Search NASA⌕ Search

SEARCH · Search NASA

Results for “long memory”

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 253 records · Page 14

Machine Learning Assisted Safety Modeling and Analysis of Advanced Reactors

With the advances in computational power and numerical methods, analysts can now rely on first-principle simulations to predict ultra-fine details in a variety of applications. Advances in machine learning (ML) have produced algorithms that can now learn high-level abstractions via hierarchical models. This project aims to leverage advances in ML techniques and the available high-resolution simulation data to develop a novel modeling and simulation (M\&S) methodology for reactor safety analysis. While application-agnostic ML techniques are available, complex physics constraints need to be incorporated into ML techniques to build ML-based closures for computationally efficient predictive simulations. This project intends to develop a physics-guided data-driven multi-scale methodology for M\&S of advanced reactors. The project focuses on thermal fluid (T/F) phenomena, which play major roles in advanced reactor safety. Specifically, we propose a data-driven coarse-mesh turbulence model based on local flow features for the transient analysis of thermal mixing and stratification in a sodium-cooled fast reactor (SFR). The model has a coarse-mesh setup to ensure computational efficiency, while it is trained by fine-mesh computational fluid dynamics (CFD) data with Reynolds-averaged Navier-Stokes (RANS) turbulence model to ensure accuracy. Three different neural networks are developed and tested for loss-of-flow transients in the hot pool of SFR, i.e. the densely connected convolutional neural network (DCNN), long-short-term-memory network based on proper orthogonal decomposition (POD-LSTM), and the DCNN informed by LSTM (DCNN-LSTM). The performances of these three neural networks are evaluated based on baseline models. The DCNN-LSTM model has been chosen for further hyperparameter optimization. Furthermore, based on a simplified two-dimensional case, uncertainty quantification (UQ) of the developed ML-based closure are investigated with three methods, i.e. Monte Carlo dropout, deep ensemble, and Bayesian neural network. The developed ML-based turbulent viscosity closure relation based on deep ensemble is then integrated into the system analysis module SAM and serves as a term in the conservation equations. Such a SAM-ML based procedure guarantees that the obtained results are consistent with the physical constraints of the thermal-fluid system. The SAM-ML simulation on the same loss-of-flow transient showed comparable accuracy with the CFD simulation but with a much coarser mesh setup. Last but not least, the ML-based closure improvement with the support of higher-fidelity data from large eddy simulation (LES) is discussed. As a first step towards this direction, a baseline LES simulation is performed to obtain comparable data with RANS results. Based on the early results, future investigation on further improving the ML-based closure is discussed. We believe the developed approach that combines scientific machine learning with nuclear system analysis code can benefit the advanced reactor community as more accurate safety analyses will better characterize reactor safety margins and reduce licensing efforts.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

An LSTM Deep Learning Network for ¿Background Radiation Prediction

Determination of appropriate background radiation is important in any measurement application. Environmental radiation monitors and monitors used to assess dose to individuals outside of controlled areas are particularly susceptible to changes in readings due to fluctuations in the environmental conditions. These fluctuations (e.g. radon progeny concentrations) lead to changes in the detector response in the actual radiation environment, and they need to be taken into account when extracting the net operational doses. Work has been ongoing to apply advances in Deep Learning and Artificial Intelligence to account for changes in detector responses based on environmental parameters; in particular, a Long-Short Term Memory (LSTM) Deep Learning architecture has been utilized to incorporate time-series data into a prediction model. In this work, we present the current status of the project to predict radiation measurements based on meteorological conditions and air packet trajectories extracted using the National Oceanic and Atmospheric Administration's (NOAA) Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT4) model.

Degtiarenko, Pavel↗

DeepCare: Improving Patient Care using Deep Learning on Electronic Health Records

Coordinating patient care using electronic health records (EHR) data presents an exciting but formidable opportunity in data extraction, analysis and modeling. Traditional methods use a manual feature driven approach to model patients with age, family history and symptoms to predict disease outcomes. We propose a novel approach to model patients based on their streaming electronic health records data combined with information from medical knowledge bases, which has been gained over years of medical research. Using a combination of representation learning and long short term memory (LSTM) networks we plan to model patient evolution over time, leading to more accurate and individualized predictive models for patient’s diseases. Our approach will be transformative in providing critical decision support for patient care, enabling accurate understanding and evolution of diseases in patients.

