SEARCH · Search NASA

Results for “statistical visualization”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 487 records · Page 27

All sources NASA NTRS DOE OSTI

DOE OSTI2014

MAVTgsa: An R Package for Gene Set (Enrichment) Analysis

Gene set analysis methods aim to determine whether an a priori defined set of genes shows statistically significant difference in expression on either categorical or continuous outcomes. Although many methods for gene set analysis have been proposed, a systematic analysis tool for identification of different types of gene set significance modules has not been developed previously. This work presents an R package, called MAVTgsa, which includes three different methods for integrated gene set enrichment analysis. (1) The one-sided OLS (ordinary least squares) test detects coordinated changes of genes in gene set in one direction, either up- or downregulation. (2) The two-sided MANOVA (multivariate analysis variance) detects changes both up- and downregulation for studying two or more experimental conditions. (3) A random forests-based procedure is to identify gene sets that can accurately predict samples from different experimental conditions or are associated with the continuous phenotypes. MAVTgsa computes the P values and FDR (false discovery rate) q -value for all gene sets in the study. Furthermore, MAVTgsa provides several visualization outputs to support and interpret the enrichment results. This package is available online.

Chien, Chih-Yi↗

DOE OSTI2016

Baselining PMU Data to Find Patterns and Anomalies

This paper looks at the application of situational awareness methodologies with respect to power grid data. These methodologies establish baselines that look for typical patterns and atypical behavior in the data. The objectives of the baselining analyses are to provide: real-time analytics, the capability to look at historical trends and events, and reliable predictions of the near future state of the grid. Multivariate algorithms were created to establish normal baseline behavior and then score each moment in time according to its variance from the baseline. Detailed multivariate analytical techniques are described in this paper that produced ways to identify typical patterns and atypical behavior. In this case, atypical behavior is behavior that is unenvisioned. Visualizations were also produced to help explain the behavior that was identified mathematically. Examples are shown to help describe how to read and interpret the analyses and visualizations. Preliminary work has been performed on PMU data sets from BPA (Bonneville Power Administration) and EI (Eastern Interconnect). Actual results are not fully shown here because of confidentiality issues. Comparisons between atypical events found mathematically and actual events showed that many of the actual events are also atypical events; however there are many atypical events that do not correlate to any actual events. Additional work needs to be done to help classify the atypical events into actual events, so that the importance of the events can be better understood.

Baselining analyses↗

DOE OSTI2015

Use of XRF to characterize pre-Hanford orchards in the 100-OL-1 operable unit - 15717

Prior to 1943, Hanford site included several small towns with approximately 5,000 acres of orchards; at the time lead arsenate (PbHAsO{sub 4}) was the most commonly used pesticide. High concentration of lead and arsenic have been recorded where trees and stumps are still visible. Pre-Hanford orchards have been designated as 100-OL-1 Operable Unit. An Optimization study evaluated optimal counting time and position of the XRF from soils collected at the site. A Pilot Study included the evaluation of a field portable x-ray fluorescence (XRF) analyzer determining if performance results meet quality assurance criteria for cleanup. XRF has only previously been used as a screening tool. Four Decision Units (DUs) are to be analyzed: Ol-14. OL-32. OL-IU6-4 and OL-FR2-1. The DUs vary in size and have had distinct historic activities; such as 46.4 acres OL-14 having a military camp in the 1950's unlike OL-FR2-1 having been disturbed as it is near the F area reactor. Together the DUs provide an adequate representation of the Operable Unit. Screening criteria for lead (250 mg/kg) and arsenic (20 mg/kg). Six samples were collected ranging above, at, and below the screening criteria of 250 mg/kg for Pb and 20 mg/kg for As at the Decision Units OL-14 and OL-IU6-4, and labeled respectively. Samples were hand sieved, homogenized and placed in sample cups. Three replicates were prepared for each sample. Each sample cup was analyzed 3 times for 30 sec. A Standard Reference Material (SRM) was analyzed after every 20 readings. Three samples were selected for 15, 30, 45, 60, 90, 120, 150 and 180 second fixed and variable analysis. Two transects at OL-14, and one at OL-IU6-4 were created by selecting locations 90. around ground zero at distances of 0.5, 1, 2, 4, 8 and 12 feet (16 ft for OL-14). Locations were scanned in triplicate for 60 seconds each. 4 Decision Units spanning roughly 370 acres were chosen to represent 100-OL-1 Operable Unit. 40 locations within each DU were selected using Visual Sample Plan (VSP) with a random start and systematic grid pattern. Each location would be analyzed with 3 replicates and a 60 second count time. The Standard Reference Material (SRM) and blank are analyzed after every 20 counts to ensure accuracy. Data is extracted from XRF to be implemented in GIS for visual representation of site with 1943 and 2013 aerial imagery. Discussion/Conclusion: - XRF provided a good indication of precision and accuracy relative to ICP with a linear correlation R{sup 2} value higher than anticipated at .9735; - MDL proved the detection limit is significantly lower than the screening criteria; - When comparing results from the first 40 locations of OL-14 to the total 80 locations of OL-14, the same variability was seen; - We expect high concentrations of Pb and As to be where past orchards are present though this does not occur as all sites. Significance: - XRF is competent for decision making as values fall within ±20% ICP data; - The highest concentrations are not where expected, which may be an issue for sites outside of Hanford that have had more development; - The size of the DU does not affect the number of samples measured. Future Work: - Verification and validation of the XRF Data (QA/QC); - Revise conceptual site model; - Statistical evaluations to investigate: Estimation of variability in surface soils, appropriate size for DU, and sample size per DU; - Coordinating sample results through CORE; - Displaying sample results in PHOENIX (GIS tool)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2017

