Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “DATA NETWORKS”

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 1,027 records · Page 57

Improving Quality of Observational Streaming Medical Data by Using Long Short-Term Memory Networks (LSTMs)

We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.

Bowie, Michael B.↗

Detailed Statistical Models of Host-Based Data for Detection of Malicious Activity

The cybersecurity research community has focused primarily on the analysis and automation of intrusion detection systems by examining network traffic behaviors. Expanding on this expertise, advanced cyber defense analysis is turning to host-based data to use in research and development to produce the next generation network defense tools. The ability to perform deep packet inspection of network traffic is increasingly harder with most boundary network traffic moving to HTTPS. Additionally, network data alone does not provide a full picture of end-to-end activity. These are some of the reasons that necessitate looking at other data sources such as host data. We outline our investigation into the processing, formatting, and storing of the data along with the preliminary results from our exploratory data analysis. In writing this report, it is our goal to aid in guiding future research by providing foundational understanding for an area of cybersecurity that is rich with a variety of complex, categorical, and sparse data, with a strong human influence component. Including suggestions for guiding potential directions for future research.

97 MATHEMATICS AND COMPUTING↗

Non-unimodal and non-concave relationships in the network Macroscopic Fundamental Diagram caused by hierarchical streets

Unimodal, concave relationships between average network productivity and accumulation or density aggregated across spatially compact regions of urban networks—so called network Macroscopic Fundamental Diagrams (MFDs)—have recently been shown to exist on homogeneous street networks. When present, MFD relationships facilitate the modeling of traffic congestion at a regional level and have led to the development of various regional traffic control strategies. However, real street networks are not homogeneous—they generally have a hierarchical structure where some streets (e.g., arterials) promote higher mobility than others (e.g., local roads). Here, this paper examines how the presence of hierarchical roadway structures may potentially cause non-unimodal patterns in a network's MFD. These are observed using three types of tools: analytical models of simple network structures, simulations of various idealized roadway networks, and empirical data. The impacts of street hierarchy depend on how vehicles use different roadway types to move within the network; i.e., their routing strategy. The findings suggest that the presence of roadway hierarchies may lead to MFDs that have non-unimodal or non-concave patterns on the free-flow branch when vehicles route themselves according to user equilibrium principles, which is closest to what would be observed in realistic situations. Such patterns are contrary to what is traditionally assumed in most MFD-based modeling frameworks. However, the unimodal and concave MFD should be expected under system optimal routing conditions that maximize network productivity for a given traffic state.

42 ENGINEERING↗

Spatially explicit network analysis reveals multi‐species annual cycle movement patterns of sea ducks

Abstract Conservation of long‐distance migratory species poses unique challenges. Migratory connectivity, that is, the extent to which groupings of individuals at breeding sites are maintained in wintering areas, is frequently used to evaluate population structure and assess use of key habitat areas. However, for species with complex or variable annual cycle movements, this traditional bimodal framework of migratory connectivity may be overly simplistic. Like many other waterfowl, sea ducks often travel to specific pre‐ and post‐breeding sites outside their nesting and wintering areas to prepare for migration by feeding extensively and, in some cases, molting their flight feathers. These additional migrations may play a key role in population structure, but are not included in traditional models of migratory connectivity. Network analysis, which applies graph theory to assess linkages between discrete locations or entities, offers a powerful tool for quantitatively assessing the contributions of different sites used throughout the annual cycle to complex spatial networks. We collected satellite telemetry data on annual cycle movements of 672 individual sea ducks of five species from throughout eastern North America and the Great Lakes. From these data, we constructed a multi‐species network model of migratory patterns and site use over the course of breeding, molting, wintering, and migratory staging. Our results highlight inter‐ and intra‐specific differences in the patterns and complexity of annual cycle movement patterns, including the central importance of staging and molting sites in James Bay, the St. Lawrence River, and southern New England to multi‐species annual cycle habitat linkages, and highlight the value of Long‐tailed Ducks ( Calengula haemalis ) as an umbrella species to represent the movement patterns of multiple sea duck species. We also discuss potential applications of network migration models to conservation prioritization, identification of population units, and integrating different data streams.

