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 1,009 records · Page 56

Criticality analysis of nuclear binding energy neural networks

Machine learning methods, in particular deep learning methods such as artificial neural networks (ANNs) with many layers, have become widespread and useful tools in nuclear physics. However, these ANNs are typically treated as ‘black boxes’, with their architecture (width, depth, and weight/bias initialization) and the training algorithm and parameters chosen empirically by optimizing learning based on limited exploration. We test a non-empirical approach to understanding and optimizing nuclear physics ANNs by adapting a criticality analysis based on renormalization group flows in terms of the hyperparameters for weight/bias initialization, training rates, and the ratio of depth to width. This treatment utilizes the statistical properties of neural network initialization to find a generating functional for network outputs at any layer, allowing for a path integral formulation of the ANN outputs as a Euclidean statistical field theory. We use a prototypical example to test the applicability of this approach: a simple ANN for nuclear binding energies. We find that with training using a stochastic gradient descent optimizer, the predicted criticality behavior is realized, and optimal performance is found with critical tuning. However, the use of an adaptive learning algorithm leads to somewhat superior results without concern for tuning and thus obscures the analysis. Nevertheless, the criticality analysis offers a way to look within the black box of ANNs, which is a first step towards potential improvements in network performance beyond using adaptive optimizers.

artificial neural network↗

Contemporary Trends in Radiation Oncology Resident Research

Purpose: To test the hypothesis that recent resident research productivity might be different than a decade ago, and to provide contemporary information about resident scholarly activity. Methods and Materials: We compiled a list of radiation oncology residents from the 2 most recent graduating classes (June 2014 and 2015) using the Association of Residents in Radiation Oncology annual directories. We queried the PubMed database for each resident's first-authored publications from postgraduate years (PGY) 2 through 5, plus a 3-month period after residency completion. We abstracted corresponding historical data for 2002 to 2007 from the benchmark publication by Morgan and colleagues (Int J Radiat Oncol Biol Phys 2009;74:1567-1572). We tested the null hypothesis that these 2 samples had the same distribution for number of publications using the Wilcoxon rank-sum test. We explored the association of demographic factors and publication number using multivariable zero-inflated Poisson regression. Results: There were 334 residents publishing 659 eligible first-author publications during residency (range 0-17; interquartile range 0-3; mean 2.0; median 1). The contemporary and historical distributions were significantly different (P<.001); contemporary publication rates were higher. Publications accrued late in residency (27% in PGY-4, 59% in PGY-5), and most were original research (75%). In the historical cohort, half of all articles were published in 3 journals; in contrast, the top half of contemporary publications were spread over 10 journals—most commonly International Journal of Radiation Oncology • Biology • Physics (17%), Practical Radiation Oncology (7%), and Radiation Oncology (4%). Male gender, non-PhD status, and larger residency size were associated with higher number of publications in the multivariable analysis. Conclusion: We observed an increase in first-author publications during training compared with historical data from the mid-2000s. These contemporary figures may be useful to medical students considering radiation oncology, current residents, training programs, and prospective employers.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Prediction model of potential hepatocarcinogenicity of rat hepatocarcinogens using a large-scale toxicogenomics database