Novel Super-Resolution Approach to Time-Resolved Volumetric 4-Dimensional Magnetic Resonance Imaging With High Spatiotemporal Resolution for Multi-Breathing Cycle Motion Assessment

Purpose: To develop and evaluate a super-resolution approach to reconstruct time-resolved 4-dimensional magnetic resonance imaging (TR-4DMRI) with a high spatiotemporal resolution for multi-breathing cycle motion assessment. Methods and Materials: A super-resolution approach was developed to combine fast 3-dimensional (3D) cine MRI with low resolution during free breathing (FB) and high-resolution 3D static MRI during breath hold (BH) using deformable image registration. A T1-weighted, turbo field echo sequence, coronal 3D cine acquisition, partial Fourier approximation, and SENSitivity Encoding parallel acceleration were used. The same MRI pulse sequence, field of view, and acceleration techniques were applied in both FB and BH acquisitions; the intensity-based Demons deformable image registration method was used. Under an institutional review board–approved protocol, 7 volunteers were studied with 3D cine FB scan (voxel size: 5 × 5 × 5 mm{sup 3}) at 2 Hz for 40 seconds and a 3D static BH scan (2 × 2 × 2 mm{sup 3}). To examine the image fidelity of 3D cine and super-resolution TR-4DMRI, a mobile gel phantom with multi-internal targets was scanned at 3 speeds and compared with the 3D static image. Image similarity among 3D cine, 4DMRI, and 3D static was evaluated visually using difference image and quantitatively using voxel intensity correlation and Dice index (phantom only). Multi-breathing-cycle waveforms were extracted and compared in both phantom and volunteer images using the 3D cine as the references. Results: Mild imaging artifacts were found in the 3D cine and TR-4DMRI of the mobile gel phantom with a Dice index of >0.95. Among 7 volunteers, the super-resolution TR-4DMRI yielded high voxel-intensity correlation (0.92 ± 0.05) and low voxel-intensity difference (<0.05). The detected motion differences between TR-4DMRI and 3D cine were −0.2 ± 0.5 mm (phantom) and −0.2 ± 1.9 mm (diaphragms). Conclusion: Super-resolution TR-4DMRI has been reconstructed with adequate temporal (2 Hz) and spatial (2 × 2 × 2 mm{sup 3}) resolutions. Further TR-4DMRI characterization and improvement are necessary before clinical applications. Multi-breathing cycles can be examined, providing patient-specific breathing irregularities and motion statistics for future 4D radiation therapy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2022

Evaluation of artificial neural network performance for classification of potato plants infected with potato virus Y using spectral data on multiple varieties and genotypes

