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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Development of a deep learning based automated data analysis for step-filter x-ray spectrometers in support of high-repetition rate short-pulse laser-driven acceleration experiments

We present a deep learning based framework for real-time analysis of a differential filter based x-ray spectrometer that is common on short-pulse laser experiments. The analysis framework was trained with a large repository of synthetic data to retrieve key experimental metrics, such as slope temperature. With traditional analysis methods, these quantities would have to be extracted from data using a time-intensive and manual analysis. Furthermore, this framework was developed for a specific diagnostic, but may be applicable to a wide variety of diagnostics common to laser experiments and thus will be especially crucial to the development of high-repetition rate (HRR) diagnostics for HRR laser systems that are coming online.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction

Understanding protein structure-function relationships is a key challenge in computational biology, with applications across the biotechnology and pharmaceutical industries. While it is known that protein structure directly impacts protein function, many functional prediction tasks use only protein sequence. In this work, we isolate protein structure to make functional annotations for proteins in the Protein Data Bank in order to study the expressiveness of different structure-based prediction schemes. We present PersGNN - an end-to-end trainable deep learning model that combines graph representation learning with topological data analysis to capture a complex set of both local and global structural features. While variations of these techniques have been successfully applied to proteins before, we demonstrate that our hybridized approach, PersGNN, outperforms either method on its own as well as a baseline neural network that learns from the same information. PersGNN achieves a 9.3% boost in area under the precision recall curve (AUPR) compared to the best individual model, as well as high F1 scores across different gene ontology categories, indicating the transferability of this approach.

Swenson, Nicolas↗
DOE OSTI2017

Deep Water Impact Ensemble Data Set

Asteroids of various sizes, speeds, and compositions are zipping around the solar system with potential future Earth engagements. Most of the earth is covered in ocean and impacts would likely occur in deep ocean water. The IEEE SciVis Contest 2018 is dedicated to the visualization and analysis of simulations designed to study asteroid impacts in deep ocean water.

"asteroid impact" meteor "in situ" visualization↗
DOE OSTI2024

AI-Driven Crack Detection for Remanufacturing Cylinder Heads Using Deep Learning and Engineering-Informed Data Augmentation

Detecting cracks in cylinder heads traditionally relies on manual inspection, which is time-consuming and susceptible to human error. As an alternative, automated object detection utilizing computer vision and machine learning models has been explored. However, these methods often face challenges due to a lack of sufficiently annotated training data, limited image diversity, and the inherently small size of cracks. Addressing these constraints, this paper introduces a novel automated crack-detection method that enhances data availability through a synthetic data generation technique. Unlike general data augmentation practices, our method involves copying cracks from one location to another, guided by both random and informed engineering decisions about likely crack formations due to cyclic thermomechanical loads. The innovative aspect of our approach lies in the integration of domain-specific engineering knowledge into the synthetic generation process, which substantially improves detection accuracy. We evaluate our method’s effectiveness using two metrics: the F2 score, which emphasizes recall to prioritize detecting all potential cracks, and mean average precision (MAP), a standard measure in object detection. Experimental results demonstrate that, without engineering insights, our method increases the F2 score from 0.40 to 0.65, while maintaining a stable MAP. Incorporating detailed engineering knowledge further enhances the F2 score to 0.70 and improves MAP to 0.57, representing increases of 63% and 43%, respectively. These results confirm that our approach not only mitigates the limitations of traditional data augmentation but also significantly advances the reliability and precision of crack detection in industrial settings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Inversion of Time-Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning-Based Approach for Estimating Dynamic Reservoir Property Changes

Carbon capture and storage is being pursued globally as a geoengineering measure for reducing the emission of anthropogenic CO 2 the atmosphere. Comprehensive monitoring, verification, and accounting programs must be established for demonstrating the safe storage of injected CO 2 . One of the most commonly deployed monitoring techniques is time-lapse seismic reservoir monitoring (also known as 4-D seismic), which involves comparing 3-D seismic survey data taken at the same study site but over different times. Analyses of 4-D seismic data volumes can help improve the quality of storage reservoir characterization, track the movement of injected CO 2 plume, and identify potential CO 2 spillover/leakage from the storage reservoirblue. However, the derivation of high-resolution CO 2 saturation maps from 4-D seismic data is a highly nonlinear and ill-posed inverse problem, often requiring significant computational effort. In this research, we apply a physics-based deep learning method to facilitate the solution of both the forward and inverse problems in seismic inversion while honoring physical constraints. A cycle generative adversarial neural network (CycleGAN) model is trained to learn the bidirectional functional mappings between the reservoir dynamic property changes and seismic attribute changes, such that both forward and inverse solutions can be obtained efficiently from the trained model. We show that our CycleGAN-based approach not only improves the reliability of 4-D seismic inversion but also expedites the quantitative interpretation. Our deep learning-based workflow is generic and can be readily used for reservoir characterization and reservoir model updates involving the use of 4-D seismic data.