60 APPLIED LIFE SCIENCES↗

Optimizing Prediction Error for Time-dependent Solar Radiation Modeling

Numerical weather forecasting models and statistical methods have found wide use to help power companies estimate renewable output, but better methods are needed, particularly for extended forecasts. Machine learning approaches have been used here as well, but so far a major limitation is the ability to also predict the corresponding uncertainty in a forecast. Here we show that both can be done and demonstrate this using a long-term-short memory neural network where the difference between predicted and ground truth data are used to train a model for the corresponding forecast uncertainties.

97 MATHEMATICS AND COMPUTING↗

Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning

Soil respiration in dryland ecosystems is challenging to model due to its complex interactions with environmental drivers. Knowledge-guided deep learning provides a much more effective means of accurately representing these complex interactions than traditional Q10-based models. Mutual information analysis revealed that future soil temperature shares more information with soil respiration than past soil temperature, consistent with their clockwise diel hysteresis. We explicitly encoded diel hysteresis, soil drying, and soil rewetting effects on soil respiration dynamics in a newly designed Long Short Term Memory (LSTM) model. The model takes both past and future environmental drivers as inputs to predict soil respiration. The new LSTM model substantially outperformed three Q10-based models and the Community Land Model when reproducing the observed soil respiration dynamics in a semi-arid ecosystem. The new LSTM model clearly demonstrated its superiority for temporally extrapolating soil respiration dynamics, such that the resulting correlation with observational data is up to 0.7 while the correlations of the Q10-based models and the Community Land Model (CLM) are less than 0.4. Our results underscore the high potential for knowledge-guided deep learning to replace Q10-based soil respiration modules in Earth system models.

Jiang, Peishi↗

Digital Twin Empowered PV Power Prediction

The accurate prediction of photovoltaic (PV) power generation is significant to ensure the economic and safe operation of power systems. To this end, the paper proposes a new digital twin (DT) empowered PV power prediction framework that is capable of ensuring reliable data transmission and employing the DT to achieve high accuracy of power prediction. With this framework, considering potential data contamination in the collected PV data, a generative adversarial network is employed to restore the historical data set, which offers a prerequisite to ensure accurate mapping from the physical space to the digital space. Further, a new DT empowered PV power prediction method is proposed. Therein, we model a DT that encompasses a digital physical model for reflecting the physical operation mechanism and a neural network model (i.e., a parallel network of convolution and bidirectional long-short-term memory model) for capturing the hidden spatial-temporal features. The proposed method enables the use of the DT to take advantages of the digital physical model and the neural network model, resulting in enhanced prediction accuracy. Finally, a real data set is conducted to access the effectiveness of the proposed method.

14 SOLAR ENERGY↗

On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars

Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse data sets has thus far hampered a direct intercomparison of different approaches. Here we perform the first comprehensive study of variants of NN-based learning and inference for astronomical time series, aiming to provide the community with an overview on relative performance and, hopefully, a set of best-in-class choices for practical implementations. In both supervised and self-supervised contexts, we study the effects of different time-series-compatible layer choices, namely the dilated temporal convolutional neural network (dTCNs), long-short term memory NNs, gated recurrent units and temporal convolutional NNs (tCNNs). Additionally, we also study the efficacy and performance of encoder-decoder (i.e., autoencoder) networks compared to direct classification networks, different pathways to include auxiliary (non-time-series) metadata, and different approaches to incorporate multi-passband data (i.e., multiple time series per source). Performance—applied to a sample of 17,604 variable stars (VSs) from the MAssive Compact Halo Objects (MACHO) survey across 10 imbalanced classes—is measured in training convergence time, classification accuracy, reconstruction error, and generated latent variables. We find that networks with recurrent NNs generally outperform dTCNs and, in many scenarios, yield to similar accuracy as tCNNs. In learning time and memory requirements, convolution-based layers perform better. We conclude by discussing the advantages and limitations of deep architectures for VS classification, with a particular eye toward next-generation surveys such as the Legacy Survey of Space and Time, the Roman Space Telescope, and Zwicky Transient Facility.

