Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 1,225 records · Page 68

Geometrical-Based Generative Adversarial Network to Enhance Digital Rock Image Quality

X-ray microcomputed tomography (micro-CT) is a common tool for the study of porous media structures and properties. High-quality micro-CT data are required to accurately capture pore structures. Acquiring high-quality micro-CT data, however, is not always possible, owing to application limitations and experimental constraints. Therefore, we propose a geometrical-based generative adversarial network (GAN) to rapidly restore noisy micro-CT images to their clean counterparts. The training data and related ground-truth (GT) data are scanned for 7 min and 9.5 h, respectively. To evaluate the performance of the geometrical-based GAN, a 6003 voxel image that has never been used for training is reconstructed and compared with the corresponding GT image. Histogram matching and linear normalization are implemented to adjust the histogram of the reconstructed image to that of the GT image. A watershed-based segmentation method is then applied to delineate pore and solid phases. Lastly, we measure the Minkowski functionals and petrophysical properties, including absolute permeability, pore size distribution, drainage capillary pressure-saturation curve, and imbibition relative permeability, to estimate the physical accuracy of the denoised image. The results show that the proposed geometrical-based GAN can accurately restore noisy micro-CT data. By reducing the scanning time from 9.5 h to 7 min, the expenditure of collecting micro-CT can be decreased significantly. This is particularly important for applications where time-lapse images of a dynamic process are required, high-throughput imaging is necessary for real-time data analysis, or where the quantification of large sample volumes is required.

58 GEOSCIENCES↗

SourceFinder: a Machine-Learning-Based Tool for Identification of Chromosomal, Plasmid, and Bacteriophage Sequences from Assemblies

High-throughput genome sequencing technologies enable the investigation of complex genetic interactions, including the horizontal gene transfer of plasmids and bacteriophages. However, identifying these elements from assembled reads remains challenging due to genome sequence plasticity and the difficulty in assembling complete sequences. In this study, we developed a classifier, using random forest, to identify whether sequences originated from bacterial chromosomes, plasmids, or bacteriophages. The classifier was trained on a diverse collection of 23,211 chromosomal, plasmid, and bacteriophage sequences from hundreds of bacterial species. In order to adapt the classifier to incomplete sequences, each complete sequence was subsampled into 5,000 nucleotide fragments and further subdivided into k-mers. This three-class classifier succeeded in identifying chromosomes, plasmids, and bacteriophages using k-mer distributions of complete and partial genome sequences, including simulated metagenomic scaffolds with minimum performance of 0.939 area under the receiver operating characteristic curve (AUC). This classifier, implemented as SourceFinder, has been made available as an online web service to help the community with predicting the chromosomal, plasmid, and bacteriophage sources of assembled bacterial sequence data (https://cge.food.dtu.dk/services/SourceFinder/).

59 BASIC BIOLOGICAL SCIENCES↗

Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models

One of the most promising devices for realizing power production through nuclear fusion is the tokamak. To maximize performance, it is preferable that tokamak reactors achieve advanced operating scenarios characterized by good plasma confinement, improved magnetohydrodynamic (MHD) stability, and a largely non-inductively driven plasma current. Such scenarios could enable steady-state reactor operation with high \emph{fusion gain} --- the ratio of produced fusion power to the external power provided through the plasma boundary. Precise and robust control of the evolution of the plasma boundary shape as well as the spatial distribution of the plasma current, density, temperature, and rotation will be essential to achieving and maintaining such scenarios. The complexity of the evolution of tokamak plasmas, arising due to nonlinearities and coupling between various parameters, motivates the use of model-based control algorithms that can account for the system dynamics. In this work, a learning-based accelerated model trained on data from the National Spherical Torus Experiment Upgrade (NSTX-U) is employed to develop planning and control strategies for regulating the density and temperature profile evolution around desired trajectories. The proposed model combines empirical scaling laws developed across multiple devices with neural networks trained on empirical data from NSTX-U and a database of first-principles-based computationally intensive simulations. The reduced execution time of the accelerated model will enable practical application of optimization algorithms and reinforcement learning approaches for scenario planning and control development. An initial demonstration of applying optimization approaches to the learning-based model is presented, including a strategy for mitigating the effect of leaving the finite validity range of the accelerated model. The approach shows promise for actuator planning between experiments and in real-time.

