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 307 records · Page 17

Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources

We live in momentous times. The science community is empowered with an arsenal of cosmic messengers to study the universe in unprecedented detail. Gravitational waves, electromagnetic waves, neutrinos, and cosmic rays cover a wide range of wavelengths and timescales. Combining and processing these datasets that vary in volume, speed, and dimensionality requires new modes of instrument coordination, funding, and international collaboration with a specialized human and technological infrastructure. In tandem with the advent of large-scale scientific facilities, the last decade has experienced an unprecedented transformation in computing and signal-processing algorithms. The combination of graphics processing units, deep learning, and the availability of open source, high-quality datasets has powered the rise of artificial intelligence. This digital revolution now powers a multibillion dollar industry, with far-reaching implications in technology and society. In this chapter, we describe pioneering efforts to adapt artificial intelligence algorithms to address computational grand challenges in multi-messenger astrophysics. We review the rapid evolution of these disruptive algorithms, from the first class of algorithms introduced in early 2017 to the sophisticated algorithms that now incorporate domain expertise in their architectural design and optimization schemes. We discuss the importance of scientific visualization and extreme-scale computing in reducing time-to-insight and obtaining new knowledge from the interplay between models and data.

Artificial Intelligence↗

Differentiable, Learnable, Regionalized Process-Based Models With Multiphysical Outputs can Approach State-Of-The-Art Hydrologic Prediction Accuracy

Predictions of hydrologic variables across the entire water cycle have significant value for water resources management as well as downstream applications such as ecosystem and water quality modeling. Recently, purely data-driven deep learning models like long short-term memory (LSTM) showed seemingly insurmountable performance in modeling rainfall runoff and other geoscientific variables, yet they cannot predict untrained physical variables and remain challenging to interpret. Here, we show that differentiable, learnable, process-based models (called δ models here) can approach the performance level of LSTM for the intensively observed variable (streamflow) with regionalized parameterization. We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework, to parameterize, enhance, or replace the process-based model's modules. Without using an ensemble or post-processor, δ models can obtain a median Nash-Sutcliffe efficiency of 0.732 for 671 basins across the USA for the Daymet forcing data set, compared to 0.748 from a state-of-the-art LSTM model with the same setup. For another forcing data set, the difference is even smaller: 0.715 versus 0.722. Meanwhile, the resulting learnable process-based models can output a full set of untrained variables, for example, soil and groundwater storage, snowpack, evapotranspiration, and baseflow, and can later be constrained by their observations. Both simulated evapotranspiration and fraction of discharge from baseflow agreed decently with alternative estimates. The general framework can work with models with various process complexity and opens up the path for learning physics from big data.

54 ENVIRONMENTAL SCIENCES↗

Towards automating structural discovery in scanning transmission electron microscopy *

Abstract Scanning transmission electron microscopy is now the primary tool for exploring functional materials on the atomic level. Often, features of interest are highly localized in specific regions in the material, such as ferroelectric domain walls, extended defects, or second phase inclusions. Selecting regions to image for structural and chemical discovery via atomically resolved imaging has traditionally proceeded via human operators making semi-informed judgements on sampling locations and parameters. Recent efforts at automation for structural and physical discovery have pointed towards the use of ‘active learning’ methods that utilize Bayesian optimization with surrogate models to quickly find relevant regions of interest. Yet despite the potential importance of this direction, there is a general lack of certainty in selecting relevant control algorithms and how to balance a priori knowledge of the material system with knowledge derived during experimentation. Here we address this gap by developing the automated experiment workflows with several combinations to both illustrate the effects of these choices and demonstrate the tradeoffs associated with each in terms of accuracy, robustness, and susceptibility to hyperparameters for structural discovery. We discuss possible methods to build descriptors using the raw image data and deep learning based semantic segmentation, as well as the implementation of variational autoencoder based representation. Furthermore, each workflow is applied to a range of feature sizes including NiO pillars within a La:SrMnO 3 matrix, ferroelectric domains in BiFeO 3 , and topological defects in graphene. The code developed in this manuscript is open sourced and will be released at github.com/nccreang/AE_Workflows .

