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 919 records · Page 51

QUBO formulations for training machine learning models

Abstract Training machine learning models on classical computers is usually a time and compute intensive process. With Moore’s law nearing its inevitable end and an ever-increasing demand for large-scale data analysis using machine learning, we must leverage non-conventional computing paradigms like quantum computing to train machine learning models efficiently. Adiabatic quantum computers can approximately solve NP-hard problems, such as the quadratic unconstrained binary optimization (QUBO), faster than classical computers. Since many machine learning problems are also NP-hard, we believe adiabatic quantum computers might be instrumental in training machine learning models efficiently in the post Moore’s law era. In order to solve problems on adiabatic quantum computers, they must be formulated as QUBO problems, which is very challenging. In this paper, we formulate the training problems of three machine learning models—linear regression, support vector machine (SVM) and balanced k-means clustering—as QUBO problems, making them conducive to be trained on adiabatic quantum computers. We also analyze the computational complexities of our formulations and compare them to corresponding state-of-the-art classical approaches. We show that the time and space complexities of our formulations are better (in case of SVM and balanced k-means clustering) or equivalent (in case of linear regression) to their classical counterparts.

97 MATHEMATICS AND COMPUTING↗

Advanced Nuclear Technology. Using Technology for Small Modular Reactor Staff Optimization, Improved Effectiveness, and Cost Containment, 3002007071

Through this grant, the U.S. Department of Energy (DOE) will review several functional areas within a nuclear power plant, including fire protection, operations and operations support, refueling, training, procurement, maintenance, site engineering, and others. Several functional areas need to be examined since there appears to be no single staffing area or approach that alone has the potential for significant staff optimization at new nuclear power plants. Several of the functional areas will require a review of technology options such as automation, remote monitoring, fleet wide monitoring, new and specialized instrumentation, human factors engineering, risk informed analysis and PRAs, component and system condition monitoring and reporting, just in time training, electronic and automated procedures, electronic tools for configuration management and license and design basis information, etc., that may be applied to support optimization. Additionally, the project will require a review key regulatory issues that affect staffing and could be optimized with additional technology input. Opportunities to further optimize staffing levels and staffing functions by selection of design attributes of physical systems and structures need also be identified. A goal of this project is to develop a prioritized assessment of the functional areas, and R&D actions needed for those functional areas, to provide the best optimization

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

America’s Cutting Edge CNC machining and metrology training

This paper describes the workforce development activities supported by America’s Cutting Edge (ACE), a national initiative for machine tool technology development and advancement. ACE is supported by the Department of Defense Industrial Base Analysis and Sustainment (IBAS) program from the Office of Industrial Policy. Both the online and in-person components of the computer numerically controlled (CNC) machining and metrology training programs are summarized and participation information is provided.

99 GENERAL AND MISCELLANEOUS↗

EVA Task Timing and Timeline Planning

EVA timeline development occurs using task execution data generated through underwater training and simulation. This project collected task time data during final training events for several Space Shuttle and International Space Station missions and compared like task time data collected during on-orbit execution. Analysis was performed to compare types of activities and times required for each looking specifically for how activities can be accurately trained from a timeline planning perspective. The data revealed two significant aspects of flight timeline planning; Zero-g task times will match training times for activities that can be accurately simulated with appropriate fidelity hardware; and not all activities can be simulated sufficiently to produce training task times that will reflect required zero-g times. An approach for timeline planning utilizing this knowledge is also presented.

Looper, Christopher A.↗

Discrete Regularization for Calibration of Geologic Facies Against Dynamic Flow Data

Abstract Subsurface flow model calibration involves many more unknowns than measurements, leading to ill‐posed problems with nonunique solutions. To alleviate nonuniqueness, the problem is regularized by constraining the solution space using prior knowledge. In certain sedimentary environments, such as fluvial systems, the contrast in hydraulic properties of different facies types tends to dominate the flow and transport behavior, making the effect of within facies heterogeneity less significant. Hence, flow model calibration in those formations reduces to delineating the spatial structure and connectivity of different lithofacies types and their boundaries. A major difficulty in calibrating such models is honoring the discrete, or piecewise constant, nature of facies distribution. The problem becomes more challenging when complex spatial connectivity patterns with higher‐order statistics are involved. This paper introduces a novel formulation for calibration of complex geologic facies by imposing appropriate constraints to recover plausible solutions that honor the spatial connectivity and discreteness of facies models. To incorporate prior connectivity patterns, plausible geologic features are learned from available training models. This is achieved by learning spatial patterns from training data, e.g., ‐SVD sparse learning or the traditional Principal Component Analysis. Discrete regularization is introduced as a penalty functions to impose solution discreteness while minimizing the mismatch between observed and predicted data. An efficient gradient‐based alternating directions algorithm is combined with variable splitting to minimize the resulting regularized nonlinear least squares objective function. Numerical results show that imposing learned facies connectivity and discreteness as regularization functions leads to geologically consistent solutions that improve facies calibration quality.

