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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 865 records · Page 48

All sources NASA NTRS DOE OSTI

DOE OSTI2015

Retrieving 4-dimensional atmospheric boundary layer structure from surface observations and profiles over a single station

Most routine measurements from climate study facilities, such as the Department of Energy’s ARM SGP site, come from individual sites over a long period of time. While single-station data are very useful for many studies, it is challenging to obtain 3-dimensional spatial structures of atmospheric boundary layers that include prominent signatures of deep convection from these data. The principal objective of this project is to create realistic estimates of high-resolution (~ 1km × 1km horizontal grids) atmospheric boundary layer structure and the characteristics of precipitating convection. These characteristics include updraft and downdraft cumulus mass fluxes and cold pool properties over a region the size of a GCM grid column from analyses that assimilate surface mesonet observations of wind, temperature, and water vapor mixing ratio and available profiling data from single or multiple surface stations. The ultimate goal of the project is to enhance our understanding of the properties of mesoscale convective systems and also to improve their representation in analysis and numerical simulations. During the proposed period (09/15/2011–09/14/2014) and the no-cost extension period (09/15/2014–09/14/2015), significant accomplishments have been achieved relating to the stated goals. Efforts have been extended to various research and applications. Results have been published in professional journals and presented in related science team meetings and conferences. These are summarized in the report.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Accurate and Data‐Efficient Micro X‐ray Diffraction Phase Identification Using Multitask Learning: Application to Hydrothermal Fluids

Traditional analysis of highly distorted micro X‐ray diffraction (μ‐XRD) patterns from hydrothermal fluid environments is a time‐consuming process, often requiring substantial data preprocessing and labeled experimental data. Herein, the potential of deep learning with a multitask learning (MTL) architecture to overcome these limitations is demonstrated. MTL models are trained to identify phase information in μ‐XRD patterns, minimizing the need for labeled experimental data and masking preprocessing steps. Notably, MTL models show superior accuracy compared to binary classification convolutional neural networks. Additionally, introducing a tailored cross‐entropy loss function improves MTL model performance. Most significantly, MTL models tuned to analyze raw and unmasked XRD patterns achieve close performance to models analyzing preprocessed data, with minimal accuracy differences. This work indicates that advanced deep learning architectures like MTL can automate arduous data handling tasks, streamline the analysis of distorted XRD patterns, and reduce the reliance on labor‐intensive experimental datasets.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2006

Interfacing with USSTRATCOM and UTTR during Stardust Earth Return

The Stardust Sample Return Capsule separated from the main spacecraft four hours prior to atmospheric entry. Between this time and the time at which the SRC touched down at the Utah Test and Training Range, two organizations external to JPL were involved in tracking the Sample Return Capsule. Orbit determination for the Stardust spacecraft during deep space cruise, the encounters of asteroid Annefrank and comet Wild 2, and the final approach to Earth used X-band radio metric Doppler and range data obtained through the Deep Space Network. The SRC lacked the electronics needed for coherently transponded radio metric tracking, so the DSN was not able to track the SRC after it separated from the main spacecraft. Although the expected delivery accuracy at atmospheric entry was well within the capability needed to target the SRC to the desired ground location, it was still desirable to obtain direct knowledge of the SRC trajectory in case of anomalies. For this reason U.S. Strategic Command was engaged to track the SRC between separation and atmospheric entry. Once the SRC entered the atmosphere, ground sensors at UTTR were tasked to acquire the descending SRC and maintain track during the descent in order to determine the landing location, to which the ground recovery team was then directed. This paper discusses organizational interfaces, data products, and delivery schedules, and the actual tracking operations are described.

