Search NASA⌕ Search

SEARCH · Search NASA

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 577 records · Page 32

A novel computer-aided lung nodule detection system for CT images

Purpose: The paper presents a complete computer-aided detection (CAD) system for the detection of lung nodules in computed tomography images. A new mixed feature selection and classification methodology is applied for the first time on a difficult medical image analysis problem. Methods: The CAD system was trained and tested on images from the publicly available Lung Image Database Consortium (LIDC) on the National Cancer Institute website. The detection stage of the system consists of a nodule segmentation method based on nodule and vessel enhancement filters and a computed divergence feature to locate the centers of the nodule clusters. In the subsequent classification stage, invariant features, defined on a gauge coordinates system, are used to differentiate between real nodules and some forms of blood vessels that are easily generating false positive detections. The performance of the novel feature-selective classifier based on genetic algorithms and artificial neural networks (ANNs) is compared with that of two other established classifiers, namely, support vector machines (SVMs) and fixed-topology neural networks. A set of 235 randomly selected cases from the LIDC database was used to train the CAD system. The system has been tested on 125 independent cases from the LIDC database. Results: The overall performance of the fixed-topology ANN classifier slightly exceeds that of the other classifiers, provided the number of internal ANN nodes is chosen well. Making educated guesses about the number of internal ANN nodes is not needed in the new feature-selective classifier, and therefore this classifier remains interesting due to its flexibility and adaptability to the complexity of the classification problem to be solved. Our fixed-topology ANN classifier with 11 hidden nodes reaches a detection sensitivity of 87.5% with an average of four false positives per scan, for nodules with diameter greater than or equal to 3 mm. Analysis of the false positive items reveals that a considerable proportion (18%) of them are smaller nodules, less than 3 mm in diameter. Conclusions: A complete CAD system incorporating novel features is presented, and its performance with three separate classifiers is compared and analyzed. The overall performance of our CAD system equipped with any of the three classifiers is well with respect to other methods described in literature.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models

Modern machine learning and autonomous experimentation schemes in materials science rely on accurate analysis of the data ingested by these models. Unfortunately, accurate analysis of the underlying data can be difficult, even for domain experts, complicating the training of the models intended to drive experiments. This is especially true when the goal is to identify the presence of weak signatures in diffraction or spectroscopic datasets. In this work, we examine a set of as-obtained diffraction data that track the phase transition from monoclinic to tetragonal in a Nb-doped VO2 film as a function of temperature and dopant concentration. We then task a set of domain experts and a set of machine learning experts with identifying which phase is present in each diffraction pattern manually and algorithmically, respectively; in both cases, the labels can vary dramatically, especially at the phase boundaries. We use the mode of the labels and the Shannon entropy as a method to capture, preserve and propagate consensus labels and their variance. Further we use the expert labels as a benchmark and demonstrate the use of Shannon entropy weighted scoring to test the performance of machine learning generated labels. Finally, we propose a material data challenge centered around generating improved labeling algorithms. This real-world dataset curated with expert labels can act as test bed for new algorithms. The raw data, annotations and code used in this study are all available online at data.gov and the interested reader is encouraged to replicate and improve the existing models

97 MATHEMATICS AND COMPUTING↗

S AP F LOWER : an automated tool for sap flow data preprocessing, gap-filling, and analysis using deep learning

Sap flow, a critical process in plant water use and ecosystem water cycles, is often measured using thermal dissipation probes (TDP) due to their ease of installation and continuous data collection. However, sap flow data frequently include noise, outliers, and gaps, creating challenges for analysis and requiring substantial manual processing. We developed S AP F LOWER , a tool that automates data preprocessing, model training, gap-filling, sapwood area scaling and modeling, and water use analysis. It integrates autocleaning, machine learning and deep learning models (e.g. random forest, Gaussian process regression, long short-term memory (LSTM), bidirectional LSTM (BiLSTM)), and efficient workflows to process sap flow data. S AP F LOWER can remove over 90% of noisy data while preserving legitimate variations and achieve high accuracy in gap-filling based on user-determined parameters. Random forest, LSTM, and BiLSTM models reduced root mean square error to 10% or less for long-term gaps. Model training and prediction can be performed efficiently within seconds. S AP F LOWER significantly enhances the efficiency and accessibility of TDP data analysis by automating complex tasks, enabling researchers without programming expertise to employ advanced techniques. Future improvements will focus on species-specific corrections for TDP and support for additional measurement methods. S AP F LOWER is openly available on GitHub (https://github.com/JiaxinWang123/SapFlower) and Zenodo (doi: 10.5281/zenodo.13665919).