Potato virus Y (Potyviridae, PVY) is a plant virus that poses a significant threat to potato producers on a global basis. The pathogen has disrupted seed potato supplies and negatively impacted yield and quality of commercial potato crops. The potato industry currently manages PVY infection levels via insecticide applications, regional seed certification programs that rely on field scouting to visually assess individual plants for infection status, and destructive and costly tissue sampling coupled with laboratory assays. Despite these efforts, PVY continues to confound potato industry stakeholders resulting in economic harm. Remote sensing and machine learning provide for the development of new tools to more accurately detect and spatially quantify PVY-infected plants versus the current state of the art. However, there is a need to understand how the occurrence of many different potato varieties impact the dynamics of developing models to detect potato plants impacted with PVY and their potential effectiveness. This study evaluates classification modelling outcomes using spectral datasets collected in different temporal and spatial environments (greenhouse and a production field) on multiple potato varieties consisting of labelled instances of plants infected with PVY and those not infected with the virus. A modelling framework was developed to support iterative modelling runs using artificial neural network (ANN) architectures configured as binary classifiers to develop sample populations to support statistical analysis on model performance using specific spectral subsets. When using spectral data to detect PVY-infected plants, ANN models achieved the highest mean accuracy of 0.894 on a single variety. Conversely, the same ANN model architecture only achieved a mean accuracy of 0.575 on a spectral data set representing 29 potato breeding lines. Additionally, statistical analysis indicates spectral regions including the red edge, near infrared and shortwave infrared contain more important spectral features for the ANN classifier introduced in this research.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

OpenET: Filling a Critical Data Gap in Water Management for the Western United States

The lack of consistent, accurate information on evapotranspiration (ET) and consumptive use of water by irrigated agriculture is one of the most important data gaps for water managers in the western United States (U.S.) and other arid agricultural regions globally. The ability to easily access information on ET is central to improving water budgets across the West, advancing the use of data-driven irrigation management strategies, and expanding incentive-driven conservation programs. Recent advances in remote sensing of ET have led to the development of multiple approaches for field-scale ET mapping that have been used for local and regional water resource management applications by U.S. state and federal agencies. The OpenET project is a community-driven effort that is building upon these advances to develop an operational system for generating and distributing ET data at a field scale using an ensemble of six well-established satellite-based approaches for mapping ET. Key objectives of OpenET include: Increasing access to remotely sensed ET data through a web-based data explorer and data services; supporting the use of ET data for a range of water resource management applications; and development of use cases and training resources for agricultural producers and water resource managers. Here we describe the OpenET framework, including the models used in the ensemble, the satellite, meteorological, and ancillary data inputs to the system, and the OpenET data visualization and access tools. We also summarize an extensive intercomparison and accuracy assessment conducted using ground measurements of ET from 139 flux tower sites instrumented with open path eddy covariance systems. Results calculated for 24 cropland sites from Phase I of the intercomparison and accuracy assessment demonstrate strong agreement between the satellite-driven ET models and the flux tower ET data. For the six models that have been evaluated to date (ALEXI/DisALEXI, eeMETRIC, geeSEBAL, PT-JPL, SIMS, and SSEBop) and the ensemble mean, the weighted average mean absolute error (MAE) values across all sites range from 13.6 to 21.6 mm/month at a monthly timestep, and 0.74 to 1.07 mm/day at a daily timestep. At seasonal time scales, for all but one of the models the weighted mean total ET is within ±8% of both the ensemble mean and the weighted mean total ET calculated from the flux tower data. Overall, the ensemble mean performs as well as any individual model across nearly all accuracy statistics for croplands, though some individual models may perform better for specific sites and regions. We conclude with three brief use cases to illustrate current applications and benefits of increased access to ET data, and discuss key lessons learned from the development of OpenET.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Bridging the Gap between Cosmological Simulations with Graph Neural Networks and Domain Adaptation

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross dataset tasks (up to 28% better relative error and up to almost an order of magnitude better χ 2 ). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2017

Visualization of dynamic fiber-matrix interfacial shear debonding

To visualize the debonding event in real time for the study of dynamic crack initiation and propagation at the fiber–matrix interface, a modified tension Kolsky bar was integrated with a high-speed synchrotron X-ray phase-contrast imaging setup. In the gage section, the pull-out configuration was utilized to understand the behavior of interfacial debonding between SC-15 epoxy matrix and S-2 glass fiber, tungsten wire, steel wire, and carbon fiber composite Z-pin at pull-out velocities of 2.5 and 5.0 m s –1 . The load history and images of the debonding progression were simultaneously recorded. Both S-2 glass fiber and Z-pin experienced catastrophic interfacial debonding whereas tungsten and steel wire experienced both catastrophic debonding and stick–slip behavior. Even though S-2 glass fiber and Z-pin samples exhibited a slight increase and tungsten and steel wire samples exhibited a slight decrease in average peak force and average interfacial shear stress as the pull-out velocities were increased, no statistical difference was found for most properties when the velocity was increased. Furthermore, the debonding behavior for each fiber material is similar with increasing pull-out velocity. Thus, the debonding mechanism, peak force, and interfacial shear stress were rate insensitive as the pull-out velocity doubled from 2.5 to 5.0 m s –1 . In conclusion, scanning electron microscope imaging of recovered epoxy beads revealed a snap-back behavior around the meniscus region of the bead for S-2 glass, tungsten, and steel fiber materials at 5.0 m s –1 whereas those at 2.5 m s –1 exhibited no snap-back behavior.