79 ASTRONOMY AND ASTROPHYSICS↗

On the design of a postprocessor for a search for extraterrestrial intelligence /SETI/ system

The design of an on-line postprocessor for a search for extraterrestrial intelligence (SETI) system is described. Signal processing tasks of the postprocessor include: (1) analysis of power level, phase coherence, and state of polarization of single-channel signals in a search for significant signals; (2) grouping or aggregation of adjacent channel data, time averaging of data; and (3) the detection of drifting and modulated signals. Control functions include multichannel spectrum analyzer frequency and clock control, system calibration and selfdiagnostic, control of data flow to and from short-term and long-term (archival) memories, and operation of detection subsystems, such as a visual display and a tunable receiver.

Healy, T. J.↗

The suitability of the ILLIAC IV architecture for image processing

The major architectural features of the ILLIAC IV large scale, array processor are summarized along with their applicability to image processing. Several image processing algorithms are considered, including multispectral classification, texture feature extraction, two-dimensional Fourier transform, and synthetic aperture radar processing. The basic parallelism of the ILLIAC IV (64 processing elements acting in lock-step) is usually fully utilized by the image processing applications. The major architectural aspect of the system with respect to image processing is the relatively small local scratch-pad memory and the long latency time to access the main storage device. The major precision used for the image processing applications is the 32-bit floating point, given a choice of 8-bit integers and 64-bit floating point.

Stevenson, D. K.↗

Flight Checklists And Interruptions

Report examines relation between performances of flight checklists and interruptions. Based on study of simulated flights of Boeing 707 Airplane. During each flight series of overlapping problems introduced. Study investigated patterns of communication that in carrying out checklists, may contribute to accidents. Showed good crews had high continuity in following checklists and it is not number of interruptions but rather duration of interruptions associated with quality of performance. Suggests greater burden placed on memory by one long interruption than by several short ones.

Linde, C.↗

Simplified jet-A kinetic mechanism for combustor application

Successful modeling of combustion and emissions in gas turbine engine combustors requires an adequate description of the reaction mechanism. For hydrocarbon oxidation, detailed mechanisms are only available for the simplest types of hydrocarbons such as methane, ethane, acetylene, and propane. These detailed mechanisms contain a large number of chemical species participating simultaneously in many elementary kinetic steps. Current computational fluid dynamic (CFD) models must include fuel vaporization, fuel-air mixing, chemical reactions, and complicated boundary geometries. To simulate these conditions a very sophisticated computer model is required, which requires large computer memory capacity and long run times. Therefore, gas turbine combustion modeling has frequently been simplified by using global reaction mechanisms, which can predict only the quantities of interest: heat release rates, flame temperature, and emissions. Jet fuels are wide-boiling-range hydrocarbons with ranges extending through those of gasoline and kerosene. These fuels are chemically complex, often containing more than 300 components. Jet fuel typically can be characterized as containing 70 vol pct paraffin compounds and 25 vol pct aromatic compounds. A five-step Jet-A fuel mechanism which involves pyrolysis and subsequent oxidation of paraffin and aromatic compounds is presented here. This mechanism is verified by comparing with Jet-A fuel ignition delay time experimental data, and species concentrations obtained from flametube experiments. This five-step mechanism appears to be better than the current one- and two-step mechanisms.

Lee, Chi-Ming↗

Morphology and kainate-receptor immunoreactivity of identified neurons within the entorhinal cortex projecting to superior temporal sulcus in the cynomolgus monkey

Projections of the entorhinal cortex to the hippocampus are well known from the classical studies of Cajal (Ramon y Cajal, 1904) and Lorente de No (1933). Projections from the entorhinal cortex to neocortical areas are less well understood. Such connectivity is likely to underlie the consolidation of long-term declarative memory in neocortical sites. In the present study, a projection arising in layer V of the entorhinal cortex and terminating in a polymodal association area of the superior temporal gyrus has been identified with the use of retrograde tracing. The dendritic arbors of neurons giving rise to this projection were further investigated by cell filling and confocal microscopy with computer reconstruction. This analysis demonstrated that the dendritic arbor of identified projection neurons was largely confined to layer V, with the exception of a solitary, simple apical dendrite occasionally ascending to superficial laminae but often confined to the lamina dissecans (layer IV). Finally, immunoreactivity for glutamate-receptor subunit proteins GluR 5/6/7 of the dendritic arbor of identified entorhinal projection neurons was examined. The solitary apical dendrite of identified entorhinal projection neurons was prominently immunolabeled for GluR 5/6/7, as was the dendritic arbor of basilar dendrites of these neurons. The restriction of the large bulk of the dendritic arbor of identified entorhinal projection neurons to layer V implies that these neurons are likely to be heavily influenced by hippocampal output arriving in the deep layers of the entorhinal cortex. Immunoreactivity for GluR 5/6/7 throughout the dendritic arbor of such neurons indicates that this class of glutamate receptor is in a position to play a prominent role in mediating excitatory neurotransmission within hippocampal-entorhinal circuits.

