Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Analysis”

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 1,711 records · Page 95
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Data-driven selection and spectral classification of white dwarf stars

The next generation of spectroscopic surveys is expected to provide spectra for hundreds of thousands of white dwarf (WD) candidates in the upcoming years. Currently, spectroscopic classification of white dwarfs is mostly done by visual inspection, requiring substantial amounts of expert attention. We propose a data-driven pipeline for fast, automatic selection, and spectroscopic classification of WD candidates, trained using spectroscopically confirmed objects with available Gaia astrometry, photometry, and Sloan Digital Sky Survey (SDSS) spectra with signal-to-noise ratios ≥9. The pipeline selects WD candidates with improved accuracy and completeness over existing algorithms, classifies their primary spectroscopic type with ≥ 90 % accuracy, and spectroscopically detects main sequence companions with similar performance. We apply our pipeline to the Gaia Data Release 3 cross-matched with the SDSS Data Release 17 (DR17), identifying 424 096 high-confidence WD candidates and providing the first catalogue of automated and quantifiable classification for 36 523 WD spectra. Both the catalogue and pipeline are made available online. Such a tool will prove particularly useful for the undergoing SDSS-V survey, allowing for rapid classification of thousands of spectra at every data release.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Enhancement of Optical Efficiency of CSP Mirrors for Reducing O&M Cost via Near-Continuous Operation of Self-Cleaning Electrodynamic Screens (EDS). Final Report

