Search NASA⌕ Search

SEARCH · Search NASA

Results for “Classifier”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Classification of Wetland Vegetation Based on NDVI Time Series from the HLS Dataset

Natural wetlands are intrinsically heterogeneous and typically composed of a mosaic of ecosystem patches with different vegetation types. Hydrological and biogeochemical processes in wetlands vary strongly among these ecosystem patches. To date, most remote sensing classification approaches for wetland vegetation either rely on coarse images that cannot capture the spatial variability of wetland vegetation or rely on very-high-resolution multi-spectral images that are detailed but very sporadic in time (less than once per year). This study aimed to use NDVI time series, generated from NASA’s HLS dataset, to classify vegetation patches. We demonstrate our approach at a temperate, coastal lake, estuarine marsh. To classify vegetation patches, a standard time series library of the four land-cover patch types was built from referencing specific locations that were identified as “pure” pixels. These were identified using a single-time high-resolution image. We calculated the distance between the HLS-NDVI time series at each pixel and the “pure”-pixel standards for each land-cover type. The resulting true-positive classified rate was >73% for all patch types other than water lily. The classification accuracy was higher in pixels of a more uniform composition. A set of vegetation maps was created for the years 2016 to 2020 at our research site to identify the vegetation changes at the site as it is affected by rapid water elevation increases in Lake Erie. Our results reveal how changes in water elevation have changed the patch distribution in significant ways, leading to the local extinction of cattail by 2019 and a continuous increase in the area cover of water lily patches.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Application of Convolutional and Feedforward Neural Networks for Fault Detection in Particle Accelerator Power Systems

High voltage converter modulators (HVCM) provide power to the accelerating cavities of the spallation neutron source (SNS) facility. HVCM experience catastrophic failures, which increase the downtime of the SNS and reduce beam time. The faults may occur due to different reasons including failures of the resonant capacitor, core saturation due to the magnetic flux, insulated-gate bipolar transistor (IGBT) failures, and others. We recently have setup a HVCM test stand to develop and test machine learning models for anomaly detection and fault prognostics. In this work, we propose binary classifiers and autoencoder architectures based on convolutional (CNN) and feedforward neural networks (FNN) to facilitate distinguishing normal from faulty waveforms coming from the HVCM during operation. The results indicate that the CNN binary classifier is the best model among the four showing very stable performance in the training and testing sets with impressive metrics of precision and recall reaching up to 99\% with a very small uncertainty. The FNN classifier shows the least performance with a large uncertainty in its metrics. The performances of the two autoencoders based on CNN and FNN were in between, showing very good performance nonetheless.

Radaideh, Majdi↗
DOE OSTI2021

The ZTF Source Classification Project. I. Methods and Infrastructure

The Zwicky Transient Facility (ZTF) has been observing the entire northern sky since the start of 2018 down to a magnitude of 20.5 (5σ for 30 s exposure) in the g, r, and i filters. Over the course of two years, ZTF has obtained light curves of more than a billion sources, each with 50–1000 epochs per light curve in g and r, and fewer in i. To be able to use the information contained in the light curves of variable sources for new scientific discoveries, an efficient and flexible framework is needed to classify them. In this paper, we introduce the methods and infrastructure that will be used to classify all ZTF light curves. Our approach aims to be flexible and modular and allows the use of a dynamical classification scheme and labels, continuously evolving training sets, and the use of different machine-learning classifier types and architectures. Finally with this setup, we are able to continuously update and improve the classification of ZTF light curves as new data become available, training samples are updated, and new classes need to be incorporated.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Toward a More Complete Optical Census of Active Galactic Nuclei via Spatially Resolved Spectroscopy

