Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Tree Classifiers”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

Mapping of taiga forest units using AIRSAR data and/or optical data, and retrieval of forest parameters

A maximum a posteriori Bayesian classifier for multifrequency polarimetric SAR data is used to perform a supervised classification of forest types in the floodplains of Alaska. The image classes include white spruce, balsam poplar, black spruce, alder, non-forests, and open water. The authors investigate the effect on classification accuracy of changing environmental conditions, and of frequency and polarization of the signal. The highest classification accuracy (86 percent correctly classified forest pixels, and 91 percent overall) is obtained combining L- and C-band frequencies fully polarimetric on a date where the forest is just recovering from flooding. The forest map compares favorably with a vegetation map assembled from digitized aerial photos which took five years for completion, and address the state of the forest in 1978, ignoring subsequent fires, changes in the course of the river, clear-cutting of trees, and tree growth. HV-polarization is the most useful polarization at L- and C-band for classification. C-band VV (ERS-1 mode) and L-band HH (J-ERS-1 mode) alone or combined yield unsatisfactory classification accuracies. Additional data acquired in the winter season during thawed and frozen days yield classification accuracies respectively 20 percent and 30 percent lower due to a greater confusion between conifers and deciduous trees. Data acquired at the peak of flooding in May 1991 also yield classification accuracies 10 percent lower because of dominant trunk-ground interactions which mask out finer differences in radar backscatter between tree species. Combination of several of these dates does not improve classification accuracy. For comparison, panchromatic optical data acquired by SPOT in the summer season of 1991 are used to classify the same area. The classification accuracy (78 percent for the forest types and 90 percent if open water is included) is lower than that obtained with AIRSAR although conifers and deciduous trees are better separated due to the presence of leaves on the deciduous trees. Optical data do not separate black spruce and white spruce as well as SAR data, cannot separate alder from balsam poplar, and are of course limited by the frequent cloud cover in the polar regions. Yet, combining SPOT and AIRSAR offers better chances to identify vegetation types independent of ground truth information using a combination of NDVI indexes from SPOT, biomass numbers from AIRSAR, and a segmentation map from either one.

Rignot, Eric↗
DOE OSTI2020

The cosmological bootstrap: inflationary correlators from symmetries and singularities

Scattering amplitudes at weak coupling are highly constrained by Lorentz invariance, locality and unitarity, and depend on model details only through coupling constants and the particle content of the theory. For example, four-particle amplitudes are analytic for contact interactions and have simple poles with appropriately positive residues for tree-level exchange. In this paper, we develop an understanding of inflationary correlators which parallels that of flat-space scattering amplitudes. Specifically, we study slow-roll inflation with weak couplings to extra massive particles, for which all correlation functions are controlled by an approximate conformal symmetry on the boundary of the spacetime. After systematically classifying all possible contact terms in de Sitter space, we derive an analytic expression for the four-point function of conformally coupled scalars mediated by the tree-level exchange of massive scalars. Conformal symmetry implies that the correlator satisfies a pair of differential equations with respect to spatial momenta, encoding bulk time evolution in purely boundary terms. The absence of unphysical singularities (and the correct normalization of physical ones) completely fixes this correlator. Moreover, a “spin-raising” operator relates it to the correlators associated with the exchange of particles with spin, while “weight-shifting” operators map it to the four-point function of massless scalars. We explain how these de Sitter four-point functions can be perturbed to obtain inflationary three-point functions. Using our formalism, we reproduce many classic results in the literature, such as the three-point function of slow-roll inflation, and provide a complete classification of all inflationary three- and four-point functions arising from weakly broken conformal symmetry. Remarkably, the inflationary bispectrum associated with the exchange of particles with arbitrary spin is completely characterized by the soft limit of the simplest scalar-exchange four-point function of conformally coupled scalars and a series of contact terms. Finally, we demonstrate that the inflationary correlators contain flat-space scattering amplitudes via a suitable analytic continuation of the external momenta, which can also be directly connected with the signals for particle production seen in the squeezed limit.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS1994

