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 919 records · Page 51
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Determination of the position of Jupiter from radio metric tracking of Voyager 1

The Voyager 1 spacecraft flew by Jupiter on March 5, 1979. Spacecraft navigation was performed with radio tracking data from NASA's Deep Space Network. In the years since then, there has been a great deal of progress in the definition of celestial reference frames and in determining the orbit and orientation of the Earth. Using these improvements, the radio metric range and Doppler data acquired from the Voyager 1 spacecraft near its encounter with Jupiter have been reanalyzed to determine the plane-of-sky position of Jupiter with much greater accuracy than was possible at the time of the encounter. The position of Jupiter at the time of encounter has been determined with an accuracy of 40 nrad in right ascension and 140 nrad in declination with respect to the celestial reference frame defined by the International Earth Rotation Service. This position estimate has been done to improve the ephemeris of Jupiter prior to the upcoming encounter of the Galileo spacecraft with Jupiter.

Folkner, W. M.↗
NASA NTRS2020

Amino Acid Encoding for Deep Learning Applications

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-ofthe-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Hesham ElAbd↗
NASA NTRS2020

Amino Acid Encoding for Deep Learning Applications

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Deep-learning↗
NASA NTRS1983

Cycle life test and failure model of nickel-hydrogen cells

Six ampere hour individual pressure vessel nickel hydrogen cells were charge/discharge cycled to failure. Failure as used here is defined to occur when the end of discharge voltage degraded to 0.9 volts. They were cycled under a low earth orbit cycle regime to a deep depth of discharge (80 percent of rated ampere hour capacity). Both cell designs were fabricated by the same manufacturer and represent current state of the art. A failure model was advanced which suggests both cell designs have inadequate volume tolerance characteristics. The limited existing data base at a deep depth of discharge (DOD) was expanded. Two cells of each design were cycled. One COMSAT cell failed at cycle 1712 and the other failed at cycle 1875. For the Air Force/Hughes cells, one cell failed at cycle 2250 and the other failed at cycle 2638. All cells, of both designs, failed due to low end of discharge voltage (0.9 volts). No cell failed due to electrical shorts. After cell failure, three different reconditioning tests (deep discharge, physical reorientation, and open circuit voltage stand) were conducted on all cells of each design. A fourth reconditioning test (electrolyte addition) was conducted on one cell of each design. In addition post cycle cell teardown and failure analysis were performed on the one cell of each design which did not have electrolyte added after failure.

Smithrick, J. J.↗
NASA NTRS1983

Cycle life test and failure model of nickel-hydrogen cells

Six ampere hour individual pressure vessel nickel hydrogen cells were charge/discharge cycled to failure. Failure as used here is defined to occur when the end of discharge voltage degraded to 0.9 volts. They were cycled under a low earth orbit cycle regime to a deep depth of discharge (80 percent of rated ampere hour capacity). Both cell designs were fabricated by the same manufacturer and represent current state of the art. A failure model was advanced which suggests both cell designs have inadequate volume tolerance characteristics. The limited existing data base at a deep depth of discharge (DOD) was expanded. Two cells of each design were cycled. One COMSAT cell failed at cycle 1712 and the other failed at cycle 1875. For the Air Force/Hughes cells, one cell failed at cycle 2250 and the other failed at cycle 2638. All cells, of both designs, failed due to low end of discharge voltage (0.9 volts). No cell failed due to electrical shorts. After cell failure, three different reconditioning tests (deep discharge, physical reorientation, and open circuit voltage stand) were conducted on all cells of each design. A fourth reconditioning test (electrolyte addition) was conducted on one cell of each design. In addition post cycle cell teardown and failure analysis were performed on the one cell of each design which did not have electrolyte added after failure. Previously announced in STAR as N83-25038

Smithrick, J. J.↗
DOE OSTI2018

Biologically inspired approaches for biosurveillance anomaly detection and data fusion