54 ENVIRONMENTAL SCIENCES↗

Comparative Performance Evaluation of High-performance Data Transfer Tools

Data transfer in wide-area networks has been long studied in different contexts, from data sharing among data centers to online access to scientific data. Many software tools and platforms have been developed to facilitate easy, reliable, fast, and secure data transfer over wide area networks, such as GridFTP, FDT, bbcp, mdtmFTP, and XDD. However, few studies have shown the full capabilities of existing data transfer tools from the perspective of whether such tools have fully adopted state-of-the-art techniques through meticulous comparative evaluations. In this paper, we evaluate the performance of the four highperformance data transfer tools (GridFTP, FDT, mdtmFTP, and XDD) in various environments. Our evaluation suggests that each tool has strengths and weaknesses. FDT and GridFTP perform consistently in diverse environments. XDD and mdtmFTP show improved performance in limited environments and datasets during our evaluation. Unlike other studies on data transfer tools, we also evaluate the predictability of the tools' performance, an important factor for scheduling different stages of science workflows. Performance predictability also helps in (auto)tuning the configurable parameters of the data transfer tool. We apply statistical learning techniques such as linear/polynomial regression, and k-nearest neighbors (kNN), to assess the performance predictability of each tool using its control parameters. Our results show that we can achieve good prediction performance for GridFTP and mdtmFTP using linear regression and kNN, respectively.

Nadig, Deepak↗

G-NetMon: A GPU-accelerated Network Performance Monitoring System for Large Scale Scientific Collaborations

At Fermilab, we have prototyped a GPU-accelerated network performance monitoring system, called G-NetMon, to support large-scale scientific collaborations. Our system exploits the data parallelism that exists within network flow data to provide fast analysis of bulk data movement between Fermilab and collaboration sites. Experiments demonstrate that our G-NetMon can rapidly detect sub-optimal bulk data movements.

99 GENERAL AND MISCELLANEOUS↗

Robustness of the Ensemble Score Filter to the Type of Assimilated Observation Networks

Recent advances in data assimilation (DA) have focused on developing more flexible approaches that can better accommodate nonlinearities in models and observations. However, it remains unclear how the performance of these advanced methods depends on the observation network characteristics. In this study, we present initial experiments with the surface quasi‐geostrophic model, in which we compare a recently developed ensemble filter using score‐based diffusion models with the standard Local Ensemble Transform Kalman Filter (LETKF). Our results show that the analysis solutions respond differently to the number, spatial distribution, and nonlinear fraction of assimilated observations. We also find notable changes in the multiscale characteristics of the analysis errors. Given that standard DA techniques will eventually be replaced by more advanced methods, we hope this study sets the ground for future efforts to reassess the value of Earth observing systems in the context of newly emerging algorithms.

97 MATHEMATICS AND COMPUTING↗

Research Activities at Fermilab for Big Data Movement

Adaptation of 100GE Networking Infrastructure is the next step towards management of Big Data. Being the US Tier-1 Center for the Large Hadron Collider's (LHC) Compact Muon Solenoid (CMS) experiment and the central data center for several other large-scale research collaborations, Fermilab has to constantly deal with the scaling and wide-area distribution challenges of the big data. In this paper, we will describe some of the challenges involved in the movement of big data over 100GE infrastructure and the research activities at Fermilab to address these challenges.

