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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Adaptive Data-Driven Deep-Learning Surrogate Model for Frontal Polymerization in Dicyclopentadiene

Frontal polymerization (FP) is a self-sustaining curing process that enables rapid and energy-efficient manufacturing of thermoset polymers and composites. Computational methods conventionally used to simulate the FP process are time-consuming, and repeating simulations are required for sensitivity analysis, uncertainty quantification, or optimization of the manufacturing process. Here, in this work, we develop an adaptive surrogate deep-learning model for FP of dicyclopentadiene (DCPD), which predicts the evolution of temperature and degree of cure orders of magnitude faster than the finite-element method (FEM). The adaptive algorithm provides a strategy to select training samples efficiently and save computational costs by reducing the redundancy of FEM-based training samples. The adaptive algorithm calculates the residual error of the FP governing equations using automatic differentiation of the deep neural network. A probability density function expressed in terms of the residual error is used to select training samples from the Sobol sequence space. The temperature and degree of cure evolution of each training sample are obtained by a 2D FEM simulation. The adaptive method is more efficient and has a better prediction accuracy than the random sampling method. With the well-trained surrogate neural network, the FP characteristics (front speed, shape, and temperature) can be extracted quickly from the predicted temperature and degree-of-cure fields.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2016

Big, Deep, and Smart Data in Scanning Probe Microscopy

Scanning probe microscopy techniques open the door to nanoscience and nanotechnology by enabling imaging and manipulation of structure and functionality of matter on nanometer and atomic scales. We analyze the discovery process by SPM in terms of information flow from tip-surface junction to the knowledge adoption by scientific community. Furthermore, we discuss the challenges and opportunities offered by merging of SPM and advanced data mining, visual analytics, and knowledge discovery technologies.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2021

Neural networks to learn protein sequence–function relationships from deep mutational scanning data

Understanding the relationship between protein sequence and function is necessary to design new and useful proteins with applications in bioenergy, medicine, and agriculture. The mapping from sequence to function is tremendously complex because it involves thousands of molecular interactions that are coupled over multiple lengths and timescales. We show that neural networks can learn the sequence–function mapping from large protein datasets. Neural networks are appealing for this task because they can learn complicated relationships from data, make few assumptions about the nature of the sequence–function relationship, and can learn general rules that apply across the length of the protein sequence. We demonstrate that learned models can be applied to design new proteins with properties that exceed natural sequences.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2014

An empirical determination of the intergalactic background light using near-infrared deep galaxy survey data out to 5 μm and the gamma-ray opacity of the universe

We extend our previous model-independent determination of the intergalactic background light, based purely on galaxy survey data, out to a wavelength of 5 μm. Our approach enables us to constrain the range of photon densities, based on the uncertainties from observationally determined luminosity densities and colors. We further determine a 68% confidence upper and lower limit on the opacity of the universe to γ-rays up to energies of 1.6/(1 + z) TeV. A comparison of our lower limit redshift-dependent opacity curves to the opacity limits derived from the results of both ground-based air Cerenkov telescope and Fermi-LAT observations of PKS 1424+240 allows us to place a new upper limit on the redshift of this source, independent of IBL modeling.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

The Cosmic Ultraviolet Baryon Survey (CUBS) – III. Physical properties and elemental abundances of Lyman-limit systems at z < 1

