Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep 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 1,459 records · Page 81
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Characterization of Operational Performance of Ka-Band Links in Deep Space Network

This paper presents a characterization of performance of 32-GHz Ka-band link in an operational environment. The data come from tracking of Kepler spacecraft by the NASA Deep Space Network (DSN) in the past few years. Ka-band link offers a significant signal-to-noise advantage compared to the more common X- or S-band; however, it is subject to more signal fluctuation caused by the weather. Kepler is the first mission supported by the DSN that solely rely on the higher deep space Ka-band communications link to return its high-rate science data. A well characterization of the operational performance of Kepler would benefit future Ka-band missions, especially for those operating with smaller link margin. The study examines how weather conditions at the DSN facilities (e.g., winds, clouds, rains) affect the received signal, particularly on telemetry data. It addresses questions such as how often the weather affects the link and how much degradation the link could suffer. Among the 22 Ka-band passes in 2012, heavy clouds affected one pass and two passes were impacted by high winds. The adverse weather caused at time as much as 3-dB instantaneous change in the signal to noise ratio (SNR). Estimates of degradation to the SNR as a function of wind speeds are captured based on observations. This study also quantifies the probability distribution of the variation of received signal power. With such information, future missions can better plan their link design. An optimal link design aims for just having enough margin to realize the data return with a targeted probability, with neither having too much margin that it reduces the downlink data rate nor insufficient reserve that causes frequent data outages. The study tries to provide some answers to the questions such as how much does SNR vary from one tracking pass to the next, and what is the cumulative distribution of signal fluctuation. Regarding the signal variation over many tracking passes, we found that the averaged symbol SNR (SSNR) for each pass changed by as much as 4 dB. Some variations were due to geometry such as the changing distance between spacecraft and Earth and different antenna pointing elevations. Other variations seem to be random in nature, reflecting the randomness of operational environments. Some passes were found to be quite stable, with a standard deviation of symbol SNR around 0.25 dB while others had greater variation, up to 1.4 dB. Overall, the cumulative distribution of the symbol SNR reflects that 50% of the fluctuations was less than 0.6 dB, 90% of fluctuation was within 1.6 dB and 95% within 2.2 dB. Some of the challenges in data processing, validation and modeling were captured in this paper. We observed some inconsistent measurements where operational data significantly deviate from a normal expectation. These inconsistent measurements made it hard to develop an accurate and consistent performance model, such as the degradation of signal SNR as a function of high wind. The difficulty was compounded by the fact that there were only a few Ka-band passes observed in high winds.

Pham, Timothy↗
DOE OSTI2019

Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm

With the development of data-driven techniques, building energy prediction on a district level has attracted increasing attention in recent years for revealing energy use patterns and reduction potentials. However, data acquisition in large building groups is difficult and adjacent buildings also interact with each other. To reduce data cost and incorporate the inter-building impact with the data-driven building energy model, this study proposes a deep learning predictive approach that fuses the building network model with a long short-term memory learning model for district-scale building energy modeling. The building network was constructed based on correlations between the energy use intensity of buildings, which can significantly reduce the computational complexity of the deep learning models for energy dynamic prediction. Five typical building groups with energy use data from 2015 to 2018 on two institutional campuses were selected to perform the validation experiment with TensorFlow. Based on the prediction error assessments, the results suggest that for total building energy use intensity prediction, the proposed model can achieve a mean absolute percentage error of 6.66% and a root mean square error of 0.36 kWh/m 2 , compared to 12.05% and 0.63 kWh/m 2 of the conventional artificial neural network model and to 11.06% and 0.89 kWh/m 2 for the support vector regression model.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Advanced data analysis in inertial confinement fusion and high energy density physics

Bayesian analysis enables flexible and rigorous definition of statistical model assumptions with well-characterized propagation of uncertainties and resulting inferences for single-shot, repeated, or even cross-platform data. This approach has a strong history of application to a variety of problems in physical sciences ranging from inference of particle mass from multi-source high-energy particle data to analysis of black-hole characteristics from gravitational wave observations. The recent adoption of Bayesian statistics for analysis and design of high-energy density physics (HEDP) and inertial confinement fusion (ICF) experiments has provided invaluable gains in expert understanding and experiment performance. In this Review, we discuss the basic theory and practical application of the Bayesian statistics framework. We highlight a variety of studies from the HEDP and ICF literature, demonstrating the power of this technique. Due to the computational complexity of multi-physics models needed to analyze HEDP and ICF experiments, Bayesian inference is often not computationally tractable. Two sections are devoted to a review of statistical approximations, efficient inference algorithms, and data-driven methods, such as deep-learning and dimensionality reduction, which play a significant role in enabling use of the Bayesian framework. We provide additional discussion of various applications of Bayesian and machine learning methods that appear to be sparse in the HEDP and ICF literature constituting possible next steps for the community. We conclude by highlighting community needs, the resolution of which will improve trust in data-driven methods that have proven critical for accelerating the design and discovery cycle in many application areas.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Enhancing Electron Microscopy Image Classification Using Data Augmentation

Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep learning applications are scarce and limited. While data augmentation techniques have shown promise for extending image datasets, very little work has been done to understand the impact of combining multiple augmentation methods sequentially or the limits of their effectiveness when combined. Our work addresses this gap by examining how standard and combinatorial data augmentation affects the performance of machine learning models when trained on small datasets for label classification tasks. For our analysis, we generate single, double and quadruple-augmented datasets for a microscopy image classification task using six standard augmentation methods, and compare the resultant improvements observed in binary classification accuracy with three standard image classification models (DenseNet169, MobileNetV2, ResNet101V2). Our experiments show a non-monotonic relationship between the number of simultaneous augmentation methods and classification accuracy, indicating that there is a trade-off between the degree of augmentation and the model performance. These findings suggest that the optimal number of augmentation methods will vary by domain and use case. We also find that the order in which augmentation methods are applied to a limited dataset matters when combining augmentation schemes, with our use case showing performance differences up to 2.6% when the augmentation order is reversed for double-augmented datasets. Our work offers insights to the limits of data augmentation when working on image classification tasks with limited datasets.

Welsman, Jordan A↗
DOE OSTI2021

Direct Observation of the Depth of Active Groundwater Circulation in an Alpine Watershed

Abstract The depth of active groundwater circulation is a fundamental control on stream flows and chemistry in mountain watersheds, yet it remains challenging to characterize and is rarely well constrained. We collected hydraulic conductivity, hydraulic head, temperature, chemical, noble gas, and 3 H/ 3 He groundwater age data from discrete levels in two boreholes 46 and 81 m deep in an alpine watershed, in combination with chemical and age data from shallow groundwater discharge, to discern groundwater flow rates at different depths and directly observe active and inactive groundwater. Vertical head gradients are steep (average of 0.4) and thermal profiles are consistent with typical linear conductive continental geotherms. Groundwater deeper than ∼20 m is distinct from shallow groundwater and creek water in its chemistry, noble gas signature, and age (dominantly >65 years compared to <9 years). Together these results suggest low vertical groundwater flow velocities and a relatively shallow active circulation depth of ∼20 m. This hypothesis is tested with a simple 2‐D numerical fluid flow and heat transport model representing a hillslope transect through the two boreholes. The modeling indicates that the subhorizontally bedded sedimentary rocks underlying the basin are highly anisotropic with low vertical hydraulic conductivity, and at most ∼10% of bedrock recharge (equivalent to <2% of stream baseflow) flows below a depth of 20 m. The study demonstrates the considerable value of discrete‐depth hydrogeologic, chemical, and age data for determining active circulation depth, and illustrates an approach for maximizing the utility of individual boreholes drilled for mountain bedrock aquifer characterization.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Reconstruction and Selection of Neutrino Interactions in MicroBooNE using Deep Convolutional Neural Networks

In this document, we describe a new reconstruction workflow developed for the MicroBooNE experiment. It features the use of Deep Convolutional Neural Networks trained to recognize key structures within the data sufficient for the 3D reconstruction of neutrino interactions within the detector. As a test of the reconstruction utility, the products of the reconstruction workflow are used to select inclusive charged-current (CC) $\nu_e$ and $\nu_\mu$ interactions in both simulated and real MicroBooNE data. In simulation, our $\nu_e$ and $\nu_\mu$ selections achieve an efficiency of 57% and 68\%, respectively, with a purity of 91% and 96%, respectively. We find that these selections are competitive with the inclusive selections used for the most recent MicroBooNE LEE searches. In particular, the CC-$\nu_e$ inclusive selection efficiency improves by over 20% while also improving sample purity. As a first step in quantifying potential bias, the data and Monte Carlo expectati ons are compared for both selections using the MicroBooNE open data. Within statistical and systematic uncertainties, both the electron and muon CC-inclusive event samples agree. A comparison of the real data events chosen by our work and another reconstruction framework shows that the two analyses each identify a sizeable fraction of events the other does not. This suggests that future analyses integrating the strengths of each could lead to combined gains. This work demonstrates, for the first time on real LArTPC data, state-of-the-art neutrino interaction reconstruction centered around deep learning algorithms.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