This study developed and tested biologically inspired computational methods to detect anomalous signals in data streams that could indicate a pending outbreak or bio-weapon attack. Current large-scale biosurveillance systems are plagued by two principal deficiencies: (1) timely detection of disease-indicating signals in noisy data and (2) anomaly detection across multiple channels. Anomaly detectors and data fusion components modeled after human immune system processes were tested against a variety of natural and synthetic surveillance datasets. A pilot scale immune-system-based biosurveillance system performed at least as well as traditional statistical anomaly detection data fusion approaches. Machine learning approaches leveraging Deep Learning recurrent neural networks were developed and applied to challenging unstructured and multimodal health surveillance data. Within the limits imposed of data availability, both immune systems and deep learning methods were found to improve anomaly detection and data fusion performance for particularly challenging data subsets.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Data-driven global ocean modeling for seasonal to decadal prediction

Accurate modeling of ocean dynamics is crucial for enhancing our understanding of complex ocean circulation processes, predicting climate variability, and tackling challenges posed by climate change. Although great efforts have been made to improve traditional numerical models, predicting global ocean variability over multiyear scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), a data-driven three-dimensional ocean model for seasonal to decadal prediction of global ocean dynamics. ORCA-DL accurately simulates the three-dimensional structure of global ocean dynamics with high physical consistency and outperforms state-of-the-art numerical models in capturing extreme events, including El Niño–Southern Oscillation and upper ocean heat waves. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections. Our results demonstrate the high potential of data-driven models for providing efficient and accurate global ocean modeling and prediction.

Science & Technology - Other Topics↗
NASA NTRS1990

Resource Allocation Planning Helper (RALPH): Lessons learned

The current task of Resource Allocation Process includes the planning and apportionment of JPL's Ground Data System composed of the Deep Space Network and Mission Control and Computing Center facilities. The addition of the data driven, rule based planning system, RALPH, has expanded the planning horizon from 8 weeks to 10 years and has resulted in large labor savings. Use of the system has also resulted in important improvements in science return through enhanced resource utilization. In addition, RALPH has been instrumental in supporting rapid turn around for an increased volume of special what if studies. The status of RALPH is briefly reviewed and important lessons learned from the creation of an highly functional design team are focused on through an evolutionary design and implementation period in which an AI shell was selected, prototyped, and ultimately abandoned, and through the fundamental changes to the very process that spawned the tool kit. Principal topics include proper integration of software tools within the planning environment, transition from prototype to delivered to delivered software, changes in the planning methodology as a result of evolving software capabilities and creation of the ability to develop and process generic requirements to allow planning flexibility.

Durham, Ralph↗
NASA NTRS1991

Emerging standards for still image compression: A software implementation and simulation study

The software implementation is described of an emerging standard for the lossy compression of continuous tone still images. This software program can be used to compress planetary images and other 2-D instrument data. It provides a high compression image coding capability that preserves image fidelity at compression rates competitive or superior to most known techniques. This software implementation confirms the usefulness of such data compression and allows its performance to be compared with other schemes used in deep space missions and for data based storage.

Pollara, F.↗
DOE OSTI2024

DLSIA: Deep Learning for Scientific Image Analysis

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1986

Digital transmitter - Simple, yet precise

A transmitter developed for operation at high digital transmission speeds is described. It is a complex system that produces a clean waveform with data rates as high as 1 Mb/s; and its design makes it possible to vary all possible modulation schemes by reprogramming a chip, to vary data-transmission rates with the clock frequency, and to shape pulses without distortion. The design, furthermore, can be adapted to very-large-scale-integration (VLSI) fabrication and mass production. A prototype QPSK residual carrier modulation transmitter was fabricated and tested. The purpose was to create a deep null in the data spectrum to transmit a tone or residual carrier along with the modulation.

Davarian, F.↗
DOE OSTI2022

Hardware-accelerated inference for real-time gravitational-wave astronomy

The field of transient astronomy has seen a revolution with the first gravitational-wave detections and the arrival of multi-messenger observations they enabled. Transformed by the first detection of binary black hole and binary neutron star mergers, computational demands in gravitational-wave astronomy are expected to grow by at least a factor of two over the next five years as the global network of kilometer-scale interferometers are brought to design sensitivity. With the increase in detector sensitivity, real-time delivery of gravitational-wave alerts will become increasingly important as an enabler of multi-messenger followup. In this work, we report a novel implementation and deployment of deep learning inference for real-time gravitational-wave data denoising and astrophysical source identification. This is accomplished using a generic Inference-as-a-Service model that is capable of adapting to the future needs of gravitational-wave data analysis. Overall, our implementation allows seamless incorporation of hardware accelerators and also enables the use of commercial or private (dedicated) as-a-service computing. Based on our results, we propose a paradigm shift in low-latency and offline computing in gravitational-wave astronomy. Such a shift can address key challenges in peak-usage, scalability and reliability, and provide a data analysis platform particularly optimized for deep learning applications. The achieved sub-millisecond scale latency will also be relevant for any machine learning-based real-time control systems that may be invoked in the operation of near-future and next generation ground-based laser interferometers, as well as the front-end collection, distribution and processing of data from such instruments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data