47 OTHER INSTRUMENTATION↗

Candidate Periodically Variable Quasars from the Dark Energy Survey and the Sloan Digital Sky Survey

Periodically variable quasars have been suggested as close binary supermassive black holes. We present a systematic search for periodic light curves in 625 spectroscopically confirmed quasars with a median redshift of 1.8 in a 4.6 deg 2 overlapping region of the Dark Energy Survey Supernova (DES-SN) fields and the Sloan Digital Sky Survey Stripe 82 (SDSS-S82). Our sample has a unique 20-year long multi-color ( griz ) light curve enabled by combining DES-SN Y6 observations with archival SDSS-S82 data. The deep imaging allows us to search for periodic light curves in less luminous quasars (down to r ~23.5 mag) powered by less massive black holes (with masses ≳ 10 8.5 M ⊙ ) at high redshift for the first time. We find five candidates with significant (at >99.74% single-frequency significance in at least two bands with a global p-value of ~7 × 10 -4 –3× 10 -3 accounting for the look-elsewhere effect) periodicity with observed periods of ~3–5 years (i.e., 1–2 years in rest frame) having ~4–6 cycles spanned by the observations. If all five candidates are periodically variable quasars, this translates into a detection rate of |${\sim }0.8^{+0.5}_{-0.3}$| % or |${\sim }1.1^{+0.7}_{-0.5}$| quasar per deg 2 . Our detection rate is 4–80 times larger than those found by previous searches using shallower surveys over larger areas. This discrepancy is likely caused by differences in the quasar populations probed and the survey data qualities. Furthermore, we discuss implications on the future direct detection of low-frequency gravitational waves. Additionally, continued photometric monitoring will further assess the robustness and characteristics of these candidate periodic quasars to determine their physical origins.

79 ASTRONOMY AND ASTROPHYSICS↗

Real-Time Cavity Fault Prediction in CEBAF Using Deep Learning

Data-dri­ven pre­dic­tion of fu­ture faults is a major re­search area for many in­dus­trial ap­pli­ca­tions. In this work, we pre­sent a new pro­ce­dure of real-time fault pre­dic­tion for su­per­con­duct­ing ra­dio-fre­quency (SRF) cav­i­ties at the Con­tin­u­ous Elec­tron Beam Ac­cel­er­a­tor Fa­cil­ity (CEBAF) using deep learn­ing. CEBAF has been af­flicted by fre­quent down­time caused by SRF cav­ity faults. We per­form fault pre­dic­tion using pre-fault RF sig­nals from C100-type cry­omod­ules. Using the pre-fault sig­nal in­for­ma­tion, the new al­go­rithm pre­dicts the type of cav­ity fault be­fore the ac­tual onset. The early pre­dic­tion may en­able po­ten­tial mit­i­ga­tion strate­gies to pre­vent the fault. In our work, we apply a two-stage fault pre­dic­tion pipeline. In the first stage, a model dis­tin­guishes be­tween faulty and nor­mal sig­nals using a U-Net deep learn­ing ar­chi­tec­ture. In the sec­ond stage of the net­work, sig­nals flagged as faulty by the first model are clas­si­fied into one of seven fault types based on learned sig­na­tures in the data. Ini­tial re­sults show that our model can suc­cess­fully pre­dict most fault types 200 ms be­fore onset. We will dis­cuss rea­sons for poor model per­for­mance on spe­cific fault types.