NASA Discipline Neuroscience↗

Ellicott City Disasters II - Building a Real-Time Predictive Flood Model for Improving Early Warning Systems in Ellicott City, Maryland

As flood events in the United States grow in frequency and intensity, the uses of applied remote sensing analyses are increasingly necessary for effective flood monitoring and warning systems. The NASA DEVELOP Ellicott City Disasters III project investigated the use of machine learning for applications in flood risk detection to support the improvement of early warning systems in Ellicott City, Maryland. To strengthen the efforts of the Howard County Office of Emergency Management (OEM) in building a more robust flood monitoring system, this term built on the predictive capability of the long-short term memory (LSTM) model created by the second term of this DEVELOP project to create a Sequentially Trained Real-time EstimAted Model (STREAM). Enhancements to the model included the integration of both real-time and predicted weather products from the National Weather Service to increase predictive capacity. These weather products were supplemented by stream gauge data from the OEM as well as real-time radar products. The resultant flood risk model was trained to evaluate input variables and predict stage height in Ellicott City in real time. The model, upgraded to predict stage height up to 8 hours in advance, was incorporated into an online dashboard in a user-friendly interface. The project demonstrated the potential for integration of open data and NASA Earth observations into a flood risk forecasting tool capable of informing real-time decision-making.

Erika Munshi↗

Ellicott City Disasters III: Building a Real-Time Statistical Flood Model for Improving Early Warning Systems in Ellicott City, Maryland

As flood events in the United States grow in frequency and intensity, the uses of applied remote sensing analyses are increasingly necessary for effective flood monitoring and warning systems. The NASA DEVELOP Ellicott City Disasters III project investigated the use of machine learning for applications in flood risk detection to support the improvement of early warning systems in Ellicott City, Maryland. To strengthen the efforts of the Howard County Office of Emergency Management (OEM) in building a more robust flood monitoring system, this term built on the predictive capability of the long-short term memory (LSTM) model created by the second term of this DEVELOP project to create a Sequentially Trained Real-time EstimAted Model (STREAM). Enhancements to the model included the integration of both real-time and predicted weather products from the National Weather Service to increase predictive capacity. These weather products were supplemented by stream gauge data from the OEM as well as real-time radar products. The resultant flood risk model was trained to evaluate input variables and predict stage height in Ellicott City in real time. The model, upgraded to predict stage height up to 8 hours in advance, was incorporated into an online dashboard in a user-friendly interface. The project demonstrated the potential for integration of open data and NASA Earth observations into a flood risk forecasting tool capable of informing real-time decision-making.

Erika Munshi↗

Early Information Parameter-Set Analysis for Satellite Close Approaches using Machine Learning

