Search NASA⌕ Search

SEARCH · Search NASA

Results for “detection network”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS1998

Observations of Total Lightning Associated with Severe Convection During the Wet Season in Central Florida

This paper will discuss findings of a collaborative lightning research project between National Aeronautics and Space Administration, the Massachusetts Institute of Technology and the National Weather Service office In Melbourne Florida. In August 1996, NWS/MLB received a workstation which incorporates data from the KMLB WSR-88D, Cloud to Ground (CG) stroke data from the National Lightning Detection Network (NLDN), and 3D volumetric lightning data collected from the Kennedy Space Centers' Lightning Detection And Ranging (LDAR) lightning system. The two primary objectives of this lightning workstation, called Lightning Imaging Sensor Data Applications Display (USDAD), are to: observe how total lightning relates to severe convective storm morphology over central Florida, and compare ground based total lightning data (LDAR) to a satellite based lightning detection system. This presentation will focus on objective #1. The LISDAD system continuously displays CG and total lighting activity overlaid on top of the KMLB composite reflectivity product. This allows forecasters to monitor total lightning activity associated with convective cells occurring over the central Florida peninsula and adjacent coastal waters. The LISDAD system also keeps track of the amount of total lightning data, and associated KMLB radar products with individual convective cells occurring over the region. By clicking on an individual cell, a history table displays flash rate information (CG and total lightning) in one minute increments, along with radar parameter trends (echo tops, maximum dBz and height of maximum dBz) every 5 minutes. This history table Is updated continuously, without user intervention, as long as the cell is identified. Reviewing data collected during the 1997 wet season (21 cases) revealed that storms which produced severe weather (hall greater or = 0.75 in. or wind damage) typically showed a rapid rise In total lightning prior to the onset of severe weather. On average, flash rate increases of 25 FPM per minute over a time scale of approximately 5 minutes were common. These pulse severe storms typically reached values of 150 to 200 FPM with some cells exceeding 400 FPM. One finding which could have a direct application to the warning process is that the rapid increase in lightning typically occurred in advance of the warning issuance time. Comparisons between the ending time of the rapid rate increase and the time of when the warning was issued by NWS/MLB meteorologist exhibited a lead time of 8 minutes. It is conceivable that if close monitoring of the LISDAD system by operational meteorologist is routinely performed, warnings for pulse severe storms could be issued up to 4 to 6 minutes earlier than what is issued currently.

Sharp, D.↗
NASA NTRS2001

Training Data Optimized and Conditioned to Learn Characteristic Patterns of Vibrating Blisks and Fan Blades

At the NASA Glenn Research Center, we have been training artificial neural networks to interpret the characteristic patterns (see the leftmost image) generated from electronic holograms of vibrating structures. These patterns not only visualize the vibration properties of structures, but small changes in the patterns can indicate structural changes, cracking, or damage. Neural networks detect these small changes well. Our objective has been to adapt the neural-network, electronic-holography combination for inspecting components in Glenn's Spin Rig.

Decker, Arthur J.↗
NASA NTRS2019

Geostationary Lightning Mapper Flash Characteristics of Electrified Snowfall Events

This study examines characteristics of lightning in snowfall events (i.e., thundersnow, 20 TSSN) from the perspective of the Geostationary Lightning Mapper (GLM) and the National Environmental Satellite Data and Information Service (NESDIS) merged Snowfall Rate (mSFR) product. A thundersnow detection algorithm (TDA) was derived from the GLM and mSFR which resulted in a probability of detection (POD) of 66.7% when compared to the Meteorological Terminal Air Report (METAR) reports of TSSN. However, using the TDA an additional 2,175 lightning flashes within detected snowfall were identified that were not observed by the METAR reports, indicating that TSSN has been under reported in previous literature. TSSN flashes observed by GLM have mean flash areas, durations, and total optical energy outputs of 754 km2, 402 ms, and 1,342 fJ, which are between the 50th and 99th percentile values for all flashes within the GLM field of view. A comparison with data from the National Lightning Detection Network (NLDN) indicated that the NLDN had at least one cloud or ground flash detection in 1,709 of the 2,214 flashes observed by GLM in snowfall. An average of 5.85 NLDN flashes were assigned to a single GLM flash when the NLDN flash data were constrained by the GLM flash duration and spatial footprint. Statistically significant (p<0.01) differences in flash area and flash energy were found between flashes that were observed by the NLDN and those that were not. Additionally, when GLM was combined with the NLDN, at least 11.1% of flashes involved a tall human-made object like an antenna or wind turbine.