ecosystem water balance↗

Evaluation of a segment-based LANDSAT full-frame approach to corp area estimation

As the registration of LANDSAT full frames enters the realm of current technology, sampling methods should be examined which utilize other than the segment data used for LACIE. The effect of separating the functions of sampling for training and sampling for area estimation. The frame selected for analysis was acquired over north central Iowa on August 9, 1978. A stratification of he full-frame was defined. Training data came from segments within the frame. Two classification and estimation procedures were compared: statistics developed on one segment were used to classify that segment, and pooled statistics from the segments were used to classify a systematic sample of pixels. Comparisons to USDA/ESCS estimates illustrate that the full-frame sampling approach can provide accurate and precise area estimates.

Bauer, M. E.↗

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

Purpose: To first demonstrate the viability of applying an image processing technique for tracking regions on low-contrast cine-MR images acquired during image-guided radiation therapy, and then outline a scheme that uses tracking data for optimizing gating results in a patient-specific manner. Methods: A first-generation MR-IGRT system—treating patients since January 2014—integrates a 0.35 T MR scanner into an annular gantry consisting of three independent Co-60 sources. Obtaining adequate frame rates for capturing relevant patient motion across large fields-of-view currently requires coarse in-plane spatial resolution. This study initially (1) investigate the feasibility of rapidly tracking dense pixel correspondences across single, sagittal plane images (with both moderate signal-to-noise and spatial resolution) using a matching objective for highly descriptive vectors called scale-invariant feature transform (SIFT) descriptors associated to all pixels that describe intensity gradients in local regions around each pixel. To more accurately track features, (2) harmonic analysis was then applied to all pixel trajectories within a region-of-interest across a short training period. In particular, the procedure adjusts the motion of outlying trajectories whose relative spectral power within a frequency bandwidth consistent with respiration (or another form of periodic motion) does not exceed a threshold value that is manually specified following the training period. To evaluate the tracking reliability after applying this correction, conventional metrics—including Dice similarity coefficients (DSCs), mean tracking errors (MTEs), and Hausdorff distances (HD)—were used to compare target segmentations obtained via tracking to manually delineated segmentations. Upon confirming the viability of this descriptor-based procedure for reliably tracking features, the study (3) outlines a scheme for optimizing gating parameters—including relative target position and a tolerable margin about this position—derived from a probability density function that is constructed using tracking results obtained just prior to treatment. Results: The feasibility of applying the matching objective for SIFT descriptors toward pixel-by-pixel tracking on cine-MR acquisitions was first retrospectively demonstrated for 19 treatments (spanning various sites). Both with and without motion correction based on harmonic analysis, sub-pixel MTEs were obtained. A mean DSC value spanning all patients of 0.916 ± 0.001 was obtained without motion correction, with DSC values exceeding 0.85 for all patients considered. While most patients show accurate tracking without motion correction, harmonic analysis does yield substantial gain in accuracy (defined using HDs) for three particularly challenging subjects. An application of tracking toward a gating optimization procedure was then demonstrated that should allow a physician to balance beam-on time and tissue sparing in a patient-specific manner by tuning several intuitive parameters. Conclusions: Tracking results show high fidelity in assessing intrafractional motion observed on cine-MR acquisitions. Incorporating harmonic analysis during a training period improves the robustness of the tracking for challenging targets. The concomitant gating optimization procedure should allow for physicians to quantitatively assess gating effectiveness quickly just prior to treatment in a patient-specific manner.

