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 1,099 records · Page 61
All sourcesNASA NTRSDOE OSTI
NASA NTRS2019

Two Decades Observing Smoke Above Clouds in the South-Eastern Atlantic Ocean: Deep Blue Algorithm Updates and Validation with ORACLES Field Campaign Data

This study presents and evaluates an updated algorithmfor quantification of absorbing aerosols above clouds(AACs) from passive satellite measurements. The focus isbiomass burning in the south-eastern Atlantic Ocean duringthe 2016 and 2017 ObseRvations of Aerosols above CLoudsand their intEractionS (ORACLES) field campaign deployments.The algorithm retrieves the above-cloud aerosoloptical depth (AOD) and underlying liquid cloud opticaldepth and is applied to measurements from the Sea-viewingWide Field-of-view Sensor (SeaWiFS), Moderate ResolutionImaging Spectroradiometer (MODIS), and Visible InfraredImaging Radiometer Suite (VIIRS) from 1997 to 2017. AirborneNASA Ames Spectrometers for Sky-Scanning, Sun-Tracking Atmospheric Research (4STAR) and NASA LangleyHigh Spectral Resolution Lidar 2 (HSRL2) data collectedduring ORACLES provide important validation for spectralAOD for MODIS and VIIRS; as the SeaWiFS missionended in 2010, it cannot be evaluated directly. The 4STARand HSRL2 comparisons are complementary and reveal performancegenerally in line with uncertainty estimates providedby the optimal estimation retrieval framework used. Atpresent the two MODIS-based data records seem the mostreliable, although there are differences between the deployments,which may indicate that the available data are not yetsufficient to provide a robust regional validation. Spatiotemporalpatterns in the data sets are similar, and the time seriesare very strongly correlated with each other (correlationcoefficients from 0.95 to 0.99). Offsets between the satellitedata sets are thought to be chiefly due to differences in absolutecalibration between the sensors. The available validationdata for this type of algorithm are limited to a small numberof field campaigns, and it is strongly recommended that suchairborne measurements continue to be made, both over thesouthern Atlantic Ocean and elsewhere.

Sayer, Andrew M.↗
NASA NTRS2020

Ensemble-Based Deep Learning for Estimating PM2.5 over California with Multisource Big Data Including Wildfire Smoke

Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g. wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.

air quality↗
NASA NTRSDate not supplied

Predicting Adverse Events and their Precursors in Aviation Using Multi-Class Multiple-Instance Learning

In recent years, there has been a rapid growth in the application of machine learning techniques that leverage aviation data collected from commercial airline operations to improve safety. Anomaly detection and predictive maintenance have been the main targets for machine learning applications. However, this paper focuses on the identification of precursors, which is a relatively newer application. Precursors are events correlated with adverse events that happen prior to the adverse event itself. Therefore, precursor mining provides many benefits including understanding the reasons behind a safety incident and the ability to identify signatures, which can be tracked throughout a flight to alert the operators of an potential upcoming adverse event. This work proposes using the multiple-instance learning (MIL) framework, a weakly supervised learning task, combined with a carefully designed Multi-Head Convolutional Neural Networks-Recurrent Neural Networks (MHCNN-RNN) architecture to predict different type of adverse events for any given flights and identify their precursors with little to no post-processing.Results obtained show that the MHCNN-RNN is able to accurately forecast high speed and high path angle events during the approach, and that it is also capable of determining the aircraft’s parameters that are correlated to these events. These parameters can be considered precursors to the events.

multiple instance learning↗
DOE OSTI2017

Beyond Fine Tuning: Adding capacity to leverage few labels

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural networks or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning. Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.

data science↗
DOE OSTI2021

Constrained Block Nonlinear Neural Dynamical Models

Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics. This work explores a novel formulation for data-efficient learning of deep control-oriented nonlinear dynamical models by embedding local model structure and constraints. The proposed method consists of neural network blocks that represent input, state, and output dynamics with constraints placed on the network weights and system variables. For handling partially observable dynamical systems, we utilize a state observer neural network to estimate the states of the system's latent dynamics. We evaluate the performance of the proposed architecture and training methods on system identification tasks for three nonlinear systems: a continuous stirred tank reactor, a two tank interacting system, and an aerodynamics body. Models optimized with a few thousand system state observations accurately represent system dynamics in open loop simulation over thousands of time steps from a single set of initial conditions. Experimental results demonstrate an order of magnitude reduction in open-loop simulation mean squared error for our constrained, block-structured neural models when compared to traditional unstructured and unconstrained neural network models.

Skomski, Elliott↗
DOE OSTI2022

Bat554: Machine Learning for Accelerated Life Prediction and Cell Design

This presentation describes work associated with the early prediction of life and failure modes using machine learning. Key areas which will be highlighted are the generation of synthetic data, the use of deep learning and other machine learning models and the use of machine learning to train life prediction models.