While emission line flux ratio diagnostics are the most common technique for identifying active galactic nuclei (AGNs) in optical spectra, applying this approach to single-fiber spectra of galaxies can omit entire subpopulations of AGNs. Here, we use spatially resolved spectroscopy from the Mapping Nearby Galaxies at Apache Point Observatory (MaNGA) survey to construct a sample of 10 galaxies where Baldwin–Philips–Terlevich line flux ratio diagnostics classify each galaxy’s central 3" spectrum as LINER or star-forming, while >10% of the spaxels in the galaxy’s MaNGA footprint are classified as Seyfert. We obtain Chandra observations of these 10 galaxies with off-nuclear Seyfert regions to determine whether AGNs are actually present in them. Our main result is that 7–10 (depending on strictness of criteria) of the galaxies host one or more X-ray AGNs, even though none of them were classified as AGNs based on their single-fiber optical spectra. We find that these AGNs were not identified in the single-fiber spectra because they are AGNs in the nuclei of companion galaxies, low-luminosity AGNs, dust-obscured AGNs, and/or flickering AGNs. In summary, we find that off-nuclear AGN signatures may increase the number of known AGNs by a factor of two over what conventional single nuclear fiber spectra identify. Our results show that spatially resolved spectroscopy can be leveraged to reveal a more complete census of AGNs that are traditionally missed by single-fiber spectra.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

On Finding Black Holes in Photometric Microlensing Surveys

There are expected to be millions of isolated black holes in the galaxy resulting from the deaths of massive stars. Measuring the abundance and properties of this remnant population would shed light on the end stages of stellar evolution and the evolution paths of black hole systems. Detecting isolated black holes is currently only possible via gravitational microlensing, which has so far yielded one definitive detection. The difficulty in finding microlensing black holes lies in having to choose a small subset of events, based on characteristics of their light curves, to allocate expensive and scarce follow-up resources to confirm the identity of the lens. Current methods either rely on simple cuts in parameter space without using the full distribution information or are only effective on small subsets of events. In this paper, we present a new lens classification method. The classifier takes in posterior constraints on light-curve parameters and combines them with a Galactic simulation to estimate the lens class probability. This method is flexible and can be used with any set of microlensing light-curve parameters, making it applicable to large samples of events. We make this classification framework available via the popclass Python package. We apply the classifier to ~10,000 microlensing events from the Optical Gravitational Lensing Experiment survey and find 23 high-probability black hole candidates. Our classifier also suggests that the only known isolated black hole is an observational outlier, according to current Galactic models, and the allocation of astrometric follow-up on this event was a high-risk strategy.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

The Dark Energy Survey: Cosmology Results with ∼1500 New High-redshift Type Ia Supernovae Using the Full 5 yr Data Set

Abstract We present cosmological constraints from the sample of Type Ia supernovae (SNe Ia) discovered and measured during the full 5 yr of the Dark Energy Survey (DES) SN program. In contrast to most previous cosmological samples, in which SNe are classified based on their spectra, we classify the DES SNe using a machine learning algorithm applied to their light curves in four photometric bands. Spectroscopic redshifts are acquired from a dedicated follow-up survey of the host galaxies. After accounting for the likelihood of each SN being an SN Ia, we find 1635 DES SNe in the redshift range 0.10 < z < 1.13 that pass quality selection criteria sufficient to constrain cosmological parameters. This quintuples the number of high-quality z > 0.5 SNe compared to the previous leading compilation of Pantheon+ and results in the tightest cosmological constraints achieved by any SN data set to date. To derive cosmological constraints, we combine the DES SN data with a high-quality external low-redshift sample consisting of 194 SNe Ia spanning 0.025 < z < 0.10. Using SN data alone and including systematic uncertainties, we find Ω M = 0.352 ± 0.017 in flat ΛCDM. SN data alone now require acceleration ( q 0 < 0 in ΛCDM) with over 5 σ confidence. We find ( Ω M , w ) = ( 0.264 − 0.096 + 0.074 , − 0.80 − 0.16 + 0.14 ) in flat w CDM. For flat w 0 w a CDM, we find ( Ω M , w 0 , w a ) = ( 0.495 − 0.043 + 0.033 , − 0.36 − 0.30 + 0.36 , − 8.8 − 4.5 + 3.7 ) , consistent with a constant equation of state to within ∼2 σ . Including Planck cosmic microwave background, Sloan Digital Sky Survey baryon acoustic oscillation, and DES 3 × 2pt data gives (Ω M , w ) = (0.321 ± 0.007, −0.941 ± 0.026). In all cases, dark energy is consistent with a cosmological constant to within ∼2 σ . Systematic errors on cosmological parameters are subdominant compared to statistical errors; these results thus pave the way for future photometrically classified SN analyses.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Data for Monitoring Fracture Saturation with Internal Transportable Seismic Sources and Twin Neural Networks

