Search NASA⌕ Search

SEARCH · Search NASA

Results for “Anomaly Classification”

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.

224 records · Page 13

Deep Learning for Enhancing Fault Tolerant Capabilities of Scientific Workflows

Deep Learning for Enhancing Fault TolerantCapabilities of Scientific WorkflowsAlok Singh, Ilkay AltintasSan Diego Supercomputer Center, UCSDLa Jolla, CA, USA{a1singh, ialtintas}@ucsd.eduMalachi Schram, Nathan TallentPacific Northwestern National LaboratoryRichland, WA, USA{malachi.schram, nathan.tallent}@pnnl.govAbstract-In the history of Computer Science, the act of ‘delegation’ has been the greatest multiplier of society’s problem-solving ability. A scientist working on detecting anomalies in a phenomenon, does not need to re-invent matrix multiplication techniques to solve her problem. Scientific workflows provide ultimate ‘delegation’ mechanism -where a domain scientist can completely forget the specifics of ‘how’ her program will execute on a large cluster in an efficient and cost-effective manner and can instead focus on the mathematical formulation and theoretical robustness of her solution. We present here an approach that directly aims to make the execution of Scientific Workflows more reliable, robust and efficient. We aim that the work presented in this paper will propel the larger effort, from the scientific workflow community, of making scientific workflow execution as simple, efficient and robust as a JOIN operation in a modern database. Specifically, we apply Deep Learning techniques to develop a mechanism that forecasts the final state (success or failure) of a dynamic job in a large-scale particle physics experiment, with minimal data gathering, and as early as possible in job’s life cycle. The key advantage of having a predictive mechanism to identify and anticipate failure-prone jobs is the potential for designing intelligent Fault Tolerance mechanisms to handle anomalous events. We achieve a 14% improvement in computational resources utilization, and an overall classification accuracy of 85% on real tasks executed in a High Energy Physics Computing workflow.To the best of our knowledge, this is the most exhaustive and first of its kind study of neural network architectures in context of a real-dataset profiled from a large-scalescientific workflow.

deep learning↗

The Relationship of Forest Fires Detected by MODIS and SRTM Derived Topographic Features in Central Siberia

Fires are a common occurrence in the Siberian boreal forest. The MOD14 Thermal anomalies product of the Terra MODIS Moderate Resolution Spectroradiometer) product set is designed to detect thermal anomalies (i.e. hotspots or fires) on the Earth's surface. Recent field studies showed a dependence of fire occurrence on topography. In this study MODIS thermal anomaly data and SRTM topography data were merged and analyzed to evaluate if forest fires are more likely to occur at certain combinations of elevation, slope and aspect. Using the satellite data over a large area can lead to better understanding how topography and forest fires are related. The study area covers a 2.5 Million krn(exp 2) portion of the Central Siberian southern taiga from 72 deg to 110 deg East and from 50 deg to 60 deg North. About 57% of the study area is forested and 80% of the forest grows between 200 and 1000 m. Forests with pine (Pinus sylvestris), larch (Larix sibirica, L. gmelinii), Siberian pine (Pinus sibirica), spruce (Picea obovata.) and fir (Abies sibirica) cover most of the landscape. Deciduous stands with birch (Betula pendula, B. pubescens) and aspen (Populus tremula) cover the areas of lower elevation in this region. The climate of this area is distinctly continental with long, cold winters and short hot summers. The tree line in this part of the world is around 1500 m in elevation with alpine tundra, snow and ice fields and rock outcrops extending up to over 3800 m. A 500 m resolution landcover map was developed using 2001 MODIS MOD13 Normalized Vegetation Index (NDVI) and Middle Infrared (MIR) products for seven 16-day periods. The classification accuracy was over 87%. The SRTM version 2 data, which is distributed in 1 degree by 1 degree tiles were mosaiced using the ENVI software. In this study, only those MODIS pixels were used that were flagged as "nominal or high confidence fire" by the MODIS fire product team. Using MODIS data from the years 2000 to 2005 along with the improved Shuttle Radar Topographic Mission (SRTM) version 2 data at 100 m resolution, the distribution of hot spots was examined by elevation, slope and aspect as well as by forest type. The results show that more forest area burns at lower elevations but a larger percentage of the available forest area burns at higher elevations. This is probably because steep slopes occur at higher elevations. Fires are only more common on slopes with a southern exposure if the slope is steeper than 15 degrees. The next step in this study will be to monitor areas where the risk of fire is high (steep slopes with a southern exposure) and to refine this method by incorporating anthropogenic features for more accurate fire disturbance monitoring.