Mhashilkar, Parag↗

The SONATA data format for efficient description of large-scale network models

Increasing availability of comprehensive experimental datasets and of high-performance computing resources are driving rapid growth in scale, complexity, and biological realism of computational models in neuroscience. To support construction and simulation, as well as sharing of such large-scale models, a broadly applicable, flexible, and high-performance data format is necessary. To address this need, we have developed the Scalable Open Network Architecture TemplAte (SONATA) data format. It is designed for memory and computational efficiency and works across multiple platforms. The format represents neuronal circuits and simulation inputs and outputs via standardized files and provides much flexibility for adding new conventions or extensions. SONATA is used in multiple modeling and visualization tools, and we also provide reference Application Programming Interfaces and model examples to catalyze further adoption. SONATA format is free and open for the community to use and build upon with the goal of enabling efficient model building, sharing, and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗

Deep neural network uncertainty quantification for LArTPC reconstruction

We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural networks with reliable estimates of prediction uncertainty and robust performance against overconfidence and out-of-distribution (OOD) samples are critical for their full deployment in analyzing experimental data. While numerous UQ methods have been tested on simple datasets, performance evaluations for more complex tasks and datasets are scarce. Here we assess the application of selected deep learning UQ methods on the task of particle classification using the PiLArNet monte carlo 3D LArTPC point cloud dataset. We observe that UQ methods not only allow for better rejection of prediction mistakes and OOD detection, but also generally achieve higher overall accuracy across different task settings. We assess the precision of uncertainty quantification using different evaluation metrics, such as distributional separation of prediction entropy across correctly and incorrectly identified samples, receiver operating characteristic curves (ROCs), and expected calibration error from observed empirical accuracy. We conclude that ensembling methods can obtain well calibrated classification probabilities and generally perform better than other existing methods in deep learning UQ literature.

47 OTHER INSTRUMENTATION↗

Early detection and evaluation of waste through sensorized containers for a collection monitoring application

The present study describes a novel application for use in the monitoring of municipal solid waste, based on distributed sensor technology and geographical information systems. Original field testing and evaluation of the application were carried out in Pudong, Shanghai (PR China). The local waste management system in Pudong features particular requirements related to the rapidly increasing rate of waste production. In view of the fact that collected waste is currently deployed to landfills or to incineration plants within the context investigated, the key aspects to be taken into account in waste collection procedures include monitoring of the overall amount of waste produced, quantitative measurement of the waste present at each collection point and identification of classes of material present in the collected waste. The case study described herein focuses particularly on the above mentioned aspects, proposing the implementation of a network of sensorized waste containers linked to a data management system. Containers used were equipped with a set of sensors mounted onto standard waste bins. The design, implementation and validation procedures applied are subsequently described. The main aim to be achieved by data collection and evaluation was to provide for feasibility analysis of the final device. Data pertaining to the content of waste containers, sampled and processed by means of devices validated on two purpose-designed prototypes, were therefore uploaded to a central monitoring server using GPRS connection. The data monitoring and management modules are integrated into an existing application used by local municipal authorities. A field test campaign was performed in the Pudong area. The system was evaluated in terms of real data flow from the network nodes (containers) as well as in terms of optimization functions, such as collection vehicle routing and scheduling. The most important outcomes obtained were related to calculations of waste weight and volume. The latter data were subsequently used as parameters for the routing optimization of collection trucks and material density evaluation.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

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 progressive deep transfer learning approach to cycle-skipping mitigation in FWI, In SEG Technical Program Expanded Abstracts 2019, pp. 2348-2352. Society of Exploration Geophysicists, 2019.

To effectively mitigate the cycle-skipping phenomenon in full waveform inversion (FWI), we developed an inception-based deep learning neural network to reconstruct the absent low frequency data by exploiting the subsurface low wavenumber information buried in the acquired high frequency data. Two unique features of our deep learning network for the low frequency data reconstruction are 1) Dual Data Feed; 2) Progressive Transfer Learning. With the Dual Data Feed feature, not only the high frequency data, but also the corresponding Beat Tone data are fed into the neural network, significantly reducing the network complexity and the network training cost. The Progressive Transfer Learning technique enables us to initiate the deep learning network with only one training dataset. Unlike other deep learning approaches in this category, our training dataset is not fixed. Instead, the training dataset and the network accuracy are progressively enhanced in an iterative manner within the Progressive Transfer Learning workflow. The numerical experiments validated that the low frequency data reconstructed by this progressive transfer learning network are sufficiently accurate for a successful FWI inversion without suffering from the cycle-skipping without any priori geological information.