Over the past decade, techno-economical advancements in solar energy systems, particularly the improvement in the conversion efficiency of PV modules made with mono-crystalline silicon solar cells from 12% to 20%, as well as the cost reduction in manufacturing by a factor of about 10%, have made it possible to achieve a levelized cost of electricity (LCOE) in PV plants that is comparable to, or less than, the cost of deriving electricity from fossil fuels. Operating PV plants in mid-latitude sun-belt regions, where the solar irradiance level is highest, provides a high annual energy-yield (kWh/kWp) due to two factors: (1) the availability of predictable high solar irradiance throughout the year with the fewest interruptions in solar flux from clouds and rain, and (2) the increased conversion efficiency of crystalline solar cells, as recombination loss has decreased with increased intensity of the sunlight that illuminates the silicon solar cells. Semi-arid and desert regions, however, are plagued by high atmospheric dust concentrations and frequent sand storms. The deposition of a layer of dust on the optical surfaces of solar collectors such as PV modules and concentrating mirrors reduces the transmission efficiency of sunlight that actually reaches the solar cells or receivers, resulting in high energy-yield soiling loss. There are two major cost components to operating a solar plant: (1) installation costs, and (2) operation-and-maintenance (O&M) costs. There is no fuel cost; hence operating a solar plant in a semi-arid or desert region provides high returns on investment if soiling losses are mitigated via efficient cleaning methods and optimized cleaning frequency. If solar collectors are not cleaned, the accumulation of dust layers on solar collectors may cause the operation of such plants in arid regions to become economically unviable. Washing solar collectors with water and detergent, as is most commonly done now, is an efficient method for cleaning. The conventional approach in utility-scale solar plants is to use a large truck with a water tank and pump system for spraying deionized water on the surface of the solar collectors. Robotic cleaning with brushes, used for many solar plants, requires lesser water for cleaning. The water consumed using semi-automated cleaning of PV modules in utility-scale solar plants is approximately 2 liters/m 2 per cleaning cycle. The total optical surface area of the solar collectors in 1 TW-scale solar installation will be more than 3 × 109 m 2 ; hence an enormous amount of water be needed for cleaning. There simply is not enough fresh water in the sun-belt areas of the world for predicted cleaning needs. In solar power plants, the estimated cost of cleaning solar collectors includes expenses related to the equipment used, labor, cost of transportation of water, the energy required for cleaning, plus ancillary costs whereas the cost of water is not considered. The water used is obtained from sources located close to plant sites, unmindful of the environmental and societal impact as the power plants are oftentimes located in regions that face severe drought. This practice is very similar to the cost calculations in deriving the levelized cost of electricity (LCOE) in conventional power plants based on burning fossil fuel such as coal and gas, while disregarding the cost of climate change and health effects. Unless a water-free or low-water cleaning method is established, the expansion of solar plants may lose public support in areas suffering long intervals of drought. The goal of this research project has been the development and application of the Electrodynamic Screen (EDS) as a means for a water-free, scalable cleaning process applicable to solar-power installations, including rooftop applications. We describe here the development of an EDS film-based cleaning process as an emerging method for use on PV modules, parabolic troughs, and heliostats. This report aims to show the feasibility of integrating or retrofitting EDS films onto the optical surfaces of solar collectors (both PV and CSP) while maintaining high transmission or reflection efficiency. The cleaning action provided by the EDS film is an active method to remove dust deposits by electrodynamic force. Current lab-scale prototype EDS films, retrofitted onto solar panels and mirrors, have shown to be capable of maintaining optical transmission or specular-reflection efficiencies higher than 90% of initial values under clean conditions. The optical surfaces of solar collectors laminated with EDS films can remove more than 90% of deposited dust when the EDS is activated for less than two minutes. As an electrodynamic dust removal process, the EDS film-based method is designed primarily for the removal of dust in solar installations located in semi-arid and desert areas, where the atmosphere is often dry and dusty and rainfall is infrequent. While EDS film application minimizes water consumption and facilitates cleaning as frequently as needed, it has limitations in removing contaminants such as soot, organic pollutants deposited as fine films on the surface, and bird droppings. The dust removal efficiency of the EDS is maximum at relative humidity RH is 40 to 50% and decreases at when RH > 65%. Many solar plant sites undergo diurnal and seasonal cycles of high ambient, early afternoon temperatures and an RH that reaches the dew point early in the morning. These variations in atmospheric conditions do not limit the operation of the EDS film. This report presents a brief review of the progress and the potential of EDS film technology for mitigating the impact of dust on solar collectors via water-free cleaning, as well as current technical challenges regarding efficiency and durability. Our experimental data on the performance of EDS films show that: (1) the dust-removal efficiency (DRE) can reach levels higher than 90%, (2) the specular reflectivity (SR) of EDS film-laminated second-surface mirrors reach levels in excess of 90%, (3) the specular reflectivity restoration (SRR) can exceed 90%, (4) the output-power restoration (OPR) of PV modules can exceed 95%, and (5) the optical transmission efficiency (TE) of the EDS films can be greater than 90%. Working with Sandia National Laboratories (NM), Corning Research and Development Corporation (NY), Eastman Kodak (NY), Tomark-Worthen Industries (NH), and EDS Chile SPA (Chile), we have produced EDS film-laminated PV modules and demonstrated their self-cleaning functions without requiring water. We have demonstrated that the operational range of EDS films will cover the expected ambient temperature of solar fields at RH cycling varying from 20 to 95% as long as the EDS films are activated in the RH range 20 to 50%. (Typical solar-field climates in deserts and semi-arid lands often reach near dew point in coastal areas.) Our experiments on the application of hydrophobic-fluorinated nanoparticle coatings on EDS film surfaces show that the EDS operational range can be extended to higher RH levels that approach the dew point. At Eastman Kodak, as one of our industrial partners, we were able to establish a process for manufacturing EDS films using flexographic printing of the electrodes onto transparent polymer films. This process utilizes an existing manufacturing line at Eastman Kodak that allows fabrication of medium-scale EDS films (26 cm × 30 cm). The manufacturing process has the capacity to produce EDS films at high production speeds. The medium-scale EDS films that have been printed at Kodak were evaluated in the lab at Boston University. The EDS films produced at Kodak were laminated at Tomark-Worthen using an industrial scale vacuum laminator to produce EDS film stacks, which can be affixed onto the optical surfaces of PV modules or concentrating mirrors. The EDS film stack consists of the EDS films that have Willow® Glass (WG) which has a thickness of 100 μm as the front surface. The WG sheets obtained from Corning Research and Development Corporation are customized in size and shape to cover the active area of the EDS films. The back surface of the EDS film stack is integrated onto the optical surface of the solar panel or mirror using optically clear adhesive (OCA) films or silicone adhesives. The OCA films (thickness 25 μm) are produced by 3M. The EDS film stacks have the architecture: WG/OCA/EDS Film/OCA/ over PV module or solar mirror. The power-supply units needed for activating the electrodes of the EDS film were designed and produced at Boston University. These power supply units provide three-phase, 1.2 kV voltage pulses at a very low current (micro-ampere) level and at a low frequency (≈ 5 Hz). The voltage pulses are applied to the electrodes in a sequence such that the train of pulses resembles a unidirectional traveling wave of electrical field on the surface of the EDS film. The dust particles on the surface become charged electrostatically and are levitated by the Coulomb force. The lateral sweeping action of the traveling electric field created by the three-phase voltages pulses then sweeps the dust off the surface. The energy consumed by the EDS electrodes is less than 0.2 Wh/m 2 /cleaning cycle, enabling energy-efficient restoration of output power (OPR) of PV module or specular reflectivity restoration (SRR) for solar mirrors. The EDS system consists of (1) an EDS film stack laminated onto the solar collectors, (2) connection of the EDS film to its power supply unit and (3) Interconnection of the power supply to PV modules or solar mirrors. Design, construction and assessment of field-testing units that have EDS stack laminated PV modules for evaluating the performance of the EDS films in solar fields is being carried out at BU. Our progress under this project, aimed at the advancement of EDS film technology, has reached DOE Technology Readiness Level (TRL) 6. Based on the extensive laboratory evaluations and limited field trials, as well as contacts with potential users, we believe that the technology has reached its commercial stage. We are conducting a cost analysis using the National Renewable Energy Laboratory (NREL) System Advisory Model (SAM) and are preparing for field trials of EDS films in different solar fields in the US, Chile, India and in the Middle East. A brief description of EDS film performance, construction and testing of the field-test unit, autonomous operation of the field-test unit for evaluating EDS performance in increasing energy yield, associated revenue savings, and water conservation is presented.