Utah Test and Training Range (UTTR)↗

DOE OSTI2026

Variable rate neural compression for sparse detector data

Particle colliders produce data at extraordinary rates, posing major challenges for transmission and storage. High-throughput compression algorithms are therefore essential. In the sPHENIX experiment taking data at the Relativistic Heavy Ion Collider, a time projection chamber records three-dimensional (3D) particle trajectories that are highly sparse, making conventional learning-free lossy compression ineffective. Convolutional neural networks have surpassed traditional methods in compression ratio and accuracy. However, they fail to exploit sparsity for efficiency. To address these gaps, we present BCAE-VS, a bicephalous convolutional autoencoder with variable compression ratio for sparse data, which adapts compression to input complexity through key-point identification and sparse convolution. BCAE-VS achieves higher accuracy and compression ratios than prior neural approaches while being orders of magnitude smaller. Moreover, its throughput increases with sparsity—a property not observed in other methods. Although it was developed for collider experiments, BCAE-VS readily extends to other sparse data domains, such as light detection and ranging (LiDAR) sensing and 3D microscopy.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

NASA NTRS2005

GALEX Study of the UV Variability of Nearby Galaxies and a Deep Probe of the UV Luminosity Function

The proposal has two aims - a deep exposure of NGC 300, about a factor of 10 deeper than the GALEX all-sky survey; and an examination of the UV variability. The data were received just prior to a series of proposal deadlines in early spring. A subsequent analysis delay includes a move from SAO to the University of Texas - San Antonio. Nevertheless, we have merged the data into a single deep exposure as well as undertaking a preliminary examination of the variability. No UV halo is present as detected in the GALEX observation of M83. No UV bursts are visible; however a more stringent limit will only be obtained through a differencing of the sub-images. Papers: we expect 2 papers at about 12 pages/paper to flow from this project. The first paper will report on the time variability while the second will focus on the deep UV image obtained from stacking the individual observations.

Schlegel, Eric↗

DOE OSTI2017

Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams

Analysis of an organization’s computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach’s potential to greatly reduce analyst workloads.

Tuor, Aaron R.↗

NASA NTRS1977

X-band antenna gain and system noise temperature of 64-meter deep space stations

A set of measured data on the X-band performance of the three 64-meter deep space stations was obtained for use in future mission telecommunication design and predictions. The test configuration and measurement procedure is described. A method of modelling attenuation due to the atmosphere is given. Radio source brightness temperature and flux density are reviewed.

Benjauthrit, B.↗

DOE OSTI2017

pnnl/safekit

Some of the most pressing machine learning applications such as cyber security and object recognition lack enough ground-truth training data to build a classifier. We solve this problem by using unsupervised deep learning techniques to determine when data were anomalous or deviated from the norm. Traditional methods require either specific context dependent expertise to construct models, or prior examples of events and large amounts of well-labeled data to perform machine learning. Some cutting-edge deep learning approaches have been used to characterize complex events, but these have not been applied to the streaming environment and require a great deal of data. We demonstrated the use of an autoencoder and relevant featurization techniques to both learn a feature space and then identify anomalous portions without the aid of labeled data or domain knowledge. In this way, we demonstrated the detection of anomalous features without domain knowledge or tagged examples, and delivered these features to users.

Central, PNNL Developer↗

NASA NTRS2006

Mars Reconnaissance Orbiter Ka-band (32 GHz) Demonstration: Cruise Phase Operations

The X-band (8.41 GHz) frequency currently used for deep space telecommunications is too narrow (50 MHz) to support future high rate missions. Because of this NASA has decided to transition to Ka-band (32 GHz) frequencies. As weather effects cause much larger fluctuations on Ka-band than on X-band, the traditional method of using a few dBs of margin to cover these fluctuations is wasteful of power for Ka-band; therefore, a different operations concept is needed for Ka-band links. As part of the development of the operations concept for Ka-band, NASA has implemented a fully functioning Ka-band communications suite on its Mars Reconnaissance Orbiter (MRO). This suite will be used during the primary science phase to develop and refine the Ka-band operations concept for deep space missions. In order to test the functional readiness of the spacecraft and the Deep Space Network's (DSN) readiness to support the demonstration activities a series of passes over DSN 34-m Beam Waveguide (BWG) antennas were scheduled during the cruise phase of the mission. MRO was launched on August 12, 2005 from Kennedy Space Center, Cape Canaveral, Florida, USA and went into Mars Orbit on March 10, 2006. A total of ten telemetry demonstration and one high gain antenna (HGA) calibration passes were allocated to the Ka-band demonstration. Furthermore, a number of "shadow" passes were also scheduled where, during a regular MRO track over a Ka-band capable antenna, Ka-band was identically configured as the X-band and tracked by the station. In addition, nine Ka-band delta differential one way ranging ((delta)DOR) passes were scheduled. During these passes, the spacecraft and the ground system were put through their respective paces. Among the highlights of these was setting a single day record for data return from a deep space spacecraft (133 Gbits) achieved during one 10-hour pass; achieving the highest data rate ever from a planetary mission (6 Mbps) and successfully demonstrating Ka-band DDOR. In addition, DSN performed well. However, there are concerns with the active pointing of the Ka-band antennas as well as delivery of the monitor data from the stations. The spacecraft also presented challenges not normally associated with planetary missions mostly because of its very high equivalent isotropic radiated power (EIRP). This caused problems in accurately evaluating the in-flight EIRP of the spacecraft which led to difficulties evaluating the quality of the HGA calibration data. These led to the development of additional measurement techniques that could be used for future high-power deep space missions.