Rahman, M.↗

Millijansky radio variability in SDSS stripe 82

We report on a blind survey for extragalactic radio variability that was carried out by comparing two epochs of data from the Faint Images of the Radio Sky at Twenty centimeters survey with a third epoch from a new 1.4 GHz survey of SDSS Stripe 82. The three epochs are spaced seven years apart and have an overlapping area of 60 deg{sup 2}. We uncover 89 variable sources down to the millijansky level, 75 of which are newly identified, and we find no evidence for transient phenomena. This new sample of variable sources allows us to infer an upper limit to the mean characteristic timescale of active galactic nucleus radio variability of 14 yr. We find that only 1% of extragalactic sources have fractional variability f {sub var} > 3, while 44% of Galactic sources vary by this much. The variable sample contains a larger fraction of quasars than a comparable non-variable control sample, though the majority of the variable sources appear to be extended galaxies in the optical. This implies that either quasars are not the dominant contributor to the variability of the sample, or that the deep optical data allow us to detect the host galaxies of some low-z quasars. We use the new, higher resolution data to report on the morphology of the variable sources. Finally, we show that the fraction of sources that are variable remains constant or increases at low flux densities. This may imply that next generation radio surveys with telescopes like Australian Square Kilometer Array Pathfinder and MeerKAT will see a constant or even increasing fraction of variable sources down into the sub-millijansky regime.

79 ASTRONOMY AND ASTROPHYSICS↗

Production of Z{sup 0} bosons with rapidity gaps: Exclusive photoproduction in {gamma}p and pp collisions and inclusive double diffractive Z{sup 0}'s

We extend the k{sub perpendicular}-factorization formalism for exclusive photoproduction of vector mesons to the production of electroweak Z{sup 0} bosons. Predictions for the {gamma}p{yields}Z{sup 0}p and pp{yields}ppZ{sup 0} reactions are given using an unintegrated gluon distribution tested against deep inelastic data. We show distributions in the Z{sup 0} rapidity, transverse momentum of Z{sup 0} as well as in relative azimuthal angle between outgoing protons. The contributions of different flavors are discussed. Absorption effects lower the cross section by a factor of 1.5-2, depending on the Z-boson rapidity. We also discuss the production of Z{sup 0} bosons in central inclusive production. Here rapidity and (x{sub IP,1},x{sub IP,2}) distributions of Z{sup 0} are calculated. The corresponding cross section is about 3 orders of magnitude larger than that for the purely exclusive process.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Accurate detection of somatic mutations is challenging but critical in understanding cancer formation, progression, and treatment. We recently proposed NeuSomatic, the first deep convolutional neural network-based somatic mutation detection approach, and demonstrated performance advantages on in silico data. In this study, we use the first comprehensive and well-characterized somatic reference data sets from the SEQC2 consortium to investigate best practices for using a deep learning framework in cancer mutation detection. Using the high-confidence somatic mutations established for a cancer cell line by the consortium, we identify the best strategy for building robust models on multiple data sets derived from samples representing real scenarios, for example, a model trained on a combination of real and spike-in mutations had the highest average performance. The strategy identified in our study achieved high robustness across multiple sequencing technologies for fresh and FFPE DNA input, varying tumor/normal purities, and different coverages, with significant superiority over conventional detection approaches in general, as well as in challenging situations such as low coverage, low variant allele frequency, DNA damage, and difficult genomic regions.

59 BASIC BIOLOGICAL SCIENCES↗

Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning

Nowadays, data generated by large-scale scientific experiments are on the scale of petabytes per month. These data are transferred through dedicated high-bandwidth networks across distributed collaboration sites for processing, storage, and analysis. Like general purpose networks, research networks experience attacks. However, monitoring traffic in such high-bandwidth network environments is challenging with conventional deep packet inspection (DPI)- based network intrusion detection systems (NIDS). Recently, machine learning (ML) algorithms have shown potential in detecting anomalous patterns with better generalizability and faster speed. Compared to the general purpose networks, traffic movement in research network is less volatile and more likely to benefit from the ML-based anomaly analysis. We present ThunderSecure, an efficient AI-powered system for detecting anomalies in 100G research networks. ThunderSecure implements a high-throughput packet processing infrastructure using multi-cores and GPUs. It takes time-series statistics from a variety of network measurements and uses 2D Convolutional Neural Network (CNN) to explore both spatial and temporal dependencies in network data stream. Patterns of science data traffic are learned with a one-class neural network, which blends an Adversarial Autoencoder (AAE) with Gaussian mixture density estimation. Testing traffic flows exhibiting significant deviations from the learned baseline of normality are marked as anomalies. We trained ThunderSecure on hundreds of billions of science data packets recorded from a 100G research network at Fermi National Accelerator Laboratory. The detection performance was evaluated on traffic captured from the same research network days and weeks after the training with different types of attack flows injected. To the best of our knowledge, this is the first ML work in the area of network anomaly detection that has been validated on such extreme scale datasets. Results show that ThunderSecure can recognize science data traffic that are captured long after the training and make nearly certain detection on those with anomalous flows injected, even in the case when the anomaly-to-normal mixing ratio is 0.1%.