Smart Preprocessing & Robust Integration Emulator

To achieve the desired particle size of biomass feedstocks during preprocessing for trouble-free handling and conversion to produce biofuels and bioproducts, the raw materials must undergo a crucial milling process. The particle size of biomass plays a critical role in subsequent biofuel manufacturing, where a larger area-to-volume ratio facilitates efficient synthesis while balancing the impact of moisture on biomass storage. To optimize biofuel production efficiency and overcome these challenges, it is imperative to accurately predict the particle size distribution (PSD) of the biomass in the design of efficient preprocessing systems. The population balance model (PBM), upon empirical calibration and validation, can provide rapid prediction of post-milling PSD of granular biomass. However, PSD has limitations related to mass conservation and the absence of moisture considerations. To overcome these drawbacks, a deep learning model called the enhanced deep neural operator (DNO+) is implemented in the code. This model not only retains the capabilities of the PBM in handling complex mapping functions but also incorporates additional factors influencing the system. By considering various experimental conditions such as sieve size and moisture content, the trained DNO+ model can effectively predict the PSD after milling for any given feed PSD. To further reduce the reliance on experimental data, the PBM is integrated into the DNO+ model, resulting in a physics-informed DNO+ (PIDNO+). The PIDNO+ model addresses the non-conservation of quality exhibited by the PBM while inheriting the advantages of the DNO+ model in considering multiple influencing factors. Moreover, the PIDNO+ model significantly reduces the amount of data required for model training. Both deep learning models, i.e., DNO+ and PIDNO+, are excellent in predictive performance, offering swift and accurate machine learning-based predictions. The use of this code that contains these models will assist in guiding the proper milling equipment selection and operational conditions to achieve the desired biomass particle sizes, ensuring the efficiency of subsequent biofuel and bioproduct production processes.

Xia, Yidong [Idaho National Laboratory (INL), Idah↗
DOE OSTI2016

First season MWA EoR power spectrum results at redshift 7

The Murchison Widefield Array (MWA) has collected hundreds of hours of Epoch of Reionization (EoR) data and now faces the challenge of overcoming foreground and systematic contamination to reduce the data to a cosmological measurement. We introduce several novel analysis techniques, such as cable reflection calibration, hyper-resolution gridding kernels, diffuse foreground model subtraction, and quality control methods. Each change to the analysis pipeline is tested against a two-dimensional power spectrum figure of merit to demonstrate improvement. We incorporate the new techniques into a deep integration of 32 hours of MWA data. This data set is used to place a systematic-limited upper limit on the cosmological power spectrum of Δ{sup 2}⩽2.7×10{sup 4} mK{sup 2} at k = 0.27 h Mpc{sup −1} and z = 7.1, consistent with other published limits, and a modest improvement (factor of 1.4) over previous MWA results. From this deep analysis, we have identified a list of improvements to be made to our EoR data analysis strategies. These improvements will be implemented in the future and detailed in upcoming publications.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2011

Identification of Abnormal System Noise Temperature Patterns in Deep Space Network Antennas Using Neural Network Trained Fuzzy Logic

This paper presents the development of a fuzzy logic function trained by an artificial neural network to classify the system noise temperature (SNT) of antennas in the NASA Deep Space Network (DSN). The SNT data were classified into normal, marginal, and abnormal classes. The irregular SNT pattern was further correlated with link margin and weather data. A reasonably good correlation is detected among high SNT, low link margin and the effect of bad weather; however we also saw some unexpected non-correlations which merit further study in the future.