machine learning↗

Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94]

Accurate energy forecasting is becoming critical due to many reasons: i ) optimal distributed energy resources operations and dispatch, ii) fault detection and diagnostics, and iii) meeting operational energy efficiency targets. Wattile uses deep learning (DL) for the building's short-term load forecasting application. Two specific types of neural networks called, Long Short Term Memory (LSTM) and Sequence-to-Sequence (S2S) models are used to make predictions. Forecasting models are trained using online historical weather and occupancy indicator data streams from the Intelligent Campus Program's data acquisition systems at the National Renewable Energy Laboratory (NREL) for main meters and sub-meters of multiple building types. These models use probabilistic methods to provide quantile-based forecasts in addition to nominal conditional median predictions of electricity consumption.

Frank, Stephen↗

Wind Energy Fundamentals for the Bangladesh Financial Sector [Slides]

Financial institutions in Bangladesh play an important role in accelerating the deployment of wind energy. The country's central bank, the Bangladesh Bank, has been a pioneer in developing green banking initiatives. This training seeks to provide the Bangladesh Bank and other stakeholders in the Bangladesh financial sector with fundamental knowledge about wind energy so that they can support its growth in the country.

17 WIND ENERGY↗

Estimation of Citation-Based Scholarly Activity Among Radiation Oncology Faculty at Domestic Residency-Training Institutions: 1996-2007

Purpose: Advancement in academic radiation oncology is largely contingent on research productivity and the perceived external influence of an individual's scholarly work. The purpose of this study was to use the Hirsch index (h-index) to estimate the research productivity of current radiation oncology faculty at U.S. academic institutions between 1996 and 2007. Methods and Materials: We performed bibliometric citation database searches for available radiation oncology faculty at domestic residency-training institutions (n = 826). The outcomes analyzed included the total number of manuscripts, total number of citations, and the h-index between 1996 and 2007. Analysis of overall h-index rankings with stratification by academic ranking, junior vs. senior faculty status, and gender was performed. Results: Of the 826 radiation oncologists, the mean h-index was 8.5. Of the individuals in the top 10% by the h-index, 34% were chairpersons, 88% were senior faculty, and 13% were women. A greater h-index was associated with a higher academic ranking and senior faculty status. Recursive partitioning analysis revealed an h-index threshold of 15 (p <0.0001) as an identified breakpoint between the senior and junior faculty. Overall, women had lower h-indexes compared with men (mean, 6.4 vs. 9.4); however, when stratified by academic ranking, the gender differential all but disappeared. Conclusion: Using the h-index as a partial surrogate for research productivity, it appears that radiation oncologists in academia today comprise a prolific group, however, with a highly skewed distribution. According to the present analysis, the h-index correlated with academic ranking. Thus, it potentially has utility in the process of promotion decisions. Overall, women in radiation oncology were less academically productive than men; the possible reasons for the gender differential are discussed.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM

We report three-dimensional (3D) X-ray micro-computed tomography (μCT) has been widely used in petroleum engineering because it can provide detailed pore structural information for a reservoir rock, which can be imported into a pore-scale numerical model to simulate the transport and distribution of multiple fluids in the pore space. The partial volume blurring (PVB) problem is a major challenge in segmenting raw μCT images of rock samples, which impacts boundaries and small targets near the resolution limit. We developed a deep-learning (DL)-based workflow for accurate and fast partial volume segmentation. The DL model's performance depends primarily on the training data quality and model architecture. This study employed the entropy-based-masking indicator kriging (IK-EBM) to segment 3D Berea sandstone images as training datasets. The comparison between IK-EBM and manual segmentation using a 3D synthetic sphere pack, which had a known ground truth, showed that IK-EBM had higher accuracy on partial volume segmentation. We then trained and tested the UNet++ model, a state-of-the-art supervised encoder-decoder model, for binary (i.e., void and solid) and four-class segmentation. We compared the UNet++ with the commonly used U-Net and wide U-Net models and showed that the UNet++ had the best performance in terms of pixel-wise and physics-based evaluation metrics. Specifically, boundary-scaled accuracy demonstrated that the UNet++ architecture outperformed the regular U-Net architecture in the segmentation of pixels near boundaries and small targets, which were subjected to the PVB effect. Feature map visualization illustrated that the UNet++ bridged the semantic gaps between the feature maps extracted at different depths of the network, thereby enabling faster convergence and more accurate extraction of fine-scale features. The developed workflow significantly enhances the performance of supervised encoder-decoder models in partial volume segmentation, which has extensive applications in fundamental studies of subsurface energy, water, and environmental systems.

02 PETROLEUM↗

Strategy for Migration of Traditional to Hybrid Control Boards in a Nuclear Power Plant

This strategy document describes the NUREG-0711 based human factors engineering (HFE) phases and associated elements required to support design, verification and validation (V&V), and implementation of new digital control room elements in a legacy analog main control room (MCR). Information from previous planning and analysis work serves as the foundation for creating a human-machine interface (HMI) specification for distributed control systems (DCSs) to be implemented as part of nuclear power plant (NPP) modernization. This document reviews ways to take the HMSI specification and use it when migrating legacy displays or designing displays with new functionality. These displays undergo iterative usability testing during the design phase and then an integrated system validation (ISV) in the full-scope control room training simulator. Following successful demonstration of operator performance using the systems during the ISV, the new DCS is implemented at the plant, first in the training simulator and then in the MCR. This document concludes with a sample project plan, including a 15-month timeline from DCS design through implementation. Included is a discussion of how the U.S. Department of Energy’s Human System Simulation Laboratory (HSSL) can be used to support design and V&V activities. This report completes a Level 4 (M4) milestone under the U.S. Department of Energy’s (DOE’s) Light Water Reactor Sustainability (LWRS) Program.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

TU-AB-201-08: Rotating Shield High Dose Rate Brachytherapy with 153Gd and 75Se Isotopes

Purpose: To introduce rotating shield brachytherapy (RSBT) for different cancer sites with {sup 153}Gd and {sup 75}Se isotopes. RSBT is a form of intensity modulated brachytherapy, using shielded rotating catheters to provide a better dose distribution in the tumour while protecting healthy tissue. Methods: BrachySource, a Geant4-based Monte Carlo dose planning system was developed for investigation of RSBT with {sup 153}Gd and {sup 75}Se for different cancer sites. Dose distributions from {sup 153}Gd, {sup 75}Se and {sup 192}Ir isotopes were calculated in a 40 cm radius water phantom by using the microSelectron-v2 source model. The source was placed inside a cylindrical platinum shield with 1.3 mm diameter. An emission window coinciding with the active core of the source was created by removing half (180°) of the wall of the shield. Relative dose rate distributions of the three isotopes were simulated. As a proof of concept, a breast cancer patient originally treated with Mammosite was re-simulated with unshielded {sup 192}Ir and shielded {sup 153}Gd. Results: The source with the lowest energy, {sup 153}Gd, decreased the dose on the shielded side by 91%, followed by {sup 75}Se and {sup 192}Ir with 36% and 16% reduction at 1 cm from the source. The breast cancer patient simulation showed the ability of shielded {sup 153}Gd to spare the chest wall by a 90% dose reduction when only one emission window angle is considered. In this case, fully covering the PTV would require more delivery angles and the chest wall dose reduction would be less, however, the simulation demonstrates the potential of shielded {sup 153}Gd to selectively isolate organs at risk. Conclusion: Introducing {sup 153}Gd and {sup 75}Se sources combined with RSBT will allow escalation of dose in the target volume while maintaining low doses in radiation sensitive healthy tissue. Tailoring treatments to each individual patient by treating all parts of the tumour without over-irradiation of normal tissues will be possible. The author acknowledges partial support by the CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290), and the Quebec Fonds de recherche Nature et Technologies.

