Search NASA⌕ Search

SEARCH · Search NASA

Results for “Complex Network Data”

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 235 records · Page 13

Coincident learning for beam-based rf station fault identification using phase information at the SLAC linac coherent light source

Anomalies in radio-frequency (rf) stations can result in unplanned downtime and performance degradation in linear accelerators such as SLAC’s Linac Coherent Light Source (LCLS). Detecting these anomalies is challenging due to the complexity of accelerator systems, high data volume, and scarcity of labeled fault data. Prior work identified faults using beam-based detection, combining rf amplitude and beam position monitor data. Due to the simplicity of the rf amplitude data, classical methods are sufficient to identify faults, but the recall is constrained by the low-frequency and asynchronous characteristics of the data. In this work, we leverage high-frequency, time-synchronous rf phase data to enhance anomaly detection in the LCLS accelerator. Due to the complexity of phase data, classical methods fail, and we instead train deep neural networks within the Coincident Anomaly Detection (CoAD) framework. We find that applying CoAD to phase data detects nearly 3 times as many anomalies as when applied to amplitude data, while achieving broader coverage across rf stations. Furthermore, the rich structure of phase data enables us to cluster anomalies into distinct physical categories. Through the integration of auxiliary system status bits, we link clusters to specific fault signatures, providing additional granularity for uncovering the root cause of faults. We also investigate interpretability via Shapley values, confirming that the learned models focus on the most informative regions of the data and providing insight for cases where the model makes mistakes. This work demonstrates that phase-based anomaly detection for rf stations improves both diagnostic coverage and root cause analysis in accelerator systems and that deep neural networks are essential for effective analysis.

Accelerator Physics (physics.acc-ph)↗

Modeling and Simulation of High Dimensional Stochastic Multiscale PDE Systems at the Exascale

The thrust of the proposal was to exploit modern data-mining tools in a way that will create a systematic, computer-assisted approach to the representation of random media -- and also to the representation of the solutions of an array of important physicochemical processes that take place in/on such media. A parsimonious representation/parametrization of the random media links directly (via uncertainty quantification tools) to good sampling of the distribution of random media realizations. It also links directly to modern multiscale computational algorithms (like the equation-free approach that has been developed in our group) and plays a crucial role in accelerating the scientific computation of solutions of nonlinear PDE models (deterministic or stochastic) in such media – both solutions in particular realizations of the random media, and estimation of the statistics of the solutions over multiple realizations (e.g. expectations).

97 MATHEMATICS AND COMPUTING↗

Time and frequency for digital telecommunications

Time and frequency (T and F) are fundamental and pervasive parameters of telecommunication technology. Advancing development of digital communications using data modulation rates above 2400 baud and time-division multiplex in complex network configurations is now requiring more accurate and precise T and F reference information for efficient operation of telecommunication systems. A schematic diagram of a general communication system is shown. This diagram is very general and can depict any type of communication. The information source selects a specific message which is encoded and sent through a communication channel. Enroute, the signal is subjected to perturbations from environmental noise. The received signal is then decoded and delivered to its destination. Through the process, the message may undergo many spurious changes, resulting in a loss of information content in the delivered message as compared to the original selected message. In digital telecommunication systems, loss of information content of the signals can be attributed to noise, distortion of waveshape, and loss of synchronization.

Folts, H. C.↗

Absolute positioning using DORIS tracking of the SPOT-2 satellite

The ability of the French DORIS system operating on the SPOT-2 satellite to provide absolute site positioning at the 20-30-centimeter level using 80 d of data is demonstrated. The accuracy of the vertical component is comparable to that of the horizontal components, indicating that residual troposphere error is not a limiting factor. The translation parameters indicate that the DORIS network realizes a geocentric frame to about 50 nm in each component. The considerable amount of data provided by the nearly global, all-weather DORIS network allowed this complex parameterization required to reduce the unmodeled forces acting on the low-earth satellite. Site velocities with accuracies better than 10 mm/yr should certainly be possible using the multiyear span of the SPOT series and Topex/Poseidon missions.