Mars Reconnaissance Orbiter (MRO)↗

NASA NTRS2006

CFDP Performance over Weather-dependent Ka-band Channel

This study presents an analysis of the delay performance of the CCSDS File Delivery Protocol (CFDP) over weather-dependent Ka-band channel. The Ka-band channel condition is determined by the strength of the atmospheric noise temperature, which is weather dependent. Noise temperature data collected from the Deep Space Network (DSN) Madrid site is used to characterize the correlations between good and bad channel states in a two-state Markov model. Specifically, the probability distribution of file delivery latency using the CFDP deferred Negative Acknowledgement (NAK) mode is derived and quantified. Deep space communication scenarios with different file sizes and bit error rates (BERs) are studied and compared. Furthermore, we also examine the sensitivity of our analysis with respect to different data sampling methods. Our analysis shows that while the weather-dependent channel only results in fairly small increases in the average number of CFDP retransmissions required, the maximum number of transmissions required to complete 99 percentile, on the other hand, is significantly larger for the weather-dependent channel due to the significant correlation of poor weather states.

deep space communications↗

NASA NTRS2006

CFDP Performance over Weather-Dependent Ka-Band Channel

weather↗

DOE OSTI2019

Towards a CAN IDS Based on a Neural Network Data Field Predictor

Modern vehicles contain a few controller area networks (CANs), which allow scores of on-board electronic control units (ECUs) to communicate messages critical to vehicle functions and driver safety. CAN provides a lightweight and reliable broadcast protocol but is bereft of security features. As evidenced by many recent research works, CAN exploits are possible both remotely and with direct access, fueling a growing CAN intrusion detection system (IDS) body of research. A challenge for pioneering vehicle-agnostic IDSs is that passenger vehicles' CAN message encodings are proprietary, defined and held secret by original equipment manufacturers (OEMs). Targeting detection of next-generation attacks, in which messages are sent from the expected ECU at the expected time but with malicious content, researchers are now seeking to leverage "CAN data models'', which predict future CAN messages and use prediction error to identify anomalous, hopefully malicious CAN messages. Yet, current works model CAN signals post-translation, i.e., after applying OEM-donated or reverse-engineered translations from raw data. We present initial IDS results testing deep neural networks used to predict CAN data at the bit level, targeting IDS capabilities that avoiding reverse engineering proprietary encodings. Our results suggest the method is promising for data with signals exhibiting dependence on previous or concurrent inputs.

Pawelec, Krzysztof↗

DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗

NASA NTRS1978

The Deep Space Network

Tracking and data acquisition research and technology for the DSN is discussed.

