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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Cyote Insights

CyOTE Insights leverages React, Vite, Typescript, Tailwind, and Daisy UI for the Graphical User Interface. It was designed in a particular style with a dark mode and a light mode. All code is broken down into components and reusable wrapper components for efficiency. All data is stored in Deep Lynx as a central data repository using an ontology based schema. The application serves as a main endpoint for the data in the COREII and CyOTE programs. The main purpose of the application is to display historical attack data in the Operational Technology space. At the time of this writing, it supports 27 historical attack reports compiled from OSINT sources. All of the data is publicly available, but what this application offers is the ability to see many years worth of publications in a detailed dashboard. It will also support future reports that are written using the other applications in the COREII program.

Pluth, AdamJ [Idaho National Laboratory (INL), Ida↗
NASA NTRS2006

NASA Tech Briefs, December 2006

Topic include: Inferring Gear Damage from Oil-Debris and Vibration Data; Forecasting of Storm-Surge Floods Using ADCIRC and Optimized DEMs; User Interactive Software for Analysis of Human Physiological Data; Representation of Serendipitous Scientific Data; Automatic Locking of Laser Frequency to an Absorption Peak; Self-Passivating Lithium/Solid Electrolyte/Iodine Cells; Four-Quadrant Analog Multipliers Using G4-FETs; Noise Source for Calibrating a Microwave Polarimeter; Hybrid Deployable Foam Antennas and Reflectors; Coating MCPs with AlN and GaN; Domed, 40-cm-Diameter Ion Optics for an Ion Thruster; Gesture-Controlled Interfaces for Self-Service Machines; Dynamically Alterable Arrays of Polymorphic Data Types; Identifying Trends in Deep Space Network Monitor Data; Predicting Lifetime of a Thermomechanically Loaded Component; Partial Automation of Requirements Tracing; Automated Synthesis of Architecture of Avionic Systems; SSRL Emergency Response Shore Tool; Wholly Aromatic Ether-Imides as n-Type Semiconductors; Carbon-Nanotube-Carpet Heat-Transfer Pads; Pulse-Flow Microencapsulation System; Automated Low-Gravitation Facility Would Make Optical Fibers; Alignment Cube with One Diffractive Face; Graphite Composite Booms with Integral Hinges; Tool for Sampling Permafrost on a Remote Planet; and Special Semaphore Scheme for UHF Spacecraft Communications.

Source record↗
NASA NTRS2000

Significant Dissipation of Tidal Energy in the Deep Ocean Inferred from Satellite Altimeter Data

How and where the ocean tides dissipate their energy are longstanding questions that have consequences ranging from the history of the Moon to the mixing of the oceans. Historically, the principal sink of tidal energy has been thought to be bottom friction in shallow seas. There has long been suggestive however, that tidal dissipation also occurs in the open ocean through the scattering by ocean-bottom topography of surface tides into internal waves, but estimates of the magnitude of this possible sink have varied widely. Here we use satellite altimeter data from Topex/Poseidon to map empirically the tidal energy dissipation. We show that approximately 10(exp 12) watts-that is, 1 TW, representing 25-30% of the total dissipation-occurs in the deep ocean, generally near areas of rough topography. Of the estimated 2 TW of mixing energy required to maintain the large-scale thermohaline circulation of the ocean, one-half could therefore be provided by the tides, with the other half coming from action on the surface of the ocean.

Egbert, G. D.↗
DOE OSTI2024

Deep Learning-Based Weather-Related Power Outage Prediction with Socio-Economic and Power Infrastructure Data

This paper presents a deep learning-based approach for hourly power outage probability prediction within census tracts encompassing a utility company's service territory. Two distinct deep learning models, conditional Multi-Layer Perceptron (MLP) and unconditional MLP, were developed to forecast power outage probabilities, leveraging a rich array of input features gathered from publicly available sources including weather data, weather station locations, power infrastructure maps, socio-economic and demographic statistics, and power outage records. Given a one-hour-ahead weather forecast, the models predict the power outage probability for each census tract, taking into account both the weather prediction and the location's characteristics. The deep learning models employed different loss functions to optimize prediction performance. Our experimental results underscore the significance of socio-economic factors in enhancing the accuracy of power outage predictions at the census tract level.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2004