pattern identification↗
DOE OSTI2022

Learning functional priors and posteriors from data and physics

In this work, we develop a new Bayesian framework based on deep neural networks to be able to extrapolate in space-time using historical data and to quantify uncertainties arising from both noisy and gappy data in physical problems. Specifically, the proposed approach has two stages: (1) prior learning and (2) posterior estimation. At the first stage, we employ the physics-informed Generative Adversarial Networks (PI-GAN) to learn a functional prior either from a prescribed function distribution, e.g., Gaussian process, or from historical data and physics. At the second stage, we employ the Hamiltonian Monte Carlo (HMC) method to estimate the posterior in the latent space of PI-GANs. In addition, we use two different approaches to encode the physics: (1) automatic differentiation, used in the physicsinformed neural networks (PINNs) for scenarios with explicitly known partial differential equations (PDEs), and (2) operator regression using the deep operator network (DeepONet) for PDE-agnostic scenarios. We then test the proposed method for (1) meta-learning for one-dimensional regression, and forward/inverse PDE problems (combined with PINNs); (2) PDE-agnostic physical problems (combined with DeepONet), e.g., fractional diffusion as well as saturated stochastic (100-dimensional) flows in heterogeneous porous media; and (3) spatial-temporal regression problems, i.e., inference of a marine riser displacement field using experimental data from the Norwegian Deepwater Programme (NDP). The results demonstrate that the proposed approach can provide accurate predictions as well as uncertainty quantification given very limited scattered and noisy data, since historical data could be available to provide informative priors. In summary, the proposed method is capable of learning flexible functional priors, e.g., both Gaussian and non-Gaussian process, and can be readily extended to big data problems by enabling mini-batch training using stochastic HMC or normalizing flows since the latent space is generally characterized as low dimensional.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS1984

Sideband-Aided Receiver Arrays

Sideband-aided receiver arrays (SARA's) offer way of extracting greater energy per bit in radio data signals. "Slave" receivers obtain modulation information from "master" receiver. Developed for reception of telemetry from vehicles in deep space, SARA concept applicable to commercial data-signal reception whenever two or more antennas are combined.

Butman, S. A.↗
NASA NTRS2007

High-Capacity Communications from Martian Distances

High capacity communications from Martian distances, required for the envisioned human exploration and desirable for data-intensive science missions, is challenging. NASA s Deep Space Network currently requires large antennas to close RF telemetry links operating at kilobit-per-second data rates. To accommodate higher rate communications, NASA is considering means to achieve greater effective aperture at its ground stations. This report, focusing on the return link from Mars to Earth, demonstrates that without excessive research and development expenditure, operational Mars-to-Earth RF communications systems can achieve data rates up to 1 Gbps by 2020 using technology that today is at technology readiness level (TRL) 4-5. Advanced technology to achieve the needed increase in spacecraft power and transmit aperture is feasible at an only moderate increase in spacecraft mass and technology risk. In addition, both power-efficient, near-capacity coding and modulation and greater aperture from the DSN array will be required. In accord with these results and conclusions, investment in the following technologies is recommended:(1) lightweight (1 kg/sq m density) spacecraft antenna systems; (2) a Ka-band receive ground array consisting of relatively small (10-15 m) antennas; (3) coding and modulation technology that reduces spacecraft power by at least 3 dB; and (4) efficient generation of kilowatt-level spacecraft RF power.

Williams, W. Dan↗
NASA NTRS2010

MaROS Strategic Relay Planning and Coordination Interfaces

The Mars Relay Operations Service (MaROS) is designed to provide planning and analysis tools in support of ongoing Mars Network relay operations. Strategic relay planning requires coordination between lander and orbiter mission ground data system (GDS) teams to schedule and execute relay communications passes. MaROS centralizes this process, correlating all data relevant to relay coordination to provide a cohesive picture of the relay state. Service users interact with the system through thin-layer command line and web user interface client applications. Users provide and utilize data such as lander view periods of orbiters, Deep Space Network (DSN) antenna tracks, and reports of relay pass performance. Users upload and download relevant relay data via formally defined and documented file structures including some described in Extensible Markup Language (XML). Clients interface with the system via an http-based Representational State Transfer (ReST) pattern using Javascript Object Notation (JSON) formats. This paper will provide a general overview of the service architecture and detail the software interfaces and considerations for interface design.

Allard, Daniel A.↗
DOE OSTI2016

The first potential energy surfaces for the C{sub 6}H{sup −}–H{sub 2} and C{sub 6}H{sup −}–He collisional systems and their corresponding inelastic cross sections

Molecular anions have recently been detected in the interstellar and circumstellar media. Accurate modeling of their abundance requires calculations of collisional data with the most abundant species that are usually He atoms and H{sub 2} molecules. In this paper, we focus on the collisional excitation of the first observed molecular anion, C{sub 6}H{sup −}, by He and H{sub 2}. Theoretical calculations of collisional cross sections rely generally on ab initio interaction potential energy surfaces (PESs). Hence, we present here the first PESs for the C{sub 6}H{sup −}–H{sub 2} and C{sub 6}H{sup −}–He van der Waals systems. The ab initio energy data for the surfaces were computed at the explicitly correlated coupled cluster with single, double, and scaled perturbative triple excitations level of theory. The method of interpolating moving least squares was used to construct 4D and 2D analytical PESs from these data. Both surfaces are characterized by deep wells and large anisotropies. Analytical models of the PESs were used in scattering calculations to obtain cross sections for low-lying rotational transitions. As could have been anticipated, important differences exist between the He and H{sub 2} cross sections. Conversely, no significant differences exist between the collisions of C{sub 6}H{sup −} with the two species of H{sub 2} (para- and ortho-H{sub 2}). We expect that these new data will help in accurately determining the abundance of the C{sub 6}H{sup −} anions in space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