Automatic cataloguing and characterization of Earth science data using SE-trees

In the future, NASA's Earth Observing System (EOS) platforms will produce enormous amounts of remote sensing image data that will be stored in the EOS Data Information System. For the past several years, the Intelligent Data Management group at Goddard's Information Science and Technology Office has been researching techniques for automatically cataloguing and characterizing image data (ADCC) from EOS into a distributed database. At the core of the approach, scientists will be able to retrieve data based upon the contents of the imagery. The ability to automatically classify imagery is key to the success of contents-based search. We report results from experiments applying a novel machine learning framework, based on Set-Enumeration (SE) trees, to the ADCC domain. We experiment with two images: one taken from the Blackhills region in South Dakota; and the other from the Washington DC area. In a classical machine learning experimentation approach, an image's pixels are randomly partitioned into training (i.e. including ground truth or survey data) and testing sets. The prediction model is built using the pixels in the training set, and its performance is estimated using the testing set. With the first Blackhills image, we perform various experiments achieving an accuracy level of 83.2 percent, compared to 72.7 percent using a Back Propagation Neural Network (BPNN) and 65.3 percent using a Gaussain Maximum Likelihood Classifier (GMLC). However, with the Washington DC image, we were only able to achieve 71.4 percent, compared with 67.7 percent reported for the BPNN model and 62.3 percent for the GMLC.

Rymon, Ron↗
DOE OSTI2015

Contrasting allelic distribution of CO / Hd1 homologues in Miscanthus sinensis from the East Asian mainland and the Japanese archipelago

The genus Miscanthus is a perennial C 4 grass native to eastern Asia and is a promising candidate bioenergy crop for cool temperate areas. Flowering time is a crucial factor governing regional and seasonal adaptation; in addition, it is also a key target trait for extending the vegetative phase to improve biomass potential. Homologues of CONSTANS (CO)/Heading date 1(Hd1) were cloned from Miscanthus sinensis and named MsiHd1 . Sequences of MsiHd1 homologues were compared among 24 wild M. sinensis accessions from Japan, 14 from China, and three from South Korea. Two to five MsiHd1 alleles in each accession were identified, suggesting that MsiHd1 consists of at least three loci in the Miscanthus genome. Verifying the open reading frame in MsiHd1 , they were classified as putative functional alleles without mutations or non-functional alleles caused by indels. The Neighbor-Joining tree indicated that one of the multiple MsiHd1 loci is a pseudogene locus without any functional alleles. The pseudogene locus was named MsiHd1b , and the other loci were considered to be part of the MsiHd1a multi-locus family. Interestingly, in most Japanese accessions 50% or more of the MsiHd1a alleles were non-functional, whereas accessions from the East Asian mainland harboured only functional alleles. Five novel miniature inverted transposable elements (MITEs) ( MsiMITE1-MsiMITE5 ) were observed in MsiHd1a/b . MsiMITE1 , detected in exon 1 of MsiHd1a , was only observed in Japanese accessions and its revertant alleles derived from retransposition were predominantly in Chinese accessions. In conclusion, these differences in MsiHd1a show that the dependency on functional MsiHd1a alleles is different between accessions from the East Asian mainland and Japan.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2018

A subleading power operator basis for the scalar quark current

Factorization theorems play a crucial role in our understanding of the strong interaction. For collider processes they are typically formulated at leading power and much less is known about power corrections in the λ << 1 expansion. Here we present a complete basis of power suppressed operators for a scalar quark current at O(λ 2 ) in the amplitude level power expansion in the Soft Collinear Effective Theory, demonstrating that helicity selection rules significantly simplify the construction. This basis applies for the production of any color singlet scalar in qq¯¯ annihilation (such as bb¯¯→H ). We also classify all operators which contribute to the cross section at O(λ 2 ) and perform matching calculations to determine their tree level Wilson coefficients. Furthermore, these results can be exploited to study power corrections in both resummed and fixed order perturbation theory, and for analyzing the factorization properties of gauge theory amplitudes and cross sections at subleading power.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2014

Leptophilic dark matter and the anomalous magnetic moment of the muon

We consider renormalizable theories such that the scattering of dark matter off leptons arises at tree level, but scattering off nuclei only arises at loop. In this framework, the various dark matter candidates can be classified by their spins and by the forms of their interactions with leptons. In this study, we determine the corrections to the anomalous magnetic moment of the muon that arise from its interactions with dark matter. We then consider the implications of these results for a set of simplified models of leptophilic dark matter. When a dark matter candidate reduces the existing tension between the standard model prediction of the anomalous magnetic moment and the experimental measurement, the region of parameter space favored to completely remove the discrepancy is highlighted. Conversely, when agreement is worsened, we place limits on the parameters of the corresponding simplified model. These bounds and favored regions are compared against the experimental constraints on the simplified model from direct detection and from collider searches. Although these constraints are severe, we find there do exist limited regions of parameter space in these simple theories that can explain the observed anomaly in the muon magnetic moment while remaining consistent with all experimental bounds.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2014

