Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “training data”

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 1,333 records · Page 74
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Identification of Plasma Current Center by Neural Network Inference in EAST

For the efficient and safe operation of experimental advanced superconducting tokamak (EAST), it is necessary to accurately identify and control the plasma current and its central position. In this article, neural network is used to identify the position of the plasma current center. The model trained by the basic back-propagation neural network can well match the relationship between the electromagnetic diagnostic signals and plasma current center positions. Both noisy simulation data and experimental data are applied to train and test the neural network inference model. Adding 0.1% noise to the training data is proven to improve the noise immunity of the inference model. Basic neural networks trained with both noisy simulation data and actual experimental data show good results with sufficient inputs; however, in both cases, the performance degrades significantly when only the poloidal field coil currents are given as inputs. For this kind of time-series problem, the dynamic neural network containing delay and feedback architecture is introduced, and an improved model requiring much fewer inputs is trained and tested for current center inference. Furthermore, some parameters of this model are compared and analyzed in this article. With suitable neural network architecture, the mapping between the controlled variables (poloidal field coil currents) and response variables (plasma current center) can be well-established.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

FedEFsz: Fair Cross-Silo Federated Learning System With Error-Bounded Lossy Compression

Cross-Silo federated learning systems have been identified as an efficient approach to scaling DNN training across geographically-distributed data silos to preserve the privacy of the training data. Communication efficiency and fairness are two major issues that need to be both satisfied when federated learning systems are deployed in practice. Simultaneously guaranteeing both of them, however, is exceptionally difficult because simply combining communication reduction and fairness optimization approaches often causes non-converged training or drastic accuracy degradation. Here, to bridge this gap, we propose FedEFsz. On the one hand, it integrates the state-of-the-art error-bounded lossy compressor SZ3 into cross-silo federated learning systems to significantly reduce communication traffic during the training. On the other hand, it achieves a high fairness (i.e., rather consistent model accuracy and performance across different clients) through a carefully designed heuristic algorithm that can tune the error-bound of SZ3 for different clients during the training. Extensive experimental results based on a GPU cluster with 65 GPU cards show that FedEFsz improves the fairness across different benchmarks by up to 60.88% and meanwhile reduces the communication traffic by up to 315×.

Cross-Silo Federated Learning Systems↗
DOE OSTI2020

Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning

Using deep convolutional neural network (CNN), the nature of the QCD transition can be identified from the final-state pion spectra from hybrid model simulations of heavy-ion collisions that combines a viscous hydrodynamic model with a hadronic cascade “after-burner”. Two different types of equations of state (EoS) of the medium are used in the hydrodynamic evolution. The resulting spectra in transverse momentum and azimuthal angle are used as the input data to train the neural network to distinguish different EoS. Different scenarios for the input data are studied and compared in a systematic way. A clear hierarchy is observed in the prediction accuracy when using the event-by-event, cascade-coarse-grained and event-fine-averaged spectra as input for the network, which are about 80%, 90% and 99%, respectively. A comparison with the prediction performance by deep neural network (DNN) with only the normalized pion transverse momentum spectra is also made. High-level features of pion spectra captured by a carefully-trained neural network were found to be able to distinguish the nature of the QCD transition even in a simulation scenario which is close to the experiments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Uncertainty-quantified phenomenological optical potentials for single-nucleon scattering

Optical-model potentials (OMPs) continue to play a key role in nuclear reaction calculations. However, the uncertainty of phenomenological OMPs in widespread use—inherent to any parametric model trained on data—has not been fully characterized, and its impact on downstream users of OMPs remains unclear. Here we assign well-calibrated uncertainties for two representative global OMPs, those of Koning-Delaroche and Chapel Hill '89, using Markov-chain Monte Carlo for parameter inference. By comparing the canonical versions of these OMPs against the experimental data originally used to constrain them, we show how a lack of outlier rejection and a systematic underestimation of experimental uncertainties contributes to bias of, and overconfidence in, best-fit parameter values. Our updated, uncertainty-quantified versions of these OMPs address these issues and yield complete covariance information for potential parameters. Scattering predictions generated from our ensembles show improved performance both against the original training corpora of experimental data and against a new “test” corpus comprising many of the experimental single-nucleon scattering data collected over the last twenty years. Finally, we apply our uncertainty-quantified OMPs to two case studies of application-relevant cross sections. We conclude that, for many common applications of OMPs, including OMP uncertainty should become standard practice. Furthermore, to facilitate their immediate use, digital versions of our updated OMPs and related tools for forward uncertainty propagation are included as Supplemental Material.