58 GEOSCIENCES↗
DOE OSTI2017

Applications of data mining technology to enhance O and M: automatic planning of electrical isolation with deep learning - 255

Data mining technology is now readily available, thanks to high powered, low cost computing resource and useful coding tools. We study several applications of data mining to enhance operation and maintenance (O and M), such as abnormality prediction, efficiency diagnosis, document traceability, image recognition, etc. In field support, we try automatic planning of electrical isolation with deep learning. Currently, a skilled engineer plans electrical isolation procedure with hundreds of the circuit diagrams and the related documents, taking man-hours. If this task becomes automatic, it is very efficient. The automatic planning has two issues. One is much calculation time of electrical circuit simulator, searching billions of electrical conducting paths. The other is interpretation of human fuzzy information, such as ease of work. Deep learning is helpful to resolve them. We performed a model case study of the electrical isolation. We applied a deep neural network (DNN) for dropping in the calculation time. We trained the circuit diagrams and the responses of the circuit simulator to the DNN, constructing an efficient path search algorithm in the DNN. The calculation time of the DNN was shorter by a factor of 32 for the model case, compared with that of the electrical circuit simulator. We applied a deep Q-network (DQN) for the interpretation of fuzzy information. The DQN optimized isolation procedure from the viewpoint of the work load with the equipment layout, related doses, and values of wet bulb globe temperature (WBGT) to prevent heatstroke. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Accelerating engineered microbe optimization through machine learning and multi-omics datasets

This project demonstrated the use of a combination of multi-omics data with deep learning and a high-throughput Design- Build-Test-Learn (DBTL) cycle to improve the production of malonic acid, a versatile product with a large market. The project leveraged the unique capabilities of both Lygos and the Agile BioFoundry (ABF): Lygos provided its expertise efficiently designing, building, and cultivating P. kudriavzevii strains; LBNL, PNNL, and NTESS provided multi-omics analysis in the Test phase, LBNL provided machine learning techniques in the Learn phase to analyze the -omics datasets and make recommendations so as to increase malonic acid production in the next DBTL cycle. This project is the first to use large amounts of multi-omics time-series data to feed deep learning models, creating around 80,000 data points in a single DBTL cycle. This project has 1) demonstrated the utility of combining deep learning and multi-omics data sets by improving the production of malonic acid two fold, 2) created a large time-series datasets to be released publicly for external development of new machine learning algorithms, and 3) shown that supply chain problems, strain building bottlenecks, and adaptation times for new ML approaches are key obstacles for fast DBTL cycle times.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Multi-task deep reinforcement learning for intelligent multi-zone residential HVAC control

In this short communication, a data-driven deep reinforcement learning (deep RL) method is applied to minimize HVAC users’ energy consumption costs while maintaining users’ comfort. The applied deep RL method's efficiency is enhanced by conducting multi-task learning that can achieve an economic control strategy for a multi-zone residential HVAC system in both cooling and heating scenarios. The applied multi-task deep RL method is compared with a rule-based benchmark case and a single-task deep deterministic policy gradient algorithm to verify its effective and generalized application in optimizing HVAC operation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2017

Cluster Mass Calibration at High Redshift: HST Weak Lensing Analysis of 13 Distant Galaxy Clusters from the South Pole Telescope Sunyaev-Zel’dovich Survey