Watkins, M. M.↗

Enhancing Neural Network Decision-Making with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. This explainability encourages people to be more inclined to justifiably trust machine decision-making.

Loc Tran↗

Enhancing Neural Network Explainability with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. Explainability inspires trust in autonomous systems that use deep learning, which is necessary for safety critical systems.

Loc Tran↗

Quantitative Assessment of Detection Frequency for the INL Ambient Air Monitoring Network

A quantitative assessment of the Idaho National Laboratory (INL) air monitoring network was performed using frequency of detection as the performance metric. The INL air monitoring network consists of 37 low-volume air samplers in 31 different locations. Twenty of the samplers are located on INL (onsite) and 17 are located off INL (offsite). Detection frequencies were calculated using both BEA and ESER laboratory minimum detectable activity (MDA) levels. The CALPUFF Lagrangian puff dispersion model, coupled with 1 year of meteorological data, was used to calculate time-integrated concentrations at sampler locations for a 1-hour release of unit activity (1 Ci) for every hour of the year. The unit-activity time-integrated concentration (TICu) values were calculated at all samplers for releases from eight INL facilities. The TICu values were then scaled and integrated for a given release quantity and release duration. All facilities modeled a ground-level release emanating either from the center of the facility or at a point where significant emissions are possible. In addition to ground-level releases, three existing stacks at the Advanced Test Reactor Complex, Idaho Nuclear Technology and Engineering Center, and Material and Fuels Complex were also modeled. Meteorological data from the 35 stations comprising the INL Mesonet network, data from the Idaho Falls Regional airport, upper air data from the Boise airport, and three-dimensional gridded data from the weather research forecasting model were used for modeling. Three representative radionuclides identified as key radionuclides in INL’s annual National Emission Standards for Hazardous Air Pollutants evaluations were considered for the frequency of detection analysis: Cs-137 (beta-gamma emitter), Pu-239 (alpha emitter), and Sr-90 (beta emitter). Source-specific release quantities were calculated for each radionuclide, such that the maximum inhalation dose at any publicly accessible sampler or the National Emission Standards for Hazardous Air Pollutants maximum exposed individual location (i.e., Frenchman’s Cabin) was no more than 0.1 mrem yr–1 (i.e., 1% of the 10 mrem yr–1 standard). Detection frequencies were calculated separately for the onsite and offsite monitoring network. As expected, detection frequencies were generally less for the offsite sampling network compared to the onsite network. Overall, the monitoring network is very effective at detecting the potential releases of Cs-137 or Sr-90 from all sources/facilities using either the ESER or BEA MDAs. The network was less effective at detecting releases of Pu-239. Maximum detection frequencies for Pu-239 using ESER MDAs ranged from 27.4 to 100% for onsite samplers and 3 to 80% for offsite samplers. Using BEA MDAs, the maximum detection frequencies for Pu-239 ranged from 2.1 to 100% for onsite samplers and 0 to 5.9% for offsite samplers. The only release that was not detected by any of the samplers under any conditions was a release of Pu-239 from the Idaho Nuclear Technology and Engineering Center main stack (CPP-708). The methodology described in this report could be used to improve sampler placement and detection frequency, provided clear performance objectives are defined.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

A graph signal processing‐based multiple model Kalman filter ( GSP‐MMKF ) tool for predictive analytics: An air separation unit process application