On the Use of Deep Convective Clouds to Calibrate AVHRR Data

Remote sensing of cloud and radiation properties from National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) satellites requires constant monitoring of the visible sensors. NOAA satellites do not have onboard visible calibration and need to be calibrated vicariously in order to determine the calibration and the degradation rate. Deep convective clouds are extremely bright and cold, are at the tropopause, have nearly a Lambertian reflectance, and provide predictable albedos. The use of deep convective clouds as calibration targets is developed into a calibration technique and applied to NOAA-16 and NOAA-17. The technique computes the relative gain drift over the life-span of the satellite. This technique is validated by comparing the gain drifts derived from inter-calibration of coincident AVHRR and Moderate-Resolution Imaging Spectroradiometer (MODIS) radiances. A ray-matched technique, which uses collocated, coincident, and co-angled pixel satellite radiance pairs is used to intercalibrate MODIS and AVHRR. The deep convective cloud calibration technique was found to be independent of solar zenith angle, by using well calibrated Visible Infrared Scanner (VIRS) radiances onboard the Tropical Rainfall Measuring Mission (TRMM) satellite, which precesses through all solar zenith angles in 23 days.

Doelling, David R.↗
DOE OSTI2026

A Public Data Set of Auto-Generated Geotagged PV Site Equipment, Generated via Deep Learning

In this research, we present a data set over 100 photovoltaic (PV) sites in TX, which have been automatically geotagged via a fully autonomous deep learning (DL) pipeline. Specifically, locations of inverters, tracker/fixed tilt rows, batteries, and substations are labeled algorithmically. To ensure high data quality, all systems have been reviewed manually and any deep learning errors have been corrected. This public data set, as well as the open-sourced pipeline used to generate it, is valuable for site planning, modelling, and insurance purposes. Given time and resources, we hope to extend the data set to additional states/regions in the US.

14 SOLAR ENERGY↗
NASA NTRS2019

VIIRS Deep Blue Aerosol Products Over Land: Extending the EOS Long‐Term Aerosol Data Records

A primary goal of the Deep Blue (DB) project is to create consistent long‐term aerosol data records, suitable for climate studies, using multiple satellite instruments. In order to continue Earth Observing System (EOS)‐era aerosol products into the Joint Polar Satellite System era, we have successfully ported the DB algorithm to process data from the Visible Infrared Imaging Radiometer Suite (VIIRS). Although the basic structure of the VIIRS algorithm is similar to that for the Moderate Resolution Imaging Spectroradiometer (MODIS), many enhancements have been made compared to the MODIS collection 6 (C6) version. Most have also been implemented in the latest MODIS Collection 6.1 (C6.1). For example, a new smoke mask was developed based on the spectral curvature of measured reflectance to distinguish biomass burning smoke from weakly absorbing urban/industrial aerosols. Consequently, a new aerosol‐type flag was added into the VIIRS DB data set. In addition, new dust models have been developed to account for the nonsphericity of mineral dust. As a result, a discontinuity in the retrieved aerosol optical depth (AOD) of Saharan dust plumes seen in MODIS C6 products near the boundary between North Africa and the Atlantic has been much reduced. We have also evaluated the VIIRS and MODIS Terra/Aqua C6.1 AOD against Aerosol Robotic Network data. VIIRS and MODIS retrievals show similar performance; around 80% of matchups agree with Aerosol Robotic Network within the expected error of ±(0.05 + 20)%, indicating that DB can provide consistent AOD through the historical EOS and present Joint Polar Satellite System eras.

aerosols↗
DOE OSTI2023

Extraction of the strong coupling with HERA and EIC inclusive data

Sensitivity to the strong coupling $∝$ s ($M^{2}_{Z}$) is investigated using existing Deep Inelastic Scattering data from HERA in combination with projected future measurements from the Electron Ion Collider (EIC) in a next-to-next-to-leading order QCD analysis. A potentially world-leading level of precision is achievable when combining simulated inclusive neutral current EIC data with inclusive charged and neutral current measurements from HERA, with or without the addition of HERA inclusive jet and dijet data. The result can be obtained with substantially less than one year of projected EIC data at the lower end of the EIC centre-of-mass energy range. Some questions remain over the magnitude of uncertainties due to missing higher orders in the theoretical framework.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS2018

