problem at hand.

97 MATHEMATICS AND COMPUTING↗

Genomes to ecosystem function: Targeting critical knowledge gaps in methanogenesis and translation to updated global biogeochemical models

Natural freshwater temperate wetland systems currently represent the largest natural source of atmospheric methane, but are relatively understudied using systems biology tools (e.g. meta-omics) compared to other high producing methane systems (e.g. peat, tropical, or reconstructed wetlands). Using field investigations at the NOAA operated sentinel site on Lake Erie, methane producing activities and responses to geochemical conditions will be determined along seasonal and spatial gradients (Objective 1). Here, a combination of high-throughput activity and gas measurements, combined with high-resolution systems biology and analytical methods, will provide in depth knowledge of the microbiological, chemical, and physical constraints on methane production in wetlands. Using laboratory microcosms, the formation of anoxic microsites and their capacity to facilitate methane production in wetland soils will be simulated (Objective 2). This objective will validate the findings from the field investigations, offering a more controlled environment for teasing out the role of different yet interrelated variables. Lastly, these field and laboratory data will be used for multi-scale, process-level evaluation of an ecosystem biogeochemical model that accommodates these newly identified processes and parameterizes representation of these processes along relevant environmental gradients (Objective 3).This research will identify multiple interacting geochemical, ecological, and metabolic constraints that are poorly understood, oversimplified, or missing in global biogeochemical methane models. This proposal targets the role of oxygen limitation on methane processes in soil domains, to improve reactive transport models of microbial carbon cycling across terrestrial-aquatic soils and generate data on nutrient cycling activities in Great Lake wetlands. This information could provide new insights into the microbial controllers of Lake Erie eutrophication.

59 BASIC BIOLOGICAL SCIENCES↗

Sensor fusion IV: Control paradigms and data structures; Proceedings of the Meeting, Boston, MA, Nov. 12-15, 1991

Various papers on control paradigms and data structures in sensor fusion are presented. The general topics addressed include: decision models and computational methods, sensor modeling and data representation, active sensing strategies, geometric planning and visualization, task-driven sensing, motion analysis, models motivated biology and psychology, decentralized detection and distributed decision, data fusion architectures, robust estimation of shapes and features, application and implementation. Some of the individual subjects considered are: the Firefly experiment on neural networks for distributed sensor data fusion, manifold traversing as a model for learning control of autonomous robots, choice of coordinate systems for multiple sensor fusion, continuous motion using task-directed stereo vision, interactive and cooperative sensing and control for advanced teleoperation, knowledge-based imaging for terrain analysis, physical and digital simulations for IVA robotics.

Schenker, Paul S.↗

VisIRR: A Visual Analytics System for Information Retrieval and Recommendation for Large-Scale Document Data

In this paper, we present an interactive visual information retrieval and recommendation system, called VisIRR, for large-scale document discovery. VisIRR effectively combines the paradigms of (1) a passive pull through query processes for retrieval and (2) an active push that recommends items of potential interest to users based on their preferences. Equipped with an efficient dynamic query interface against a large-scale corpus, VisIRR organizes the retrieved documents into high-level topics and visualizes them in a 2D space, representing the relationships among the topics along with their keyword summary. In addition, based on interactive personalized preference feedback with regard to documents, VisIRR provides document recommendations from the entire corpus, which are beyond the retrieved sets. Such recommended documents are visualized in the same space as the retrieved documents, so that users can seamlessly analyze both existing and newly recommended ones. This article presents novel computational methods, which make these integrated representations and fast interactions possible for a large-scale document corpus. We illustrate how the system works by providing detailed usage scenarios. Finally, we present preliminary user study results for evaluating the effectiveness of the system.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations

In this paper, we propose a visual analytics workflow to help data scientists explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages “instance-level explanations”, measures of local feature relevance that explain single instances and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct or incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The work is validated through a long-term collaboration with a group of healthcare professionals who used our method to make sense of machine learning models they developed. The case studies from this collaboration demonstrate that the proposed method helps experts derive useful knowledge about the model and the phenomena it describes and also generates useful hypotheses on how a model can be improved.

Krause, Josua↗