ABSTRACT We present a systematic investigation of physical conditions and elemental abundances in four optically thick Lyman-limit systems (LLSs) at z = 0.36–0.6 discovered within the Cosmic Ultraviolet Baryon Survey (CUBS). Because intervening LLSs at z < 1 suppress far-UV (ultraviolet) light from background QSOs, an unbiased search of these absorbers requires a near-UV-selected QSO sample, as achieved by CUBS. CUBS LLSs exhibit multicomponent kinematic structure and a complex mix of multiphase gas, with associated metal transitions from multiple ionization states such as C ii, C iii, N iii, Mg ii, Si ii, Si iii, O ii, O iii, O vi, and Fe ii absorption that span several hundred km s−1 in line-of-sight velocity. Specifically, higher column density components (log N(H i)/cm−2≳ 16) in all four absorbers comprise dynamically cool gas with $\langle T \rangle =(2\pm 1) \times 10^4\,$K and modest non-thermal broadening of $\langle b_\mathrm{nt} \rangle =5\pm 3\,$km s−1. The high quality of the QSO absorption spectra allows us to infer the physical conditions of the gas, using a detailed ionization modelling that takes into account the resolved component structures of H i and metal transitions. The range of inferred gas densities indicates that these absorbers consist of spatially compact clouds with a median line-of-sight thickness of $160^{+140}_{-50}$ pc. While obtaining robust metallicity constraints for the low density, highly ionized phase remains challenging due to the uncertain $N\mathrm{(H\, {\small I})}$, we demonstrate that the cool-phase gas in LLSs has a median metallicity of $\mathrm{[\alpha /H]_{1/2}}=-0.7^{+0.1}_{-0.2}$, with a 16–84 percentile range of [α/H] = (−1.3, −0.1). Furthermore, the wide range of inferred elemental abundance ratios ([C/α], [N/α], and [Fe/α]) indicate a diversity of chemical enrichment histories. Combining the absorption data with deep galaxy survey data characterizing the galaxy environment of these absorbers, we discuss the physical connection between star-forming regions in galaxies and diffuse gas associated with optically thick absorption systems in the z < 1 circumgalactic medium.

Zahedy, Fakhri S. (ORCID:0000000178692551)↗
DOE OSTI2016

Constraints on large- x parton distributions from new weak boson production and deep-inelastic scattering data

A new set of leading twist parton distribution functions, referred to as "CJ15", is presented, which take advantage of developments in the theoretical treatment of nuclear corrections as well as new data. The analysis includes for the first time data on the free neutron structure function from Jefferson Lab, and new high-precision charged lepton and W-boson asymmetry data from Fermilab, which significantly reduce the uncertainty on the d/u ratio at large values of x.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Data for Natural Deep Eutectic Solvents (NADES) Assisted Deconstruction of Oilcane Bagasse for High Lipid and Sugar Recovery

In a novel approach, metabolically engineered sugarcane “Oilcane” has been investigated for fractionation of lipid and cellulose-rich pulp, using certain Natural deep eutectic solvents (NADES). The exploration of eco-friendly solvents are at the forefront of harnessing the biofuel potential of modern bioenergy crops. For this, six combinations of NADES were prepared using choline chloride (ChCl) as HBA and lactic acid (LA), oxalic acid (OA) and glycerol (Gly) as HBD and were further explored for pretreatment of oilcane bagasse in a molar ratio of 1:1 and 1:2. The impact of NADES ratio, biomass loading (10–50%), residence time (1–2 h), and temperature (90–140 °C) were evaluated for delignification, lipid content, sugar release after enzymatic hydrolysis. The finding demonstrated that under the optimal condition of ChCl: LA (1:2 molar ratio), 140 °C with 2 h retention time, the lipid content in the pre-treated substrate was increased to 2.5-fold (∼8% w/w) and > 80% glucose yield was achieved after 72 h of hydrolysis of pre-treated bagasse. High solid loading (∼50%) during pretreatment resulted in a similar glucose yield. Furthermore, recycling studies demonstrated that nearly 95 to 98% NADES could be recycled after each pretreatment for up to five consecutive cycles without any significant loss in chemical structure as confirmed by 1H NMR and FT IR. FT IR and XRD analyses of native and pre-treated biomass were performed to visualize the morphological changes during NADES pretreatment and their impact on sugar yield. The findings of the study may be used to establish NADES-based biorefinery for the valorization of lipids, and carbohydrates for fuels and chemicals production.