58 GEOSCIENCES↗

Data efficiency and extrapolation trends in neural network interatomic potentials

Abstract Recently, key architectural advances have been proposed for neural network interatomic potentials (NNIPs), such as incorporating message-passing networks, equivariance, or many-body expansion terms. Although modern NNIP models exhibit small differences in test accuracy, this metric is still considered the main target when developing new NNIP architectures. In this work, we show how architectural and optimization choices influence the generalization of NNIPs, revealing trends in molecular dynamics (MD) stability, data efficiency, and loss landscapes. Using the 3BPA dataset, we uncover trends in NNIP errors and robustness to noise, showing these metrics are insufficient to predict MD stability in the high-accuracy regime. With a large-scale study on NequIP, MACE, and their optimizers, we show that our metric of loss entropy predicts out-of-distribution error and data efficiency despite being computed only on the training set. This work provides a deep learning justification for probing extrapolation and can inform the development of next-generation NNIPs.

36 MATERIALS SCIENCE↗

SAM-ML: Integrating data-driven closure with nuclear system code SAM for improved modeling capability

Advanced reactors often involve complicated thermal-fluid (T-F) phenomena. Modeling such phenomena with the traditional one-dimensional (1-D) system code is a challenging task. The System Analysis Module (SAM), a modern nuclear system code, has developed a coarse mesh multi-dimensional (multi-D) flow model to capture the spatial effect of T-F phenomena in advanced reactors. As a coarse mesh solver, constitutive relations are required for SAM's multi-D model for unresolved fine-scale physics, such as turbulence. Here this work presents a novel approach that integrates neural networks as data-driven closure for SAM's multi-D flow model. The data-driven closure is trained with fine-resolution data to ensure its accuracy while maintaining a coarse mesh setup to ensure its efficiency and consistency with SAM. We demonstrate the applicability of this SAM-ML capability in an open volume thermal stratification problem, where a neural network model serves as the eddy viscosity closure. A customized interface between the neural network and SAM is developed to ensure flexible and efficient data exchange. The SAM-ML results demonstrate superior performance compared to SAM's built-in zero-equation eddy viscosity closure. The case study shows that although the generalization capability of the data-driven closure still needs to be improved for different transient case or different geometric setup, SAM -ML demonstrates good potential for challenging simulation problems with improved accuracy and computational efficiency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Analyzing Data Movements and Identifying Techniques for Next-generation High-bandwidth Networks

High-bandwidth networks are poised to provide new opportunities in tackling large data challenges in today's scientific applications. However, increasing the bandwidth is not sufficient by itself; we need careful evaluation of future high-bandwidth networks from the applications’ perspective. We have investigated data transfer requirements of climate applications as a typical scientific example and evaluated how the scientific community can benefit from next generation high-bandwidth networks. We have experimented with current state-of-the-art data movement tools, and realized that there is no single solution for presetting transfer parameters for optimal use of the available bandwidth. Thus, we developed an adaptive transfer methodology for tuning and optimization in wide-area data transfers. This worked well with large files. However, typical scientific datasets may include many small files. Current filecentric data transfer protocols do not perform well with managing the transfer of small files, even when using parallel streams or concurrent transfers over high bandwidth networks. In order to overcome this problem, we develop a new block-based data movement method (in contrast to the current file-based methods) to improve data movement performance and efficiency in moving large scientific datasets that contain many small files. We implemented the new block-based data movement tool, which takes the approach of aggregating files into blocks and providing dynamic data channel management. In our work, we also realized that one of the major obstacles in use of high-bandwidth networks is the limitation in host system resources. 100Gbps is beyond the capacity of today’s commodity machine, since we need substantial amount of processing power and involvement of multiple cores to fill a 40Gbps or 100Gbps network. As a result, host system performance plays an important role in the use of highbandwidth networks. We have conducted a large number of experiments with our new block-based method and with current available file-based data movement tools. In this white paper, we describe future research problems and challenges for efficient use of next-generation science networks, based on the lessons learnt and the experiences gained with 100Gbps network applications.

100Gbps network applications↗