A comparison of neural network architectures for data-driven reduced-order modeling

The popularity of deep convolutional autoencoders (CAEs) has engendered new and effective reduced-order models (ROMs) for the simulation of large-scale dynamical systems. Despite this, it is still unknown whether deep CAEs provide superior performance over established linear techniques or other network-based methods in all modeling scenarios. To elucidate this, the effect of autoencoder architecture on its associated ROM is studied through the comparison of deep CAEs against two alternatives: a simple fully connected autoencoder, and a novel graph convolutional autoencoder. Through benchmark experiments, it is shown that the superior autoencoder architecture for a given ROM application is highly dependent on the size of the latent space and the structure of the snapshot data, with the proposed architecture demonstrating benefits on data with irregular connectivity when the latent space is sufficiently large.

42 ENGINEERING↗
DOE OSTI2025

Large-scale deep learning for metastasis detection in pathology reports

Objectives No existing algorithm can reliably identify metastasis from pathology reports across multiple cancer types and the entire US population. In this study, we develop a deep learning model that automatically detects patients with metastatic cancer by using pathology reports from many laboratories and of multiple cancer types. Materials and Methods We use 60 471 unstructured pathology reports from 4 Surveillance, Epidemiology, and End Results (SEER) registries. The reports were coded into 1 of 3 labels: metastasis negative, metastases positive, or metastasis undetermined. We utilize a task-specific deep neural network trained from scratch and compare its performance with a widely used large language model (LLM). Results Our deep learning architecture trained on task-specific data outperforms a general-purpose LLM, with a recall of 0.894 compared to 0.824. We quantified model uncertainty and used it to defer reports for human review. We found that retaining 72.9% of reports increased recall from 0.894 to 0.969. Discussion A smaller deep learning architecture trained on task-specific data outperforms a general LLM. Equally critical to model performance is the incorporation of uncertainty quantification, achieved here through an abstention mechanism. Conclusions This study’s finding demonstrate the feasibility of developing algorithms to automatically identify metastatic cancer cases from unstructured pathology reports.

machine learning↗
DOE OSTI2019

Predicting the mechanical response of oligocrystals with deep learning

In this study, we employ data-driven homogenization approaches to predict the particular mechanical evolution of polycrystalline aggregates with tens of individual crystals. In these oligocrystals the differences in stress response due to microstructural variation is pronounced. Shell-like structures produced by metal-based additive manufacturing and the like make the prediction of the behavior of oligocrystals technologically relevant. The predictions of traditional homogenization theories based on grain volumes are not sensitive to variations in local grain neighborhoods. Direct simulation of the local response with crystal plasticity finite element methods is more detailed, but the computations are expensive. To represent the stress-strain response of a polycrystalline sample given its initial grain texture and morphology we have designed a novel neural network that incorporates a convolution component to observe and reduce the information in the crystal texture field and a recursive component to represent the causal nature of the history information. This model exhibits accuracy on par with crystal plasticity simulations at minimal computational cost per prediction.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Using Deep Learning to Derive Shear-Wave Velocity Models from Surface-Wave Dispersion Data

We present a new algorithm for derivations of 1D shear-wave velocity models from surface-wave dispersion data using convolutional neural networks (CNNs). The technique is applied for continental China and the plate boundary region in southern California. Different CNNs are designed for these two regions and are trained using theoretical Rayleigh-wave phase and group velocity images computed from reference 1D VS models. The methodology is tested with 3260 phase–group images for continental China and 4160 phase–group images for southern California. The conversions of these images to velocity profiles take ~23 s for continental China and ~30 s for southern California on a personal laptop with the NVIDIA GeForce GTX 1060 core and a memory of 6 GB. The results obtained by the CNNs show high correlation with previous studies using conventional methods. The effectiveness of the CNN technique makes this fast method an important alternative for deriving shear-wave velocity models from large datasets of surface-wave dispersion data.

Geochemistry & Geophysics↗