61 RADIATION PROTECTION AND DOSIMETRY↗

PlasmoData.jl — A Julia framework for modeling and analyzing complex data as graphs

Datasets encountered in scientific and engineering applications appear in complex formats (e.g., images, multivariate time series, molecules, video, text strings, networks). Graph theory provides a unifying framework to model such datasets and enables the use of powerful tools that can help analyze, visualize, and extract value from data. In this work, we present PlasmoData.jl, an open-source, Julia framework that uses concepts of graph theory to facilitate the modeling and analysis of complex datasets. The core of our framework is a general data modeling abstraction, which we call a DataGraph. We show how the abstraction and software implementation can be used to represent diverse data objects as graphs and to enable the use of tools from topology, graph theory, and machine learning (e.g., graph neural networks) to conduct a variety of tasks. We illustrate the versatility of the framework by using real datasets: (i) an image classification problem using topological data analysis to extract features from the graph model to train machine learning models; (ii) a disease outbreak problem where we model multivariate time series as graphs to detect abnormal events; and (iii) a technology pathway analysis problem where we highlight how we can use graphs to navigate connectivity. Further, our discussion also highlights how PlasmoData.jl leverages native Julia capabilities to enable compact syntax, scalable computations, and interfaces with diverse packages. Overall, we show that the DataGraph abstraction and PlasmoData.jl Julia package are able to model data within graphs and enable useful analysis.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Clinical Outcome Metrics for Optimization of Robust Training

Introduction: The emphasis of this research is on the Human Research Program (HRP) Exploration Medical Capability's (ExMC) "Risk of Unacceptable Health and Mission Outcomes Due to Limitations of In-Flight Medical Capabilities." Specifically, this project aims to contribute to the closure of gap ExMC 2.02: We do not know how the inclusion of a physician crew medical officer quantitatively impacts clinical outcomes during exploration missions. The experiments are specifically designed to address clinical outcome differences between physician and non-physician cohorts in both near-term and longer-term (mission impacting) outcomes. Methods: Medical simulations will systematically compare success of individual diagnostic and therapeutic procedure simulations performed by physician and non-physician crew medical officer (CMO) analogs using clearly defined short-term (individual procedure) outcome metrics. In the subsequent step of the project, the procedure simulation outcomes will be used as input to a modified version of the NASA Integrated Medical Model (IMM) to analyze the effect of the outcome (degree of success) of individual procedures (including successful, imperfectly performed, and failed procedures) on overall long-term clinical outcomes and the consequent mission impacts. The procedures to be simulated are endotracheal intubation, fundoscopic examination, kidney/urinary ultrasound, ultrasound-guided intravenous catheter insertion, and a differential diagnosis exercise. Multiple assessment techniques will be used, centered on medical procedure simulation studies occurring at 3, 6, and 12 months after initial training (as depicted in the following flow diagram of the experiment design). Discussion: Analysis of procedure outcomes in the physician and non-physician groups and their subsets (tested at different elapsed times post training) will allow the team to 1) define differences between physician and non-physician CMOs in terms of both procedure performance (pre-IMM analysis) and overall mitigation of the mission medical impact (IMM analysis); 2) refine the procedure outcome and clinical outcome metrics themselves; 3) refine or develop innovative medical training products and solutions to maximize CMO performance; and 4) validate the methods and products of this experiment for operational use in the planning, execution, and quality assurance of the CMO training process The team has finalized training protocols and developed a software training/testing tool in collaboration with Butler Graphics (Detroit, MI). In addition to the "hands on" medical procedure modules, the software includes a differential diagnosis exercise (limited clinical decision support tool) to evaluate the diagnostic skills of participants. Human subject testing will occur over the next year.

Ebert, D.↗

Water Flow Testing and Unsteady Pressure Analysis of a Two-Bladed Liquid Oxidizer Pump Inducer

The unsteady fluid dynamic performance of a cavitating two-bladed oxidizer turbopump inducer was characterized through sub-scale water flow testing. While testing a novel inlet duct design that included a cavitation suppression groove, unusual high-frequency pressure oscillations were observed. With potential implications for inducer blade loads, these high-frequency components were analyzed extensively in order to understand their origins and impacts to blade loading. Water flow testing provides a technique to determine pump performance without the costs and hazards associated with handling cryogenic propellants. Water has a similar density and Reynolds number to liquid oxygen. In a 70%-scale water flow test, the inducer-only pump performance was evaluated. Over a range of flow rates, the pump inlet pressure was gradually reduced, causing the flow to cavitate near the pump inducer. A nominal, smooth inducer inlet was tested, followed by an inlet duct with a circumferential groove designed to suppress cavitation. A subsequent 52%-scale water flow test in another facility evaluated the combined inducer-impeller pump performance. With the nominal inlet design, the inducer showed traditional cavitation and surge characteristics. Significant bearing loads were created by large side loads on the inducer during synchronous cavitation. The grooved inlet successfully mitigated these loads by greatly reducing synchronous cavitation, however high-frequency pressure oscillations were observed over a range of frequencies. Analytical signal processing techniques showed these oscillations to be created by a rotating, multi-celled train of pressure pulses, and subsequent CFD analysis suggested that such pulses could be created by the interaction of rotating inducer blades with fluid trapped in a cavitation suppression groove. Despite their relatively low amplitude, these high-frequency pressure oscillations posed a design concern due to their sensitivity to flow conditions and test scale. The amplitude and frequency of oscillations varied considerably over the pump s operating space, making it difficult to predict blade loads.