Khaninezhad, Mohammad‐Reza↗

Analytical Validation of a Portable Mass Spectrometer Featuring Interchangeable, Ambient Ionization Sources for High Throughput Forensic Evidence Screening

Forensic evidentiary backlogs are indicative of the growing need for cost-effective, high-throughput instrumental methods. One such emerging technology that shows high promise in meeting this demand while also allowing on-site forensic investigation is portable mass spectrometric (MS) instrumentation, particularly that which enables the coupling to ambient ionization techniques. While the benefits of rapid, on-site screening of contraband can be anticipated, the inherent legal implications of field-collected data necessitates that the analytical performance of technology employed be commensurate with accepted techniques. To this end, comprehensive analytical validation studies are required before broad incorporation by forensic practitioners can be considered, and are the focus of this work. Pertinent performance characteristics such as throughput, selectivity, accuracy/precision, method robustness, and ruggedness have been investigated. Reliability in the form of false positive/negative response rates is also assessed, examining the effect of variables such as user training and experience level. To provide flexibility toward broad chemical evidence analysis, a suite of rapidly-interchangeable ion sources has been developed and characterized through the analysis of common illicit chemicals and emerging threats like substituted phenethylamines. .

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Incorporating space and time into random forest models for analyzing geospatial patterns of drug-related crime incidents in a major U.S. metropolitan area

The opioid crisis has hit American cities hard, and research on spatial and temporal patterns of drug-related activities including detecting and predicting clusters of crime incidents involving particular types of drugs is useful for distinguishing hot zones where drugs are present that in turn can further provide a basis for assessing and providing related treatment services. In this study, we investigated spatiotemporal patterns of more than 52,000 reported incidents of drug-related crime at block group granularity in Chicago, IL between 2016 and 2019. We applied a space-time analysis framework and machine learning approaches to build a model using training data that identified whether certain locations and built environment and sociodemographic factors were correlated with drug-related crime incident patterns, and establish the top contributing factors that underlaid the trends. Space and time, together with multiple driving factors, were incorporated into a random forest model to analyze these changing patterns. We accommodated both spatial and temporal autocorrelation in the model learning process to assist with capturing the changes over time and tested the capabilities of the space-time random forest model by predicting drug-related activity hot zones. Overall, we focused particularly on crime incidents that involved heroin and synthetic drugs as these have been key drug types that have highly impacted cities during the opioid crisis in the U.S.

97 MATHEMATICS AND COMPUTING↗

A hybrid Penman-Monteith and machine learning model for simulating evapotranspiration and its components

Integrating physical processes with machine learning has advanced evapotranspiration (ET) simulation, yet most hybrid models fail to partition total ET into its components: soil evaporation (E) and vegetation transpiration (T). This study introduces Residual Neural Network–Penman–Monteith (RNN-PM), a novel hybrid dual-source ET model designed to overcome this limitation. The model synergizes the physically-based Penman–Monteith framework with three specialized residual neural networks trained to estimate key conductance parameters (canopy conductance, soil surface conductance, and aerodynamic conductance). Furthermore this explicit parameterization allows for the direct partitioning of total ET. Validation at National Ecological Observatory Network (NEON) flux sites using high-frequency partitioned E and T shows that RNN-PM reliably reproduces ET and the transpiration fraction (T/ET). For ET, the model achieves an average Kling–Gupta efficiency (KGE) of 0.89 and a root-mean-square error (RMSE) of 0.55 mm/day; for T/ET, the KGE is 0.87 with an RMSE of 0.06. Furthermore, RNN-PM demonstrates robust generalization, accurately simulating ET and its components well beyond the initial training dataset, even under extreme climatic conditions. This study extended the analysis by comparing the RNN-PM model with seven established dual-source ET models. The results indicate that RNN-PM outperforms both conventional machine learning models and purely physical process-based models in simulating ET components in most cases. Among the purely physical process-based dual-source models, those based on surface temperature decomposition showed improved performance as the leaf area index (LAI) decreased when evaluated against high-frequency ET component datasets. In contrast, the performance of conductance-based dual-source models declined with decreasing LAI. Although purely machine learning-based models can produce relatively accurate simulations of ET components, they often exhibit limited generalization capability, an issue that the RNN-PM model effectively overcomes. Ultimately, the RNN-PM model represents a significant advance in simulating ET components, offering a novel and scalable approach for improving the representation of land–atmosphere interactions in Earth system models.