150 ≤ A ≤ 189↗
DOE OSTI2020

A Step Towards Machine Learning-based Coherent Generator Grouping for Emergency Control Applications in Modern Power Grid

A dynamic neural network (NN) based multi-class classifier is proposed for improving online prediction of coherent generator groups (CGGs), following the occurrences of various contingencies in the power grid. This is motivated by the increasing availability of the measurements from phasor measurement units (PMUs) and the number of grouping schemes is limited. The proposed method consists of three steps. First, by performing offline simulations, a library of system dynamic responses characterized by post-contingency rotor angles and speeds of individual generators is obtained. To generate sufficient data, up to N-2 contingencies and the uncertain parameters associated with the power grid including type and location of disturbance and fault clearing times are modeled. Secondly, the training data-set is produced by generating labels for individual contingencies using a hierarchical clustering method based on rotor angle and speed data. Lastly, the dynamic NN models are trained for online applications such as emergency controls and controlled islanding. The proposed method is tested on the standard 16-generator 68-bus system to demonstrate its performance. Furthermore, the impact of the sample data lengths on the CGG numbers is evaluated. It is interesting to observe that the time domain stability behaviors can be determined by examining the changes in the CGG numbers.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
NASA NTRS2018

GEONEX: Progressive Conditional Generative Adversarial Training Using Transfer learning

Obtaining accurate segmentation on large scale images is an open problem in deep learning. The main problem is the amount of labeled data that exists for large scale images. Traditionally, the common solution to this problem is to crop the large images into smaller images to increase the amount of available data and train a Conditional Generative Adversarial Network (CGAN). CGANs are currently the state of the art in image to image translation and provide better accuracy than the traditional method of training a encoder based conv-net architecture to minimize the loss at each pixel. This method can produce noisy and discontinuous images with inaccurate results. We seek to solve this problem by utilizing the concepts of transfer learning and progressive training to create a CGAN that can segment large scale images with a limited amount of labeled data. In transfer learning we recognize that many learned features are applicable to many classes from multiple domains. This introduces the concept of feature reusability, which is the basis for finetuning. Progressive training got its start in training models on the same images at different resolutions. In this work we instead train a GAN on increasing image scales by transferring the weights from the smaller scales to the larger scales. The learned features at the smaller scales are continually reused and applied to larger scales to create a CGAN that can perform accurate segmentation on large scale images. We apply this method to detect building footprints on very high-resolution overhead imagery (e.g Digital Globe and high resolution airborne platforms).

GEONEX↗
DOE OSTI2017

Best practice data life cycle approaches for the life sciences

Throughout history, the life sciences have been revolutionised by technological advances; in our era this is manifested by advances in instrumentation for data generation, and consequently researchers now routinely handle large amounts of heterogeneous data in digital formats. The simultaneous transitions towards biology as a data science and towards a ‘life cycle’ view of research data pose new challenges. Researchers face a bewildering landscape of data management requirements, recommendations and regulations, without necessarily being able to access data management training or possessing a clear understanding of practical approaches that can assist in data management in their particular research domain. Here we provide an overview of best practice data life cycle approaches for researchers in the life sciences/bioinformatics space with a particular focus on ‘omics’ datasets and computer-based data processing and analysis. We discuss the different stages of the data life cycle and provide practical suggestions for useful tools and resources to improve data management practices.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2023

Online evolutionary neural architecture search for multivariate non-stationary time series forecasting

Time series forecasting (TSF) is one of the most important tasks in data science. TSF models are usually pre-trained with historical data and then applied on future unseen datapoints. However, real-world time series data is usually non-stationary and models trained offline usually face problems from data drift. Models trained and designed in an offline fashion can not quickly adapt to changes quickly or be deployed in real-time. To address these issues, this work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. These results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies. Additionally, results show that utilizing multiple populations of RNNs which are periodically repopulated provide significant performance improvements, allowing this online neural network architecture design and training to be successful.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Accelerating multiscale electronic stopping power predictions with time-dependent density functional theory and machine learning