14 SOLAR ENERGY↗
DOE OSTI2025

Data‐Driven Insights into Rare Earth Mineralization: Machine Learning Applications Using Functional Material Synthesis Data

Understanding rare‐earth element (REE) mineralization mechanisms is essential for developing efficient separation strategies. Although the geochemical pathways that generate REE deposits are qualitatively known, quantitative links between specific conditions and mineralization outcomes remain limited. Herein, the repurpose laboratory REE hydrothermal synthesis data—originally collected for functional‐materials fabrication—as a surrogate for studying mineralization with data‐driven methods. The compiled 1,200+ hydrothermal reaction records and trained three machine‐learning models—K‐nearest neighbors (KNN), random forest (RF), and extreme gradient boosting (XGB)—to predict product elements and phases from precursors, additives, reaction conditions, and engineered features. Validation shows XGB achieves the highest accuracy. Feature importance indicates thermodynamic properties of cations and anions dominate model decisions. Correlations reveal positive relationships among precursor concentration, reaction time, pH, and temperature, consistent with classical crystallization behavior. XGB‐based regressors are built to predict crystallization temperature and pH from precursor/product attributes. Performance is strongest when similar training examples exist, while accuracy declines for underrepresented reactions, notably REE carbonates and heavy‐REE systems. Overall, the study shows that functional‐materials datasets can illuminate REE mineralization and provide priors for exploration and processing. Expanding datasets with less‐studied chemistries and conditions will improve generality and support deposit discovery and more efficient REE recovery.

feature importance analysis↗
DOE OSTI2025

Simplified Model and Approach to Transform Infrared Surface Temperature to Film Effectiveness in a Conjugate Heat Transfer Experiment

In the pursuit of more efficient gas turbines, film cooling is a critical technology. This article describes a simplified engineering model based on a one-dimensional thermal resistance network. The model is used to relate film-cooling effectiveness and heat transfer augmentation to local overall cooling effectiveness in a conjugate flat plate experiment. Here, this article presents experimental proof-of-concept data to demonstrate the potential for this model. In contrast to previous approaches, neither the wall heat flux nor the adiabatic wall temperature is required to estimate the local film-cooling performance parameters. The model predicts surface temperatures that are within the experimental uncertainties over the range for which the model is trained and to within five percent when the model is extrapolated to higher coolant channel Reynolds numbers. This article is relevant to conjugate test rigs that can measure the hot-surface temperature distribution with and without film cooling. This information may also be relevant to designers as a method to approximate surface temperatures or used as an approximate heat transfer model for optimization studies.