Seismic coda-wave analysis is a well-developed method for detecting subtle physical changes in complex media by measuring arrival times in the late-arriving energy from multiply-scattered or reflected waves. However, a challenge arises when multiply-scattered waves are not sufficiently separated in time from the direct arrivals to provide a clear coda wave train. Additional complications for monitoring changes in fracture systems arise when the signals originate from unsynchronized internal sources, such as natural induced seismicity, from acoustic emission, or from transportable intra-fracture sources (chattering dust), that generate uncontrolled signals that vary in arrival time, amplitude and frequency content. Here, we use a twin neural network (also known as a Siamese neural network) for dimensionality reduction to analyze signals from chattering dust to classify the fluid saturation state of a synthetic fracture system. The twin neural network with shared weights generates a low-dimensional representation of the data input by minimizing contrastive loss, serving as the input to a multiclass classifier that accurately classifies whether multiple fractures in a fracture system are fully saturated or partially saturated, or whether a change in saturation has occurred in different fractures in the system. These results show that information buried in unresolved codas from uncontrolled sources can be extracted using machine learning to monitor the evolution of fracture systems caused by physical and chemical processes even when the scattered and direct wave fields overlap.

58 GEOSCIENCES↗
DOE OSTI2024

A network approach for multiscale catchment classification using traits

Abstract. The classification of river catchments into groups with similar biophysical characteristics is useful to understand and predict their hydrological behavior. The increasing availability of remote sensing and other large-scale geospatial datasets has enabled the use of advanced data-driven approaches to classify catchments using traits such as topography, geology, climate, land cover, land use, and human influence. Unsupervised clustering algorithms based on the Euclidean distance are commonly used for trait-based classification but are not suitable for highly dimensional data. In this study we present a new network-based method for multi-scale catchment classification, which can be applied to large datasets and used to determine the traits associated with different catchment groups. In this framework, two networks are analyzed in parallel: the first being where the nodes are traits and the second being where the nodes are catchments. In both cases, edges represent pairwise similarity, and a network cluster detection algorithm is used for the classification. The trait network is used to investigate redundancy in the trait data and to condense this information into a small number of interpretable categories. The catchments network is used to classify the catchments into clusters and to identify representative catchments for the different groups using the degree centrality metric. We apply this method to classify 9067 river catchments across the contiguous United States at both regional and continental scales using 274 non-categorical traits. At the continental scale, we identify 25 interpretable trait categories and 34 catchment clusters of sizes greater than 50. We find that catchments with similar trait categories are typically located in the same region, with different spatial patterns emerging among clusters dominated by natural and anthropogenic traits. We also find that the catchment clusters exhibit distinct hydrological behavior based on an analysis of streamflow indices. This network approach provides several advantages over traditional means of classification, including better separation of clusters, the use of alternate similarity metrics that are more suitable for highly dimensional data, and reducing redundancy in the trait information. The paired catchment–trait networks enable analysis of hydrological behavior using the dominant trait categories for each catchment cluster. The approach can be used at multiple spatial scales since the network topologies adjust automatically to reflect the trait patterns at the scale of investigation. Finally, the representative catchments identified as hub nodes in the network can be used to guide transferable observational and modeling strategies. The method is broadly applicable beyond hydrology for classification of other complex systems that utilize different types of trait datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Automated Classification of Vehicle Movements at Signalized Intersections Using Vehicle Trajectories