54 ENVIRONMENTAL SCIENCES↗

Progress toward Biomass and Coal-Derived Syngas Warm Cleanup: Proof-of-Concept Process Demonstration of Multicontaminant Removal for Biomass Application

Systems comprising of multiple sorbent and catalytic beds have been developed for the warm syngas cleanup of coal- and biomass-derived syngas. Tailored specifically for biomass application the process described here consists of six primary unit operations: 1) Na2CO3 bed for HCl removal, 2) two regenerable ZnO beds for bulk H2S removal, 3) ZnO bed for H2S polishing, 4) NiCu/SBA-16 sorbent for trace metal (e.g. AsH3) removal, 5) steam reforming catalyst bed for tars and light hydrocarbons reformation and NH3 decomposition, and a 6) Cu-based LT-WGS catalyst bed. Simulated biomass-derived syngas containing a multitude of inorganic contaminants (H2S, AsH3, HCl, and NH3) and hydrocarbon additives (methane, ethylene, benzene, and naphthalene) was used to demonstrate process effectiveness. The efficiency of the process was demonstrated for a period of 175 hours, during which no signs of deactivation were observed. Post-run analysis revealed small levels of sulfur slipped through the sorbent bed train to the two downstream catalytic beds. Future improvements could be made to the trace metal polishing sorbent to ensure complete inorganic contaminant removal (to low ppb level) prior to the catalytic steps. However, dual, regenerating ZnO beds were effective for continuous removal for the vast majority of the sulfur present in the feed gas. The process was effective for complete AsH3 and HCl removal. The steam reforming catalyst completely reformed all the hydrocarbons present in the feed (methane, ethylene, benzene, and naphthalene) to additional syngas. However, post-run evaluation, under kinetically-controlled conditions, indicates deactivation of the steam reforming catalyst. Spent material characterization suggests this is attributed, in part, to coke formation, likely due to the presence of benzene and/or naphthalene in the feed. Future adaptation of this technology may require dual, regenerable steam reformers. The process and materials described in this report hold promise for a warm cleanup of a variety of contaminant species within warm syngas.

Environmental Molecular Sciences Laboratory↗

Knowledge management: Role of the the Radiation Safety Information Computational Center (RSICC)

The Radiation Safety Information Computational Center (RSICC) at Oak Ridge National Laboratory (ORNL) is an information analysis center that collects, archives, evaluates, synthesizes and distributes information, data and codes that are used in various nuclear technology applications. RSICC retains more than 2,000 software packages that have been provided by code developers from various federal and international agencies. RSICC’s customers (scientists, engineers, and students from around the world) obtain access to such computing codes (source and/or executable versions) and processed nuclear data files to promote on-going research, to ensure nuclear and radiological safety, and to advance nuclear technology. The role of such information analysis centers is critical for supporting and sustaining nuclear education and training programs both domestically and internationally, as the majority of RSICC’s customers are students attending U.S. universities. Additionally, RSICC operates a secure CLOUD computing system to provide access to sensitive export-controlled modeling and simulation (M&S) tools that support both domestic and international activities. This presentation will provide a general review of RSICC’s activities, services, and systems that support knowledge management and education and training in the nuclear field.

Valentine, Timothy↗

Tree-based algorithms for weakly supervised anomaly detection

Weakly supervised methods have emerged as a powerful tool for model-agnostic anomaly detection at the Large Hadron Collider (LHC). While these methods have shown remarkable performance on specific signatures such as dijet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. In this paper, we show that using boosted decision trees as classifiers in weakly supervised anomaly detection gives superior performance compared to deep neural networks. Boosted decision trees are well known for their effectiveness in tabular data analysis. Our results show that they not only offer significantly faster training and evaluation times, but they are also robust to a large number of noisy input features. By using advanced gradient boosted decision trees in combination with ensembling techniques and an extended set of features, we significantly improve the performance of weakly supervised methods for anomaly detection at the LHC. This advance is a crucial step toward a more model-agnostic search for new physics. Published by the American Physical Society 2024

Astronomy & Astrophysics↗

Machine learning inversion from scattering for mechanically driven polymers

A machine learning inversion method is developed for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled as a chain of fixed-length bonds constrained by bending energy, and it is subject to external forces such as stretching and shear. We generate a data set consisting of random combinations of energy parameters, including bending modulus, stretching and shear force, along with Monte Carlo-calculated scattering functions and conformation variables such as end-to-end distance, radius of gyration and off-diagonal component of the gyration tensor. The effects of the energy parameters on the polymer are captured by the scattering function, and principal component analysis ensures the feasibility of the machine learning inversion. Finally, we train a Gaussian process regressor using part of the data set as a training set and validate the trained regressor for inversion using the rest of the data. The regressor successfully extracts the feature parameters.