25 ENERGY STORAGE↗
DOE OSTI2023

Green Computing Opportunities & Strategy

Computation is critical to emerging fields of data intensive research, enabling new methodologies, approaches and tools. As the rate of hardware efficiency gains slows, computational time and energy costs increase. To match pace with computation demand, new approaches are needed to keep the opportunity for impact open. Charles Tripp, lead of the Green Computing Catalyzer, discusses research efforts to improve software efficiency to enable faster, less energy-intensive computing.

algorithmic efficiency↗
NASA NTRSDate not supplied

Exploring Radiation, Water and Energy Closure in Key Deep Tropical Regions Over the Last 3 Decades

The closure of global energy and water budgets at various time scales depends heavily upon the on the processes of water and energy exchange in the deep tropics. A key process observed is the change in convection regimes from disorganized convection to organized deep convection. During these periods an imbalance in key tropical regions is observed of water budget terms between observations and atmospheric reanalysis systems, implying that processes are not simulated well. For instance, periods of imbalance in the water budget may be at least partly attributed to precipitation estimates due to the transition between cloud and precipitation systems in which ice cloud affects microwave radar estimates (Lietmann-Niimi et al. 2024, submitted). A recent paper by Hsaio et al (2023, pre-published version) found that the transition process is characterized by wind shear and longwave cloud radiative feedback signatures as well. This is just one example how these processes also affect the radiative fluxes and thus the energy budget at the TOA. In this presentation, we assess the net radiative budget and components in the deep tropics by comparing multiple data products (GEWEX SRB Rel4IP, CERES EBAF/SYN1deg Ed4.2, ISSCP FH, etc.) and describing the temporal variability of energy balance terms across the deep tropics for the period from 1988 to near present in six key oceanic regions. These six key tropical oceanic regions are West Indian Ocean, the south Indian Ocean east, tropical western, central and eastern Pacific Ocean, and Tropical Atlantic Ocean. In these regions we assess the sensitivity of the fluxes as a function of fluctuations in cloud types in response to various larger scale atmospheric processes (e.g. El Niño, Indian Ocean Dipole). We assess this variability of the radiative flux anomalies (including the net TOA, surface and the atmospheric divergence fluxes) against water vapor divergence, cloud properties (include ISCCP “Weather States, Tselioudis et al. 2021) and larger scale wind shear to assess the uncertainties of energy closure in these regions. These are contrasted against the modeled radiative fluxes from ERA-5 and MERRA-2. Ocean buoy measurements of radiative fluxes are utilized to help assess data radiative flux uncertainty over the nearly 40 year period. In general, the variability for overlap periods of these various data products agrees well, but there are significant differences in the net fluxes that vary according to the rendering of surface, atmospheric, aerosol and cloud properties. These differences also affect closure terms and inferences on systematic uncertainties within the observational estimates. We conclude with recommendations for continuing work

Radiation budget↗
NASA NTRS1987

DSS 43 antenna gain analysis for Voyager Uranus encounter: 8.45-GHz radio science data correction

A malfunction of the Deep Space Network (DSN) 64-meter antenna in Australia forced the antenna to operate with a mispositioned subreflector during the Voyager Uranus encounter period (January 24, 1986). Because of changing main reflector shape and quadripod position as a function of elevation angle, the antenna gain and pointing were not as expected, and the 8.45 GHz received signal level changed during the pass. The study described here used the Geometrical Theory of Diffraction (GTD) analysis to determine actual antenna gain and pointing during that period in an attempt to reconstruct the radio science data. It is found that the 1.4 dB of signal variation can be accounted for by antenna geometry changes and pointing error. Suggested modifications to the values measured during the pass are presented. Additionally, an extremely useful tool for the analysis of gravity deformed reflectors was developed for use in future antenna design and analysis projects.

Slobin, S. D.↗
DOE OSTI2024

Integrating the PanDA Workload Management System with the Vera C. Rubin Observatory

The Vera C. Rubin Observatory will produce an unprecedented astronomical data set for studies of the deep and dynamic universe. Its Legacy Survey of Space and Time (LSST) will image the entire southern sky every three to four days and produce tens of petabytes of raw image data and associated calibration data over the course of the experiment’s run. More than 20 terabytes of data must be stored every night, and annual campaigns to reprocess the entire dataset since the beginning of the survey will be conducted over ten years. The Production and Distributed Analysis (PanDA) system was evaluated by the Rubin Observatory Data Management team and selected to serve the Observatory’s needs due to its demonstrated scalability and flexibility over the years, for its Directed Acyclic Graph (DAG) support, its support for multi-site processing, and its highly scalable complex workflows via the intelligent Data Delivery Service (iDDS). PanDA is also being evaluated for prompt processing where data must be processed within 60 seconds after image capture. This paper will briefly describe the Rubin Data Management system and its Data Facilities (DFs). Finally, it will describe in depth the work performed in order to integrate the PanDA system with the Rubin Observatory to be able to run the Rubin Science Pipelines using PanDA.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1986

Usuda Deep Space Center support for ICE

The planning, implementation and operations that took place to enable the Usuda, Japan, Deep Space Center to support the International Cometary Explorer (ICE) mission are summarized. The results show that even on very short notification our two countries can provide mutual support to help ensure mission success. The data recovery at the Usuda Deep Space Center contributed significantly to providing the required continuity of the experimental data stream at the encounter of the Comet Giacobini-Zinner.