Ranson, Jon K.↗

Multilabel proportion prediction and out-of-distribution detection on gamma spectra of short-lived fission products

In the machine learning problem of multilabel classification, the objective is to determine for each test instance which classes the instance belongs to. In this work, we consider an extension of multilabel classification, called multilabel proportion prediction, in the context of radioisotope identification (RIID) using gamma spectra data. We aim to not only predict radioisotope proportions, but also identify out-of-distribution (OOD) spectra. We achieve this goal by viewing gamma spectra as discrete probability distributions, and based on this perspective, we develop a custom semi-supervised loss function that combines a traditional supervised loss with an unsupervised reconstruction error function. Our approach was motivated by its application to the analysis of short-lived fission products from spent nuclear fuel. In particular, we demonstrate that a neural network model trained with our loss function can successfully predict the relative proportions of 37 radioisotopes simultaneously. The model trained with synthetic data was then applied to measurements taken by Pacific Northwest National Laboratory (PNNL) to conduct analysis typically done by subject-matter experts. Here, we also extend our approach to successfully identify when measurements are OOD, and thus should not be trusted, whether due to the presence of a novel source or novel proportions.

Anomaly detection↗

Toward memory-efficient melt pool monitoring: a classification framework using event-based imaging and sparse sensing technique

Vision sensors like CMOS and CCD cameras are often used for in-process monitoring of melt pools in laser-based additive and welding processes, but they require transferring large amounts of data and computational processing resources. Event-based neuromorphic imagery, on the other hand, detects only the change in pixel intensity, thus potentially reducing the data amount and latency. With an event imager, this study develops a framework for melt pool condition classification, including image construction, time scale selection, optimal pixel selection, and sparse classification, to achieve a highly memory-efficient scheme. These are based on sparse sensing techniques with singular value decomposition (SVD) and QR pivoting, the two fundamental matrix transformations for linear dimensionality reduction. The framework is then validated by classifying a controlled experiment by exciting various mode shapes of liquid gallium pools of varying depths (3, 6, and 8 mm). At 200 pixels, the classifier can reach overall accuracy of 75%, while at 2000 pixels (0.013% of the total possible pixels), the accuracy is nearly 90% (89.86%). At the same number of pixels, random selection can only achieve 46% and 67%, respectively. The memory savings of the sparsely sampled event data compared to a conventional imager is about 500 times. In addition to performance, implementation and limitations of the framework are also discussed.

42 ENGINEERING↗

Validating Protection System Behavior with Machine Learning in a Master State Overseer

As power system protection devices continue the widespread transition from analog to digital, they become increasingly intricate. The internal functions and communication between critical grid components must now be significantly more complex to keep up with the demands of the modern smart grid. This brings increased difficulty in maintenance and monitoring, making it harder to identify potential misoperation, power anomalies, and cyber threats. Such issues are often only pinpointed after an exhaustive and costly post-mortem analysis, when a major outage or damage has already occurred. A solution is needed for validating protection systems as they operate, independently evaluating grid state and confirming whether the protection system is behaving accordingly. As opposed to incident response, this acts as a constant verification mechanism that raises a flag when subtler issues are noticed, catching them earlier and preventing larger incidents. This work presents the implementation of such a system, expanding on the prototype developed by the authors in a previous paper. This is accomplished with a machine learning (ML) system capable of validating the performance of protection systems by classifying anomalous events and characterizing protection system responses based solely on available current and voltage measurements. Additionally, this system is contextualized within a larger, modular Master State awareness Overseer (MSO) framework, responsible for monitoring, analyzing, and managing an electric grid.