Schwarz, Jordan B.↗

COUPLING OF RELAP5-SCDAP MOD4.0 AND NEUTRONIC CODES

High-fidelity and accurate nuclear system codes play a key role in the design and analysis of complex nuclear power plants, which consist of multiple subsystems, such as the reactor core (and its fuel, burnable poisons, control elements, etc.), the reactor internal structures, the vessel, and the energy conversion subsystem and beyond to grid demand. Most commonly the interplay between these various subsystems is modeled using coupled codes, each of which represents one of the subsystems. And the most common direct coupling is that of thermal-hydraulics and neutronics codes. The subject of this paper is the coupling of codes that model not only thermal-hydraulics and neutronics, but also structural components damage. Furthermore, the neutronic component is not limited to the sole core solver. The coupled code system encompasses thermal-hydraulics, material performance of the fuel, neutronic solver, and neutronic data preparation. Thus, this paper presents a framework for coupling RELAP5/SCDAPSIM/MOD4.0 with a suite of neutron kinetics codes that includes NESTLE, DRAGON and a version of the ENDF library. The version of the RELAP5/SCDAPSIM/MOD4.0 code used in this work is one developed by Innovate System Software (ISS) as part of the international SCDAP Development and Training Program (SDTP) for best-estimate analysis to model reactor transients including severe accident phenomena. This RELAP5/SCDAPSIM/MOD4.0 code version is also capable of predicting nuclear fuel performance. It uses nodal power distributions to calculate mechanical and thermal parameters such as heat-up, oxidation and meltdown of fuel rods and control rods, the ballooning and rupture of fuel rod cladding, the release of fission products from fuel rods, and the disintegration of fuel rods into porous debris and molten material. On the neutronics side, this work uses the NESTLE and DRAGON codes. NESTLE is a multi-dimensional static and kinetic neutronic code developed at North Carolina State University. It solves up to four energy groups neutron diffusion equations utilizing the Nodal Expansion Method (NEM) in Cartesian or hexagonal geometry. The DRAGON code, developed at Ecole Polytechnique de Montreal, performs lattice physics calculations based on the neutron transport equation and is capable of using very fine energy group structures. In this work, we have developed a coupling approach to exchange data among the various modules. In the coupling process, the generated nuclear data (in fine multigroup energy structure) are collapsed down into two- or four-group energy structures for use in NESTLE. The neutron kinetics and thermal-hydraulics modules are coupled at each time step by using the cross-section data. The power distribution results of the neutronic calculations are transmitted to the thermal-hydraulics code. The spatial distribution of coolant density and the fuel-moderator temperature, which result from the thermal-hydraulic calculations, are transmitted back to the neutron kinetics codes and then the loop is closed using new neutronics results. Details of the actual data transfers will be described in the full length paper.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Recent Test Results of the High Field Nb3Sn Dipole Magnet HD2

The 1 m long Nb{sub 3}Sn dipole magnet HD2, fabricated and tested at Lawrence Berkeley National Laboratory, represents a step towards the development of block-type accelerator quality magnets operating in the range of 13-15 T. The magnet design features two coil modules composed of two layers wound around a titanium-alloy pole. The layer 1 pole includes a round cutout to provide room for a bore tube with a clear aperture of 36 mm. After a first series of tests where HD2 reached a maximum bore field of 13.8 T, corresponding to an estimated peak field on the conductor of 14.5 T, the magnet was disassembled and reloaded without the bore tube and with a clear aperture increased to 43 mm. We describe in this paper the magnet training observed in two consecutive tests after the removal of the bore tube, with a comparison of the quench performance with respect to the previous tests. An analysis of the voltage signals recorded before and after training quenches is then presented and discussed, and the results of coil visual inspections reported.