Goodwin, J. P.↗
DOE OSTI2024

Physics-informed State-space Neural Networks for transport phenomena

This work introduces Physics -informed State -space neural network Models (PSMs), a novel solution to achieving real-time optimization, flexibility, and fault tolerance in autonomous systems, particularly in transportdominated systems such as chemical, biomedical, and power plants. Traditional data -driven methods fall short due to a lack of physical constraints like mass conservation; PSMs address this issue by training deep neural networks with sensor data and physics -informing using components' Partial Differential Equations (PDEs), resulting in a physics -constrained, end -to -end differentiable forward dynamics model. Further, through two in silico experiments - a heated channel and a cooling system loop - we demonstrate that PSMs offer a more accurate approach than a purely data -driven model. In the former experiment, PSMs demonstrated significantly lower average root -mean -square errors across test datasets compared to a purely data -driven neural network, with reductions of 44 %, 48 %, and 94 % in predicting pressure, velocity, and temperature, respectively. Beyond accuracy, PSMs demonstrate a compelling multitask capability, making them highly versatile. In this work, we showcase two: supervisory control of a nonlinear system through a sequentially updated state -space representation and the proposal of a diagnostic algorithm using residuals from each of the PDEs. The former demonstrates PSMs' ability to handle constant and time -dependent constraints, while the latter illustrates their value in system diagnostics and fault detection.

42 ENGINEERING↗
DOE OSTI2022

A comparison of deep-learning-based inpainting techniques for experimental X-ray scattering

The implementation is proposed of image inpainting techniques for the reconstruction of gaps in experimental X-ray scattering data. The proposed methods use deep learning neural network architectures, such as convolutional autoencoders, tunable U-Nets, partial convolution neural networks and mixed-scale dense networks, to reconstruct the missing information in experimental scattering images. In particular, the recovered pixel intensities are evaluated against their corresponding ground-truth values using the mean absolute error and the correlation coefficient metrics. The results demonstrate that the proposed methods achieve better performance than traditional inpainting algorithms such as biharmonic functions. Overall, tunable U-Net and mixed-scale dense network architectures achieved the best reconstruction performance among all the tested algorithms, with correlation coefficient scores greater than 0.9980.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗
DOE OSTI2024

Dataset for "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models" Willard et al. (2024)

This data release provides all data and code used in the paper " "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models" Willard et al. (2024)" to model stream temperature, evaluate, and assess results. The associated manuscript explores current open questions in prediction in ungauged and unmonitored basins concerning top-down versus bottom-up approaches, tradeoffs between data available and input requirements, and the appropriate representation of catchment attributes as inputs to deep learning models. Modeling was done primarily with long short-term memory (LSTM) models, and stream site coverage spans 1362 locations across the conterminous United States. The data is organized into these items items:Code repository and data for the paper " "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models" Willard et al. (2024)".Code: stream_temp_ml_regionalization.zip contains the code repositoryData to run the code: - data_dir.zip -- contains all files that should be moved to the "DATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- metadata_dir.zip -- contains all files that should be moved to the "METADATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- error_analysis_attribute_and_groundwater_dir.zip - workflows for the extended error analysis by stream attribute and groundwater influenceData produced by the code and used in the paper:- outputs_dir.zip - contains model output and results (outputs_dir/results), model weights (outputs_dir/models), and all other outputs used for the paper including feature importances.To cite this code, please use the following BibTeX or MLA entries:bibtex:@misc{willard2024streamdata, author = {Jared Willard and Fabio Ciulla and Helen Weierbach and Vipin Kumar and Charuleka Varadharajan}, title = {Dataset for "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models"}, year = {2024}, doi = {10.15485/2448016}, publisher = {ESS-DIVE Repository}, url = {https://doi.org/10.15485/2448016}}MLA: Willard, Jared, et al. Dataset for "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models". 2024. ESS-DIVE Repository, doi:10.15485/2448016.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2016

Deep Borehole Field Test Research Activities at LBNL

The goal of the U.S. Department of Energy Used Fuel Disposition’s (UFD) Deep Borehole Field Test is to drill two 5 km large-diameter boreholes: a characterization borehole with a bottom-hole diameter of 8.5 inches and a field test borehole with a bottom-hole diameter of 17 inches. These boreholes will be used to demonstrate the ability to drill such holes in crystalline rocks, effectively characterize the bedrock repository system using geophysical, geochemical, and hydrological techniques, and emplace and retrieve test waste packages. These studies will be used to test the deep borehole disposal concept, which requires a hydrologically isolated environment characterized by low permeability, stable fluid density, reducing fluid chemistry conditions, and an effective borehole seal. During FY16, Lawrence Berkeley National Laboratory scientists conducted a number of research studies to support the UFD Deep Borehole Field Test effort. This work included providing supporting data for the Los Alamos National Laboratory geologic framework model for the proposed deep borehole site, conducting an analog study using an extensive suite of geoscience data and samples from a deep (2.5 km) research borehole in Sweden, conducting laboratory experiments and coupled process modeling related to borehole seals, and developing a suite of potential techniques that could be applied to the characterization and monitoring of the deep borehole environment. The results of these studies are presented in this report.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