Toward a NASA Deep Space Optical Communications System

As discussed at SpaceOps in 2016, we expect the data rates from deep space missions to increase approximately one order of magnitude per decade for the next 50 years. The first order of magnitude improvement will come from existing plans for radio frequency (RF) communications including enhancements to both spacecraft and Deep Space Network (DSN) facilities. The next two orders of magnitude are predicted to come from the introduction of deep space optical communications. Studies indicate that optical receive apertures of between 8m12m are desired. The large cost of dedicated receive telescopes makes this method unrealistic – at least in the near-term. The cost of large optical ground terminals is driven primarily by the cost of the optics and by the cost of a stable structure for the telescope. We propose a novel hybrid design in which existing DSN 34m beam waveguide (BWG) radio antennas can be modified to include an 8m equivalent optical primary. By utilizing a low-cost segmented spherical mirror optical design, pioneered by the optical astronomical community, and by exploiting the already existing extremely stable large radio aperture structures in the DSN, we can minimize both of these cost drivers for implementing large optical communications ground terminals. Two collocated hybrid RF/optical antennas could be arrayed to synthesize the performance of an 11.3m receive aperture to support more capable or more distant space missions or used separately to communicate with two optical spacecraft simultaneously. NASA is in the midst of building six new 34m BWG antennas in the DSN. The final two are planned to be built at the DSN Goldstone, California and Canberra complexes. We are now investigating building these last two antennas as RF/optical hybrids. By delaying their operational dates by two years, we would be able to add the 8m optical receive capability for these two antennas while fitting within existing budgetary constraints. This paper describes the hybrid antenna design, the technical challenges being addressed, and plan for using this concept, together with ongoing work on optical flight terminals, to infuse operation optical communications into deep space missions.

Cornwell, Donald M.↗
DOE OSTI2025

Scale-up Unlearnable Examples Learning with High-performance Computing

Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .

Zhu, Yanfan [Vanderbilt University, Nashville, TN,↗
DOE OSTI2023

Fast and efficient identification of anomalous galaxy spectra with neural density estimation

ABSTRACT Current large-scale astrophysical experiments produce unprecedented amounts of rich and diverse data. This creates a growing need for fast and flexible automated data inspection methods. Deep learning algorithms can capture and pick up subtle variations in rich data sets and are fast to apply once trained. Here, we study the applicability of an unsupervised and probabilistic deep learning framework, the probabilistic auto-encoder, to the detection of peculiar objects in galaxy spectra from the SDSS survey. Different to supervised algorithms, this algorithm is not trained to detect a specific feature or type of anomaly, instead it learns the complex and diverse distribution of galaxy spectra from training data and identifies outliers with respect to the learned distribution. We find that the algorithm assigns consistently lower probabilities (higher anomaly score) to spectra that exhibit unusual features. For example, the majority of outliers among quiescent galaxies are E+A galaxies, whose spectra combine features from old and young stellar population. Other identified outliers include LINERs, supernovae, and overlapping objects. Conditional modelling further allows us to incorporate additional information. Namely, we evaluate the probability of an object being anomalous given a certain spectral class, but other information such as metrics of data quality or estimated redshift could be incorporated as well. We make our code publicly available.