advanced turbines↗
DOE OSTI2023

AFRRI TRIGA Reactor Neutron and Gamma Dose Characterization Preliminary Results

Integral Experiment Request (IER) 484 is part of a series of dose characterization and nuclear accident dosimeter (NAD) exercises performed under the Department of Energy (DOE) Nuclear Criticality Safety Program (NCSP). The Armed Forces Radiobilogy Research Institute (AFRRI) 1.1 MW Training, Research, Isotopes, General Atomics (TRIGA) Mark-F reactor is the third facility to undergo a dose study to establish reference dose values. A preliminary measurement was performed earlier this year, where a variety of foils were irradiated and activation gamma rays were measured using a high-purity germanium (HPGe) detector. The data was taken and analyzed to calculate the neutron spectrum in the irradiation facility. This paper will present preliminary results of the neutron dose measured. The characterization of the AFRRI dose field is planned in August.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Ensemble Federated Machine Learning‐Based Cybersecurity Situational Awareness in Microgrid Network

Cyber-physical microgrids are vulnerable to stealthy cybersecurity threats that disguise their actions through the exploitation of system knowledge. Such actions can severely impacts microgrids deployed in defense bases, slowing the response time of military forces during national emergencies. Several machine-learning algorithms have been proposed to detect intrusions in the grid networks; however, these traditional machine-learning algorithms lack data privacy and are subject to several adversarial machine-learning threats. This paper proposes a novel federated machine learning (FML)-based three-model framework to detect and identify stealthy data-integrity attacks while ensuring data privacy in microgrid networks. The proposed architecture uses a variational mode decomposition technique to extract derived features from incoming measurement and control datasets. The extraction of these derived features allows FML models to learn minute variations in data patterns that allow them to perform significantly better than the models trained with generic datasets consisting of raw features. Our experimental results show the efficient performance of the proposed methodology against different types of data integrity attacks while considering primary and secondary controllers in microgrids. Further, the applied FML-integrated random forest ensemble algorithm outperforms the existing generic FML algorithms during noisy and noise-free datasets with prediction latencies of only 91–134 µs per sample within the 0.1 s sampling interval and requires communication bandwidth of around ∼8.25 KB/s at the control center and ∼2.7 KB/s per edge client for communication.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Do We Really Need All That Data: From Data to Agency in Automated Microscopy

Microscopy is entering an era of automated laboratories and AI-enabled instruments, often justified by a simple narrative of automating experiments to collect more data and train better models. In this work, we argue that, for microscopy, this framing is incomplete and can be counterproductive.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

DeepSZ: identification of Sunyaev–Zel’dovich galaxy clusters using deep learning

Galaxy clusters identified via the Sunyaev–Zel’dovich (SZ) effect are a key ingredient in multiwavelength cluster cosmology. In this paper, we present and compare three methods of cluster identification: the standard matched filter (MF) method in SZ cluster finding, a convolutional neural networks (CNN), and a ‘combined’ identifier. We apply the methods to simulated millimeter maps for several observing frequencies for a survey similar to SPT-3G, the third-generation camera for the South Pole Telescope. The MF requires image pre-processing to remove point sources and a model for the noise, while the CNN requires very little pre-processing of images. Additionally, the CNN requires tuning of hyperparameters in the model and takes cut-out images of the sky as input, identifying the cut-out as cluster-containing or not. We compare differences in purity and completeness. The MF signal-to-noise ratio depends on both mass and redshift. Our CNN, trained for a given mass threshold, captures a different set of clusters than the MF, some with signal-to-noise-ratio below the MF detection threshold. However, the CNN tends to mis-classify cut-out whose clusters are located near the edge of the cut-out, which can be mitigated with staggered cut-out. We leverage the complementarity of the two methods, combining the scores from each method for identification. The purity and completeness are both 0.61 for MF, and 0.59 and 0.61 for CNN. The combined method yields 0.60 and 0.77, a significant increase for completeness with a modest decrease in purity. We advocate for combined methods that increase the confidence of many low signal-to-noise clusters.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Ideas and perspectives: Enhancing research and monitoring of carbon pools and land-to-atmosphere greenhouse gases exchange in developing countries