The present study was performed to develop a robust gene-based prediction model for early assessment of potential hepatocarcinogenicity of chemicals in rats by using our toxicogenomics database, TG-GATEs (Genomics-Assisted Toxicity Evaluation System developed by the Toxicogenomics Project in Japan). The positive training set consisted of high- or middle-dose groups that received 6 different non-genotoxic hepatocarcinogens during a 28-day period. The negative training set consisted of high- or middle-dose groups of 54 non-carcinogens. Support vector machine combined with wrapper-type gene selection algorithms was used for modeling. Consequently, our best classifier yielded prediction accuracies for hepatocarcinogenicity of 99% sensitivity and 97% specificity in the training data set, and false positive prediction was almost completely eliminated. Pathway analysis of feature genes revealed that the mitogen-activated protein kinase p38- and phosphatidylinositol-3-kinase-centered interactome and the v-myc myelocytomatosis viral oncogene homolog-centered interactome were the 2 most significant networks. The usefulness and robustness of our predictor were further confirmed in an independent validation data set obtained from the public database. Interestingly, similar positive predictions were obtained in several genotoxic hepatocarcinogens as well as non-genotoxic hepatocarcinogens. These results indicate that the expression profiles of our newly selected candidate biomarker genes might be common characteristics in the early stage of carcinogenesis for both genotoxic and non-genotoxic carcinogens in the rat liver. Our toxicogenomic model might be useful for the prospective screening of hepatocarcinogenicity of compounds and prioritization of compounds for carcinogenicity testing. - Highlights: >We developed a toxicogenomic model to predict hepatocarcinogenicity of chemicals. >The optimized model consisting of 9 probes had 99% sensitivity and 97% specificity. >This model enables us to detect genotoxic as well as non-genotoxic hepatocarcinogens.

60 APPLIED LIFE SCIENCES↗

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student t process regression. We apply Student t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Autonomous phase mapping of gold nanoparticles synthesis with differentiable models of spectral shape

Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis, characterization, and data-driven decision-making. We present a closed-loop workflow for the on-demand synthesis and structural characterization of colloidal gold nanoparticles, enabling direct mapping from composition to nanoscale structure. Our framework leverages differentiable models of spectral shape to address two central tasks in self-driving labs: (a) phase mapping, or identifying compositional regions with distinct structural behavior; and (b) material retrosynthesis, or optimizing compositions for target structure. Using functional data analysis, we develop a data-driven model with generative pre-training, active learning, and high-throughput experiments to predict spectral responses across composition space. We demonstrate the approach on seed-mediated growth of gold nanoparticles, showcasing its ability to extract design rules, reveal secondary interactions, and efficiently navigate morphology space. Gradient-based optimization of the models enables inverse design, making this a unified platform.

36 MATERIALS SCIENCE↗

A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters

A Continuous Filter Convolutional Neural Network (CF-CNN) was trained to predict the potential energy of water cluster networks \ce{(H2O)_{\textit{N}}}, \textit{N}=10--30, corresponding to local minima lying within 5 kcal/mol from the putative minima taken from a newly published database containing over 5 million unique networks. The chemical sampling space of the database was characterized using chemical descriptors derived from graph theory, which led to the identification of important trends in the topology, connectivity, polygon structures associated with the various networks as a function of cluster size. The resulting graphs are available alongside the original database at \url{https://sites.uw.edu/wdbase/}. The CF-CNN trained on a subset of 500,000 networks for (\textit{N}=10, 30) yielded a mean absolute error of 0.002$\pm$0.002 kcal/mol per water molecule, giving the trained CF-CNN the highest accuracy of any neural network-based surrogate model to date. In addition, clusters of sizes not included in the training set exhibited errors of the same magnitude, indicating that the CF-CNN ptotocol is general enough to accurately predict energies of networks for both smaller and larger sizes than those used during training. The graph-theoretical descriptors were developed in order to analyze the properties of the full database and interpret the predictive power of the CF-CNN. Using topology measures, such as the Wiener index and the average shortest path length along with two similarity measures, we showed that all networks from the test set were within the range of the ones from the training set, suggesting that the training set covered the chemical space of interest quite well. Our graph analysis suggests that the mean degree and number of polygons for networks with larger errors tend to lie further from the mean than those with lower errors. The generality of the used CF-CNN was thus demonstrated, while the use of the graph-theoretical descriptors assisted in interpreting the predicted results.