Böhm, Vanessa↗
DOE OSTI2020

Deep learning model to detect various synchrophasor data anomalies

High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Additionally, four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

42 ENGINEERING↗
DOE OSTI2025

Toward Drilling the Perfect Geothermal Well: An International Research Coordination Network for Geothermal Drilling Optimization Supported by Deep Machine Learning and Cloud Based Data Aggregation

The EDGE project, supported by the U.S. Department of Energy Geothermal Technologies Office under award DE-EE0008793, established a data-driven framework for improving the efficiency, cost-effectiveness, and reliability of geothermal well drilling. The project focused on developing scalable data infrastructure, advanced machine learning and probabilistic models, and integrated analytics tools to support continuous drilling optimization. A central objective was to reduce geothermal drilling costs by up to seventy percent while minimizing the risk of well failure through predictive diagnostics and adaptive planning. Over the project period, a comprehensive data repository was designed and deployed, incorporating records from over one hundred geothermal wells across varied geological settings. This repository supported both structured and unstructured data and adhered to FAIR data principles, enabling provenance tracking, quality control, and standardized metadata. The project introduced automated ingestion pipelines and a cloud-hosted platform that facilitated access to raw, processed, and derived datasets. This infrastructure served as the foundation for model development and analysis. Machine learning workflows were developed to predict key drilling metrics including rate of penetration, non-productive time, and total drilling costs. Self-organizing maps and dimensionality reduction methods were used to uncover operational patterns and outliers, while supervised learning algorithms such as random forests and deep neural networks were applied to forecast performance outcomes. The models were validated on heterogeneous datasets from both U.S. and Icelandic fields, demonstrating variable but significant predictive accuracy. The results indicated that finer temporal resolution, inclusion of lithological data, and consistency in operational annotations could substantially improve model performance. The project also implemented process mining techniques to reconstruct state-transition models from drilling event logs. These models enabled the identification of deviations from optimal workflows and provided insights into recurring failure modes. Analysis of non-productive time highlighted the impact of equipment failures, geological challenges, and human factors, offering opportunities for targeted mitigation strategies. The EDGE Dashboard was developed as a web-based expert system integrating data visualization, model outputs, and user-driven queries. It provided an accessible interface for operators to explore historical data, evaluate predicted outcomes, and compare drilling scenarios. Initial feedback from project partners suggested that the dashboard could serve as a foundation for more advanced advisory and optimization tools. Overall, the EDGE project demonstrated the feasibility and value of applying modern data science techniques to geothermal drilling. It delivered a set of interoperable tools and models that can support more efficient, lower-risk well development. The findings point toward a viable path for transitioning from advisory analytics to semi-autonomous drilling systems, contingent on continued collaboration, expanded datasets, and field validation. The project results have immediate relevance for drilling operations, data management practices, and future geothermal R&D efforts aimed at achieving reliable, cost-competitive geothermal energy at scale.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Deep Learning for Automated Identification of Eels in Sonar Data

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploited new data collected in the laboratory and the existing data from the prior EPRI field study to develop and test deep learning and other data analytic tools, including wavelet filtering, differencing for static object removal, and convolutional neural network analysis. The analysis of the laboratory data demonstrated feasibility of the approach, revealed object characteristics observed with the sonar that distinguish eels from similarly sized and shaped acoustic targets, and provided additional data for algorithm selection and training. Deep learning algorithms trained and tested on the laboratory data alone achieved accuracy rates of greater than 98% when classifying acoustic images of eels and similar-sized neutrally buoyant sticks. The algorithm trained and tested on the pre-existing field data alone, and yielded classification accuracy of 9.3% false positives and 13.3% false negatives when distinguishing between eels and sticks/PVC pipes based on video clips (i.e., multiple, consecutive images). This performance is comparable to the classification accuracy achieved by human analysts in the prior study. The deep learning algorithm trained on a combination of video clips obtained in the laboratory and the field and tested on video clips from the field, was able to distinguish eels from sticks and PVC pipes (a river debris analog) of similar size with 100% accuracy. Outreach to the hardware, software, and end-user communities early in the project helped to identify needs and specify the application space. Outreach to those communities at the end of the project communicated project results and opportunities for further development. The project achieved proof of concept for automated identification of eel in multibeam sonar data. Future work should focus on acquisition of additional data for more robust algorithm training and testing; modification of the software tools to accommodate multiple acoustic targets in the acoustic field at a given time; identification of additional object classes; incorporation of motion in the object identification and classification algorithms; operationalizing the software tools, including integration with other existing sonar data analysis tools; and partnering with hardware and software providers for distribution of the software tools with their commercial products.