36 MATERIALS SCIENCE↗

DOE OSTI2024

The persistence of memory in ionic conduction probed by nonlinear optics

Predicting practical rates of transport in condensed phases enables the rational design of materials, devices and processes. This is especially critical to developing low-carbon energy technologies such as rechargeable batteries. For ionic conduction, the collective mechanisms, variation of conductivity with timescales and confinement, and ambiguity in the phononic origin of translation, call for a direct probe of the fundamental steps of ionic diffusion: ion hops. However, such hops are rare-event large-amplitude translations, and are challenging to excite and detect. Here we use single-cycle terahertz pumps to impulsively trigger ionic hopping in battery solid electrolytes. This is visualized by an induced transient birefringence, enabling direct probing of anisotropy in ionic hopping on the picosecond timescale. The relaxation of the transient signal measures the decay of orientational memory, and the production of entropy in diffusion. We extend experimental results using in silico transient birefringence to identify vibrational attempt frequencies for ion hopping. Using nonlinear optical methods, we probe ion transport at its fastest limit, distinguish correlated conduction mechanisms from a true random walk at the atomic scale, and demonstrate the connection between activated transport and the thermodynamics of information.

25 ENERGY STORAGE↗

DOE OSTI2026

The 2025 Evaluation of Experimental Thermonuclear Reaction Rates (ETR25)

This work describes the formalism for estimating thermonuclear reaction rates for astrophysical applications, emphasizing modern statistical approaches such as Monte Carlo sampling and Bayesian models. We discuss related topics including the calculation of resonance energies from nuclear Q values, indirect estimates of particle partial widths, and matching of reaction rates at elevated temperatures to statistical model results. We have evaluated available experimental data on cross sections, resonance energies and strengths, partial widths, lifetimes, spin-parities, and spectroscopic factors. Based on these results, we have estimated numerical values of 78 experimental charged-particle thermonuclear reaction rates for target nuclei in the A = 2–40 mass region, for temperatures ranging from 1 MK to 10 GK. For each reaction, three rate values are provided: low, median, and high, corresponding to the 16th, 50th, and 84th percentiles, respectively, of the cumulative reaction rate probability density distribution. Additionally, we present the factor uncertainty of each rate at each temperature grid point. These results enable users to sample the reaction rate probability density in nucleosynthesis calculations, facilitating uncertainty estimates of nuclidic abundances. The rates presented here refer to their laboratory values. For use in stellar model simulations, these values need to be corrected for the effects of thermal excitations of the interacting nuclei. For each reaction, we include graphs that illustrate the fractional contributions to the overall reaction rate along with the associated uncertainty. These visuals are designed to assist both stellar modelers and nuclear experimentalists by identifying the primary sources of rate uncertain=^texttx);ty at specific stellar temperatures. A graphical comparison with earlier Monte Carlo rates is also provided.

Nuclear astrophysics↗

DOE OSTI2022

Demonstrating the viability of Lagrangian in situ reduction on supercomputers

Performing exploratory analysis and visualization of large-scale time-varying computational science applications is challenging due to inaccuracies that arise from under-resolved data. In recent years, Lagrangian representations of the vector field computed using in situ processing are being increasingly researched and have emerged as a potential solution to enable exploration. However, prior works have offered limited estimates of the encumbrance on the simulation code as they consider “theoretical” in situ environments. Further, the effectiveness of this approach varies based on the nature of the vector field, benefitting from an in-depth investigation for each application area. With this study, an extended version of Sane et al. (2021), we contribute an evaluation of Lagrangian analysis viability and efficacy for simulation codes executing at scale on a supercomputer. We investigated previously unexplored cosmology and seismology applications as well as conducted a performance benchmarking study by using a hydrodynamics mini-application targeting exascale computing. Here, to inform encumbrance, we integrated in situ infrastructure with simulation codes, and evaluated Lagrangian in situ reduction in representative homogeneous and heterogeneous HPC environments. To inform post hoc accuracy, we conducted a statistical analysis across a range of spatiotemporal configurations as well as a qualitative evaluation. Additionally, our study contributes cost estimates for distributed-memory post hoc reconstruction. In all, we demonstrate viability for each application — data reduction to less than 1% of the total data via Lagrangian representations, while maintaining accurate reconstruction and requiring under 10% of total execution time in over 90% of our experiments.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Machine learning to discover mineral trapping signatures due to CO 2 injection