lightning↗
NASA NTRS2012

GOES-R AWG GLM Val Tool Development

We are developing tools needed to enable the validation of the Geostationary Lightning Mapper (GLM). In order to develop and test these tools, we have need of a robust, high-fidelity set of GLM proxy data. Many steps have been taken to ensure that the proxy data are high quality. LIS is the closest analog that exists for GLM, so it has been used extensively in developing the GLM proxy. We have verified the proxy data both statistically and algorithmically. The proxy data are pixel (event) data, called Level 1B. These data were then clustered into flashes by the Lightning Cluster-Filter Algorithm (LCFA), generating proxy Level 2 data. These were then compared with the data used to generate the proxy, and both the proxy data and the LCFA were validated. We have developed tools to allow us to visualize and compare the GLM proxy data with several other sources of lightning and other meteorological data (the so-called shallow-dive tool). The shallow-dive tool shows storm-level data and can ingest many different ground-based lightning detection networks, including: NLDN, LMA, WWLLN, and ENTLN. These are presented in a way such that it can be seen if the GLM is properly detecting the lightning in location and time comparable to the ground-based networks. Currently in development is the deep-dive tool, which will allow us to dive into the GLM data, down to flash, group and event level. This will allow us to assess performance in comparison with other data sources, and tell us if there are detection, timing, or geolocation problems. These tools will be compatible with the GLM Level-2 data format, so they can be used beginning on Day 0.

Bateman, Monte↗
DOE OSTI2023

1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems

This paper presents a 1-D convolutional and graph convolutional networks for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spatial-temporal correlations from the voltage measurements in microgrids. The fault detection scheme includes fault event detection, fault type and phase classification, and fault location. There are five neural network model training to handle these tasks. Transfer learning and fine-tuning are applied to reduce training efforts. The combined 1-D convolutional and graph convolutional networks (1D-CGCN) is compared with the traditional ANN structure on the Potsdam 13-bus microgrid dataset. The accuracy of 99.5%, 98.4%, 99.2%, and 95.5% are achieved in fault event detection, fault type classification, fault phase identification, and fault location respectively. The detailed confusion matrices of fault type and fault phase classification are provided for validation.

deep neural network↗
NASA NTRS1982

On the adequacy of the fixed locations of the surface-based international network for inferring interannual ozone variability

The influence of the geographical distribution and the number of the surface stations in the ozone detecting network on changes in global ozone inferred from the surface measurements is investigated by comparison with information obtained from satellite backscattered UV observations on the Nimbus 4 with nearly complete global coverage for the period 1970-1972. Results show that the geographical distribution of the stations does not properly represent different latitudes. While the number of stations in the north temperate zone appears adequate to represent monthly ozone averages to within 0.5% except during the early phase of the Northern Hemisphere spring maximum, the resultant error in the derived change in north temperature zone ozone between 1970-1972 is 0.5%. In the tropical and south temperate zones the smaller number of stations reduces precision, and the ozone averages for use in deriving seasonal variability and trends are uncertain by about 1%. However, in the south temperature zone, the average from the sample may differ as much as 5% in some months from the averages derived from the full set. It is concluded that the resulting uncertainty in the global averages is comparable in size to typical yearly changes.