Bilbrey, Jenna A.↗

The LCLStream Ecosystem for Multi-Institutional Dataset Exploration

We describe a new end-to-end experimental data streaming framework designed from the ground up to support new types of applications – AI training, extremely high-rate X-ray time-of-flight analysis, crystal structure determination with distributed processing, and custom data science applications and visualizers yet to be created. Throughout, we use design choices merging cloud microservices with traditional HPC batch execution models for security and flexibility. This project makes a unique contribution to the DOE Integrated Research Infrastructure (IRI) landscape. By creating a flexible, API-driven data request service, we address a significant need for high-speed data streaming sources for the X-ray science data analysis community. With the combination of data request API, mutual authentication web security framework, job queue system, high-rate data buffer, and complementary nature to facility infrastructure, the LCLStreamer framework has prototyped and implemented several new paradigms critical for future generation experiments.

Rogers, David [ORNL] (ORCID:0000000251871768)↗

TrackTable Trajectory Analysis

Tracktable is designed for analysis and rendering of the trajectories of moving objects such as planes, trains, automobiles and ships. Its purpose is to operate on large sets of trajectories (millions) to help a user detect, analyze and display patterns. It will also be used to disseminate trajectory research results from Sandia's PANTHER Grand Challenge LDRD.

Wilson, AndrewT.↗

Integral and Separate Effects Tests for Thermal Hydraulics Code Validation for Liquid-Salt Cooled Nuclear Reactors

The objective of the 3-year project was to collect integral effects test (IET) data to validate the RELAP5-3D code and other thermal hydraulics codes for use in predicting the transient thermal hydraulics response of liquid salt cooled reactor systems, including integral transient response for forced and natural circulation operation. The reference system for the project is a modular, 900-MWth Pebble Bed Advanced High Temperature Reactor (PB-AHTR), a specific type of Fluoride salt-cooled High temperature Reactor (FHR). Two experimental facilities were developed for thermal-hydraulic integral effects tests (IETs) and separate effects tests (SETs). The facilities use simulant fluids for the liquid fluoride salts, with very little distortion to the heat transfer and fluid dynamics behavior. The CIET Test Bay facility was designed, built, and operated. IET data for steady state and transient natural circulation was collected. SET data for convective heat transfer in pebble beds and straight channel geometries was collected. The facility continues to be operational and will be used for future experiments, and for component development. The CIET 2 facility is larger in scope, and its construction and operation has a longer timeline than the duration of this grant. The design for the CIET 2 facility has drawn heavily on the experience and data collected on the CIET Test Bay, and it was completed in parallel with operation of the CIET Test Bay. CIET 2 will demonstrate start-up and shut-down transients and control logic, in addition to LOFC and LOHS transients, and buoyant shut down rod operation during transients. Design of the CIET 2 Facility is complete, and engineering drawings have been submitted to an external vendor for outsourced quality controlled construction. CIET 2 construction and operation continue under another NEUP grant. IET data from both CIET facilities is to be used for validation of system codes used for FHR modeling, such as RELAP5-3D. A set of numerical models were developed in parallel to the experimental work. RELAP5-3D models were developed for the salt-cooled PB-AHTR, and for the simulat fluid CIET natural circulation experimental loop. These models are to be validated by the data collected from CIET. COMSOL finite element models were used to predict the temperature and fluid flow distribution in the annular pebble bed core; they were instrumental for design of SETs, and they can be used for code-to-code comparisons with RELAP5-3D. A number of other small SETs, and numerical models were constructed, as needed, in support of this work. The experiments were designed, constructed and performed to meet CAES quality assurance requirements for test planning, implementation, and documentation; equipment calibration and documentation, procurement document control; training and personnel qualification; analysis/modeling software verification and validation; data acquisition/collection and analysis; and peer review.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Final Scientific/Technical Report

In this work, we have built upon our results from previous DOE funding (DEFG 0204ER25655), where we developed new and more efficient methods for solving certain optimization problems with many inequality constraints. This past work resulted in efficient algorithms (and analysis of their convergence) for linear programming, convex quadratic programming, and the training of support vector machines. The algorithms are based on using constraint reduction in interior point methods: at each iteration we consider only a smaller subset of the inequality constraints, focusing on the constraints that are close enough to be relevant. Surprisingly, we have been able to show theoretically that such algorithms are globally convergent and to demonstrate experimentally that they are much more efficient than standard interior point methods.