Carbon (C) and greenhouse gas (GHG) research has traditionally required data collection and analysis using advanced and often expensive instruments, complex and proprietary software, and highly specialized research technicians. Partly as a result, relatively little C and GHG research has been conducted in resource-constrained developing countries. At the same time, these are often the same countries and regions in which climate change impacts will likely be strongest and in which major science uncertainties are centered, given the importance of dryland and tropical systems to the global C cycle. Increasingly, scientific communities have adopted appropriate technology and approach (AT&A) for C and GHG research, which focuses on low-cost and low-technology instruments, open-source software and data, and participatory and networking-based research approaches. Adopting AT&A can mean acquiring data with fewer technical constraints and lower economic burden and is thus a strategy for enhancing C and GHG research in developing countries. However, AT&A can have higher uncertainties; these can often be mitigated by carefully designing experiments, providing clear protocols for data collection, and monitoring and validating the quality of obtained data. For implementing this approach in developing countries, it is first necessary to recognize the scientific and moral importance of AT&A. At the same time, new AT&A techniques should be identified and further developed. All these processes should be promoted in collaboration with local researchers and through training local staff and encouraged for wide use and further innovation in developing countries.

Kim, Dong-Gill↗
DOE OSTI2022

Integrating very-high-resolution UAS data and airborne imaging spectroscopy to map the fractional composition of Arctic plant functional types in Western Alaska

Widespread changes in vegetation cover and composition are driving strong impacts on Arctic ecosystem functioning and global climate feedbacks. An accurate characterization of tundra vegetation composition is required to understand how the Arctic will respond to future climate change. However, quantifying tundra vegetation composition over large areas is challenging as commonly-used satellite observations are too coarse, spatially and spectrally, to differentiate low-lying tundra vegetation types. Recent airborne and spaceborne imaging spectroscopy platforms provide better data to characterize vegetation composition. Yet, our ability to characterize vegetation composition with imaging spectroscopy remains largely unexplored in the Arctic, particularly due to a lack of ground observations needed to train and test classification models. To address this problem, we collected very-high-resolution (VHR, ~5 cm) unoccupied aerial system (UAS) imagery at three low-Arctic tundra sites located on the Seward Peninsula, western Alaska. In this paper, we examine the feasibility of integrating imagery from the UAS and the hyperspectral Airborne Visible/Infrared Imaging Spectrometer, Next Generation (AVIRIS-NG) airborne instrument to map the fractional composition of 12 key Arctic plant functional types (PFTs). To this end, we first mapped the 12 PFTs from our VHR UAS imagery using random forest classification. We then used these UAS-derived PFT maps as ground truth to develop partial least squares regression (PLSR) models to predict the fractional cover (FCover) of each PFT from AVIRIS-NG imagery. Further, we evaluated the performance of our PLSR models using reserved UAS samples, as well as by mapping PFT FCover and dominant PFT for large tundra landscapes. Our results show that 1) Arctic PFTs can be effectively mapped using VHR UAS imagery, with overall accuracy between 86% and 92%, 2) when the UAS mapped PFTs were used to inform PLSR scaling models, the FCover of the 12 PFTs could be effectively estimated from AVIRIS-NG imagery with a mean absolute error (MAE) <0.13, and 3) our PLSR models outperformed traditional, fully constrained least-squares (FCLS) linear mixture analysis and produced high-quality, spatially contiguous PFT FCover and PFT maps that captured vegetation spatial patterns with similar accuracy to those developed from UAS imagery. The developed PLSR models have the potential to be broadly applied for quantifying vegetation composition with AVIRIS-NG images to help monitor tundra vegetation dynamics and improve process-based modeling of tundra ecosystems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Induced microearthquakes predict permeability creation in the brittle crust

Predicting the evolution of permeability accurately during stimulation at the reservoir scale and at the resolution of individual fractures is essential to characterize the fluid transport and the reactive/heat-transfer characteristics of reservoirs where stress exerts significant control. Here, we develop a hybrid machine learning (ML) model to visualize in situ permeability evolution for an intermediate-scale (~10 m) hydraulic stimulation experiment. This model includes an ML model that was trained using the well history of flow rate and wellhead pressure and MEQ data from the first three stimulation episodes to predict average permeability from the statistical features of the MEQs alone for later episodes. Moreover, a physics-inspired model is integrated to estimate in situ fracture permeability spatially. This method relates fracture permeability to fracture dilation and scales dilation to the equivalent MEQ magnitude, according to laboratory observations. The seismic data are then applied to define incremental changes in permeability in both space and time. Our results confirm the excellent agreement between the ground truth and model-predicted permeability evolution. The resulting permeability map defines and quantifies flow paths in the reservoir with the averaged permeability comparing favorably with the ground truth of permeability.