Abstract Artificial intelligence (AI) and machine learning (ML) have been increasingly used in materials science to build predictive models and accelerate discovery. For selected properties, availability of large databases has also facilitated application of deep learning (DL) and transfer learning (TL). However, unavailability of large datasets for a majority of properties prohibits widespread application of DL/TL. We present a cross-property deep-transfer-learning framework that leverages models trained on large datasets to build models on small datasets of different properties. We test the proposed framework on 39 computational and two experimental datasets and find that the TL models with only elemental fractions as input outperform ML/DL models trained from scratch even when they are allowed to use physical attributes as input, for 27/39 (≈ 69%) computational and both the experimental datasets. We believe that the proposed framework can be widely useful to tackle the small data challenge in applying AI/ML in materials science.

36 MATERIALS SCIENCE↗
NASA NTRS2012

Development of the Optical Communications Telescope Laboratory: A Laser Communications Relay Demonstration Ground Station

The Laser Communications Relay Demonstration (LCRD) project will demonstrate high bandwidth space to ground bi-directional optical communications links between a geosynchronous satellite and two LCRD optical ground stations located in the southwestern United States. The project plans to operate for two years with a possible extension to five. Objectives of the demonstration include the development of operational strategies to prototype optical link and relay services for the next generation tracking and data relay satellites. Key technologies to be demonstrated include adaptive optics to correct for clear air turbulence-induced wave front aberrations on the downlink, and advanced networking concepts for assured and automated data delivery. Expanded link availability will be demonstrated by supporting operations at small sun-Earth-probe angles. Planned optical modulation formats support future concepts of near-Earth satellite user services to a maximum of 1.244 Gb/s differential phase shift keying modulation and pulse position modulations formats for deep space links at data rates up to 311 Mb/s. Atmospheric monitoring instruments that will characterize the optical channel during the link include a sun photometer to measure atmospheric transmittance, a solar scintillometer, and a cloud camera to measure the line of sight cloud cover. This paper describes the planned development of the JPL optical ground station.

optical commuication↗
DOE OSTI2022

Risk-Informed Operations and Maintenance Decision Making Using Deep Reinforcement Learning

A challenge for operating nuclear power plants is the significant cost of operations and maintenance, at times consuming up to 66% of annual operating costs. This project aims to build a framework for a risk-informed asset-management tool that integrates inspections, repairs, spare-part inventory, supply chain, and business choices to lower overall O&M costs. Our approach uses a combination of data-driven modeling and deep reinforcement learning to create and implement optimal maintenance policies for the existing nuclear fleet, as well as new advanced reactors. The creation of an asset management tool that uses these advanced methods will give operators new capabilities to help reduce the burden of O&M spending in nuclear power plants.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2018

Hawthorne Nevada Deep Direct-Use Feasibility Study - Temperature and Geochemistry Well Data

The objective of this project is to use a multi-disciplinary, three-tiered approach to assess the geothermal resource and determine the feasibility of implementing a large-scale, direct-use facility for the Hawthorne Army Depot (HAD) and the various town and county facilities in Hawthorne, Nevada. This assessment directly targets a geothermal resource recently characterized by the Navy Geothermal Program Office (GPO) as part of a focused exploration and development campaign. This data batch contains: Zip file containing well and water data from 2002, including reports, isotope analysis, shallow well data, and data by well; Zip folder containing 2009 GPO well data including well logs, geochemistry, and mud logs; Compiled data from 2010 in excel and word format; 2010 Final data from TG, well HAD-1; Zip file containing PDFs and Excel files for wells Haw1, HAD1, HWADD2-3, HWAD4-5; Zip folder containing Word docs and images pertaining to final well reports and discussion.

15 GEOTHERMAL ENERGY↗