24 - POWER TRANSMISSION AND DISTRIBUTION↗

Full-flow-regime storage-streamflow correlation patterns provide insights into hydrologic functioning over the continental US

Interannual changes in low, median, and high regimes of streamflow have important implications for flood control, irrigation, and ecologic and human health. The Gravity Recovery and Climate Experiment (GRACE) satellites record global terrestrial water storage anomalies (TWSA), providing an opportunity to observe, interpret, and potentially utilize the complex relationships between storage and full-flow-regime streamflow. Here we show that utilizable storage-streamflow correlations exist throughout vastly different climates in the continental US (CONUS) across low- to high-flow regimes. A panoramic framework, the storage-streamflow correlation spectrum (SSCS), is proposed to examine macroscopic gradients in these relationships. SSCS helps form, corroborate or reject hypotheses about basin hydrologic behaviors. SSCS patterns vary greatly over CONUS with climate, land surface, and geologic conditions. Data mining analysis suggests that for catchments with hydrologic settings that favor storage over runoff, e.g., a large fraction of precipitation as snow, thick and highly-permeable permeable soil, SSCS values tend to be high. Based on our results, we form the hypotheses that groundwater flow dominates streamflows in South-eastern CONUS and Great Plains, while thin soils in a belt along the Appalachian Plateau impose a limit on water storage. SSCS also suggests shallow water table caused by high-bulk density soil and flat terrain induces rapid runoff in several regions. Our results highlight the importance of subsurface properties and groundwater flow in capturing flood and drought. Finally, we propose that SSCS can be used as a fundamental hydrologic signature to constrain models and to provide insights that lead us to better understand hydrologic functioning.

54 ENVIRONMENTAL SCIENCES↗

Light-Duty Vehicle Trip Classification Using One-Class Novelty Detection and Exhaustive Feature Extraction

Travel mode classification within travel survey data sets, especially light-duty vehicle (LDV) trips, is foundational, though nontrivial, to emerging mobility systems, travel behavior analysis, and fuel consumption estimation. Current travel mode detection approaches require well-sampled and balanced data sets with ground truth travel mode labels. The detection approaches are rarely applied and validated on large-scale, real-world data sets, which may not satisfy the dataset requirements. This work proposes an LDV trip detection model as a supplement to current travel mode detection methods, for the case when the training set is highly (and/or completely) unbalanced, to the extent that classical machine-learning approaches become difficult or impossible to deploy. The proposed model uses a novelty detection technique - one-class support vector machines (OCSVMs) - and a novel exhaustive feature extraction (EFE) technique on continuous time series data (i.e., Global Positioning System [GPS] speed profiles) for single-mode trip trajectories. Training and validation of the model are conducted on a large-scale, real-world data set. The proposed method accurately identifies LDV trips from a broad set of multimodal trips by leveraging a wealth of preexisting in-vehicle GPS travel data. Additional sensitivity analysis sheds light on the optimal training size and feature selection, which will benefit applications limited by highly imbalanced data. The paper also discusses performance comparison with regular machine-learning approaches, the model's robustness, and the potential to extend the proposed model to multi-modal trip prediction.

33 ADVANCED PROPULSION SYSTEMS↗

Mondo: integrating disease terminology across communities

Precision medicine aims to enhance diagnosis, treatment, and prognosis by integrating multimodal data at the point of care. However, challenges arise due to the vast number of diseases, differing methods of classification, and conflicting terminological coding systems and practices used to represent molecular definitions of disease. This lack of interoperability artificially constrains the potential for diagnosis, clinical decision support, care outcome analysis, as well as data linkage across research domains to support the development or repurposing of therapeutics. There is a clear and pressing need for a unified system for managing disease entities⁠—including identifiers, synonyms, and definitions. To address these issues, we created the Mondo disease ontology—a community-driven, open-source, unified disease classification system that harmonizes diverse terminologies into a consistent, computable framework. Mondo integrates key medical and biomedical terminologies, including Online Mendelian Inheritance in Man (OMIM), Orphanet, Medical Subject Headings (MeSH), National Cancer Institute Thesaurus (NCIt), and more, to provide a comprehensive and accurate representation of disease concepts with fully provenanced and attributed links back to the sources. Mondo can be used as the handle for curation of gene–disease associations utilized in diagnostic applications, research applications such as computational phenotyping, and in clinical coding systems in clinical decision support by pointing the clinician to the numerous knowledge resources linked to the Mondo identifier. Mondo's community-centric approach, stewarded by the Monarch Initiative's expertise in ontologies, ensures that the ontology remains adaptable to the evolving needs of biomedical research and clinical communities, as well as the knowledge providers.

biomedical informatics↗