Results for “Deep” — Page 68

NASA NTRSDate not supplied

NASA's Deep Space Network (DSN) Lunar Exploration Upgrades (DLEU)

In the near future, the National Aeronautics and Space Administration (NASA) will return to the moon beginning the next era of human exploration. NASA’s Space Communications and Navigation (SCaN) program will play a vital role in establishing communications and navigation support to realize the ambitious goals of the Artemis program. SCaN’s overall lunar communications support plan will be covered in a separate 2023 SpaceOps paper: “NASA’s Communications and Navigation Architecture Plans to Support the Return to the Moon and a Sustainable Lunar Presence”. The plan as it currently stands, includes a three-fold approach of lunar relay services, a dedicated set of new ground stations and support through the Deep Space Network (DSN). This paper will have a more granular focus on the DSN and NASA’s plans to upgrade and expand the network to be better suited for human spaceflight on and around the lunar surface. NASA’s Deep Space Network (DSN) will be a critical communications component for the upcoming lunar activities. There will be multiple spacecraft, using different bands, and some of those spacecraft will be transmitting and receiving using multiple bands, requiring DSN support of S-band (2 GHz), X-band (7 GHz up, 8 GHz down), and K-band (22.5 GHz up, 26 GHz down). Since there may be more than one spacecraft in the beamwidth of the DSN antennas, the DSN support will require an extension of the DSN’s capability to support multiple spacecraft using one antenna, expanding it to provide two simultaneous uplinks in the different bands at each antenna. Achieving this requires using new techniques for manufacturing the frequency selective surfaces, called dichroics, which steer the different frequency beams from and to the appropriate transmitting and receiving equipment, along with the addition of a new K-band uplink system. Additionally, due to the relative closeness of the moon from Earth (as opposed to the planetary missions the DSN supports daily), significantly higher data rates on both uplink and downlink are required, specifically up to 20 Mbps on the uplink and 150 Mbps on the downlink, both using Low Density Parity Check (LDPC) error correcting codes. And, again due to the relative closeness of the moon, there is a need for low latency data delivery of the high rate downlink telemetry which requires a change in the current DSN paradigm of delivering higher rate data with higher latency.

deep space network↗

NASA NTRSDate not supplied

Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network

This paper studies the Multiple Sources and Multiple Destinations (MSMD) routing problem in a dynamic Air-to-Air Ad-hoc Network (AAAN). We consider a spectrum limited scenario where multiple links have to share the same frequency channel so that co-channel interference becomes inevitable. As a result, routing decisions and spectrum access are coupled and must be jointly considered. This paper proposes a deep Q-learning based algorithm to find an optimal routing and channel selection strategy that minimizes the end-to-end communication delay. Specifically, under the assumption that only local information is available to every node, the Deep Q-Network (DQN) is trained offline to learn the optimal routing and channel selection strategy. After the trained DQN is implemented in every node, multiple relay nodes can simultaneously determine their next-hop relay and channel selections in real-time. Simulation results demonstrate the efficacy of our proposed algorithm.

AAAN↗

NASA NTRSDate not supplied

Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network

This paper studies the Multiple Sources and Multiple Destinations (MSMD) routing problem in a dynamic Air-to-Air Ad-hoc Network (AAAN). We consider a spectrum limited scenario where multiple links have to share the same frequency channel so that co-channel interference becomes inevitable. As a result, routing decisions and spectrum access are coupled and must be jointly considered. This paper proposes a deep Q-learning based algorithm to find an optimal routing and channel selection strategy that minimizes the end-to-end communication delay. Specifically, under the assumption that only local information is available to every node, the Deep Q-Network (DQN) is trained offline to learn the optimal routing and channel selection strategy. After the trained DQN is implemented in every node, multiple relay nodes can simultaneously determine their next-hop relay and channel selections in real-time. Simulation results demonstrate the efficacy of our proposed algorithm.