97 MATHEMATICS AND COMPUTING↗

Learning-based Computational Study of the Thermodynamic, Structural, and Dynamic Properties of Molten Salt at the Atomic and Electronic Scale and Experimental Validations (Final Report for Project 19-16909)

The project completed several milestones related to the work scope to determine thermophysical properties of the molten salt FLiNaK. A combined approach to integrate advanced computations with neutron scattering experimental interrogation was used to quantify the structure and mass transport of pure FLiNaK and FLiNaK with additives. The additives investigated included Ce, Cs, Zr, and Cr. The primary outcome of the computational work was the development of a neutral network force field interatomic potential (referred to as the NNFF model in this document). The computational work also involved ab initio calculations to determine the ground truth and molecular dynamics simulations to provide computational analogs to the experimental campaign. The experimental work used enriched F 7 LiNaK prepared by Argonne National Laboratory. The use of enriched F 7 LiNaK reduced parasitic neutron absorption and significantly improved data collection and data quality. Several graduate students were supported during the course of the project, which included a one year no-cost extension. These students were trained in advanced computational methods, advanced neutron scattering methods, neutron scattering data analysis and interpretation, and molten salt sample preparation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Optimizing Residential HVAC Systems: Evaluating How the Usage of Smart Diagnostic Tools for Quality Installation and Commissioning Impacts System Performance and HVAC Contractor Businesses

The adoption of digital quality installation and fault detection tools has the potential to transform the $14 billon residential heating, ventilating, and air conditioning (HVAC) service and installation industry. Increased market penetration can be accelerated by providing an increased understanding of the energy and economic value proposition of the usage of these tools. In tandem with energy and HVAC system performance impact research and analysis, the Southface Team investigated the economic business implications for HVAC service and installation contractors adopting the use of measureQuick (mQ), a smart diagnostic app that aids in quality installation and fault detection and works agnostically with Bluetooth-enabled HVAC technician tools.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Liquid centrifugation-based isotope separation of 7 Li, 37 Cl and D

Liquid centrifugation is an emerging method to separate isotopes. By spinning a liquid containing target isotopes (e.g., pure chemical or solution), the heavier isotope will be enriched at the outer part of a centrifuge, and the lighter ones will be enriched at the inner part of a centrifuge. The separation capability is positively correlated with rotation speed, outer radius and mass difference between isotopes to separate. This award targets to understand whether liquid centrifugation is effective in separating isotopes important for nuclear fission technologies. The results include the following three sections: 1) Effects of solute concentration on isotope separation; 2) Preliminary progress of building a low-speed countercurrent centrifuge, and 3) Analysis on possible candidates for 7 Li and 37 Cl. The award trained one research scientist, one Ph.D. student, one master student, and one undergraduate on liquid centrifugation and isotope measurements.

07 ISOTOPE AND RADIATION SOURCES↗

Battery Life Prediction Using Reduced-Order Physics Models and Machine Learning (CRADA Final Report)

Phase 1 (Original CRADA, plus no-cost extension modifications #1-3, 6/1/2017 to 3/13/2021): The Australian Department of Defence (AUDoD) is performing accelerated aging tests of Li-ion batteries to benchmark their reliability and degradation characteristics. Using its previously developed battery lifetime predictive model framework, the National Laboratory of the Rockies (NLR) will develop analytical models based the AUDoD data to predict lifetime of the multiple Li-ion battery chemistries under real-world use scenarios of interest to AUDoD. The NLR model is based on physical degradation mechanisms encountered by Li-ion batteries and has been previously validated. Phase 2 (CRADA modification #4, plus no-cost extension modification #5, 2/22/2021 to 3/30/2025): Train and support Australian Department of Defence personnel to use NLR software for model-based estimation of Li-ion battery lifetime using accelerated battery aging data collected by the Australian Department of Defence. Under separate DOE funding from 2019 to 2021, NLR enhanced its battery life-prediction software using machine learning algorithms to automate portions of the model-fitting process, requiring significantly less labor and expert judgment and also adding uncertainty quantification, increasing statistical rigor. Under Phase 2, NLR will customize NLR Software and provide it to AuDoD. NLR will enhance its NLR Model to capture aging modes of AuDoD's multi-cell modules, including cell-balancing effects. NLR will develop example single-cell and multi-cell models based on one AuDoD battery aging dataset. NLR will train AuDoD personnel on NLR Software. By the conclusion of the project, NLR will have provided AuDoD the training materials, a user manual and software needed to perform their own analysis of additional and/or future battery aging datasets.