60 APPLIED LIFE SCIENCES↗

Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters

Second-order photon correlation measurements [g (2) (τ) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations – such as quantum dots – by evaluating the value of g (2) (τ = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g (2) (τ) functions from noise-dominated, few-shot inputs. The model is trained with simulated g (2) (τ) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g (2) (τ = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g (2) (τ) functions (~100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g (2) (τ) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. Furthermore, this work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

An adaptive approach to machine learning for compact particle accelerators

Abstract Machine learning (ML) tools are able to learn relationships between the inputs and outputs of large complex systems directly from data. However, for time-varying systems, the predictive capabilities of ML tools degrade if the systems are no longer accurately represented by the data with which the ML models were trained. For complex systems, re-training is only possible if the changes are slow relative to the rate at which large numbers of new input-output training data can be non-invasively recorded. In this work, we present an approach to deep learning for time-varying systems that does not require re-training, but uses instead an adaptive feedback in the architecture of deep convolutional neural networks (CNN). The feedback is based only on available system output measurements and is applied in the encoded low-dimensional dense layers of the encoder-decoder CNNs. First, we develop an inverse model of a complex accelerator system to map output beam measurements to input beam distributions, while both the accelerator components and the unknown input beam distribution vary rapidly with time. We then demonstrate our method on experimental measurements of the input and output beam distributions of the HiRES ultra-fast electron diffraction (UED) beam line at Lawrence Berkeley National Laboratory, and showcase its ability for automatic tracking of the time varying photocathode quantum efficiency map. Our method can be successfully used to aid both physics and ML-based surrogate online models to provide non-invasive beam diagnostics.

97 MATHEMATICS AND COMPUTING↗

Particle Filter Based Inference Testing

The primary intent of PAR-FIT (Particle Filter based Inference Testing) is to provide hard inductive evidence that a machine learning model is capable and proven for an individual test input. By examining training data used to form the underlying model functional correlation, an estimate of the reliability that a model will make the correct prediction can be made. The Sequential Probability Ratio Test is used to derive a qualitative evaluation for reliability based on hypothesis testing. The PAR-FIT framework achieves this by implementing a particle filter and the sequential probability ratio test algorithms on the machine learning model training data to determine relevancy of new individual test samples to the training dataset. The kernel function evaluates the local proximity and density of training data used to derive a prediction outcome. Particles are used to probabilistically determine which training data to evaluate for proximity. For test samples that are within a close proximity to and surrounded by multiple training data points, the evaluated reliability of the prediction is high. For test samples that are anomalies not represented by the training dataset, in low density data clusters, or are far from existing data points, the evaluated reliability is low as insufficient training evidence exists to suggest the model is capable of making the correct prediction. Sequential Probability Ratio Test is further used to determine when a hypothesis on whether a signal can be rejected or accepted for use. The ratio test collects sequence information from the particle filter to test whether the signal is anomalous or normal via hypothesis testing of the underlying distributions.

Chen, Edward [Idaho National Laboratory (INL), Ida↗

Impulsively Generated Wave Trains in Coronal Structures. I. Effects of Transverse Structuring on Sausage Waves in Pressureless Tubes

The behavior of the axial group speeds of trapped sausage modes plays an important role in determining impulsively generated wave trains, which have often been invoked to account for quasi-periodic signals with quasi-periods of the order of seconds in a considerable number of coronal structures. We conduct a comprehensive eigenmode analysis, both analytically and numerically, on the dispersive properties of sausage modes in pressureless tubes with three families of continuous radial density profiles. We find a rich variety of the dependence on the axial wavenumber k of the axial group speed v{sub gr}. Depending on the density contrast and profile steepness as well as on the detailed profile description, the v{sub gr}--k curves either possess or do not possess cutoff wavenumbers, and they can behave in either a monotonical or non-monotonical manner. With time-dependent simulations, we further show that this rich variety of the group speed characteristics heavily influences the temporal evolution and Morlet spectra of impulsively generated wave trains. In particular, the Morlet spectra can look substantially different from the “crazy tadpoles” found for the much-studied discontinuous density profiles. We conclude that it is necessary to re-examine available high-cadence data to look for the rich set of temporal and spectral features that can be employed to discriminate between the unknown forms of the density distributions transverse to coronal structures.