AAAN↗

NASA NTRSDate not supplied

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

NASA NTRSDate not supplied

Anomaly Detection in Flight Operational Data Using Deep Learning

In this session, we demonstrate two recently developed deep learning models for anomaly detection in flight operational data by the Data Sciences Group at NASA Ames Research Center. The first model is Convolutional Variational Auto-Encoder (CVAE) [1], which is an unsupervised deep encoder-decoder model, designed specifically for finding anomalies in heterogeneous multivariate time series data. We will demonstrate its application to finding anomalies in streaming data from NASA’s Digital Information Platform’s Fuser source. CVAE identifies data instances that are not representative of expected nominal behavior as anomalous. Since it is an unsupervised approach, the flagged anomalies will need to be reviewed by the subject matter experts (SMEs) for validation and labeling and is designed to assist with vulnerability discovery within Safety Monitoring System programs. The second model is Robust and Explainable Semi-supervised Anomaly Detection (RESAD) model [2], which builds on CVAE to allow learning from both minimally labeled data (previously reviewed by the SMEs) as well as majority unlabeled data. RESAD takes advantage of graph theoretic techniques to propagate the labels from the labeled data to the unlabeled data based on a pre-defined similarity metric and structures the learned feature space from flight time-series so that data of the same class would cluster tightly together. This model characteristic is enabled by training with an augmented loss function and allows learning of a more informative feature space for down-stream tasks such as search and active learning. We demonstrate RESAD using data from the NASA DASHlink project [3].

anomaly detection↗

NASA NTRSDate not supplied

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

NASA NTRS2024

VIIRS Version 2 Deep Blue Aerosol Products

NASA's Deep Blue aerosol project has developed global aerosol data records using consistent retrieval algorithms applied to various satellite sensors. The primary components of these data records are derived from the series of Visible Infrared Imaging Radiometer Suite (VIIRS) aboard the Suomi National Polar-orbiting Partnership (SNPP) and the National Oceanic and Atmospheric Administration or NOAA-20+ satellites as well as the Moderate Resolution Imaging Spectroradiometer (MODIS), among others. These instruments provide over 23 years of measurements with similar radiometric characteristics for aerosol retrievals. The algorithms used for the initial Version 1 SNPP VIIRS data set were based on the MODIS Collection 6.1 Deep Blue algorithm over land and Satellite Ocean Aerosol Retrieval (SOAR) algorithm over water. For VIIRS Version 2 data reprocessing, major updates have been made to the algorithm suite, including better accounting for effects of surface pressure, improved determination of surface reflectance, and the inclusion of fine-mode aerosol optical models to better represent anthropogenic aerosols over land. Cross-calibration gain factors are derived for the NOAA-20 VIIRS measurements to be consistent with the SNPP VIIRS, which allows the use of a unified algorithm package for both instruments. Comparisons against AERONET observations indicate that the Version 2 AOD data from SNPP VIIRS are significantly better than the Version 1 counterpart over land and slightly degraded over water in exchange for better spatial coverage. The AOD data from SNPP and NOAA-20 VIIRS are comparable, indicating that cross-calibration enables the creation of consistent aerosol data records using the series of VIIRS sensors.

Deep Blue↗

NASA NTRSDate not supplied

The Application of Artificial Intelligence and Deep Learning to Visually Identify Micrometeoroid and Orbital Debris Impacts

Recent advancements in Artificial Intelligence (AI) have made Machine Learning (ML) techniques readily available for practical applications while using a fraction of time that was previously required. In particular, the use of Deep Learning (DL) algorithms has advanced the field of image and pattern recognition. With the use of Deep Learning algorithms, Micrometeoroid and Orbital Debris(MMOD) penetrations can be identified with high accuracy and give possibilities to new understandings of hypervelocity impacts.