Abstract The industrial Air Separations Unit (ASU) is a complicated and tightly operated process. The use of dynamic process analytics is also a key element of safe and economic operation of these processes, with increasing focus on predictive analytics to take preemptive actions. With the availability of real‐time data from hundreds of sensors, the data analysis process should also consider the topology of the data, as seen in sensor networks. In this paper, a novel tool is presented that considers the complex connectivity patterns in the sensor network and uses local adaptive disturbance estimations to predict global network‐scale trends. The paper introduces the emerging field of Graph Signal Processing (GSP) and presents a rigorous derivation of the tool starting from the extraction of the sensor‐network (in a graph theoretical sense) from the data. This network, which is in the form of a matrix, is then used to derive a Kalman‐filter type of state‐space model driven by input disturbances. Multiple disturbance models (e.g., step, ramp, periodic) are included to allow the model to have different kinds of disturbance propagation. Each graph node (representing the sensors used) dynamically adapts to the most recent detected disturbance individually. These estimated disturbances are propagated to the global network using the graph. Modifications to ensure stability are also discussed. The fidelity of the tool is tested on certain downtime events and the paper concludes by discussing the advantages of the method and planned future improvements.

Ghosh, Sambit↗

High-Reliability Systems and the Control of National Security Data and Information

High-reliability systems are characterized by catastrophic implications in the event of failure. These implications can include substantive damage to the environment, social order, and loss of life. Examples of high-reliability systems include nuclear submarines, nuclear reactors, the electric grid, and nuclear weapons. Due to the catastrophic implications of failure, there are heightened awareness and control mechanisms surrounding related data and information. However, defining the difference between data and information is often ambiguous across scholarly disciplines and in United States policy and legislation. For high-reliability systems, the implications of ambiguity between data and information may affect the security of United States interests and even cost lives. For security, data are raw facts or figures without context, while information is the compilation or articulation of data that forms context. Security depends on clarity in the differences between data and information and how to control them. Control is necessary to ensure that data and information are not unintentionally released to foreign governments, the public, or those without need-to-know. A primary concern in the practice of security is the control of data to avoid the unintended conversion to information. Intra-institutionally, this control is highly complex given the amalgam of legacy data systems and the numerous and constantly evolving nature of modern data systems that were not necessarily designed to be integrated. The complexity of this concern is augmented when institutions are part of inter-institutional collaborations or networks of public-private partnerships that share data and information. Additionally, institutions that share data as a function of policy and legislative action—particularly formally integrated data and information system infrastructures—may be at higher security risk. This paper will present an intra-institutional paradigm that utilizes and integrates concepts from numerous disciplines to frame a critical and underspecified practical issue in security—controlling for the unintended conversion of data to information.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification

Modeling strong gravitational lenses is computationally expensive for the complex data from modern and next-generation cosmic surveys. Deep learning has emerged as a promising approach for finding lenses and predicting lensing parameters, such as the Einstein radius. Mean-variance Estimators (MVEs) are a common approach for obtaining aleatoric (data) uncertainties from a neural network prediction. However, neural networks have not been demonstrated to perform well on out-of-domain target data successfully - e.g., when trained on simulated data and applied to real, observational data. In this work, we perform the first study of the efficacy of MVEs in combination with unsupervised domain adaptation (UDA) on strong lensing data. The source domain data is noiseless, and the target domain data has noise mimicking modern cosmology surveys. We find that adding UDA to MVE increases the accuracy on the target data by a factor of about two over an MVE model without UDA. Including UDA also permits much more well-calibrated aleatoric uncertainty predictions. Advancements in this approach may enable future applications of MVE models to real observational data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Inferring Correlation Networks from Genomic Survey Data

High-throughput sequencing based techniques, such as 16S rRNA gene profiling, have the potential to elucidate the complex inner workings of natural microbial communities - be they from the world's oceans or the human gut. A key step in exploring such data is the identification of dependencies between members of these communities, which is commonly achieved by correlation analysis. However, it has been known since the days of Karl Pearson that the analysis of the type of data generated by such techniques (referred to as compositional data) can produce unreliable results since the observed data take the form of relative fractions of genes or species, rather than their absolute abundances. Using simulated and real data from the Human Microbiome Project, we show that such compositional effects can be widespread and severe: in some real data sets many of the correlations among taxa can be artifactual, and true correlations may even appear with opposite sign. Additionally, we show that community diversity is the key factor that modulates the acuteness of such compositional effects, and develop a new approach, called SparCC (available at https://bitbucket.org/yonatanf/sparcc), which is capable of estimating correlation values from compositional data. To illustrate a potential application of SparCC, we infer a rich ecological network connecting hundreds of interacting species across 18 sites on the human body. Using the SparCC network as a reference, we estimated that the standard approach yields 3 spurious species-species interactions for each true interaction and misses 60% of the true interactions in the human microbiome data, and, as predicted, most of the erroneous links are found in the samples with the lowest diversity.