LABEL: Fast and Accurate Lineage Assignment with Assessment of H5N1 and H9N2 Influenza A Hemagglutinins

The evolutionary classification of influenza genes into lineages is a first step in understanding their molecular epidemiology and can inform the subsequent implementation of control measures. We introduce a novel approach called Lineage Assignment By Extended Learning (LABEL) to rapidly determine cladistic information for any number of genes without the need for time-consuming sequence alignment, phylogenetic tree construction, or manual annotation. Instead, LABEL relies on hidden Markov model profiles and support vector machine training to hierarchically classify gene sequences by their similarity to pre-defined lineages. We assessed LABEL by analyzing the annotated hemagglutinin genes of highly pathogenic (H5N1) and low pathogenicity (H9N2) avian influenza A viruses. Using the WHO/FAO/OIE H5N1 evolution working group nomenclature, the LABEL pipeline quickly and accurately identified the H5 lineages of uncharacterized sequences. Moreover, we developed an updated clade nomenclature for the H9 hemagglutinin gene and show a similarly fast and reliable phylogenetic assessment with LABEL. While this study was focused on hemagglutinin sequences, LABEL could be applied to the analysis of any gene and shows great potential to guide molecular epidemiology activities, accelerate database annotation, and provide a data sorting tool for other large-scale bioinformatic studies.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2016

Machine- z : Rapid machine-learned redshift indicator for Swift gamma-ray bursts

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce ‘machine-z’, a redshift prediction algorithm and a ‘high-z’ classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve ~100 per cent recall. As a result, the most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2016

Machine-z: Rapid Machine-Learned Redshift Indicator for Swift Gamma-Ray Bursts

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce 'machine-z', a redshift prediction algorithm and a 'high-z' classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve approximately 100 per cent recall. The most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

gamma-ray burst: general↗
DOE OSTI2019

Situational Awareness in Distribution Grid Using Micro-PMU Data: A Machine Learning Approach

The recent development of distribution-level phasor measurement units, a.k.a. micro-PMUs, has been an important step towards achieving situational awareness in power distribution networks. The challenge however is to transform the large amount of data that is generated by micro-PMUs to actionable information and then match the information to use cases with practical value to system operators. This open problem is addressed in this paper. First, we introduce a novel data-driven event detection technique to pick out valuable portion of data from extremely large raw micro-PMU data. Subsequently, a datadriven event classifier is developed to effectively classify power quality events. Importantly, we use field expert knowledge and utility records to conduct an extensive data-driven event labeling. Moreover, certain aspects from event detection analysis are adopted as additional features to be fed into the classifier model. In this regard, a multi-class support vector machine (multi-SVM) classifier is trained and tested over 15 days of real-world data from two micro-PMUs on a distribution feeder in Riverside, CA. In total, we analyze 1.2 billion measurement points, and 10,700 events. Here, the effectiveness of the developed event classifier is compared with prevalent multi-class classification methods, including k-nearest neighbor method as well as decision-tree method. Importantly, two real-world use-cases are presented for the proposed data analytics tools, including remote asset monitoring and distribution-level oscillation analysis.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2018

Differences in Pre and Post Vascular Patterning Within Retinas from ISS Crew Members and Head-Down Tilt (HDT) Subjects by VESGEN Analysis