Deep Learning↗

NASA NTRSDate not supplied

Observation of Deep Convective Cloud-Top Height and Vertical Temperature Structure of Hurricane Using Hyperspectral Infrared Sounder and its Single-Field-View Retrieval Products

A new method utilizing hyperspectral infrared sounders is developed to estimate cloud top height (CTH) for deep convective clouds from hurricane, or tropical cyclone (TC). By analyzing measurements from the Cross-track Infrared Sounder (CrIS), and further validating with radiative transfer simulations, we identified an inverted-V spectral feature in the ozone (O3) band near 9.6 μm, which correlates with deep convective clouds. The depth of this feature can be used to estimate the CTH of a TC's eyewall and surrounding rain bands. This approach effectively captures the cloud structure of the TC. Additionally, a new single Field of View sounder products (SiFSAP), derived from CrIS and the Advanced Technology Microwave Sounder (ATMS), will be used to analyze the vertical temperature and water vapor structure, offering more insights into TC dynamics.

Single-field-view retrieval↗

NASA NTRSDate not supplied

First N 2 Profile for Venus’ Deep Lower Atmosphere

We present the first N 2 profile for Venus’ deep lower atmosphere (<15 km) and a constrained isotopic composition for cloud N 2 [1]. This work directly addresses unresolved questions for Venus using legacy observations. Prior to this work, there were no reported measurements for N 2 abundances at <15 km and the isotopic composition remained unconstrained [2]. The N 2 parameters are critical to understanding the evolution and thermal properties of the atmosphere [3-7]. Our N 2 results were obtained by re-analysis of data acquired in 1978 by the Pioneer Venus Large Probe Neutral Mass Spectrometer (LNMS) [8]. The archived mass spectra from 64.2 to 0.2 km were treated using the analytical procedures specifically developed for the LNMS [9-11]. Judicious peak fitting permitted disambiguation of (A) N 2 + and CO + at 28 u and (B) 14 N 15 N+, 13 CO + , and C 2 H 5 + at 29 u. Quality controls included comparing the (A) LNMS CO + /CO 2 + ratios to the NIST database and literature and (B) fitted counts for CO + to the expected counts of CO + calculated from C 18 O + and 13 CO + using the LNMS 16 O/ 18 O and 12 C/ 13 C ratios (obtained from CO 2 ). Our results show that N 2 is uniformly mixed across the deep lower atmosphere between ~0.2 and 15 km (2.49 ± 0.10 v%). In contrast, N 2 is non-uniformly mixed across the sub-cloud atmosphere and clouds (~15–59 km), where N 2 abundances increase by ~ 2-fold between ~15 km (2.45 ± 0.32 v%) and ~59-51 km (5.21 ± 0.18 v%). Using the cloud data, we also obtained a constrained 15 N/ 14 N ratio (2.93×10 -3 ± 0.13×10 -3 ) and δ 15 N value (-204 ± 35‰). Thus, the LNMS results [1] suggest that (A) the atmosphere is unstable at <15 km, (B) N 2 is not well-mixed >15 km, and (C) the cloud δ 15 N falls between Earth and the solar wind [12, 13]. Comparisons of the N 2 abundances and isotopic compositions for nitrogen, carbon, and oxygen to other Venus measurements will be discussed.

deep lower atmosphere↗

DOE OSTI2016

A Deep Generative Deconvolutional Image Model

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic unpooling is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-layer features, yielding max-margin discrimination. Deep deconvolutional inference is employed when testing, to infer the latent features, and the top-layer features are connected with the max-margin classifier for discrimination tasks. The model is efficiently trained using a Monte Carlo expectation-maximization (MCEM) algorithm; the algorithm is implemented on graphical processor units (GPU) to enable large-scale learning, and fast testing. Excellent results are obtained on several benchmark datasets, including ImageNet, demonstrating that the proposed model achieves results that are highly competitive with similarly sized convolutional neural networks.