Accurate vehicle movement classification through signalized intersections is of paramount importance to the analysis of intersection performance and the optimization of traffic control strategies. Conventional techniques for tracking vehicle turning movements depend on infrastructure-based strategies like human counts, loop detectors, and video analytics, all of which are costly, prone to errors, and spatially constrained. High-frequency trajectory data can be utilized to determine vehicle movement patterns in a scalable and infrastructure-independent method due to the adoption of connected vehicles (CVs). In recent years, several studies have utilized connected vehicle data to generate performance measures. Most of the trajectory-based performance measures approaches, however, require map matching-i.e., extracting geospatial references from maps to identify the movements that individual vehicles make at a signalized intersection. These approaches are often time-consuming and hinder scalability since geographic features need to be provided for an analysis to be conducted. Map matching methods are prone to errors as different map versions change these geographic features. This research presents a novel automatic classification pipeline that uses CV trajectory data to classify vehicle movements at signalized crossings, specifically pass-through left-turn and right-turn maneuvers. The process starts by filtering trips that cross a spatial bounding box that has been defined at the target intersection. Approach and departure headings for each trajectory crossing the boundary are computed and are clustered together to identify dominant movements. The proposed algorithm is used to classify the movement of vehicles at 10 intersections in the state of California, and the results indicate that the algorithm can classify movements at these intersections with varying traffic volumes and road network configurations, all in a map-less framework with no need for conflation of vehicle trajectories to a digital base map.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Outlier classification using autoencoders: application for fluctuation driven flows in fusion plasmas

Understanding the statistics of fluctuation driven flows in the boundary layer of magnetically confined plasmas is desired to accurately model the lifetime of the vacuum vessel components. Mirror Langmuir probes (MLPs) are a novel diagnostic that uniquely allow us to sample the plasma parameters on a time scale shorter than the characteristic time scale of their fluctuations. Sudden large-amplitude fluctuations in the plasma degrade the precision and accuracy of the plasma parameters reported by MLPs for cases in which the probe bias range is of insufficient amplitude. While some data samples can readily be classified as valid and invalid, we find that such a classification may be ambiguous for up to 40% of data sampled for the plasma parameters and bias voltages considered in this study. In this contribution, we employ an autoencoder (AE) to learn a low-dimensional representation of valid data samples. By definition, the coordinates in this space are the features that mostly characterize valid data. Ambiguous data samples are classified in this space using standard classifiers for vectorial data. In this way, we avoid defining complicated threshold rules to identify outliers, which require strong assumptions and introduce biases in the analysis. By removing the outliers that are identified in the latent low-dimensional space of the AE, we find that the average conductive and convective radial heat fluxes are between approximately 5% and 15% lower as when removing outliers identified by threshold values. For contributions to the radial heat flux due to triple correlations, the difference is up to 40%.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Damaged Fuel in the United States