43 PARTICLE ACCELERATORS↗

A computer aided treatment event recognition system in radiation therapy

Purpose: To develop an automated system to safeguard radiation therapy treatments by analyzing electronic treatment records and reporting treatment events. Methods: CATERS (Computer Aided Treatment Event Recognition System) was developed to detect treatment events by retrieving and analyzing electronic treatment records. CATERS is designed to make the treatment monitoring process more efficient by automating the search of the electronic record for possible deviations from physician's intention, such as logical inconsistencies as well as aberrant treatment parameters (e.g., beam energy, dose, table position, prescription change, treatment overrides, etc). Over a 5 month period (July 2012–November 2012), physicists were assisted by the CATERS software in conducting normal weekly chart checks with the aims of (a) determining the relative frequency of particular events in the authors’ clinic and (b) incorporating these checks into the CATERS. During this study period, 491 patients were treated at the University of Iowa Hospitals and Clinics for a total of 7692 fractions. Results: All treatment records from the 5 month analysis period were evaluated using all the checks incorporated into CATERS after the training period. About 553 events were detected as being exceptions, although none of them had significant dosimetric impact on patient treatments. These events included every known event type that was discovered during the trial period. A frequency analysis of the events showed that the top three types of detected events were couch position override (3.2%), extra cone beam imaging (1.85%), and significant couch position deviation (1.31%). The significant couch deviation is defined as the number of treatments where couch vertical exceeded two times standard deviation of all couch verticals, or couch lateral/longitudinal exceeded three times standard deviation of all couch laterals and longitudinals. On average, the application takes about 1 s per patient when executed on either a desktop computer or a mobile device. Conclusions: CATERS offers an effective tool to detect and report treatment events. Automation and rapid processing enables electronic record interrogation daily, alerting the medical physicist of deviations potentially days prior to performing weekly check. The output of CATERS could also be utilized as an important input to failure mode and effects analysis.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

The overview in safety review of human factors engineering and control room design in chinese AP1000 nuclear power plant - 174

The first AP1000 nuclear power plant is constructed in Sanmen county in Zhejiang Province in China, which has creative and distinctive design characteristics. Human factors engineering disciplines are applied to the design of the AP1000. In addition to the elements of the program review model(including human factors engineering program management, operating experience review, functional requirements analysis and allocation, task analysis, staffing, integration of human reliability analysis with human factors engineering, human system interface design, procedure development, training program development, human system interface verification and validation, design implementation, human performance monitoring),the minimum inventory of controls, displays, and alarms present in the main control room and at the remote shutdown workstation. These contents mentioned above are reviewed according to standards, rules and regulations. This article introduces review process, and several important issues during the reviewing are described in detail. These issues include many elements, such as operating experience review, task analysis, human system interface design, verification and validation,and so on. This paper emphasizes on the main control room design(including environment and layout). Background noise in the actual main control room may exceed too much to design value. Another important issue is about main control room habitability systems(VES) changes to satisfy post-actuation performance requirements in AP1000 design change proposal. All the wall panel displays will be closed in this design change proposal. Review process and proposal are described in the paper. Since the AP1000 unit in China is the first constructed all over the world, verification and validation are especially important and necessary. The plan of verification and validation, the results summary report of verification and validation, the report of human engineering discrepancies are focus attention. Verification and validation in human factors engineering include HSI task support verification, HFE design verification and integrated system validation. This paper introduces the review process of verification and validation, the issues found in verification and validation. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding

Over the last decade, scanning transmission electron microscopy (STEM) has emerged as a powerful tool for probing atomic structures of complex materials with picometer precision, opening the pathway toward exploring ferroelectric, ferroelastic, and chemical phenomena on the atomic scale. Analyses to date extracting a polarization signal from lattice coupled distortions in STEM imaging rely on discovery of atomic positions from intensity maxima/minima and subsequent calculation of polarization and other order parameter fields from the atomic displacements. Here, we explore the feasibility of polarization mapping directly from the analysis of STEM images using deep convolutional neural networks (DCNNs). In this approach, the DCNN is trained on the labeled part of the image (i.e., for human labelling), and the trained network is subsequently applied to other images. We explore the effects of the choice of the descriptors (centered on atomic columns and grid-based), the effects of observational bias, and whether the network trained on one composition can be applied to a different one. This analysis demonstrates the tremendous potential of the DCNN for the analysis of high-resolution STEM imaging and spectral data and highlights the associated limitations.