convolutional neural network↗

DOE OSTI2016

Electronic health record analysis via deep poisson factor models

Electronic Health Record (EHR) phenotyping utilizes patient data captured through normal medical practice, to identify features that may represent computational medical phenotypes. These features may be used to identify at-risk patients and improve prediction of patient morbidity and mortality. We present a novel deep multi-modality architecture for EHR analysis (applicable to joint analysis of multiple forms of EHR data), based on Poisson Factor Analysis (PFA) modules. Each modality, composed of observed counts, is represented as a Poisson distribution, parameterized in terms of hidden binary units. In-formation from different modalities is shared via a deep hierarchy of common hidden units. Activation of these binary units occurs with probability characterized as Bernoulli-Poisson link functions, instead of more traditional logistic link functions. In addition, we demon-strate that PFA modules can be adapted to discriminative modalities. To compute model parameters, we derive efficient Markov Chain Monte Carlo (MCMC) inference that scales efficiently, with significant computational gains when compared to related models based on logistic link functions. To explore the utility of these models, we apply them to a subset of patients from the Duke-Durham patient cohort. We identified a cohort of over 12,000 patients with Type 2 Diabetes Mellitus (T2DM) based on diagnosis codes and laboratory tests out of our patient population of over 240,000. Examining the common hidden units uniting the PFA modules, we identify patient features that represent medical concepts. Experiments indicate that our learned features are better able to predict mortality and morbidity than clinical features identified previously in a large-scale clinical trial.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2018

Development of 3-D Geological Model of Tuscarora Sandstone for Feasibility of Deep Direct-Use Geothermal at West Virginia University’s Main Campus

The Morgantown campus of West Virginia University (WVU) is uniquely positioned to host the first geothermal deep direct-use district heating system in the eastern United States. While much of the eastern United States is not blessed with extremely high heat flow and elevated temperatures, the northeastern part of West Virginia is unique in having a basin that is expected to support the achievable flowrate of geofluid through target formations, with sufficient temperatures at depth. These two factors were identified in the 2006 MIT Future of Geothermal Energy Report to be the two most critical factors in minimizing cost of geothermal energy. Our overall project objective is to determine the feasibility of designing a Geothermal District Heating and Cooling (GDHC) system for the West Virginia University campus utilizing Geothermal Deep Direct-Use (DDU) by 1) minimization of the uncertainty and risk associated with developing the geothermal resource for use on campus at WVU and 2) completion of an optimized design for the geothermal system, minimizing the delivered Levelized Cost of Heat (LCOH). Our first goal, to minimize the risk of project development, will be achieved by decreasing the uncertainty in both the subsurface geothermal system as well the surface distribution system. The subsurface uncertainty is dominated by the uncertainty in the projections of geofluid flowrate in the target formation, the Tuscarora Sandstone. In this paper, three cores from the heterogeneous reservoir, available through West Virginia Geologic and Economic Survey, are analyzed by performing core analysis using CT scanning and permeability measurements via minipermeameter. Additional geological data are collected through cores, published literature, seismic data, and nearby, existing wells to estimate thickness, fracture network configuration and geothermal gradient to minimize the uncertainty of well deliverability. Using these estimated reservoir properties; a 3D conceptual model for the proposed geothermal site is developed.

15 GEOTHERMAL ENERGY↗

DOE OSTI2018

Deep Direct-Use for Industrial Applications: Producing Chilled Water for Gas-Turbine Inlet Cooling

Direct use of deep, low-temperature geothermal resources is underutilized due to challenging project economics associated with developing a deep geothermal resource for what are historically small-scale, variable-demand projects. This project assesses the feasibility of geothermal energy integration in natural-gas combined cycle power stations in the Sabine Uplift and Gulf Coast regions of Texas. The low-grade geothermal resource is tapped to drive absorption chillers for production of chilled water at 5-10 degrees C (41-50 degrees F). This chilled water is stockpiled and dispatched to provide turbine inlet cooling (TIC) at the inlet to the compressor of a natural-gas combined cycle power plant, thereby boosting power production during periods of high temperature and high-power demand. This presentation focuses on the system design related to geothermal well-site selection (proximity vs. resource quality), absorption chiller size and location, chilled-water storage capacity, and dispatch logic to realize the maximum financial benefit.