Over the years of commercial nuclear power plant operations in the United States (U.S.), many fuel assemblies have lost the capability to perform all of their desired functions. These assemblies have lost the capability to be handled, stored, or transported to meet regulations resulting in them being classified as damaged fuel. The causes of these failed assemblies are diverse and plant-specific. The majority of these failed assemblies are contained in a damaged fuel can that will be used in conjunction with a storage and/or transportation system. The storage and transportation systems have a limit on how many slots can be filled with damaged fuel cans. A damaged fuel can is generally a stainless steel container that confines damaged SNF and is closed on its end by screened openings. These screened openings allow gaseous and liquid media to escape but minimize the dispersal of gross particulate material. Out of an abundance of caution a few reactors have loaded high burnup fuel into damaged fuel cans. Damaged fuel is not licensed for storage or transport in the U.S., because the regulations for storage and transport do not specify exactly how to classify damaged fuel. Instead the regulations license/certify packages that specify approved contents. Damaged fuel must be included in the approved contents to be a viable option. In many cases damaged SNF is encapsulated in a damaged fuel can to ensure it can confine gross fuel particles, debris, and or damaged assemblies to a known volume within a loaded cask. This damaged fuel can may then be utilized in the same way as an assembly in a storage and transportation design system. Some storage cask systems utilize top and bottom plugs to confine debris in damaged fuel. The most recent domestic documentation on damaged SNF was performed by the U.S. Energy Information Administration (EIA) and used data from U.S. reactors concluding in June 30th 2013 to produce Form GC-859, “Nuclear Fuel Data Survey”. Based on this form there were 136,821 boiling water reactor (BWR) spent nuclear fuel (SNF) assemblies and 104,647 pressurized water reactor (PWR) SNF assemblies for a total of 241,468 SNF assemblies in the U.S. Out of these 241,468 SNF assemblies, 4,521 assemblies were classified as failed. Some assemblies were also disassembled and the fuel rods or pieces of fuel rods were combined together to make a consolidated assembly. A consolidated assembly may include damaged fuel, or it could have been consolidated as part of a demonstration project. The GC-859 data includes 2,550 consolidated assemblies containing between 0 and 264 whole fuel rods. These consolidated assemblies could be placed in single assembly canisters and stored in the spent fuel pool. For dry storage and transportation, a single assembly canister is generally placed in a damaged fuel can. In addition to the consolidated assemblies, 2,391 uncanistered fuel rod pieces exist, which were removed from 494 assemblies.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

Feature identification or classification using task-specific metadata

Innovations in the identification or classification of features in a data set are described, such as a data set representing measurements taken by a scientific instrument. For example, a task-specific processing component, such as a video encoder, is used to generate task-specific metadata. When the data set includes video frames, metadata can include information regarding motion of image elements between frames, or other differences between frames. A feature of the data set, such as an event, can be identified or classified based on the metadata. For example, an event can be identified when metadata for one or more elements of the data set exceed one or more threshold values. When the feature is identified or classified, an output, such as a display or notification, can be generated. Although the metadata may be useable to generate a task-specific output, such as compressed video data, the identifying or classifying is not used solely in production of, or the creation of an association with, the task-specific output.

Teuton, Jeremy R.↗
DOE OSTI2022

Wireless signal monitoring and analysis, and related methods, systems, and devices

Wireless signal classifiers and systems that incorporate the same may include an energy-based detector configured to analyze an entire set of measurements and generate a first signal classification result, a cyclostationary-based detector configured to analyze less than the entire set of measurements and generate a second signal classification result; and a classification merger configured to merge the first signal classification result and the second signal classification result. Ensemble wireless signal classification and systems and devices the incorporate the same are disclosed. Some ensemble wireless signal classification may include energy-based classification processes and machine learning-based classification processes. In some embodiments, incremental machine learning techniques may be incorporated to add new machine learning-based classifiers to a system or update existing machine learning-based classifiers.

Derr, Kurt W.↗
DOE OSTI2020

Critical Infrastructure Classification via CNN-based Modeling and Image Analysis

With recent advances in the fields of satellite imagery and machine learning we now have the ability to develop explainable deep learning models that enhance critical infrastructure analysis. Funded through Idaho National Laboratory’s (INL) Laboratory Directed Research and Development (LDRD) office we are in the process of developing a deep learning model capable of identifying critical infrastructure facilities and embedded features within those facilities. Utilizing current limit of practice techniques in the machine learning areas of explainability and transfer learning our model, once complete, will have the capacity to be used on multiple different imagery data sets and produce results that not only classify critical infrastructure facilities, but also explain why a critical infrastructure facility was classified as a certain type of facility. These advancements eliminate the ‘black box’ approach deep learning models have had in the past, where a user will have to trust the conclusion of a model without understanding what reasoning when into the model’s classification process. They also expand a model’s usefulness, traditionally a deep learning model will have to use the same data set it was originally trained on. Given the long training times of deep learning models this is impractical in a number of scenarios. By utilizing transfer learning advancements, we are eliminating the need to train our model on the same data set it is then run on to classify critical infrastructure facilities. We are also enabling the analysis and classification of data sets that are potentially too small to be divided into a training and testing data set. Once completed this model can provide a foundation to enhanced critical infrastructure analysis, dependency analysis, and potential disaster relief efforts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Introduction to Fuel Cycle Front End: From Mining Through Utilization