Gong, Qian↗

AN IN-DEPTH STUDY OF THE ABUNDANCE PATTERN IN THE HOT INTERSTELLAR MEDIUM IN NGC 4649

We present our X-ray imaging spectroscopic analysis of data from deep Suzaku and XMM-Newton Observatory exposures of the Virgo Cluster elliptical galaxy NGC 4649 (M60), focusing on the abundance pattern in the hot interstellar medium (ISM). All measured elements show a radial decline in abundance, with the possible exception of O. We construct steady-state solutions to the chemical evolution equations that include infall in addition to stellar mass return and Type Ia supernova (SNIa) enrichment, and consider recently published SNIa yields. By adjusting a single model parameter to obtain a match to the global abundance pattern in NGC 4649, we infer that introduction of subsolar metallicity external gas has reduced the overall ISM metallicity and diluted the effectiveness of SNIa to skew the pattern toward low {alpha}/Fe ratios, and estimate the combination of SNIa rate and level of dilution. Evidently, newly introduced gas is heated as it is integrated into, and interacts with, the hot gas that is already present. These results indicate a complex flow and enrichment history for NGC 4649, reflecting the continual evolution of elliptical galaxies beyond the formation epoch. The heating and circulation of accreted gas may help reconcile this dynamic history with the mostly passive evolution of elliptical stellar populations. In an Appendix, we examine the effects of the recent updated atomic database AtomDB in spectral fitting of thermal plasmas with hot ISM temperatures in the elliptical galaxy range.

79 ASTRONOMY AND ASTROPHYSICS↗

ALIEN MAPS OF AN OCEAN-BEARING WORLD

When Earth-mass extrasolar planets first become detectable, one challenge will be to determine which of these worlds harbor liquid water, a widely used criterion for habitability. Some of the first observations of these planets will consist of disc-averaged, time-resolved broadband photometry. To simulate such data, the Deep Impact spacecraft obtained light curves of Earth at seven wavebands spanning 300-1000 nm as part of the EPOXI mission of opportunity. In this paper, we analyze disc-integrated light curves, treating Earth as if it were an exoplanet, to determine if we can detect the presence of oceans and continents. We present two observations each spanning 1 day, taken at gibbous phases of 57 deg. and 77 deg., respectively. As expected, the time-averaged spectrum of Earth is blue at short wavelengths due to Rayleigh scattering, and gray redward of 600 nm due to reflective clouds. The rotation of the planet leads to diurnal albedo variations of 15%-30%, with the largest relative changes occurring at the reddest wavelengths. To characterize these variations in an unbiased manner, we carry out a principal component analysis of the multi-band light curves; this analysis reveals that 98% of the diurnal color changes of Earth are due to only two dominant eigencolors. We use the time variations of these two eigencolors to construct longitudinal maps of the Earth, treating it as a non-uniform Lambert sphere. We find that the spectral and spatial distributions of the eigencolors correspond to cloud-free continents and oceans despite the fact that our observations were taken on days with typical cloud cover. We also find that the near-infrared wavebands are particularly useful in distinguishing between land and water. Based on this experiment, we conclude that it should be possible to infer the existence of water oceans on exoplanets with time-resolved broadband observations taken by a large space-based coronagraphic telescope.