15 GEOTHERMAL ENERGY↗

DOE OSTI2019

Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems

The Koopman operator has recently garnered much attention for its value in dynamical systems analysis and data-driven model discovery. However, its application has been hindered by the computational complexity of extended dynamic mode decomposition; this requires a combinatorially large basis set to adequately describe many nonlinear systems of interest, e.g. cyber-physical infrastructure systems, biological networks, social systems, and fluid dynamics. Often the dictionaries generated for these problems are manually curated, requiring domain-specific knowledge and painstaking tuning. In this paper we introduce a deep learning framework for learning Koopman operators of nonlinear dynamical systems. We show that this novel method automatically selects efficient deep dictionaries, outperforming state-of-the-art methods. We benchmark this method on partially observed nonlinear systems, including the glycolytic oscillator and show it is able to predict quantitatively 100 steps into the future, using only a single timepoint, and qualitative oscillatory behavior 400 steps into the future.

koopman operators, machine learning, deep learning↗

DOE OSTI2018

Deep Learning for Unsupervised Insider Threat Detection in Structured Cyber Security 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.

Deep Learning, Insider Threat↗

DOE OSTI2023

Distributed Power Allocation for 6-GHz Unlicensed Spectrum Sharing via Multi-agent Deep Reinforcement Learning

We consider the problem of power allocation over the 6 GHz Unlicensed National Information Infrastructure (UNII)- 5 spectrum. We propose a novel deep Reinforcement Learning (DRL)-based distributed power allocation scheme which utilizes the multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm. In particular, we model the base stations (BSs) as DRL agents that simultaneously determine the transmit powers to their scheduled user equipment (UE) in a synchronized manner. The power decision of each BS is based on its own observation of the radio environment, which consists of several local interference measurements and a limited amount of information obtained from other BSs. One advantage of the proposed scheme is that it addresses the single-agent non-stationarity problem of RL in the multi-agent scenario by incorporating the actions and observations of other BSs into each BS’s own critic which helps it to gain a more accurate perception of the overall radio environment. A centralized-training-distributed execution framework is used to train the policies where the critics are trained over the joint actions and observations of all BSs while the actor of each BS only takes the local observation as input in order to produce the transmit power. Simulation shows that the proposed power allocation scheme can achieve better throughput performance than several state-of-the-art approaches.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2023

A Novel Multi-Agent Deep Reinforcement Learning-enabled Distributed Power Allocation Scheme for mmWave Cellular Networks

We consider the power allocation problem over shared spectrum for millimeter-Wave (mmWave) cellular downlink. Existing approaches usually find sub-optimal solutions by solving a non-convex optimization which leads to scalability issues due to centralized control. Therefore, distributed and adaptive approaches are desirable. Recently, model-free Deep Reinforcement Learning (DRL) has achieved success in such wireless resource management tasks. By modeling the radio environment as a Markov Decision Process (MDP) with the base stations (BSs) being the agents, power allocation can be automated at the agent level with comparable throughput performance to conventional centralized schemes. The multi-agent setting presents new challenges as the radio environment is impacted by the joint actions of the agents and is no longer stationary from any individual agent’s perspective. Existing literature bypasses this non-stationarity violation by ignoring it which may cause performance degradation. To tackle this issue, we propose a distributed continuous power allocation scheme based on a modified version of multi-agent Deep Deterministic Policy Gradient (MADDPG) that is tailored for the distributed multiple-agent setting. The proposed scheme employs a centralized-training distributed-execution framework where Q-functions are trained over subsets of BSs while each BS determines its transmit power based only on its own local observation. It admits constant per-BS communication and computation complexity and is thus scalable to large networks. Numerical evaluation shows that the proposed scheme adapts well to a wide range of interference conditions and can achieve comparable or better performance than several state-of-the-art non-learning approaches.

99 GENERAL AND MISCELLANEOUS↗