A comprehensive study of the young open star cluster NGC 6611 based on deep VRI CCD images and 2MASS data
Explore the source record for details and available documents.
I.M. Selim↗
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.
Deep Space Navigation with Noncoherent Tracking Data
Navigation capabilities of noncoherent tracking data are evaluated for interplanetary cruise phase and planetary (Venus) flyby orbit determination. Results of a formal covariance analysis are presented which show that a combination of one-way Doppler and delta DOR yields orbit accuracies comparable to conventional two-way Doppler tracking. For the interplanetary cruise phase, a tracking cycle consisting of a 3-hour Doppler pass and delta DOR (differential one-way range) from two baselines (one observation per overlap) acquired 3 times a month results in 100-km orbit determination accuracy. For reconstruction of a Venus flyby orbit, 10 days tracking at encounter consisting of continuous one-way Doppler and delta DOR sampled at one observation per overlap is sufficient to satisfy the accuracy requirements.
Ellis, J.↗
Determination of the inner planet frame tie using VLBI data
The problem of connecting the independent reference frames formed by the planetary ephemeris and the radio source catalog is one of growing importance to spacecraft navigation. Using quasar-relative VLBI delay data collected by the Deep Space Network, and Soviet coherent data from the Venus flyby of the Soviet Vega 1 and 2 spacecraft, a self-consistent estimate of the frame tie offset has been found, along with its uncertainty.
Mcelrath, Timothy P.↗
CORRIGENDUM of the MJO Transition from Shallow to Deep Convection in Cloudsat-Calipso Data and GISS GCM Simulations
We have identified several errors in the calculations that were performed to create Fig. 3 of Del Genio et al. (2012). These errors affect the composite evolution of precipitation and column water vapor versus lag relative to the Madden-Julian oscillation (MJO) peak presented in that figure. The precipitation and column water vapor data for the April and November 2009 MJO events were composited incorrectly because the date of the MJO peak at a given longitude was assigned to the incorrect longitude band. In addition, the precipitation data for all MJO events were first accumulated daily and the daily accumulations averaged at each lag to create the composite, rather than the averaging of instantaneous values that was used for other composite figures in the paper. One poorly sampled day in the west Pacific therefore biases the composite precipitation in that region at several lags after the MJO peak. Finally, a 4-day running mean was mistakenly applied to the precipitation and column water vapor data rather than the intended 5-day running mean. The results of the corrections are that an anomalous west Pacific precipitation maximum510 days after the MJO peak is removed and the maximum in west Pacific precipitation one pentad before the MJO peak is now more evident; there is now a clear maximum in precipitation for the entire warm pool one pentad before the MJO peak; west Pacific column water vapor now varies more strongly as a function of lag relative to the peak; and precipitation, and to a lesser extent column water vapor, in general vary more smoothly with time. The corrections do not affect any other parts of the paper nor do they change the scientific conclusions we reached. The 4-day running mean error also affects Figs. 1 and 2 therein, with almost imperceptible impacts that do not affect any results or necessitate major changes to the text.
correction↗
Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model
Explore the source record for details and available documents.
Milad Memarzadeh↗
Contrasting aerosol refractive index and hygroscopicity in the inflow and outflow of deep convective storms: Analysis of airborne data from DC3
Explore the source record for details and available documents.
Armin Sorooshian↗
Deep learning to estimate permeability using geophysical data
Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.
58 GEOSCIENCES↗
Learning dynamical systems from data: An introduction to physics-guided deep learning
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.
97 MATHEMATICS AND COMPUTING↗
Data to Support Development of Geologic Framework Models for the Deep Borehole Field Test
This report summarizes work conducted in FY2017 to identify and document publically available data for developing a Geologic Framework Model (GFM) for the Deep Borehole Field Test (DBFT). Data was collected for all four of the sites being considered in 2017 for a DBFT site.