induced seismicity↗
DOE OSTI2021

AGR 5/6/7 Data Qualification Report for ATR Cycles 162B through 168A

This report provides the qualification status of experimental data for the Advanced Gas Reactor (AGR) 5/6/7 fuel irradiation. AGR-5/6/7 was conducted in the Advanced Test Reactor (ATR) at Idaho National Laboratory (INL) in support of development and qualification of tri-structural isotropic (TRISO) low-enriched fuel for use in high temperature gas-cooled reactors. The objectives of the AGR-5/6/7 experiments are to: (i) irradiate reference-design fuel particles to support fuel qualification, (ii) establish operating margins for the fuel beyond normal operating conditions, and (iii) provide irradiated-fuel performance data and irradiated-fuel samples for post-irradiation examination (PIE) and safety testing. The test train contains five separate capsules that were independently controlled and monitored. Each capsule contains multiple 12.51-mm-long compacts filled with low enriched uranium carbide/oxide (UCO) TRISO fuel particles. The primary objective of the AGR-5/6 test (Capsules 1, 2, 4, and 5) is to verify successful performance of the reference-design fuel under normal operating conditions. The AGR-7 test (Capsule 3) was designed to explore fuel performance at higher temperatures to demonstrate the capability of the fuel to withstand conditions beyond normal operating conditions in support of plant design and licensing. AGR 5/6/7 will also provide irradiated-fuel performance data on fission-gas release from failed particles during irradiation. The AGR-5/6/7 capsules were irradiated in the ATR northeast flux trap location. The experiment began on February 16, 2018 and ended on July 22, 2020, spanning nine ATR cycles over two and a half years. Thus, the AGR-5/6/7 fuel compacts were irradiated for a total of 360.9 effective full power days. The AGR 5/6/7 experiment was able to remain in the reactor core during all three Powered Axial Locator Mechanism (PALM) cycles (163A, 165A, and 167A) without overheating its fuel compacts. This report includes irradiation monitoring data from nine ATR Cycles: 162B, 163A, 164A, 164B, 165A, 166A, 166B, 167A, and 168A, as stored in the Nuclear Data Management and Analysis System (NDMAS). During irradiation, data records consisted of instantaneous measurements recorded every minute and provided by text files automatically every 2 hours. The AGR 5/6/7 data streams addressed in this report include thermocouple (TC) temperatures, sweep gas data (flow rates [capsule inlet, outlet, and downstream at detector], pressure, and moisture content), and Fission Product Monitoring System (FPMS) data (release rates and release to birth rate ratios [R/Bs]) for each of the five capsules. A total of 94,989,908 TC temperature and sweep gas data records were received and processed by NDMAS for AGR 5/6/7 irradiation. Of these records, 41,593,387 (or 43.7% of the total) met data collection and accuracy requirements and are labeled as Qualified. A total of 57,746,693 TC temperature readings were captured from 54 installed TCs. Among them, 10,034,676 TC temperature records (only 17.4%) were Qualified and 47,701,371 TC temperatures (or 82.6%) are Failed due to 48 TC failures (63.5%) and due to missing values (19.1%). To assess performance of the operational TCs, analysis of daily correlations between TCs found no evidence of virtual junction failure for any TCs. Analyses on control charts of TC temperature differences revealed trending in TC readings for TC2, 4, 5, and 13 in Capsule 3, but there is no conclusive indication of TC drift failure that caused those trends. Therefore, TC control charts are not used to disqualify TC data, but only for users’ consideration. For sweep gas flow rates, a total of 31,519,747 gas flow records (84.4%) are Qualified for use for AGR-5/6/7 experiment; 5,723,468 gas flow records (15.4%) are Failed due mostly to missing values; and 74,641 high sweep gas flow rates (0.2 %) are Trend. A large number of Failed missing TC temperature and gas flow values were caused by an error in the data output script that outputted a ‘NULL’ value when values were unchanged. This problem was fixed during the outage of Cycle 166B, which led to a substantially decreased number of missing values during the last three cycles. Nonetheless, a large amount of non-missing data remained because of the high data acquisition frequency (1-minute) and still provided sufficient data to effectively monitor the experiment as designed. For FPMS data, NDMAS received and processed fission product release and R/B data for nine ATR cycles, when ATR core reached full power during AGR 5/6/7 irradiation. These data consist of 110,388 release rate records and 110,388 R/B records for the twelve radionuclides (Kr 85m, Kr 87, Kr 88, Kr 89, Kr 90, Xe 131m, Xe 133, Xe 135, Xe 135m, Xe 137, Xe 138, and Xe 139) for each of the five capsules. Equivalent numbers of uncertainty records associated the release rates and R/B values were provided. To date, qualification status of the FPMS data stored in the NDMAS dat