This book chapter introduces the Fuel Cycle Front End: Mining through Utilization Section of this Encyclopedia, providing context for the chapters that follow. It presents an overview of the nuclear fuel cycle and describes design considerations important to fuel technology. This manuscript version of a book chapter from the Encyclopedia of Nuclear Energy (Elsevier, 2021) that was not reviewed in LRS prior to being sent to the book general editor for review or for final publication. It also has not yet been uploaded to SORT/OSTI. The content includes classified subject matter topics, but does not include any classified information (judgement of the author as a Derivative Classifier).

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Search for the NΔ resonance in the 𝛾𝑑 → 𝑑𝜋 +𝜋 − reaction

A dibaryon which is an object with baryon number B = 2 has been studied for a long time. Dyson and Xuong classified non-strangeness dibaryon states based on SU(6) symmetries in 1960?s. In the framework, the deuteron is classified as one of the sextet states of dibaryons. Although dibaryon have been an interesting subject of research for a long time, most of the experimental studies up to the early 2000?s were unsuccessful. The CELCIUS/WASA collaboration reported this state via the double-pionic fusion reaction (?= ! 3c0c0) in 2009. Thereafter, the WASA-at-COSY collaboration revealed properties of the isoscaler resonance state via the ?= ! 3c0c0 reaction in 2011. The dibaryon resonance state with isospin ? = 0 and spin ( = 3 thought to be a ?03 which was predicted by Dyson and Xuong at 2.35 GeV?22 with a configuration of ??. The reported mass and width of that state were 2?37 GeV?22 and 0?07 GeV?22, espectively. The mass was ?0?08 GeV?22 smaller than that of 2?, the width was narrower than that of single ?. This surprising result made dibaryon study come back into the limelight. ?12 is one of the dibaryon states classified by Dyson and Xuong with isospin ? = 1, spin ( = 2. This state can be regarded as an s-wave #? resonance. ?12 is an interesting state from the point of view of the possibilities of existence as an internal structure of ?03 and contribution to many-body effects in nuclei. Though there were some experimental clues and theoretical studies of this state, it was unclear whether the obtained experimental results represented a real resonance or not due to the difficulty of separation from kinematical effects. Very recently, the FOREST group at Tohoku University reported a photoproduced isovector dibaryon state at mass of 2.14 GeV?22 in the 3c0 invariant mass spectra of the W3 ! 3c0c0 reaction. The most probable ?% configuration was 2¸ although they didn?t exclude the possibility of ?% = 1¸ or 3?. They separated the dibaryon production process from conventional pion production process for the first time using angular distribution of deuteron. We investigated the W3 ! 3c¸c? reaction for study of a possible #? dibaryon state using a deuterium target at the Research Center for Electron Photon Science, Tohoku University, Japan. In the experiment, ?3 ? 1012 tagged photon beam at energies ranging from 0.8 to 1.1 GeV was impinged to the liquid deuterium target (?520 mg?cm2) and the charged particles in the final state: deuteron, c¸, and c?, were detected by a magnetic spectrometer with a large solid angle named NKS2. NKS2 had capabilities of reconstructing momentum of charged particles, multi-track analysis, and ??c separation. We performed two different analyses named 2-track analysis and 3-track analysis. The 2-track (3-track) analysis was for events in which two (three) particles of 3c¸c? in the final state, including deuteron, were detected by NKS2. In the 3-track and 2-track analysis, ?2000? ?15000 events were identified as the W3 ! 3c¸c? reaction events, respectively. The 2-track analysis with higher statistics was mainly used to derive the cross sections, and the 3-track analysis was used to check the consistency of the 2-track analysis. In this thesis, we have shown the total cross section, the differential cross sections of the W3 ! 3c¸c? reaction in the region of jC j ¡ 0?15 GeV2. This is the world?s first measurement of this reaction in this energy region. Dibaryon resonance structures were observed below the #? threshold in the differential cross section of the invariant mass of 3c?. The mass and width of the structure were consistent with these of ?12 measured by the W3 ! 3c0c0 reaction. The mechanism of the production process was discussed based on the angular distribution of emitted deuteron.