99 GENERAL AND MISCELLANEOUS↗

Electron mass enhancement and magnetic phase separation near the Mott transition in double-layer ruthenates

Here, we present a detailed investigation of the specific heat of Ca 3 (Ru 1-x M x ) 2 O 7 (M = Ti, Fe, Mn) single crystals. Depending on the dopant and doping level, three distinct regions are present: a quasitwo-dimensional metallic state with antiferromagnetic (AFM) order formed by ferromagnetic bilayers (AFM-b), a Mott insulating state with G-type AFM order (G-AFM), and a localized state with a mixed AFM-b and G-AFM phase. Our specific heat data provide deep insights into the Mott transitions induced by Ti and Mn doping. We observed not only an anomalous large mass enhancement, but also an additional term in the specific heat, i.e., C ∝ T 2 , in the localized region. The C ∝ T 2 term is most likely due to long-wavelength excitations with both FM and AFM components. A decrease in the Debye temperature is observed in the G-type AFM region, indicating lattice softening associated with the Mott transition.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

MicroRNA-187, down-regulated in clear cell renal cell carcinoma and associated with lower survival, inhibits cell growth and migration though targeting B7-H3

Highlights: •miR-187 is down-regulated in clear cell renal cell carcinoma (ccRCC). •Down-regulation of miR-187 is associated with poor outcomes in patients with ccRCC. •miR-187 inhibits cell growth and migration though targeting B7-H3 in ccRCC. -- Abstract: Aberrantly expressed microRNAs (miRNAs) are frequently associated with the aggressive malignant behavior of human cancers, including clear cell renal cell carcinoma (ccRCC). Based on the preliminary deep sequencing data, we hypothesized that miR-187 may play an important role in ccRCC development. In this study, we found that miR-187 was down-regulated in both tumor tissue and plasma of ccRCC patients. Lower miR-187 expression levels were associated with higher tumor grade and stage. All patients with high miR-187 expression survived 5 years, while with low miR-187 expression, only 42% survived. Suppressed in vitro proliferation, inhibited in vivo tumor growth, and decreased motility were observed in cells treated with the miR-187 expression vector. Further studies showed that B7 homolog 3 (B7-H3) is a direct target of miR-187. Over-expression of miR-187 decreased B7-H3 mRNA level and repressed B7-H3-3′-UTR reporter activity. Knockdown of B7-H3 using siRNA resulted in similar phenotype changes as that observed for overexpression of miR-187. Our data suggest that miR-187 is emerging as a novel player in the disease state of ccRCC. miR-187 plays a tumor suppressor role in ccRCC.

60 APPLIED LIFE SCIENCES↗

Microstructure evolution and mechanical performance of nickel based superalloy C1023 at elevated temperatures

Highlights: • Growth and strengthening mechanisms of carbide in superalloy C1023 were investigated. • Carbide dendrite primary arm grows selectively based on the vertex of blocky carbonitride. • Monolayer or multilayer carbide dendrite arm has certain crystal relationship with γ′ and γ. • Plastic deformation of γ hinders interior crack propagating from MC to matrix at 650 °C. • Oxidation of GBs significantly weakens the tensile strength of the superalloy at 850 °C. - Abstract: Microstructure evolution of polycrystalline nickel based superalloy C1023 casting was investigated by comparing as cast superalloy and heat treated superalloy in the paper. Influences of strengtheners and carbides on the tensile behaviors of heat treated superalloy at different temperatures (20 °C, 650 °C, and 850 °C) were studied. Resulting data from deep corrosion suggested that growth mode of scripted carbide included nucleation on the vertex of blocky carbonitride, expansion of dendrite arm in C-rich area, and enlargement of dendrite cap. Decomposition of MC carbide generated numerous octahedral M{sub 23}C{sub 6} carbide as well as nanoscale Cr-Mo-rich nuclei. Diffusion of Mo from γ to precipitates such as γ', MC, and M{sub 23}C{sub 6}, occurred during the heat treatment while irregular γ' (4 nm–500 nm) transformed into cuboidal particles. At 650 °C, no significant deterioration of tensile strength was found while plastic deformation ability of γ base was improved. Oxidation of grain boundaries (GBs) dominated the crack behavior of the superalloy at 850 °C.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms

This study examines the effectiveness of generative models in drug discovery, material science, and polymer science, aiming to overcome constraints associated with traditional inverse design methods relying on heuristic rules. Generative models generate synthetic data resembling real data, enabling deep learning model training without extensive labeled datasets. They prove valuable in creating virtual libraries of molecules for material science and facilitating drug discovery by generating molecules with specific properties. While generative adversarial networks (GANs) are explored for these purposes, mode collapse restricts their efficacy, limiting novel structure variability. To address this, we introduce a masked language model (LM) inspired by natural language processing. Although LMs alone can have inherent limitations, we propose a hybrid architecture combining LMs and GANs to efficiently generate new molecules, demonstrating superior performance over standalone masked LMs, particularly for smaller population sizes. This hybrid LM-GAN architecture enhances efficiency in optimizing properties and generating novel samples.

97 MATHEMATICS AND COMPUTING↗

Determination of the strong coupling and its running from measurements of inclusive jet production

The value of the strong coupling α S is determined in a comprehensive analysis at next-to-next-to-leading order accuracy in quantum chromodynamics. The analysis uses double-differential cross section measurements from the CMS Collaboration at the CERN LHC of inclusive jet production in proton-proton collisions at centre-of-mass energies of 2.76, 7, 8, and 13 TeV, combined with inclusive deep-inelastic data from HERA. The value α S (m z ) = 0.1176 $^{+0.0014}_{-0.0016}$ is obtained at the scale of the Z boson mass. By using the measurements in different intervals of jet transverse momentum, the running of α S is probed for energies between 100 and 1600 GeV.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The importance of temporal and spatial incoherence in quantitative interpretation of 4D-STEM

Recent developments in pixelated detectors, when combined with aberration correction of probe forming optics have greatly enhanced the field of scanning electron diffraction. Differential phase contrast is now routine and deep learning has been proposed as a method to extract maximum information from diffraction patterns. This study examines the effects of temporal and spatial incoherence on convergent beam electron diffraction patterns and demonstrates that simple center of mass measurements cannot be naively interpreted. The inclusion of incoherence in deep learning data sets is also discussed.

36 MATERIALS SCIENCE↗

A Mass Conservation Relaxed (MCR) LSTM Model for Streamflow Simulation Across CONUS

The recent development of the physics-aware Mass-Conserving Long Short-Term Memory network (MC-LSTM) provides an alternative to other data-driven Deep Learning (DL) models in hydrology. Mass-Conserving Long Short-Term Memory incorporates mass conservation directly into the LSTM architecture. Despite the theoretical advancements, studies have reported a surprisingly limited performance of the MC-LSTM in streamflow simulation. We hypothesize that such a limitation is due to the unrealistic mass conservation scheme in MC-LSTM, which overlooks unobserved incoming water fluxes beyond precipitation. As an attempt to verify this hypothesis, we propose a Mass Conservation Relaxed LSTM (MCR-LSTM), which incorporates a bi-directional mass relaxation (MR) component to account for potential incoming water fluxes beyond precipitation. We train and test the proposed MCR-LSTM model across 531 watersheds in the contiguous United States (CONUS) against three baseline models: the Sacramento Soil Moisture Accounting, LSTM, and MC-LSTM. Our results show that MCR-LSTM outperforms MC-LSTM despite its underperformance compared to LSTM. Specifically, MCR-LSTM's advantage over MC-LSTM is mainly seen in the Plains and Western U.S., where the newly incorporated MR component better simulates water loss and suggests the likely existence of additional incoming water fluxes beyond precipitation, respectively. The novelty and contribution of this study are twofold: firstly, it introduces an alternative physics-aware DL tool (i.e., MCR-LSTM) in hydrology with higher accuracy in specific regions compared to MC-LSTM. Secondly, it provides a diagnosis of regions where strict, precipitation-based mass conservation constraints may be unrealistic in streamflow simulation.

deep learning↗