13 HYDRO ENERGY↗
DOE OSTI2022

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Deep-learning models have been increasingly exploited in astrophysical studies, but these data-driven algorithms are prone to producing biased outputs that are detrimental for subsequent analyses. In this work, we investigate two main forms of biases: class-dependent residuals, and mode collapse. We do this in a case study, in which we estimate photometric redshift as a classification problem using convolutional neural networks (CNNs) trained with galaxy images and associated spectroscopic redshifts. We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training data, and leveraging soft labels. The residuals can be viewed as a function of spectroscopic redshift or photometric redshift, and the biases with respect to these two definitions are incompatible and should be treated individually. We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space. Experiments show that our methods can better control biases than benchmark methods, and they are robust in various implementing and training conditions with high-quality data. Our methods hold promises for future cosmological surveys that require a good constraint of biases, and they may be applied to regression problems and other studies that make use of data-driven models. Nonetheless, the bias-variance tradeoff and the requirement of sufficient statistics suggest that we need better methods and optimized data usage strategies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Deep learning Hamiltonians from disordered image data in quantum materials

The capabilities of image probe experiments are rapidly expanding, providing new information about quantum materials on unprecedented length- and timescales. Many such materials feature inhomogeneous electronic properties with intricate pattern formation on the observable surface. This rich spatial structure contains information about interactions, dimensionality, and disorder—a spatial encoding of the Hamiltonian driving the pattern formation. Image recognition techniques from machine learning are an excellent tool for interpreting information encoded in the spatial relationships in such images. Here, we develop a deep learning framework for using the rich information available in these spatial correlations in order to discover the underlying Hamiltonian driving the patterns. We first vet the method on a known case, scanning near-field optical microscopy on a thin film of V⁢O 2 . We then apply our trained convolutional neural network architecture to new optical microscope images of a different V⁢O 2 film as it goes through the metal-insulator transition. We find that a two-dimensional Hamiltonian with both interactions and random field disorder is required to explain the intricate, fractal intertwining of metal and insulator domains during the transition. This detailed knowledge about the underlying Hamiltonian paves the way for using the model to control the pattern formation via, e.g., tailored hysteresis protocols. Finally, we also introduce a distribution-based confidence measure on the results of a multilabel classifier, which does not rely on adversarial training. In addition, we propose a machine-learning-based criterion for diagnosing a physical system's proximity to criticality.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

The growth of intracluster light in XCS-HSC galaxy clusters from 0.1 < z < 0.5

ABSTRACT We estimate the intracluster light (ICL) component within a sample of 18 clusters detected in the XMM Cluster Survey (XCS) data using the deep (∼26.8 mag) Hyper Suprime-Cam Subaru Strategic Programme data release 1 i-band data. We apply a rest-frame μB = 25 mag arcsec−2 isophotal threshold to our clusters, below which we define light as the ICL within an aperture of RX,500 (X-ray estimate of R500) centred on the brightest cluster galaxy (BCG). After applying careful masking and corrections for flux losses from background subtraction, we recover ∼20 per cent of the ICL flux, approximately four times our estimate of the typical background at the same isophotal level (${\sim}5{{\ \rm per\ cent}}$). We find that the ICL makes up about ${\sim}24{{\ \rm per\ cent}}$ of the total cluster stellar mass on average (∼41 per cent including the flux contained in the BCG within 50 kpc); this value is well matched with other observational studies and semi-analytic/numerical simulations, but is significantly smaller than results from recent hydrodynamical simulations (even when measured in an observationally consistent way). We find no evidence for any links between the amount of ICL flux with cluster mass, but find a growth rate of 2–4 for the ICL between 0.1 < z < 0.5. We conclude that the ICL is the dominant evolutionary component of stellar mass in clusters from z ∼ 1. Our work highlights the need for a consistent approach when measuring ICL alongside the need for deeper imaging, in order to unambiguously measure the ICL across as broad a redshift range as possible (e.g. 10-yr stacked imaging from the Vera C. Rubin Observatory).

Furnell, Kate E.↗