We present an HST/Advanced Camera for Surveys (ACS) weak gravitational lensing analysis of 13 massive high-redshift (z(median) = 0.88) galaxy clusters discovered in the South Pole Telescope (SPT) Sunyaev-Zel'dovich Survey. This study is part of a larger campaign that aims to robustly calibrate mass-observable scaling relations over a wide range in redshift to enable improved cosmological constraints from the SPT cluster sample. We introduce new strategies to ensure that systematics in the lensing analysis do not degrade constraints on cluster scaling relations significantly. First, we efficiently remove cluster members from the source sample by selecting very blue galaxies in V - I colour. Our estimate of the source redshift distribution is based on Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) data, where we carefully mimic the source selection criteria of the cluster fields. We apply a statistical correction for systematic photometric redshift errors as derived from Hubble Ultra Deep Field data and verified through spatial cross-correlations. We account for the impact of lensing magnification on the source redshift distribution, finding that this is particularly relevant for shallower surveys. Finally, we account for biases in the mass modelling caused by miscentring and uncertainties in the concentration-mass relation using simulations. In combination with temperature estimates from Chandra we constrain the normalization of the mass-temperature scaling relation ln (E(z) M-500c/10(14)M(circle dot)) = A + 1.5ln (kT/7.2 keV) to A = 1.81(-0.14)(+0.24)(stat.)+/- 0.09(sys.), consistent with self-similar redshift evolution when compared to lower redshift samples. Additionally, the lensing data constrain the average concentration of the clusters to c(200c) = 5.6(-1.8)(+3.7).

cosmology: observations↗
DOE OSTI2021

Deep glassy state dynamic data challenge glass models: Elastic models

The idea of an “ideal” glass transition temperature has persisted at least since the work from Kauzmann when it was observed that the entropy of glass-forming liquids extrapolated to below that of the crystal, thus suggesting the need for a phase transition at a finite or non-zero absolute temperature. This thermodynamic paradox was also found to be related to the observations of a diverging of the extrapolated viscosity or relaxation times at a temperature near to this ideal glass transition. Recently, however, we have carried out experiments using both an ancient amber material and an ultra-stable amorphous fluoropolymer that challenge the ideas of the divergence of the viscosity or relaxation times at this ideal glass transition. In the present manuscript we have evaluated two theories of the glass transition that are based on ideas related to elasticity of the amorphous glass-forming material. We find that the models from both J. Dyre and his group and of K.S. Schweizer and his group not only show non-diverging behavior but are also in some agreement with the new data, though still showing somewhat slower dynamics than those observed in the experiments. The work shows that the data are good enough to distinguish between theories and it is suggested that other mechanisms may be needed to fully describe the non-diverging responses of the ultra-stable glasses.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Combining Deep Learning With Physics Based Features in Explosion-Earthquake Discrimination

This paper combines the power of deep-learning with the generalizability of physics-based features, to present an advanced method for seismic discrimination between earthquakes and explosions. The proposed method contains two branches: a deep learning branch operating directly on seismic waveforms or spectrograms, and a second branch operating on physics-based parametric features. These features are high-frequency P/S amplitude ratios and the difference between local magnitude (ML) and coda duration magnitude (MC). The combination achieves better generalization performance when applied to new regions than models that are developed solely with deep learning. Further, we also examined which parts of the waveform data dominate deep learning decisions (i.e., via Grad-CAM). Such visualization provides a window into the black-box nature of the machine-learning models and offers new insight into how the deep learning derived models use data to make decisions.

58 GEOSCIENCES↗
DOE OSTI2021

Where’s Swimmy?: Mining unique color features buried in galaxies by deep anomaly detection using Subaru Hyper Suprime-Cam data

Abstract We present the Swimmy (Subaru WIde-field Machine-learning anoMalY) survey program, a deep-learning-based search for unique sources using multicolored (grizy) imaging data from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP). This program aims to detect unexpected, novel, and rare populations and phenomena, by utilizing the deep imaging data acquired from the wide-field coverage of the HSC-SSP. This article, as the first paper in the Swimmy series, describes an anomaly detection technique to select unique populations as “outliers” from the data-set. The model was tested with known extreme emission-line galaxies (XELGs) and quasars, which consequently confirmed that the proposed method successfully selected $\sim\!\! 60\%$–$70\%$ of the quasars and $60\%$ of the XELGs without labeled training data. In reference to the spectral information of local galaxies at z = 0.05–0.2 obtained from the Sloan Digital Sky Survey, we investigated the physical properties of the selected anomalies and compared them based on the significance of their outlier values. The results revealed that XELGs constitute notable fractions of the most anomalous galaxies, and certain galaxies manifest unique morphological features. In summary, deep anomaly detection is an effective tool that can search rare objects, and, ultimately, unknown unknowns with large data-sets. Further development of the proposed model and selection process can promote the practical applications required to achieve specific scientific goals.