36 MATERIALS SCIENCE↗

How does increasing horizontal resolution in a global climate model improve the simulation of aerosol-cloud interactions?

The Community Atmosphere Model Version 5 is run at horizontal grid spacing of 2, 1, 0.5, and 0.25 degrees, with the meteorology nudged towards the Year Of Tropical Convection analysis, and cloud simulators and the collocated A-Train satellite observations are used to explore the resolution dependence of aerosol-cloud interactions. The higher-resolution model produces results that agree better with observations, showing an increase of susceptibility of cloud droplet size, indicating a stronger first aerosol indirect forcing (AIF), and a decrease of susceptibility of precipitation probability, suggesting a weaker second AIF. The resolution sensitivities of AIF are attributed to those of droplet nucleation and precipitation parameterizations. The annual average AIF in the northern hemisphere mid-latitudes (where most anthropogenic emissions occur) in the 0.25° model is reduced by about 1 W m⁻² (-30%) compared to the 2° model, leading to a 0.26 W m⁻² reduction (-15%) in the global annual average AIF.

Ma, Po -Lun↗

Microcomputer-based digital image processing - A tutorial package for exploration geologists

An Apple II microcomputer-based software package for analysis of digital data developed at the University of Oklahoma, the Digital Image Analysis System (DIAS), provides a relatively low-cost, portable alternative to large, dedicated minicomputers for digital image processing education. Digital processing techniques for analysis of Landsat MSS data and a series of tutorial exercises for exploration geologists are described and evaluated. DIAS allows in-house training that does not interfere with computer-based prospect analysis objectives.

Harrington, J. A., Jr.↗

Monitoring the Mesoamerican Biological Corridor: A NASA/CCAD Cooperative Research Project

To foster scientific cooperation under a Memorandum of Understanding between NASA and the Central American countries, the research project developed regional databases to monitor forest condition and environmental change throughout the region. Of particular interest is the Mesoamerican Biological Corridor (MBC), a chain of protected areas and proposed conservation areas that will link segments of natural habitats in Central America from the borders of northern Columbia to southern Mexico. The first and second year of the project focused on the development of regional satellite databases (JERS-IC, MODIS, and Landsat-TM), training of Central American cooperators and forest cover and change analysis. The three regional satellite mosaics were developed and distributed on CD-ROM to cooperators and regional outlets. Four regional remote sensing training courses were conducted in 3 countries including participants from all 7 Central American countries and Mexico. In year 3, regional forest change assessment in reference to Mesoamerican Biological Corridor was completed and land cover maps (from Landsat TM) were developed for 7 Landsat scenes and accuracy assessed. These maps are being used to support validation of MODIS forest/non forest maps and to examine forest fragmentation and forest cover change in selected study sites. A no-cost time extension (2003-2004) allowed the completion of an M.S. thesis by a Costa Rican student and preparation of manuscripts for future submission to peer-reviewed outlets. Proposals initiated at the end of the project have generated external funding from the U.S. Forest Service (to U. Maine), NASA-ESSF (Oregon State U.) and from USAID and EPA (to NASA-MSFC-GHCC) to test MODIS capabilities to detect forest change; conduct literature review on biomass estimation and carbon stocks and develop a regional remote sensing monitoring center in Central America. The success of the project has led to continued cooperation between NASA, other federal agencies, and scientists from all seven Central American Countries (see SERVIR web site for this ongoing work - servir.nsstc.nasa.gov).

Sever, Thomas↗

Moving image analysis to the cloud: A case study with a genome-scale tomographic study

Over the last decade, the time required to measure a terabyte of microscopic imaging data has gone from years to minutes. This shift has moved many of the challenges away from experimental design and measurement to scalable storage, organization, and analysis. As many scientists and scientific institutions lack training and competencies in these areas, major bottlenecks have arisen and led to substantial delays and gaps between measurement, understanding, and dissemination. We present in this paper a framework for analyzing large 3D datasets using cloud-based computational and storage resources. We demonstrate its applicability by showing the setup and costs associated with the analysis of a genome-scale study of bone microstructure. We then evaluate the relative advantages and disadvantages associated with local versus cloud infrastructures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