58 GEOSCIENCES↗
Data and scripts associated with the manuscript "Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning"
This package contains the data and scripts used in "Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning" (Jiang et al., 2022). The data.zip file contains the flux tower and automated chamber observations used for developing the deep learning model for modeling soil respiration. The scripts.zip file contains the Jupyter notebooks and python scripts for preprocessing the data, training the deep learning models, and postprocessing the results. The src.zip contains the source code for training the deep learning model, performing mutual information analysis, and plotting functions. The trained_models.zip contains multiple folders used for hosting the trained deep-learning models and the associated soil respiration predictions. The whole process is performed using python. We include the REAMD.md to document the python package requirements.Soil respiration in dryland ecosystems is challenging to model due to its complex interactions with environmental drivers. Knowledge-guided deep learning provides a much more effective means of accurately representing these complex interactions than traditional Q10-based models. Mutual information analysis revealed that future soil temperature shares more information with soil respiration than past soil temperature, consistent with their clockwise diel hysteresis. We explicitly encoded diel hysteresis, soil drying, and soil rewetting effects on soil respiration dynamics in a newly designed Long Short Term Memory (LSTM) model. The model takes both past and future environmental drivers as inputs to predict soil respiration. The new LSTM model substantially outperformed three Q10-based models and the Community Land Model when reproducing the observed soil respiration dynamics in a semi-arid ecosystem. The new LSTM model clearly demonstrated its superiority for temporally extrapolating soil respiration dynamics, such that the resulting correlation with observational data is up to 0.7 while the correlations of both Q10-based models and the Community Land Model (CLM) are less than 0.4. Our results underscore the high potential for knowledge-guided deep learning to replace Q10-based soil respiration modules in Earth system models.
54 ENVIRONMENTAL SCIENCES↗
An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation
The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.
Bayesian neural network↗
Sensitive Detection of Structural Differences using a Statistical Framework for Comparative Crystallography
Chemical and conformational changes underlie the functional cycles of proteins. Comparative crystallography can reveal these changes over time, over ligands, and over chemical and physical perturbations in atomic detail. A key difficulty, however, is that the resulting observations must be placed on the same scale by correcting for experimental factors. We recently introduced a Bayesian framework for correcting (scaling) X-ray diffraction data by combining deep learning with statistical priors informed by crystallographic theory. To scale comparative crystallography data, we here combine this framework with a multivariate statistical theory of comparative crystallography. By doing so, we find strong improvements in the detection of protein dynamics, element-specific anomalous signal, and the binding of drug fragments.
Hekstra, Doeke R. [Harvard Univ., Cambridge, MA (U↗
Satellite orbit determination
A historic account of the activities of the Satellite OD Group during the MM'71 mission is given along with an assessment of the accuracy of the determined orbit of the Mariner 9 spacecraft. Preflight study results are reviewed, and the major error sources described. Tracking and data fitting strategy actually used in the real time operations is itemized, and Deep Space Network data available for orbit fitting during the mission and the auxiliary information used by the navigation team are described. A detailed orbit fitting history of the first four revolutions of the satellite orbit of Mariner 9 is presented, with emphasis on the convergence problems and the delivered solution for the first orbit trim maneuver. Also included are a solution accuracy summary, the history of the spacecraft orbit osculating elements, the results of verifying the radio solutions with TV imaging data, and a summary of the normal points generated for the relativity experiment.
Jordan, J. F.↗
Demonstration of precise estimation of polar motion parameters with the global positioning system: Initial results
Data from the Global Positioning System (GPS) were used to determine precise polar motion estimates. Conservatively calculated formal errors of the GPS least squares solution are approx. 10 cm. The GPS estimates agree with independently determined polar motion values from very long baseline interferometry (VLBI) at the 5 cm level. The data were obtained from a partial constellation of GPS satellites and from a sparse worldwide distribution of ground stations. The accuracy of the GPS estimates should continue to improve as more satellites and ground receivers become operational, and eventually a near real time GPS capability should be available. Because the GPS data are obtained and processed independently from the large radio antennas at the Deep Space Network (DSN), GPS estimation could provide very precise measurements of Earth orientation for calibration of deep space tracking data and could significantly relieve the ever growing burden on the DSN radio telescopes to provide Earth platform calibrations.
Lichten, S. M.↗
Neural network methods for radiation detectors and imaging
Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).
edge computing↗
DSN data systems software methodology
A software methodology for JPL deep space network (DSN) data systems software implementations through transfer and delivery is presented. The DSN Data Systems Software Methodology is compatible with and depends on DSN software methodology and also incorporates the characteristics of real-time program development in a DSN environment. The DSN Data Systems software implementation consists of a series of six distinct phases. An Independent Group is responsible for verification and validation of the DSN Data Systems software during developing phases. The DSN data systems software methodology is applied to all development software provided for or by the DSN data systems section in Mark IV where there is a desire for reliability, maintainability, and usability within budget and schedule constraints.
Hung, C. K.↗