Gaussian process regressors↗

Artifact identification in X-ray diffraction data using machine learning methods

In situ synchrotron high-energy X-ray powder diffraction (XRD) is highly utilized by researchers to analyze the crystallographic structures of materials in functional devices ( e.g. battery materials) or in complex sample environments ( e.g. diamond anvil cells or syntheses reactors). An atomic structure of a material can be identified by its diffraction pattern along with a detailed analysis of the Rietveld refinement which yields rich information on the structure and the material, such as crystallite size, microstrain and defects. For in situ experiments, a series of XRD images is usually collected on the same sample under different conditions ( e.g. adiabatic conditions) yielding different states of matter, or is simply collected continuously as a function of time to track the change of a sample during a chemical or physical process. In situ experiments are usually performed with area detectors and collect images composed of diffraction patterns. For an ideal powder, the diffraction pattern should be a series of concentric Debye–Scherrer rings with evenly distributed intensities in each ring. For a realistic sample, one may observe different characteristics other than the typical ring pattern, such as textures or preferred orientations and single-crystal diffraction spots. Textures or preferred orientations usually have several parts of a ring that are more intense than the rest, whereas single-crystal diffraction spots are localized intense spots owing to diffraction of large crystals, typically >10 µm. In this work, an investigation of machine learning methods is presented for fast and reliable identification and separation of the single-crystal diffraction spots in XRD images. The exclusion of artifacts during an XRD image integration process allows a precise analysis of the powder diffraction rings of interest. When it is trained with small subsets of highly diverse datasets, the gradient boosting method can consistently produce high-accuracy results. The method dramatically decreases the amount of time spent identifying and separating single-crystal diffraction spots in comparison with the conventional method.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Mixed Delay/Nondelay Embeddings Based Neuromorphic Computing with Patterned Nanomagnet Arrays

Patterned nanomagnet arrays (PNAs) have been shown to exhibit a strong geometrically frustrated dipole interaction. Some PNAs have also shown emergent domain wall dynamics. Previous works have demonstrated methods to physically probe these magnetization dynamics of PNAs to realize neuromorphic reservoir systems that exhibit chaotic dynamical behavior and high-dimensional nonlinearity. These PNA reservoir systems from prior works leverage echo state properties and linear/nonlinear short-term memory of component reservoir nodes to map and preserve the dynamical information of the input time-series data into nondelay spatial embeddings. Such mappings enable these PNA reservoir systems to imitate and predict/forecast the input time series data. However, these prior PNA reservoir systems are based solely on the nondelay spatial embeddings obtained at component reservoir nodes. As a result, they require a massive number of component reservoir nodes, or a very large spatial embedding (i.e., high-dimensional spatial embedding) per reservoir node, or both, to achieve acceptable imitation and prediction accuracy. These requirements reduce the practical feasibility of such PNA reservoir systems. To address this shortcoming, we present a mixed delay/nondelay embeddings-based PNA reservoir system. Our system uses a single PNA reservoir node with the ability to obtain a mixture of delay/nondelay embeddings of the dynamical information of the time-series data applied at the input of a single PNA reservoir node. Our analysis shows that when these mixed delay/nondelay embeddings are used to train a perceptron at the output layer, our reservoir system outperforms existing PNA-based reservoir systems for the imitation of NARMA 2, NARMA 5, NARMA 7, and NARMA 10 time series data, and for the short-term and long-term prediction of the Mackey Glass time series data.

Ti, Changpeng↗

Machine Learning-Based Temperature Prediction for Runtime Thermal Management Across System Components