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Photometric redshift-aided classification using ensemble learning

We present SHEEP, a new machine learning approach to the classic problem of astronomical source classification, which combines the outputs from the XGBoost, LightGBM, and CatBoost learning algorithms to create stronger classifiers. A novel step in our pipeline is that prior to performing the classification, SHEEP first estimates photometric redshifts, which are then placed into the data set as an additional feature for classification model training; this results in significant improvements in the subsequent classification performance. SHEEP contains two distinct classification methodologies: (i) Multi-class and (ii) one versus all with correction by a meta-learner. We demonstrate the performance of SHEEP for the classification of stars, galaxies, and quasars using a data set composed of SDSS and WISE photometry of 3.5 million astronomical sources. The resulting F1 -scores are as follows: 0.992 for galaxies; 0.967 for quasars; and 0.985 for stars. In terms of the F1-scores for the three classes, SHEEP is found to outperform a recent RandomForest-based classification approach using an essentially identical data set. Our methodology also facilitates model and data set explainability via feature importances; it also allows the selection of sources whose uncertain classifications may make them interesting sources for follow-up observations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗
DOE OSTI2025

Direct NeTS sampling of nuclear graphite $S(α, β, T)$ in Serpent

For advanced reactor applications, Neural Thermal Scattering (NeTS) modules were developed to predict the thermal scattering law (TSL or $S(α, β, T)$) of a nuclear graphite neutron moderator. NeTS are multi-layer, feedforward artificial neural networks, which act as universal function approximators designed for TSL datasets. In this case, a 4-layer neural network with 164 neurons per layer is trained using FLASSH evaluated data in PyTorch and serialized as a torchscript dictionary to predict $S(α, β, T)$ on-the-fly. Relative, absolute and maximum percent deviations of NeTS from File 7 data generated using the FLASSH code are on the order of 0.01%, 0.1% and 1%, respectively, with low inference latencies of 0.000172 s per $S(α, β, T)$ at a given temperature. Capturing the full dimensionality of possible inelastic neutron-lattice interactions, NeTS functionality is embedded in the Serpent Monte Carlo code, where $S(α, β, T)_{NeTS}$ sampling is conducted on-the-fly and compared to ACE look-up-tables for predicting TREAT criticality. k-eff differences between sampling algorithms of 6 pcm are observed and are within the order of Monte Carlo uncertainty. Compared to discrete and continuous-energy ACE files (30 MB and 131 MB per temperature), the NeTS format is on the order of 200–300 kB for a continuous-temperature, interpolation-free representation of $S(α, β, T)$ and cross sections. NeTS-in-Serpent runtimes comparable with ACE look-up tables are achieved by scaling NeTS for high performance computing architectures with hybrid OpenMP + MPI parallelization. This work validates a novel, self-contained reactor physics framework for predictive cross sections, and demonstrates a general methodology for embedding modern machine learning libraries within existing neutronic analysis frameworks.