Heath, D. F.↗
NASA NTRS2003

Doppler Radar and Lightning Network Observations of a Severe Outbreak of Tropical Cyclone Tornadoes

Data from a single WSR-88D Doppler radar and the National Lightning Detection Network are used to examine in detail the characteristics of the convective storms that produced a severe tornado outbreak within Tropical Storm Beryl's remnants on 16 August 1994. Comparison of the radar data with reports of tornadoes suggests that only 13 cells produced the 29 tornadoes that were documented in Georgia and the Carolinas on that date. Six of these cells spawned multiple tornadoes, and the radar data confirm the presence of miniature supercells. One of the cells was identifiable on radar for 11 hours, spawning tornadoes over a time period spanning approximately 6.5 hours. Several other tornadic cells also exhibited great longevity, with cell lifetimes greater than ever previously documented in a landfalling tropical cyclone tornado event, and comparable to those found in major midlatitude tornadic supercell outbreaks. Time-height analyses of the three strongest tornadic supercells are presented in order to document storm kinematic structure and to show how these storms appear at different ranges from a WSR-88D radar. In addition, cloud-to-ground (CG) lightning data are examined for the outbreak, the most intense tropical cyclone tornado event studied thus far. Although the tornadic cells were responsible for most of Beryl's CG lightning, flash rates were only weak to moderate, even in the most intense supercells, and in all the tornadic storms the lightning flashes were almost entirely negative in polarity. A few of the single-tornado storms produced no detectable CG lightning at all. In the stronger cells, there is some evidence that CG lightning rates decreased during tornadogenesis, as has been documented before in some midlatitude tornadic storms. A number of the storms spawned tornadoes just after producing their final CG lightning flashes. Surprisingly, both peak currents and positive flash percentages were larger in Beryl s nontornadic storms than in the tornadic ones. Despite some intriguing patterns, the CG lightning behavior in this outbreak remains mostly inconsistent and ambiguous, and offers only secondary value for warning guidance. The present findings argue in favor of the implementation of observing systems capable of continuous monitoring of total lightning activity in storms.

McCaul, Eugene W., Jr.↗
NASA NTRS2008

Potential Use of a Bayesian Network for Discriminating Flash Type from Future GOES-R Geostationary Lightning Mapper (GLM) data

Continuous monitoring of the ratio of cloud flashes to ground flashes may provide a better understanding of thunderstorm dynamics, intensification, and evolution, and it may be useful in severe weather warning. The National Lighting Detection Network TM (NLDN) senses ground flashes with exceptional detection efficiency and accuracy over most of the continental United States. A proposed Geostationary Lightning Mapper (GLM) aboard the Geostationary Operational Environmental Satellite (GOES-R) will look at the western hemisphere, and among the lightning data products to be made available will be the fundamental optical flash parameters for both cloud and ground flashes: radiance, area, duration, number of optical groups, and number of optical events. Previous studies have demonstrated that the optical flash parameter statistics of ground and cloud lightning, which are observable from space, are significantly different. This study investigates a Bayesian network methodology for discriminating lightning flash type (ground or cloud) using the lightning optical data and ancillary GOES-R data. A Directed Acyclic Graph (DAG) is set up with lightning as a "root" and data observed by GLM as the "leaves." This allows for a direct calculation of the joint probability distribution function for the lighting type and radiance, area, etc. Initially, the conditional probabilities that will be required can be estimated from the Lightning Imaging Sensor (LIS) and the Optical Transient Detector (OTD) together with NLDN data. Directly manipulating the joint distribution will yield the conditional probability that a lightning flash is a ground flash given the evidence, which consists of the observed lightning optical data [and possibly cloud data retrieved from the GOES-R Advanced Baseline Imager (ABI) in a more mature Bayesian network configuration]. Later, actual GLM and NLDN data can be used to refine the estimates of the conditional probabilities used in the model; i.e., the Bayesian network is a learning network. Methods for efficient calculation of the conditional probabilities (e.g., an algorithm using junction trees), finding data conflicts, goodness of fit, and dealing with missing data will also be addressed.