Knowing the rate at which particle radiation releases energy in a material, the “stopping power,” is key to designing nuclear reactors, medical treatments, semiconductor and quantum materials, and many other technologies. While the nuclear contribution to stopping power, i.e., elastic scattering between atoms, is well understood in the literature, the route for gathering data on the electronic contribution has for decades remained costly and reliant on many simplifying assumptions, including that materials are isotropic. We establish a method that combines time-dependent density functional theory (TDDFT) and machine learning to reduce the time to assess new materials to hours on a supercomputer and provide valuable data on how atomic details influence electronic stopping. Our approach uses TDDFT to compute the electronic stopping from first principles in several directions and then machine learning to interpolate to other directions at a cost of 10 million times fewer core-hours. We demonstrate the combined approach in a study of proton irradiation in aluminum and employ it to predict how the depth of maximum energy deposition, the “Bragg Peak,” varies depending on the incident angle—a quantity otherwise inaccessible to modelers and far outside the scales of quantum mechanical simulations. The lack of any experimental information requirement makes our method applicable to most materials, and its speed makes it a prime candidate for enabling quantum-to-continuum models of radiation damage. The prospect of reusing valuable TDDFT data for training the model makes our approach appealing for applications in the age of materials data science.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Temperature outweighs light and flow as the predominant driver of dissolved oxygen in US rivers

The concentration of dissolved oxygen (DO), an important measure of water quality and river metabolism, varies tremendously in time and space. Riverine DO is commonly perceived as regulated by interacting and competing drivers (light, temperature and flow) that define rivers’ climate. Its continental-scale drivers, however, have remained elusive, partly due to the scarcity and spatio-temporal inconsistency of water quality data. Here we show, via a deep learning model (long short-term memory) trained using data from 580 rivers, that temperature predominantly drives daily DO dynamics in the contiguous United States. Light comes a close second, whereas flow imparts minimal influence. This work showcases the promise of using deep learning models for data filling that enables large-scale systematic analysis of patterns and drivers. Results show fairly accurate prediction of DO by temperature alone, and declining DO in warming rivers, which has important implications for water security and ecosystem health in the future climate.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Brief Overview of the NCSP [Slides]

The mission of the NCSP is to provide sustainable expert leadership, direction, and the technical infrastructure necessary to develop, maintain, and disseminate the essential technical tools, training, and data required to support safe, efficient fissionable material operations within the Department of Energy. The vision of the NCSP is a continually improving, adaptable, and transparent program that communicates and collaborates globally to incorporate technology, practices, and programs to be responsive to the essential technical needs of those responsible for developing, implementing, and maintaining nuclear criticality safety.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2016

In-situ trainable intrusion detection system

A computer implemented method detects intrusions using a computer by analyzing network traffic. The method includes a semi-supervised learning module connected to a network node. The learning module uses labeled and unlabeled data to train a semi-supervised machine learning sensor. The method records events that include a feature set made up of unauthorized intrusions and benign computer requests. The method identifies at least some of the benign computer requests that occur during the recording of the events while treating the remainder of the data as unlabeled. The method trains the semi-supervised learning module at the network node in-situ, such that the semi-supervised learning modules may identify malicious traffic without relying on specific rules, signatures, or anomaly detection.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Design of Digital Twin Sensing Strategies Via Predictive Modeling and Interpretable Machine Learning

This work develops a methodology for sensor placement and dynamic sensor scheduling decisions for digital twins. The digital twin data assimilation is posed as a classification problem, and predictive models are used to train optimal classification trees that represent the map from observed data to estimated digital twin states. In addition to providing a rapid digital twin updating capability, the resulting classification trees yield an interpretable mathematical representation that can be queried to inform sensor placement and sensor scheduling decisions. The proposed approach is demonstrated for a structural digital twin of a 12 ft wingspan unmanned aerial vehicle. Offline, training data are generated by simulating scenarios using predictive reduced-order models of the vehicle in a range of structural states. Furthermore, these training data can be further augmented using experimental or other historical data. In operation, the trained classifier is applied to observational data from the physical vehicle, enabling rapid adaptation of the digital twin in response to changes in structural health. Within this context, we study the performance of the optimal tree classifiers and demonstrate how they enable explainable structural assessments from sparse sensor measurements and also inform optimal sensor placement.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Physics informed neural network can retrieve rate and state friction parameters from acoustic monitoring of laboratory stick-slip experiments