Nuclear Criticality Safety Program (NCSP)↗
DOE OSTI2025

Deployment of neural-network-based neutron microscopic cross sections in the Griffin reactor physics application

The capability to utilize neural networks to predict macroscopic and microscopic cross section parametric spaces has been developed for the Griffin reactor physics application. The LibTorch interface enables Griffin's MOOSE-based materials to interact with LibTorch-trained models, allowing for the evaluation of complex macroscopic or microscopic cross section spaces, which are then used to evaluate the neutronic properties of the Griffin finite element model. This study benchmarks traditional ISOXML-formatted tabulation libraries against neural network-based models for 279 nuclides on 20,160 grid points for zero-dimensional and two-dimensional reactor models. Benchmark metrics include the fundamental mode eigenvalue, fission and absorption rates, and various temperature coefficients of reactivity (isothermal, fuel, and moderator). From the perspective of storage space, the complete set of LibTorch models uses 11 MB on disk, compared to the 10 GB for the ISOXML multigroup library that covers the same grid space. For the two-dimensional performance case considered in Griffin, the Torch model uses 97% less RAM than the reference ISOXML dataset while runtime increases by a factor of 3 when using the LibTorch model compared to the ISOXML dataset with multi-linear interpolation. The LibTorch model consistently yields errors within 0.01% for most analyzed quantities except for the temperature coefficients of reactivity where the maximum discrepancies are up to 0.3 $\frac{pcm}{K}$. Due to the neural network attempting to best predict quantities with no regard for a positive or negative bias for any given quantity, predictions may experience random fluctuations, resulting in both positive and negative errors. Future work will entail both depletion and coupled transient analysis to determine the predictive capabilities of Griffin with neural network-based cross sections.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Emission line predictions for mock galaxy catalogues: a new differentiable and empirical mapping from DESI

ABSTRACT We present a simple, differentiable method for predicting emission line strengths from rest-frame optical continua using an empirically determined mapping. Extensive work has been done to develop mock galaxy catalogues that include robust predictions for galaxy photometry, but reliably predicting the strengths of emission lines has remained challenging. Our new mapping is a simple neural network implemented using the JAX Python automatic differentiation library. It is trained on Dark Energy Spectroscopic Instrument Early Release data to predict the equivalent widths (EWs) of the eight brightest optical emission lines (including H α, H β, [O ii], and [O iii]) from a galaxy’s rest-frame optical continuum. The predicted EW distributions are consistent with the observed ones when noise is accounted for, and we find Spearman’s rank correlation coefficient ρs > 0.87 between predictions and observations for most lines. Using a non-linear dimensionality reduction technique, we show that this is true for galaxies across the full range of observed spectral energy distributions. In addition, we find that adding measurement uncertainties to the predicted line strengths is essential for reproducing the distribution of observed line-ratios in the BPT diagram. Our trained network can easily be incorporated into a differentiable stellar population synthesis pipeline without hindering differentiability or scalability with GPUs. A synthetic catalogue generated with such a pipeline can be used to characterize and account for biases in the spectroscopic training sets used for training and calibration of photo-z’s, improving the modelling of systematic incompleteness for the Rubin Observatory LSST and other surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Important Human Actions for Advanced Reactors: Implications for Human Factors

As advanced reactor platforms continue to develop and gain traction in the energy sector there is a need for risk-informed, scalable regulations that match that progress. This is a core component of the U.S. Nuclear Regulatory Commission’s proposed Part 53 Rule Making; the Accelerating Deployment of Versatile, Advanced Nuclear for Clean Energy (ADVANCE) Act; and other efforts that seek to update nuclear power regulations. This paper covers one key aspect of that regulatory evolution: Important Human Actions (IHA). In this paper, we discuss how the understanding and definitions of IHAs have changed and what that means for human factors engagement through the process of developing these technologies. Instead of a narrow focus on control actions that led to an increase in core damage risk, the new focus is on IHAs is “wherever they occur.” What this means is that having a highly automated or passive safety system does not eliminate IHAs. Rather, it shifts the focus point to all the actions that enable these systems. Everything from maintenance, to design, to training can be considered an IHA and that dramatically shifts the efforts and level of engagement necessary for human factors to enable these technologies. We discuss the notions of risk-informed human factors that underpin these efforts, give several examples, and briefly describe the risk assessment methodologies that will be needed. In the past, IHAs were identified and then became a focus point of human factors engineering (HFE) activities to ensure a robust evaluation of the task was completed. The future is less clear. HFE for nuclear energy will need to evolve and become more integrated in technology development than ever before.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