Solakiewiz, Richard↗
NASA NTRS1994

Hideen Markov Models and Neural Networks for Fault Detection in Dynamic Systems

None given. (From conclusion): Neural networks plus Hidden Markov Models(HMM)can provide excellene detection and false alarm rate performance in fault detection applications. Modified models allow for novelty detection. Also covers some key contributions of neural network model, and application status.

space network↗
DOE OSTI2022

Out of Distribution Detection with Neural Network Anchoring

This is code to reproduce and build on OOD detection from the paper "Out of Distribution Detection with Neural Network Anchoring". Our goal here is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection. Heteroscedasticity here refers to the fact that the optimal temperature parameter for each sample can be different, as opposed to conventional approaches that use the same value for the entire distribution. To enable this, we propose a new training strategy called anchoring that can estimate appropriate temperature values for each sample, leading to state-of-the-art OOD detection performance across several benchmarks. Using NTK theory, we show that this temperature function estimate is closely linked to the epistemic uncertainty of the classifier, which explains its behavior. In contrast to some of the best-performing OOD detection approaches, our method does not require exposure to additional outlier datasets, custom calibration objectives, or model ensembling. Through empirical studies with different OOD detection settings - far OOD, near OOD, and semantically coherent OOD - we establish a highly effective OOD detection approach.

Thiagarajan, Jayaraman↗
DOE OSTI2021

Assembling a Cyber Range to Evaluate Artificial Intelligence / Machine Learning (AI/ML) Security Tools

In this case study, we will describe the design and assembly of a cyber security test range we have built at Oak Ridge National Laboratory in Oak Ridge, TN, USA. The range is designed to provide a flexible environment to evaluate cyber security tools—particularly those involving AI/ML—in a way that provides realistic environments and where we can control the experiments to determine the strengths and weaknesses of the tools. We have designed in the ability to repeat the evaluations, so additional tools can be evaluated and compared at a later time. The system is one that can be scaled up or down for experiment sizes. At the time of the conference we will have completed two full-scale, national, government challenges on this range. These challenges are evaluating the performance and operating costs for AI/ML-based cyber security tools for application into large, government-sized environments. These evaluations will be described, in order to provide motivation and context for various design decisions and adaptations we have made. The first challenge measured end-point security tools against 100K malware samples chosen across a range of types. The second is network detection of attempted penetration and exploitations with varying levels of covertness in a high-volume, business network. The scale of each of these challenges is requiring us to create automation systems to repeat the experiments identically for each tool. Preventing there being easy signs of malicious activity for the AI/ML tools to focus on has been a particularly interesting and challenging aspect of designing and executing these challenge events. After the events, the range continues to be used for other research such as adversarial machine learning where the repeatability, scale, and automation required for the national challenge events become essential elements for research.

Nichols, Jeff↗
NASA NTRS2004

Doppler Radar and Lightning Network Observations of a Severe Outbreak of Tropical Cyclone Tornadoes

Data from a single Weather Surveillance Radar-1988 Doppler (WSR-88D) and the National Lightning Detection Network are used to examine the characteristics of the convective storms that produced a severe tornado outbreak, including three tornadoes that reached F3 intensity, within Tropical Storm Beryl s remnants on 16 August 1994. Comparison of the radar data with reports of tornadoes suggests that only 13 cells produced the 29 tornadoes that were documented in Georgia and the Carolinas on that date. Six of these cells spawned multiple tornadoes, and the radar data confirm the presence of miniature supercells. One of the cells was identifiable on radar for 11 h. spawning tornadoes over a time period spanning approximately 6.5 h. Several other tornadic cells also exhibited great longevity, with cell lifetimes longer than ever previously documented in a landfalling tropical cyclone (TC) tornado event. This event is easily the most intense TC tornado outbreak yet documented with WSR-88Ds. Time-height analyses of the three strongest tornadic supercells are presented in order to document storm kinematic structure and to show how these storms appear at different ranges from a WSR-88D. In addition, cloud-to-ground (CG) lightning data are examined in Beryl s remnants. Although the tornadic cells were responsible for most of Beryl's CG lightning, their flash rates were only weak to moderate, and in all the tornadic storms the lightning flashes were almost entirely negative in polarity. A few of the single-tornado storms produced no detectable CG lightning at all. There is evidence that CG lightning rates decreased during the tornadoes, compared to 30-min periods before the tornadoes. A number of the storms spawned tornadoes just after producing their final CG lightning flashes. Contrary to the findings for flash rates, both peak currents and positive flash percentages were larger in Beryl's nontornadic storms than in the tornadic ones.