33 ADVANCED PROPULSION SYSTEMS↗

Atomic Emission, Absorption and Fluorescence in the Laser-induced Plasma

The main result of our efforts is the development and successful application of the theoretical model of laser induced plasma (LIP) that allows a back-calculation of the composition of the plasma (and the condensed phase) based on the observable plasma spectrum. The model has an immediate experimental input in the form of LIP spectra and a few other experimentally determined parameters. The model is also sufficiently simple and, therefore, practical. It is conveniently interfaced in a graphical user-friendly form for using by students and any laboratory personnel with only minimal training. In our view, the model opens up the possibility for absolute analysis, i.e. the analysis which requires no standards and tedious calibration. The other parts of this proposal (including plasma diagnostics) were somewhat subordinate to this main goal. Plasma diagnostics provided the model with the necessary experimental input and led to better understanding of plasma processes. Another fruitful direction we pursued was the use of the correlation analysis for material identification and plasma diagnostics. Through a number of computer simulations we achieved a clear understanding of how, where and why this approach works being applied to emission spectra from a laser plasma. This understanding will certainly improve the quality of forensic and industrial analyses where fast and reliable material identification and sorting are required.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Transience of the Retinal Output Is Determined by a Great Variety of Circuit Elements

Retinal ganglion cells (RGCs) encrypt stimulus features of the visual scene in action potentials and convey them toward higher visual centers in the brain. Although there are many visual features to encode, our recent understanding is that the ~46 different functional subtypes of RGCs in the retina share this task. In this scheme, each RGC subtype establishes a separate, parallel signaling route for a specific visual feature (e.g., contrast, the direction of motion, luminosity), through which information is conveyed. The efficiency of encoding depends on several factors, including signal strength, adaptational levels, and the actual efficacy of the underlying retinal microcircuits. Upon collecting inputs across their respective receptive field, RGCs perform further analysis (e.g., summation, subtraction, weighting) before they generate the final output spike train, which itself is characterized by multiple different features, such as the number of spikes, the inter-spike intervals, response delay, and the rundown time (transience) of the response. These specific kinetic features are essential for target postsynaptic neurons in the brain in order to effectively decode and interpret signals, thereby forming visual perception. We review recent knowledge regarding circuit elements of the mammalian retina that participate in shaping RGC response transience for optimal visual signaling.

59 BASIC BIOLOGICAL SCIENCES↗

WaterTAP3 Model Input Data for NAWI's Eight Source Water Baseline Analyses

This folder contains the input data for the WaterTAP3 model that was used for the eight NAWI (National Alliance for Water Innovation) source water baselines studies published in the Environmental Science and Technology special issue: Technology Baselines and Innovation Priorities for Water Treatment and Supply. There are also eight other separate DAMS submissions, one per source water, that include the model results for the published studies. In this data submission, all model inputs across the eight baselines are included. The data structure and content are described in a README.txt file. For more details on how to use the data in WaterTAP3 please refer to the model documentation and GitHub site found at "WaterTAP3 Github" linked in the submission resources.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative datasets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student-t process regression. We apply Student-t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via coloring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics, and classic machine learning clustering algorithms.

97 MATHEMATICS AND COMPUTING↗