79 ASTRONOMY AND ASTROPHYSICS↗

UAS Edge Computing of Energy Infrastructure Damage Assessment

Energy infrastructure assessments are needed within 72 hours of natural disasters, and previous data collection methods have proven too slow. We demonstrate a scalable end-to-end solution using a prototype unmanned aerial system that performs on-the-edge detection, classification (i.e., damaged or undamaged), and geo-location of utility poles. The prototype is suitable for disaster response because it requires no local communication infrastructure and is capable of autonomous missions. Collections before, during, and after Hurricane Ida in 2021 were used to test the system. The system delivered an F1 score of 0.65 operating with a 2.7 s/frame processing speed with the YOLOv5 large model and an F1 score of 0.55 with a 0.48 s/frame with the YOLOv5 small model. Geo-location uncertainty in the bottom half of the frame was ~8 m, mostly driven by error in camera pointing measurement. With additional training data to improve performance and detect additional types of features, a fleet of similar drones could autonomously collect actionable post-disaster data.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Flexible Framework for Building Occupancy Detection Using Spatiotemporal Pattern Networks

This paper presents a reliable, scalable, and transferable framework to predict occupancy in a building utilizing diverse, multi-modal information. We propose a new methodology for learning-driven occupancy detection built on the concepts of probabilistic graphical modeling and observable Markov chain modeling. To capture the relationship between multi-sensor data and occupancy, we propose this Occ-STPN framework that is flexible to support both multivariate and univariate formulations. While the multivariate Occ-STPN performs feature-level fusion of multiple predictors and occupancy time-series data, the univariate Occ-STPN involves decision fusion of occupancy predictions using individual predictors based on a mutual information weighted fusion scheme. We also propose a new metric to evaluate the performance of occupancy prediction algorithms. Two popular datasets are used to validate our approach and demonstrate that our framework is scalable in terms of the number of information sources (e.g., sensors) as well as it is possible to transfer trained models from one building to another without significant reduction in performance. Reliability of the algorithm is also tested by injecting noise into the datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Using Boosted Decision Trees to Select High Quality Measurements in the Mu2e Experiment at Fermilab

This thesis presents the implementation and evaluation of a Boosted Decision Tree (BDT) model to improve the selection of high-quality track measurements in the Mu2e experiment at Fermilab. The Mu2e experiment is a high-energy physics experiments seeking to observe a rare theoretical physics process known as Charged Lepton Flavor Violation. A significant challenge faced by the Mu2e experiment are so-called background events, which are events whose data mimics that of the rare physics process the experiment seeks to observe. Without a mechanism to reduce background, it would be impossible to know whether Charged Lepton Flavor Violation occurred or not. To this end, high-quality track measurements must be distinguished from low-quality track measurements. A track can be conceived of as the reconstructed path of a particle that traveled through the Mu2e detector. In addition to other data, data about such tracks is stored using a C++-based framework, specific to the domain of high-energy physics, known as ROOT. A boosted decision tree model was trained using ROOT’s Toolkit For Multivariate Analysis by leveraging variables ancillary to track quality. In evaluation, the BDT achieves a ROC-AUC of 0.927 in discriminating good-quality tracks from poor-quality tracks. Such a score is indicative of both strong discrimination and strong generalization. Subsequently, it is shown that applying a BDT-based quality cut to the distribution of particle momenta significantly enhances the signal-to-background distinction for signal electrons, paving the way for improved sensitivity to Charged Lepton Flavor Violation.

Mullany, Brendan T. [Drew U.] (ORCID:0009000818888↗

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↗