Astronomy & Astrophysics↗
DOE OSTI2013

PROBING THE DAWN OF GALAXIES AT z {approx} 9-12: NEW CONSTRAINTS FROM HUDF12/XDF AND CANDELS DATA

We present a comprehensive analysis of z > 8 galaxies based on ultra-deep WFC3/IR data. We exploit all the WFC3/IR imaging over the Hubble Ultra-Deep Field from the HUDF09 and the new HUDF12 program, in addition to the HUDF09 parallel field data, as well as wider area imaging over GOODS-South. Galaxies are selected based on the Lyman break technique in three samples centered around z {approx} 9, z {approx} 10, and z {approx} 11, with seven z {approx} 9 galaxy candidates, and one each at z {approx} 10 and z {approx} 11. We confirm a new z {approx} 10 candidate (with z = 9.8 {+-} 0.6) that was not convincingly identified in our first z {approx} 10 sample. Using these candidates, we perform one of the first estimates of the z {approx} 9 UV luminosity function (LF) and improve our previous constraints at z {approx} 10. Extrapolating the lower redshift UV LF evolution should have revealed 17 z {approx} 9 and 9 z {approx} 10 sources, i.e., a factor {approx}3 Multiplication-Sign and 9 Multiplication-Sign larger than observed. The inferred star formation rate density (SFRD) in galaxies above 0.7 M{sub Sun} yr{sup -1} decreases by 0.6 {+-} 0.2 dex from z {approx} 8 to z {approx} 9, in excellent agreement with previous estimates. From a combination of all current measurements, we find a best estimate of a factor 10 Multiplication-Sign decrease in the SFRD from z {approx} 8 to z {approx} 10, following (1 + z){sup -11.4{+-}3.1}. Our measurements thus confirm our previous finding of an accelerated evolution beyond z {approx} 8, and signify a very rapid build-up of galaxies with M{sub UV} < -17.7 mag within only {approx}200 Myr from z {approx} 10 to z {approx} 8, in the heart of cosmic reionization.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Deep Lynx MOOSE Adapter

The Deep Lynx MOOSE Adapter connects the Deep Lynx data warehouse with any MOOSE executable. The Adapter can receive events from Deep Lynx and will take incoming data to format a template input file for the MOOSE executable. Returns from the MOOSE run are sent back to Deep Lynx for use by other applications.

Browning, JerenM↗
DOE OSTI2016

Probing the transition from shallow to deep convection using ASR data and large-eddy simulations

Over the duration of this project, we have made the following advances. 1) We have developed a novel approach to obtain a Lagrangian view of convection from high-resolution numerical model through Lagrangian tracking. This approach nicely complements the more traditionally used Eulerian statistics. We have applied this approach to a range of problem. 2) We have looked into improving and extending our parameterizations based on stochastically entraining parcels, developed previously for shallow convection. 3) This grant also supported our effort on a paper where we compared cumulus parameterizations and cloud resolving models in terms of their linear response functions. This work will help the community to better evaluate and develop cumulus parameterization. 4) We have applied Lagrangian tracking to shallow convection, deep convection with and without convective organization to better characterize their dynamics and the transition between them. 5) We have devised a novel way of using Lagrangian to identify cold pools, an area identified as of great interest by the ASR community. Our algorithm has a number of advantages and in particular can handle merging cold pools more gracefully than existing techniques. 6) We demonstrated that we can, for the first time, correctly reproduce both the diurnal and seasonal cycle of the hydrologic cycle in the Amazon using a strategy that explicitly represents convection but parameterizes large-scale circulation. In addition we showed that the main cause of the wet season is the presence of an early morning fog, which insulate the surface from top of the atmosphere shortwave radiation. In essence this fog makes the day shorter because radiation cannot penetrate to the surface in the early morning. This is why all fluxes are reduced in the wet season compared to the dry season. 7) We have investigated the life cycle of cold pools and the role of surface diabatic heating. We show that surface heating can kill cold pols and reduce the number of large cold pools and the organization of convection. The effect is quite dramatic over land where the entire distribution of cold pools is modified, and the cold pools are much warmer and more humid with surface diabatic heating below the cold pools. The PI and the co-PI continue to work together on parameterization of cold pools.

54 ENVIRONMENTAL SCIENCES↗