Various machine learning (ML) and deep learning (DL) techniques have been recently applied to the forecasting of laboratory earthquakes from friction experiments. The magnitude and timing of shear failures in stick-slip cycles are predicted using features extracted from the recorded ultrasonic or acoustic emission (AE) signals. In addition, the Rate and State Friction (RSF) constitutive laws are extensively used to model the frictional behavior of faults. In this work, we use data from shear experiments coupled with passive acoustic (variance, kurtosis, and AE rate) interleaved with active source ultrasonic monitoring (transmitted wave amplitude) to develop physics-informed neural network (PINN) models incorporating the RSF law and AE rate generation equation with wave amplitude serving as a proxy for friction state variable. This PINN framework allows learning RSF parameters from stick-slip experiments rather than measuring them through a series of velocity step experiments. We observe that when the stick-slip cycles are irregular, the PINN models outperform the data-driven DL models. Transfer learning (TL) PINN models are also developed by pre-training on data collected at one normal stress level followed by forecasting shear failures and retrieving RSF parameters at other stress levels (i.e., with different recurrence intervals) after retraining on a limited amount of new data. Our findings suggest that TL models perform better compared to standalone models. Both standalone and TL PINN-estimated RSF parameters and their ground truth values show excellent agreements thus demonstrating that RSF parameters can be retrieved from laboratory stick-slip experiments using the corresponding acoustic data and that the transmitted wave amplitude provides a good representation of the evolving frictional state during stick-slips.

58 GEOSCIENCES↗
NASA NTRS2015

NASA's Functional Task Test: Providing Information for an Integrated Countermeasure System

Exposure to the microgravity conditions of spaceflight causes astronauts to experience alterations in multiple physiological systems. These physiological changes include sensorimotor disturbances, cardiovascular deconditioning, and loss of muscle mass and strength. Some or all of these changes might affect the ability of crewmembers to perform critical mission tasks immediately after landing on a planetary surface. The goals of the Functional Task Test (FTT) study were to determine the effects of spaceflight on functional tests that are representative of critical exploration mission tasks and to identify the key physiological factors that contribute to decrements in performance. The FTT was comprised of seven functional tests and a corresponding set of interdisciplinary physiological measures targeting the sensorimotor, cardiovascular and muscular changes associated with exposure to spaceflight. Both Shuttle and ISS crewmembers participated in this study. Additionally, we conducted a supporting study using the FTT protocol on subjects before and after 70 days of 6 head-down bed rest. The bed rest analog allowed us to investigate the impact of body unloading in isolation on both functional tasks and on the underlying physiological factors that lead to decrements in performance, and then to compare them with the results obtained in our spaceflight study. Spaceflight data were collected on three sessions before flight, on landing day (Shuttle only) and 1, 6 and 30 days after landing. Bed rest subjects were tested three times before bed rest and immediately after getting up from bed rest as well as 1, 6, and 12 days after reambulation. We have shown that for Shuttle, ISS and bed rest subjects, functional tasks requiring a greater demand for dynamic control of postural equilibrium (i.e. fall recovery, seat egress/obstacle avoidance during walking, object translation, jump down) showed the greatest decrement in performance. Functional tests with reduced requirements for postural stability (i.e. hatch opening, ladder climb, manual manipulation of objects and tool use) showed little reduction in performance. These changes in functional performance were paralleled by similar decrements in sensorimotor tests designed to specifically assess postural equilibrium and dynamic gait control. Bed rest subjects experienced similar deficits both in functional tests with balance challenges and in sensorimotor tests designed to evaluate postural and gait control as spaceflight subjects indicating that body support unloading experienced during spaceflight plays a central role in post-flight alteration of functional task performance. To determine how differences in body-support loading experienced during in-flight treadmill exercise affect postflight functional performance, the loading history for each subject during in-flight treadmill (T2) exercise was correlated with postflight measures of performance. ISS crewmembers who walked on the treadmill with higher pull-down loads had enhanced post-flight performance on tests requiring mobility. Taken together the spaceflight and bed rest data point to the importance of supplementing inflight exercise countermeasures with balance and sensorimotor adaptability training. These data also support the notion that inflight treadmill exercise performed with higher body loading provides sensorimotor benefits leading to improved performance on functional tasks that require dynamic postural stability and mobility.

Bloomberg, J. J.↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
NASA NTRS1976

Coastal zone classification from satellite imagery

The author has identified the following significant results. Studies of cover distribution along Delaware's coast, especially in tidal wetlands, were made, utilizing semi-automated analysis of LANDSAT-1 MSS digital data. Cover maps with eleven vegetation and other cover categories were produced with accuracy of identification above 80% in all categories. Recent studies have tested a new technique for training automated analysis which uses ground measured reflectance and atmospheric correction techniques to derive signatures for specific categories in preference to the relative radiance signatures derived from training sets within LANDSAT data itself. Initial tests using a four category scheme indicate that training data based on absolute measured reflectance and atmospheric correction of LANDSAT data can produce comparable accuracy of categorization to that achieved using more conventional relative radiance training. The analysis of the same four categories produced average categorization accuracies of 82.1% by conventional reflative radiance training and 81.9% by use of absolute reflectance signatures.

Klemas, V.↗