59 BASIC BIOLOGICAL SCIENCES↗

The Niwot Ridge Subalpine Forest US-NR1 AmeriFlux site – Part 1: Data acquisition and site record-keeping

Abstract. The Niwot Ridge Subalpine Forest AmeriFlux site (US-NR1) has been measuring eddy-covariance ecosystem fluxes of carbon dioxide, heat, and water vapor since 1 November 1998. Throughout this 17-year period there have been changes to the instrumentation and improvements to the data acquisition system. Here, in Part 1 of this three-part series of papers, we describe the hardware and software used for data-collection and metadata documentation. We made changes to the data acquisition system that aimed to reduce the system complexity, increase redundancy, and be as independent as possible from any network outages. Changes to facilitate these improvements were (1) switching to a PC/104-based computer running the National Center for Atmospheric Research (NCAR) In-Situ Data Acquisition Software (NIDAS) that saves the high-frequency data locally and over the network, and (2) time-tagging individual 10 Hz serial data samples using network time protocol (NTP) coupled to a GPS-based clock, providing a network-independent, accurate time base. Since making these improvements almost 2 years ago, the successful capture of high-rate data has been better than 99.98 %. We also provide philosophical concepts that shaped our design of the data system and are applicable to many different types of environmental data collection.

54 ENVIRONMENTAL SCIENCES↗

Adiabatic Quantum Computation Applied to Deep Learning Networks

Training deep learning networks is a difficult task due to computational complexity, and this is traditionally handled by simplifying network topology to enable parallel computation on graphical processing units (GPUs). However, the emergence of quantum devices allows reconsideration of complex topologies. We illustrate a particular network topology that can be trained to classify MNIST data (an image dataset of handwritten digits) and neutrino detection data using a restricted form of adiabatic quantum computation known as quantum annealing performed by a D-Wave processor. We provide a brief description of the hardware and how it solves Ising models, how we translate our data into the corresponding Ising models, and how we use available expanded topology options to explore potential performance improvements. Although we focus on the application of quantum annealing in this article, the work discussed here is just one of three approaches we explored as part of a larger project that considers alternative means for training deep learning networks. The other approaches involve using a high performance computing (HPC) environment to automatically find network topologies with good performance and using neuromorphic computing to find a low-power solution for training deep learning networks. Our results show that our quantum approach can find good network parameters in a reasonable time despite increased network topology complexity; that HPC can find good parameters for traditional, simplified network topologies; and that neuromorphic computers can use low power memristive hardware to represent complex topologies and parameters derived from other architecture choices.

97 MATHEMATICS AND COMPUTING↗

New trends in photonic switching and optical networking architectures for data centers and computing systems [Invited]

The rapid increases in data traffic coupled with user preferences are driving the data center and computing system service providers to offer energy-efficient, intelligent, flexible, cost-effective, high-capacity, and low-latency data services without added complexity to the users. Disaggregated heterogeneous reconfigurable computing systems realized by photonic switching and interconnects can enhance throughput and energy efficiency for artificial intelligence/machine learning (AI/ML) workloads, especially when aided by the AI/ML-enhanced control plane. Photonic switching and new optical networking architectures are expected to solve many of these challenging problems. This paper discusses new trends in photonic switching and optical network architectures for future data centers and computing systems summarized as follows: (1) flat reconfigurable disaggregated computing enabled by high-radix photonic switching and interconnects in data centers; (2) chiplet-based computing architectures empowered by embedded photonics toward heterogeneous reconfigurable computing; (3) nanosecond-scale photonic switching in data centers and computing systems; (4) AI/ML in self-driving, application-aware, and situation-aware data centers; (5) the emergence of flexible networking for cloud computing, edge computing, and split computing, as well as flexible networking for 5G/6G RF-optical networks; and (6) the deployment of embedded co-designed silicon photonics being considered for future data centers.