Mineral trapping is pursued as a geological CO 2 sequestration (GCS) mechanism because it permanently stores CO 2 in solid phases or minerals. However, CO 2 mineral-trapping mechanisms are poorly understood due to (1) lack of sufficient field and laboratory data characterizing these complex processes, and (2) challenges to develop site-specific reactive-transport models coupling fluid flow and geochemical reactions occurring at various temporal (from milliseconds to years) and spatial (from pore (millimeters) to field (kilometers)) scales. Reactive transport with additional complexities such as heterogeneity can make the simulation outputs even more difficult to interpret because of complex nonlinearity and multi-scale interdependencies. Furthermore, the values of model outputs such as concentrations can vary by several orders of magnitude, making it harder to correlate and characterize the impact of the variables via traditional data interpretation techniques such as exploratory data analyses. Recently, machine learning (ML) has shown promise in feature discovery and in highlighting hidden mechanisms that cannot be obtained by existing data-analytics and statistical methods. In this study, we applied an unsupervised ML approach, non-negative matrix factorization with custom -means clustering (NMF) to the data generated by reactive-transport simulations of GCS. The reactive-transport data consisted of 19 attributes, including four physio-chemical variables (pH, porosity, aqueous CO 2 , and sequestered CO 2 ), six chemical species (K + , Na + , HCO, Ca 2+ , Mg 2+ , Fe 2+ ), and four carbonate minerals (calcite, dolomite, siderite, and ankerite), a feldspar mineral (albite), and four clay minerals (illite, clinochlore, kaolinite, and smectite) over a period of 200 years of simulation time. Furthermore, the simulation data used was for Morrow B sandstone at the Farnsworth hydrocarbon unit in Texas. Data are sampled at two locations within the model domain: (1) at the injection well and (2) 200 m west of the injection well. The injection was performed for a period of 10 years. Using NMF, we estimated the temporal interdependencies among the 19 attributes over a span of 200 years. We found that NMF was able to identify four reaction stages and their dominant attributes; these cannot be directly discerned through traditional visualization (e.g., line plots, Pareto analysis, Glyph-based visualization methods) or exploratory data analysis tools of the simulation data. The four stages were: reactions in the injection phase followed by short-, mid-, and long-term reactions. The NMF analysis also revealed that 10 among the 19 attributes are dominant. These dominant attributes for mineral trapping include calcite, dolomite at injection well, siderite at 200 m away from the injection well, clinochlore, kaolinite, Na + , K + , Ca 2+ , Mg 2+ , pH, and aqeuous CO 2 . Finally, at late times (65–200 years), our results showed that calcite plays a major role in mineral trapping with insignificant contribution from siderite, ankerite, and clay minerals. These findings make the proposed unsupervised ML-model attractive for reactive-transport sensing towards real-time GCS monitoring.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Discovering invariant spatial features in electron energy loss spectroscopy images on the mesoscopic and atomic levels

Over the last two decades, Electron Energy Loss Spectroscopy (EELS) imaging with a scanning transmission electron microscope has emerged as a technique of choice for visualizing complex chemical, electronic, plasmonic, and phononic phenomena in complex materials and structures. The availability of the EELS data necessitates the development of methods to analyze multidimensional data sets with complex spatial and energy structures. Traditionally, the analysis of these data sets has been based on analysis of individual spectra, one at a time, whereas the spatial structure and correlations between individual spatial pixels containing the relevant information of the physics of underpinning processes have generally been ignored and analyzed only via the visualization as 2D maps. Here, we develop a machine learning-based approach and workflows for the analysis of spatial structures in 3D EELS data sets using a combination of dimensionality reduction and multichannel rotationally invariant variational autoencoders. This approach is illustrated for the analysis of both the plasmonic phenomena in a system of nanowires and in the core excitations in functional oxides using low loss and core-loss EELS, respectively. The code developed in this manuscript is open sourced and freely available and provided as a Jupyter notebook for the interested reader.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Deep learning for in situ data compression of large turbulent flow simulations