Conversion↗
DOE OSTI2021

New Determination of Fundamental Properties of Palomar 5 Using Deep DESI Imaging Data

The legacy imaging surveys for the Dark Energy Spectroscopic Instrument project provides multiple-color photometric data, which are about 2 mag deeper than those from the SDSS. In this study, we redetermine the fundamental properties for an old halo globular cluster of Palomar 5 based on these new imaging data, including structure parameters, stellar population parameters, and luminosity and mass functions. These characteristics, together with its tidal tails, are key for dynamical studies of the cluster and constraining the mass model of the Milky Way. By fitting the King model to the radial surface density profile of Palomar 5, we derive the core radius of [[Formula]], tidal radius of [[Formula]], and concentration parameter of c = 0.78 ± 0.04. We apply a Bayesian analysis method to derive the stellar population properties and get an age of 11.508 ± 0.027 Gyr, metallicity of [Fe/H] = −1.798 ± 0.014, reddening of E(B − V) = 0.0552 ± 0.0005, and distance modulus of (m−M){sub 0} = 16.835±0.006. The main-sequence luminosity and mass functions for both the cluster center and tidal tails are investigated. The luminosity and mass functions at different distances from the cluster center suggest that there is obvious spatial mass segregation. Many faint low-mass stars have been evaporated at the cluster center, and the tidal tails are enhanced by low-mass stars. Both the concentration and relaxation times suggest that Palomar 5 is a totally relaxed system.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks. Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Deep Learning on Multimodal Chemical and Whole Slide Imaging Data for Predicting Prostate Cancer Directly from Tissue Images

Prostate cancer is one of the most common cancers globally and is the second most common cancer in the male population in the US. Here we develop a study based on correlating the hematoxylin and eosin (H&E)-stained biopsy data with MALDI mass-spectrometric imaging data of the corresponding tissue to determine the cancerous regions and their unique chemical signatures and variations of the predicted regions with original pathological annotations. We obtain features from high-resolution optical micrographs of whole slide H&E stained data through deep learning and spatially register them with mass spectrometry imaging (MSI) data to correlate the chemical signature with the tissue anatomy of the data. We then use the learned correlation to predict prostate cancer from observed H&E images using trained coregistered MSI data. This multimodal approach can predict cancerous regions with ~80% accuracy, which indicates a correlation between optical H&E features and chemical information found in MSI. Further, we show that such paired multimodal data can be used for training feature extraction networks on H&E data which bypasses the need to acquire expensive MSI data and eliminates the need for manual annotation saving valuable time. Two chemical biomarkers were also found to be predicting the ground truth cancerous regions. This study shows promise in generating improved patient treatment trajectories by predicting prostate cancer directly from readily available H&E-stained biopsy images aided by coregistered MSI data.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Accelerating Collective Communication in Data Parallel Training across Deep Learning Frameworks

This work develops new techniques within Horovod, a generic communication library supporting data parallel training across deep learning frameworks. In particular, we improve the Horovod control plane by implementing a new coordination scheme that takes advantage of the characteristics of the typical data parallel training paradigm, namely the repeated execution of collectives on the gradients of a fixed set of tensors. Using a caching strategy, we execute Horovod’s existing coordinator-worker logic only once during a typical training run, replacing it with a more efficient decentralized orchestration strategy using the cached data and a global intersection of a bitvector for the remaining training duration. Next, we introduce a feature for end users to explicitly group collective operations, enabling finer grained control over the communication buffer sizes. To evaluate our proposed strategies, we conduct experiments on a world-class supercomputer — Summit. We compare our proposals to Horovod’s original design and observe 2x performance improvement at a scale of 6000 GPUs; we also compare them against tf.distribute and torch.DDP and achieve 12% better and comparable performance, respectively, using up to 1536 GPUs; we compare our solution against BytePS in typical HPC settings and achieve about 20% better performance on a scale of 768 GPUs. Finally, we test our strategies on a scientific application (STEMDL) using up to 27,600 GPUs (the entire Summit) and show that we achieve a near-linear scaling of 0.93 with a sustained performance of 1.54 exaflops (with standard error +- 0.02) in FP16 precision.

Romero, Joshua↗