Yoo, S. J. Ben (ORCID:0000000274201871)↗

When less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates

Previous moderate- and high-temperature geothermal resource assessments of the western United States utilized data-driven methods and expert decisions to estimate resource favorability. Although expert decisions can add confidence to the modeling process by ensuring reasonable models are employed, expert decisions also introduce human and, thereby, model bias. This bias can present a source of error that reduces the predictive performance of the models and confidence in the resulting resource estimates. Our study aims to develop robust data-driven methods with the goals of reducing bias and improving predictive ability. We present and compare nine favorability maps for geothermal resources in the western United States using data from the U.S. Geological Survey's 2008 geothermal resource assessment. Two favorability maps are created using the expert decision-dependent methods from the 2008 assessment (i.e., weight-of-evidence and logistic regression). With the same data, we then create six different favorability maps using logistic regression (without underlying expert decisions), XGBoost, and support-vector machines paired with two training strategies. The training strategies are customized to address the inherent challenges of applying machine learning to the geothermal training data, which have no negative examples and severe class imbalance. We also create another favorability map using an artificial neural network. We demonstrate that modern machine learning approaches can improve upon systems built with expert decisions. We also find that XGBoost, a non-linear algorithm, produces greater agreement with the 2008 results than linear logistic regression without expert decisions, because the expert decisions in the 2008 assessment rendered the otherwise linear approaches non-linear despite the fact that the 2008 assessment used only linear methods. The F1 scores for all approaches appear low (F1 score < 0.10), do not improve with increasing model complexity, and, therefore, indicate the fundamental limitations of the input features (i.e., training data). Until improved feature data are incorporated into the assessment process, simple non-linear algorithms (e.g., XGBoost) perform equally well or better than more complex methods (e.g., artificial neural networks) and remain easier to interpret.

15 GEOTHERMAL ENERGY↗

Topological structure of complex predictions

Abstract Current complex prediction models are the result of fitting deep neural networks, graph convolutional networks or transducers to a set of training data. A key challenge with these models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into a simplified topological view of the prediction landscape. The result is a map of the predictions that enables inspection of the model results with more specificity than dimensionality-reduction methods such as tSNE and UMAP. The methods scale up to large datasets across different domains. We present a case study of a transformer-based model previously designed to predict expression levels of a piece of DNA in thousands of genomic tracks. When the model is used to study mutations in the BRCA1 gene, our topological analysis shows that it is sensitive to the location of a mutation and the exon structure of BRCA1 in ways that cannot be found with tools based on dimensionality reduction. Moreover, the topological framework offers multiple ways to inspect results, including an error estimate that is more accurate than model uncertainty. Further studies show how these ideas produce useful results in graph-based learning and image classification.

Computer Science↗

State-based network similarity visualization

We introduce an approach for the interactive visual analysis of weighted, dynamic networks. These networks arise in areas such as computational neuroscience, sociology, and biology. Network analysis remains challenging due to complex time-varying network behavior. For example, edges disappear/reappear, communities grow/vanish, or overall network topology changes. Our technique, TimeSum, detects the important topological changes in graph data to abstract the dynamic network and visualize one summary representation for each temporal phase, a state. We define a network state as a graph with similar topology over a specific time interval. To enable a holistic comparison of networks, we use a difference network to depict edge and community changes. Here, we present case studies to demonstrate that our methods are effective and useful for extracting and exploring complex dynamic behavior of networks.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