As the size of turbulent flow simulations continues to grow, in situ data compression is becoming increasingly important for visualization, analysis, and restart checkpointing. For these applications, single-pass compression techniques with low computational and communication overhead are crucial. In this paper we present a deep-learning approach to in situ compression using an autoencoder architecture that is customized for three-dimensional turbulent flows and is well suited for contemporary heterogeneous computing resources. The autoencoder is compared against a recently introduced randomized single-pass singular value decomposition (SVD) for three different canonical turbulent flows: decaying homogeneous isotropic turbulence, a Taylor-Green vortex, and turbulent channel flow. Our proposed fully convolutional autoencoder architecture compresses turbulent flow snapshots by a factor of 64 with a single pass, allows for arbitrarily sized input fields, is cheaper to compute than the randomized single-pass SVD for typical simulation sizes, performs well on unseen flow configurations, and has been made publicly available. The results reported here show that the autoencoder dramatically outperforms a randomized single-pass SVD with similar compression ratio and yields comparable performance to a higher-rank decomposition with an order of magnitude less compression in regard to preserving a number of important statistical quantities such as turbulent kinetic energy, enstrophy, and Reynolds stresses.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

AEflow (Autoencoder fluid flow compression network) [SWR-22-29]

King, Ryan↗

DOE OSTI2020

An Applied Strategy for Using Empirical and Hybrid Models in Online Monitoring

The monitoring of plant equipment for failure prediction is one of the key contributors to operation and maintenance (O&M) costs for a nuclear power plant (NPP) because O&M monitoring depends on labor-intensive activities that are required to meet high equipment reliability standards. These activities rely primarily on humans for information gathering, condition diagnosis, and predictive analysis. Online monitoring aims to automate these activities by relying on sensors to replace human information gathering and machine learning to replace human analysis and decision making. To facilitate automated monitoring, a systematic strategy for anomaly detection is needed to optimally use the available sensor data, empirical models, and physics-supported models. This strategy is essential to provide credible reasoning on why and when an empirical (i.e., purely data-driven) versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. The extant methods usually adopt an ad hoc trial-and-error approach that, in addition to being time-consuming and costly, is also highly subjective; it is impacted by the background and the skill set of the personnel making the decisions. Thus, such an approach cannot guarantee an optimum outcome. This represents the motivation of the current research effort, which is focused on devising a scientifically supported strategy for the optimum selection of anomaly detection methods. This report presents a detailed assessment of the main anomaly detection techniques within the empirical or hybrid method streams. Empirical methods include pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The listed techniques within these two streams represent the vast majority of techniques performed for anomaly detection. Using the techniques as outcomes, a strategy was developed to enable a systematic decision-making process to lead to one of these techniques. The strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability and suitability for training and testing, cause-effect, entropy inference, and model fitting. Each of these decision points in the strategy is explained in detail in this report with examples, along with the scientific basis behind the decisions and outcomes in common and simplified terminology. The strategy is developed for use by any NPP staff with basic engineering or science knowledge. A user-friendly graphical state flow diagram was also developed as a visual presentation of the strategy. The strategy was tested and demonstrated through two pilot projects for the application of anomaly detection at an NPP. Each pilot had two use cases: an initial case in which certain decisions were made that resulted in one or more empirical techniques and a revised use case where one or more key decisions were modified resulting in using a set of hybrid methods.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

Classification of Cloud Particle Imagery and Thermodynamics (COCPIT): A New Databasing Tool for the Characterization of Cloud Particle Images Captured During DOE Field Campaigns

The Department of Energy for decades has explored the earth system and atmosphere through research and deployment of in-situ and remote sensing platforms during field campaigns. Among these datasets exists a vast supply of cloud particle images that provide visual insight into the complex microphysics in the clouds that span our globe. The millions of images collected over decades of deployments provides a unique opportunity to further our understanding of our atmosphere down to the crystal size. This work over the past 5 years has sought to organize these images into digestible datasets that can then be used by scientists to further our understanding of microphysics. A machine learning model was developed that categorizes over 1.5 million images across 11 weather events with over 90% accuracy according to particle type. The database was then extended to include dimensional characteristics of the particle as well as co-location of environmental properties, such as temperature and water content. Then, to initialize the connection between these data and our understanding of how crystals form and grow, weather research and forecasting simulations were run to generate the growth histories of the classified crystals. This research culminates with 2 databases per event: (1) a database of all classified crystals and their dimensional and environmental properties and (2) simulated growth histories of each crystal. Finally, a user interface was created to allow researchers to explore data statistics.

54 ENVIRONMENTAL SCIENCES↗