Mccaul, Eugene W., Jr.↗
DOE OSTI2022

Assessing the Impact of Lightning NOx Emissions in CMAQ Using Lightning Flash Data from WWLLN over the Contiguous United States

Comparison of lightning flash data from the National Lightning Detection Network (NLDN) and from the World Wide Lightning Location Network (WWLLN) over the contiguous United States (CONUS) for the 2016–2018 period reveals temporally and spatially varying flash rates that would influence lightning NO x (LNO x ) production due to known detection efficiency differences especially during summer months over land (versus over ocean). However, the lightning flash density differences between the two networks show persistent seasonal patterns over geographical regions (e.g., land versus ocean). Since the NLDN data are considered to have higher accuracy (lightning detection with >95% efficiency), we developed scaling factors for the WWLLN flash data based on the ratios of WWLLN to NLDN flash data over time (months of year) and space. In this study, sensitivity simulations using the Community Multiscale Air Quality (CMAQ) model are performed utilizing the original data sets (both NLDN and WWLLN) and the scaled WWLLN flash data for LNO x production over the CONUS. The model performance of using the different lightning flash datasets for ambient O 3 and NO x mixing ratios that are directly impacted by LNO x emissions and the wet and dry deposition of oxidized nitrogen species that are indirectly impacted by LNO x emissions is assessed based on comparisons with ground-based observations, vertical profile measurements, and satellite products. During summer months, the original WWLLN data produced less LNO x emissions (due to its lower lightning detection efficiency) compared to the NLDN data, which resulted in less improvement in model performance than the simulation using NLDN data as compared to the simulation without any LNO x emissions. However, the scaled WWLLN data produced LNO x estimates and model performance comparable with the NLDN data, suggesting that scaled WWLLN may be used as a substitute for the NLDN data to provide LNO x estimates in air quality models when the NLDN data are not available (e.g., due to prohibitive cost or lack of spatial coverage).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

ODDS: Real-Time Object Detection Using Depth Sensors on Embedded GPUs

Detecting objects that are carried when someone enters or exits a room is very useful for a wide range of smart building applications including safety, security, and energy efficiency. While there has been a significant amount of work on object recognition using large-scale RGB image datasets, RGB cameras are too privacy invasive in many smart building applications and they work poorly in the dark. Additionally, deep object detection networks require powerful and expensive GPUs. We propose a novel system that we call ODDS (Object Detector using a Depth Sensor) that can detect objects in real-time using only raw depth data on an embedded GPU, e.g., NVIDIA Jetson TX1. Hence, our solution is significantly less privacy invasive (even if the sensor is compromised) and less expensive, while maintaining a comparable accuracy with state of the art solutions. Specifically, we resort to training a deep convolutional neural network using raw depth images, with curriculum based learning to improve accuracy by considering the complexity and imbalance in object classes and developing a sparse coding based technique that speeds up the system ~2× with minimal loss of accuracy. Based on a complete implementation and real-world evaluation, we see ODDS achieve 80.14% mean average precision in object detection in real-time (5-6 FPS) on a Jetson TX1.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2011

Towards Resilient Critical Infrastructures: Application of Type-2 Fuzzy Logic in Embedded Network Security Cyber Sensor