Understanding orbital mechanics is essential in space flight and navigation applications, and leveraging modern force models for flight path projection remains an important aspect in space mission design and operation. However, force models do not capture all the dynamics or perturbations in the space environment and thus are subject to errors in predicting the state vectors. The further out the predicted miss distance between spacecraft is from the time of closest approach (TCA), the larger the propagated errors in the predicted miss distance at TCA is. The dependency on these force models for spacecraft flight state prediction calls for a more reliable method that can quantify, or even reduce, these propagated errors. With recent advances in the field artificial intelligence, specifically in machine and deep learning algorithms, a model that implements these approaches can improve on the modern force model approach. The goal for this work is to provide an early-information decision-making threshold, in order to prioritize risk assessment implementation, given the ongoing increase of space objects. In analyzing the relationship of several parameters from conjunction data messages(CDMs) and solar information, early information becomes viable in miss distance prediction with unsupervised learning techniques, which learn the parameters that are linked together with miss distance and probability of collision (Pc) variables. Another approach implemented for identifying relationships within CDMs is supervised learning, in which a shallow neural network binary classifier learns to distinguish events with Pc values¡108. These parameters detected in the unsupervised process are then applied to a regression neural network, which predicts the miss distance at TCA for a specific event within a given uncertainty bound. For the regression neural network, a Long Short Term Memory (LSTM) neural network is implemented, which yields memory about each time step in an event. Using an LSTM network, the model learns to predict miss distance within 0.2km of the value measured at TCA. Although there is a limited amount of "close miss" data to train a network, the network learns to associate parameters, like large energy dissipation rates with the secondary object, with an elevated Pc

Brianna I. Robertson↗

Multi-Variate LSTM Prediction of Alaska Magnetometer Chain Utilizing a Coupled Model Approach

During periods of rapidly changing geomagnetic conditions electric fields form within the Earth’s surface and induce currents known as geomagnetically induced currents(GICs), which interact with unprotected electrical systems our society relies on. In this study, we train multi-variate Long-Short Term Memory neural networks to predict magnitude of north-south component of the geomagnetic field (|BN|) at multiple ground magnetometer stations across Alaska provided by the SuperMAG database with a future goal of predicting geomagnetic field disturbances. Each neural network is driven by solar wind and interplanetary magnetic field inputs from the NASA OMNI database spanning from 2000–2015 and is fine tuned for each station to maximize the effectiveness in predicting |BN|. The neural networks are then compared against multivariate linear regression models driven with the same inputs at each station using Heidke skill scores with thresholds at the 50, 75, 85, and 99 percentiles for |BN|. The neural network models show significant increases over the linear regression models for |BN| thresholds. We also calculate the Heidke skill scores for d|BN|/dt by deriving d|BN|/dt from |BN| predictions. However, neural network models do not show clear outperformance compared to the linear regression models. To retain the sign information and thus predict BN instead of |BN|, a secondary so-called polarity model is utilized. The polarity model is run in tandem with the neural networks predicting geomagnetic field in a coupled model approach and results in a high correlation between predicted and observed values for all stations. We find this model a promising starting point for a machine learned geomagnetic field model to be expanded upon through increased output time history and fast turnaround times.

Matthew Blandin↗

Document Classification Techniques for Aviation Letters of Agreement

Often when working with technical documents, it is helpful to classify them into specific categories. In this paper, we conduct a thorough review of natural language processing techniques to perform this classification task on Letters of Agreement (LOAs), technical aviation documents outlining rules for utilizing US airspace. We evaluate multiple techniques, including Transfer Learning, for representing the text in the documents as embeddings: unigram and bigram Term Frequency Inverse Document Frequency (TFIDF), Word2Vec, Doc2Vec, GloVe and RoBERTa. We investigate a wide range of classification models: K-Nearest Neighbors, Random Forest, Support Vector Machines (SVM), Logistic Regression, Naive Bayes, Feed-Forward Neural Network, Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM). By comparing the different methods, we found the best overall approach for our task was to use unigram TFIDF representations with SVM while also gaining insight into how the other methodologies performed on a small technical datasets.

Aayushi Batra↗

Document Classification Techniques for Aviation Letters of Agreement

Often when working with historic air traffic management (ATM) documents, it is helpful to classify them into specific categories. In this paper, we conduct a thorough review of natural language processing techniques to perform this classification task on Letters of Agreement (LOAs), technical aviation documents outlining rules for utilizing US airspace. We evaluate multiple techniques for representing the text in the documents as embeddings: unigram and bigram Term Frequency Inverse Document Frequency (TFIDF), Word2Vec, Doc2Vec, GloVe and RoBERTa. We investigate a wide range of classification models: K-Nearest Neighbors, Random Forest, Support Vector Machines (SVM), Logistic Regression, Naive Bayes, Feed-Forward Neural Network, Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM). By comparing the different methods, we found the best overall approach for our task was to use unigram TFIDF representations with SVM while also gaining insight into how the other methodologies performed on a small technical datasets.

ATM↗