Elevated temperatures limit the peak performance of systems because of frequent interventions by thermal throttling. Non-uniform thermal states across system nodes also cause performance variation within seemingly equivalent nodes leading to significant degradation of overall performance. In this paper we present a framework for creating a lightweight thermal prediction system suitable for run-time management decisions. We pursue two avenues to explore optimized lightweight thermal predictors. First, we use feature selection algorithms to improve the performance of previously designed machine learning methods. Second, we develop alternative methods using neural network and linear regression-based methods to perform a comprehensive comparative study of prediction methods. We show that our optimized models achieve improved performance with better prediction accuracy and lower overhead as compared with the Gaussian process model proposed previously. Specifically we present a reduced version of the Gaussian process model, a neural network-based model, and a linear regression-based model. Using the optimization methods, we are able to reduce the average prediction errors in the Gaussian process from 4: 2 degrees C to 2: 9 degrees C. We also show that the newly developed models using neural network and Lasso linear regression have average prediction errors of 2: 9 degrees C and 3: 8 degrees C respectively. The prediction overheads are 0.22, 0.097, and 0.026 ms per prediction for reduced Gaussian process, neural network, and Lasso linear regression models, respectively, compared with 0.57 ms per prediction for the previous Gaussian process model. We have implemented our proposed thermal prediction models on a two-node system configuration to help identify the optimal task placement. The task placement identified by the models reduces the average system temperature by up to 11: 9 degrees C without any performance degradation. Furthermore, these models respectively achieve 75, 82.5, and 74.17 percent success rates in correctly pointing to those task placements with better thermal response, compared with 72.5 percent success for the original model in achieving the same objective. Lastly, we extended our analysis to a 16-node system and we were able to train models and execute them in real time to guide task migration and achieve on average 17 percent reduction in the overall system cooling power.

97 MATHEMATICS AND COMPUTING↗

pnnl/doa

This is a set of Python scripts designed to implement a method of determining the domain of applicability for a trained machine model for molecular property prediction. Additionally, the scripts implement analysis methods to evaluate and explore the results of the method. These scripts are designed to support the submission of a manuscript describing the methods for publication.

Panapitiya, Gihan↗

Silicon Carbide Temperature Monitor Processing Improvements. Status Report

Silicon carbide (SiC) temperature monitors are used as temperature sensors in Advanced Test Reactor (ATR) irradiations at the Idaho National Laboratory (INL). Although thermocouples are typically used to provide real-time temperature indication in instrumented lead tests, other indicators, such as melt wires, are also often included in such tests as an independent technique of detecting peak temperatures incurred during irradiation. In addition, less expensive static capsule tests, which have no leads attached for real-time data transmission, often rely on melt wires as a post-irradiation technique for peak temperature indication. Melt wires are limited in that they can only detect whether a single temperature is or is not exceeded. SiC monitors are advantageous because a single monitor can be used to detect for a range of temperatures that occurred during irradiation. As part of the process initiated to make SiC temperature monitors available at the ATR, post-irradiation evaluations of these monitors have been previously completed at the High Temperature Test Laboratory (HTTL). INL selected the resistance measurement approach for determining irradiation temperature from SiC temperature monitors because it is considered to be the most accurate measurement. The current process involves the repeated annealing of the SiC monitors at incrementally increasing temperature, with resistivity measurements made between annealing steps. The process is time consuming and requires the nearly constant attention of a trained staff member. In addition to the expensive and lengthy post analysis required, the current process adds many potential sources of error in the measurement, as the sensor must be repeatedly moved from furnace to test fixture. This time-consuming post irradiation analysis is a significant portion of the total cost of using these otherwise inexpensive sensors. An additional consideration of this research is that, if the SiC post processing can be automated, it could be performed in an MFC hot cell, further reducing the time and expense of lengthy decontaminations prior to processing. Sections of this report provide a general description of resistivity techniques currently used to infer peak irradiation temperature from silicon carbide temperature monitors along with some representative data, the proposed concepts to improve the process of analyzing irradiated SiC temperature monitors, the completed efforts to prove the proposed concepts, and future activities. The efforts detailed here succeeded in designing and developing a real-time automated SiC resistivity measurement system, and performed two initial test runs. Activities carried out include the assembly and integration of the system hardware; the design and development of a preliminary monitor fixture; the design of a technique to automate the data analysis and processing; the development of the communication, coordination, and user software; and the execution and troubleshooting of test run experiments using the box furnace. Although the automation system performed as required, the designed fixture did not succeed in establishing the needed electrical contacts with the SiC monitor.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Structural Health Monitoring of Epoxy Bond between Dissimilar Materials

Structures composed of adhesively bonded materials face many challenges when subjected to thermal loading, as adherend material(s) behave differently and can induce stresses in the glue bond. Current methods to test bond strength are limited to destructive tests, which increase costs to produce adhesively bonded structures. Strain gages are proposed to monitor the expansion profile of adhesive bonds as structures undergo thermal loading. Because resulting signals are DC in nature, no spectral quantities can be observed. Principle component analysis (PCA) is proposed to differentiate between damaged and undamaged structures. Training data are taken for various damage states and the minimum Mahalanobis distance is calculated to categorize testing data into damage state. The results indicate the potential for a strain-gage based monitoring system with PCA based decision-making, with further research necessary prior to implementation of the system.

36 MATERIALS SCIENCE↗