Toyama, Yuichi↗
DOE OSTI2020

Damaged Fuel in the United States - 20325

Throughout the history of commercial nuclear power plant operations in the U.S., many fuel assemblies have lost the capability to perform all of their desired functions. Since they can no longer be handled, stored, or transported in accordance with established regulations, they are classified as damaged fuel. The causes of these failed assemblies are diverse and plant-specific. The majority of these failed assemblies are contained in damaged fuel cans to be used in conjunction with storage and/or transportation systems. These systems have a limited number of slots that can be filled with damaged fuel cans. A damaged fuel can is generally a stainless-steel container that confines damaged spent nuclear fuel (SNF) and is closed at one end by mesh endpoints that allow gaseous and liquid media to escape but minimize the dispersal of gross particulate material. Out of extreme caution, a few reactors have loaded high burnup fuel into damaged fuel cans. Damaged fuel is not licensed for storage or transport in the U.S. because relevant regulations do not specify exactly how to classify damaged fuel. Instead, these regulations license/certify packages that specify approved contents. Damaged fuel must be included among the approved contents to be considered acceptable. In many cases, damaged SNF is encapsulated in damaged fuel cans to ensure it can confine gross fuel particles, debris, and/or damaged assemblies to known volumes within loaded casks. A damaged fuel can may then be utilized in the same way as an assembly in a storage and transportation system. Some storage cask systems utilize top and bottom plugs to confine debris in damaged fuel. The most recent domestic documentation on damaged SNF was published by the U.S. Energy Information Administration (EIA), which used data from U.S. reactors compiled from 1968 to June 30, 2013, to produce Form GC-859, 'Nuclear Fuel Data Survey.' According to this form, there were 136,821 boiling water reactor (BWR) SNF assemblies and 104,647 pressurized water reactor (PWR) SNF assemblies, for a combined total of 241,468. Of these, 4,521 were classified as failed. Some were also disassembled and the fuel rods or pieces of fuel rods combined to make consolidated assemblies. These consolidated assemblies may include damaged fuel or were perhaps consolidated as part of a demonstration project. The GC-859 data includes 2,550 consolidated assemblies containing 0 - 264 entire fuel rods. These consolidated assemblies could be placed in single assembly canisters and stored in the spent fuel pool. For dry storage and transportation, a single assembly canister is generally placed in each damaged fuel can. In addition to the consolidated assemblies, 2,391 un-canistered fuel rod pieces exist, which were removed from 494 assemblies. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Physics-Based Machine Learning Methods for U-235 Forensics Signatures

Signatures of low-intensity U-235 sources have been recently studied by utilizing a variety of machine learning (ML) classifiers using features derived from gamma spectral measurements collectedunder structured campaigns. Several ML classifiers, such as ensemble of tress and classification trees, revealed misleadingly-optimistic training error due to over-fitting, and furthermore,their performance is not directly relatable to the physical properties due to their data-driven, opaque designs. We present a regression-based ML method that first estimates the inverse distanceto the source and then utilizes a threshold to infer its presence, by representing the background as a source located at an infinite distance. For the inverse distance estimation, we study the ensembleof trees and Gaussian process regression methods, and a hyper parameter auto-tuning and selection method that employs five regression estimators. These methods avoid the over-fittingobserved in several ML classifiers, while providing the classification error nearly comparable to them based on independent test data. Their error is directly related to estimates of the inversephysical distance to source, and the precision of error determines the seperability property that determines the false alarm and missed detection rates. The property of monotonic decrease of thesource strength with increasing detector distance combined with Poisson distribution of measurements is utilized to analytically validate these methods by deriving the generalization equations ofunderlying regression methods.

Rao, Nageswara↗