Source record↗

NASA NTRS2017

Data Production on Past and Future NASA Missions

Data return is a metric that is commonly publicized for all space science missions. In the early days of the Space Program, this figure was small, and could be described in bits or maybe even megabits. But now, missions are capable of returning data volumes two or three orders of magnitude larger. For example, Voyager 1 and 2 combined produced a little over 5 Terabits of data in 39 years of operation. In contrast, the Cassini mission, launched two decades after Voyager, produced about one and a half times those data volumes in half the time. NISAR, an Earth Science Mission currently in implementation, plans to produce over 28 Petabits of raw data in just 3 years. This means that NISAR will produce about as many data in 30 days as the combined data production of nearly all planetary missions to date. These increases in capability are a result of technology enhancements in two main areas: telecommunications architecture (both space and ground segments) and data storage technology. This paper describes the progression of these two technologies over the course of more than three decades of space missions and provides additional insight into the design of the end-to-end NISAR Data System Architecture. Trends in the data are briefly explored and compared to Moore’s Law which provides only a qualitative model for memory growth but not for data production. In summary, early missions are found to be driven by unrefined processes while later missions, having utilized earlier lessons learned, focus more on improvements to flight and ground capabilities. Data return seems to fall into three categories. First, deep space missions are driven by the large distances that limit data return to the Earth. Next, the orbiter infrastructure around Mars helps these missions generate more data than other deep space spacecraft. Finally, near-Earth missions have the greatest capabilities for the studied metrics due to their close proximity to Earth and the ground network availability.

Xaypraseuth, Peter↗

DOE OSTI2022

New data-driven approach to bridging power system protection gaps with deep learning

Protection is a critical function in power systems to avoid equipment damage, maintain personnel safety, and support system reliability. However, current protective relay technology cannot adequately protect equipment and personnel from effects of some events; these deficiencies are termed protection gaps. In this paper, a data-driven approach is proposed to complement traditional protection technology and distinguish fault conditions from transients caused by normal operations. A combined convolutional neural network and long short-term memory (CNN-LSTM) network is implemented to achieve data translation invariance and capture the temporal correlation of the time-series input data. As a result, the data-driven method can accurately detect system faults despite variation and noise in the input data. In addition, using the CNN-LSTM--based method avoids the complicated, manual feature extraction procedure required by many traditional data-driven methods. The effectiveness of the proposed approach is tested on two kinds of protection gaps: high-impedance faults and transformer inter-turn faults. Lastly, a transfer learning method is also proposed to address the common issue of data-driven methods for which real-world training data are scarce. Extensive study results demonstrate that the proposed approach can accurately bridge power system protection gaps.

42 ENGINEERING↗

NASA NTRS2016

Performance Analysis of Operational Ka-Band Link with Kepler

This paper presents some observations on the signal behavior from an analysis of Kepler Ka-band link. The goal is to characterize the link performance with operational data obtained from the Deep Space Network (DSN) tracking of Kepler spacecraft. Kepler is the first mission supported by the DSN that uses Ka-band as a primary means to return science data. We examine how operational data may differ from the expectation. Operational data often show many surprises where data variations occur without an apparent cause. We try to quantify the signal power fluctuation so that future missions can adequately plan for the link design, especially for missions that operate with lower margin. We also attempt to quantify the effect of rains/heavy clouds and high winds.

performance analysis↗

DOE OSTI2017

EVIDENCE FOR REDUCED SPECIFIC STAR FORMATION RATES IN THE CENTERS OF MASSIVE GALAXIES AT z = 4

We perform the first spatially resolved stellar population study of galaxies in the early universe ( z = 3.5–6.5), utilizing the Hubble Space Telescope Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey imaging data set over the GOODS-S field. We select a sample of 418 bright and extended galaxies at z = 3.5–6.5 from a parent sample of ∼8000 photometric-redshift-selected galaxies from Finkelstein et al. We first examine galaxies at 3.5 ≲ z ≲ 4.0 using additional deep K -band survey data from the HAWK-I UDS and GOODS Survey which covers the 4000 Å break at these redshifts. We measure the stellar mass, star formation rate, and dust extinction for galaxy inner and outer regions via spatially resolved spectral energy distribution fitting based on a Markov Chain Monte Carlo algorithm. By comparing specific star formation rates (sSFRs) between inner and outer parts of the galaxies we find that the majority of galaxies with high central mass densities show evidence for a preferentially lower sSFR in their centers than in their outer regions, indicative of reduced sSFRs in their central regions. We also study galaxies at z ∼ 5 and 6 (here limited to high spatial resolution in the rest-frame ultraviolet only), finding that they show sSFRs which are generally independent of radial distance from the center of the galaxies. This indicates that stars are formed uniformly at all radii in massive galaxies at z ∼ 5–6, contrary to massive galaxies at z ≲ 4.

79 ASTRONOMY AND ASTROPHYSICS↗