Resiliency and cyber security of modern critical infrastructures is becoming increasingly important with the growing number of threats in the cyber-environment. This paper proposes an extension to a previously developed fuzzy logic based anomaly detection network security cyber sensor via incorporating Type-2 Fuzzy Logic (T2 FL). In general, fuzzy logic provides a framework for system modeling in linguistic form capable of coping with imprecise and vague meanings of words. T2 FL is an extension of Type-1 FL which proved to be successful in modeling and minimizing the effects of various kinds of dynamic uncertainties. In this paper, T2 FL provides a basis for robust anomaly detection and cyber security state awareness. In addition, the proposed algorithm was specifically developed to comply with the constrained computational requirements of low-cost embedded network security cyber sensors. The performance of the system was evaluated on a set of network data recorded from an experimental cyber-security test-bed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks. Detecting anomalies for multiple time series, however, is a challenging subject, owing to the intricate interdependencies among the constituent series. We hypothesize that anomalies occur in low density regions of a distribution and explore the use of normalizing flows for unsupervised anomaly detection, because of their superior quality in density estimation. Moreover, we propose a novel flow model by imposing a Bayesian network among constituent series. A Bayesian network is a directed acyclic graph (DAG) that models causal relationships; it factorizes the joint probability of the series into the product of easy-to-evaluate conditional probabilities. We call such a graph-augmented normalizing flow approach GANF and propose joint estimation of the DAG with flow parameters. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of GANF for density estimation, anomaly detection, and identification of time series distribution drift.

Dai, Enyan↗
NASA NTRS1999

Cross-Sensor Validation of the Optical Transient Detector (OTD)

Lightning data from the U.S. National Lightning Detection Network (NLDN) is used to perform preliminary validation of the satellite-based Optical Transient Detector (OTD). Sensor precision, accuracy, detection efficiency and biases of the deployed instrument are considered. We estimate the sensor to have, on average, better than 30 km spatial and 100 ms temporal accuracy. The detection efficiency for cloud-to-ground lightning is about 45-70%, slightly higher for intracloud lightning. There are only marginal day/night biases in the dataset, although 55 day averaging is required to remove sampling-based diurnal lightning cycle biases. The sensor detects statistically significant differences in the optical characteristics of intracloud, negative cloud-to-ground and positive cloud-to-ground lightning, although it cannot a priori determine flash types.

Boccippio, D. J.↗
NASA NTRS2015

Kinematic and Microphysical Control of Lightning Flash Rate over Northern Alabama

The Deep Convective Clouds and Chemistry (DC3) experiment seeks to examine the relationship between deep convection and the production of nitrogen oxides (NO (sub x)) via lightning (LNO (sub x)). A critical step in estimating LNO (sub x) production in a cloud-resolving model (CRM) without explicit lightning is to estimate the flash rate from available model parameters that are statistically and physically correlated. As such, the objective of this study is to develop, improve and evaluate lightning flash rate parameterizations in a variety of meteorological environments and storm types using radar and lightning mapping array (LMA) observations taken over Northern Alabama from 2005-2012, including during DC3. UAH's Advanced Radar for Meteorological and Operational Research (ARMOR) and the Weather Surveillance Radar - 1988 Doppler (WSR 88D) located at Hytop (KHTX) comprises the dual-Doppler and polarimetric radar network, which has been in operation since 2004. The northern Alabama LMA (NA LMA) in conjunction with Vaisala's National Lightning Detection Network (NLDN) allow for a detailed depiction of total lightning during this period. This study will integrate ARMOR-KHTX dual Doppler/polarimetric radar and NA LMA lightning observations from past and ongoing studies, including the more recent DC3 results, over northern Alabama to form a large data set of 15-20 case days and over 20 individual storms, including both ordinary multicell and supercell convection. Several flash rate parameterizations will be developed and tested, including those based on 1) graupel/small hail volume; 2) graupel/small hail mass, and 3) convective updraft volume. Sensitivity of the flash rate parameterizations to storm intensity, storm morphology and environmental conditions will be explored.

Carey, Lawrence D.↗