Accelerated research by NASA has investigated the significant risks incurred during long-duration missions in microgravity for Space Flight-Associated Neuro-ocular Syndrome (SANS, formerly known as Visual Impairments associated with Increased Intracranial Pressure, VIIP) [1]. For our study, NASA's VESsel GENeration Analysis (VESGEN) was used to investigate the role of retinal blood vessels in the etiology of SANS/VIIP. The response of retinal vessels to microgravity was evaluated in astronaut crew members pre and post flight to the International Space Station (ISS), and compared to the response of retinal vessels in healthy volunteers to 6deg head-down tilt during 70 days of bed rest (HDTBR). For the study, we are testing the hypothesis that long-term cephalad fluid shifts resulting in ocular and visual impairments are necessarily mediated in part by retinal blood vessels, and therefore are accompanied by structural adaptations of the vessels. METHODS: Vascular patterns in the retinas of crew members and HDTBR subjects extracted from 30deg infrared (IR) Heidelberg Spectralis images collected pre/postflight and pre/post HDTBR, respectively, were analyzed by VESGEN (patent pending). VESGEN is a mature, automated software developed as a research discovery tool for progressive vascular diseases in the retina and other tissues. The multi-parametric VESGEN analysis generates maps of branching arterial and venous trees quantified by parameters such as the fractal dimension (Df, a modern measure of vascular space-filling capacity), vessel diameters, and densities of vessel length and number classified into specific branching generations according to vascular physiological branching rules. The retrospective study approved by NASA's Institutional Review Board included the analysis of bilateral retinas in eight ISS crew members monitored by routine occupational surveillance and six HDTBR subjects (NASA FARU Campaign 11, for example). The VESGEN analysis was conducted in a blinded fashion, with IR retinal images masked to the subject's identity, ophthalmic and clinical characteristics, and to the temporal sequence of image collection. To complete our study, VESGEN results will be analyzed statistically and correlated with other ophthalmic and medical findings. RESULTS: Preliminary results for changes in the pre to post status of vascular patterning in the retinas of crew members and HDTBR subjects are interestingly opposite. By Df and other vascular branching measures, the space-filling capacity of arterial and venous trees decreased in the majority of crew members (11/16 retinas). In contrast, vascular densities increased in HDTBR subjects by the same parameters (6/10 retinas). To conclude the study, biostatistics and medical analyses will be conducted to quantify and draw conclusions about how the changes associated with flight compare to those associated with HDTBR. CONCLUSIONS: Vascular densities appeared to decrease in the retinas of ISS crew members and increase in HDTBR subjects. Differences in arterial and venous response to cephalad fluid shifts induced by ISS and HDTBR may have resulted from a long-duration conditioning phenomenon (for example, 6-month ISS missions compared to 70 days HDTBR), or the presence of gravity in HDTBR compared to microgravity on the ISS. In addition, increased and decreased vessel diameters for Crew Members and HDTBR, respectively, are subject to limits of im

Vascular↗
NASA NTRS2019

Evaluation of Classifier Complexity for Delay Tolerant Network Routing

The growing popularity of small cost effective satellites (SmallSats, CubeSats, etc.) creates the potential for a variety of new science applications involving multiple nodes functioning together or independently to achieve a task, such as swarms and constellations. As this technology develops and is deployed for missions in Low Earth Orbit and beyond, the use of delay tolerant networking (DTN) techniques may improve communication capabilities within the network. In this paper, a network hierarchy is developed from heterogeneous networks of SmallSats, surface vehicles, relay satellites and ground stations which form an integrated network. There is a tradeoff between complexity, flexibility, and scalability of user defined schedules versus autonomous routing as the number of nodes in the network increases. To address these issues, this work proposes a machine learning classifier based on DTN routing metrics. A framework is developed which will allow for the use of several categories of machine learning algorithms (decision tree, random forest and deep learning) to be applied to a dataset of historical network statistics, which allows for the evaluation of algorithm complexity versus performance to be explored. We develop the emulation of a hierarchical network, consisting of tens of nodes which form a cognitive network architecture. CORE (Common Open Research Emulator) is used to emulate the network using bundle protocol and DTN IP neighbor discovery.

Dudukovich, Rachel↗
DOE OSTI2025

Parallel sorting algorithm classification: is manual instrumentation necessary?

Understanding parallel algorithms is crucial for accelerating scientific simulations on complex, distributed memory, high-performance computers. Modern algorithm classification approaches learn semantics directly from source code to differentiate between algorithms, however, accessing source code is not always possible. We can learn about parallel algorithms from observing their performance, as programs running the same algorithms and using the same hardware should exhibit similar performance characteristics. We present an approach to learn algorithm classes from parallel performance data directly in order to classify algorithms without access to the source code. We extend previous work to enable classifying parallel sorting algorithms using automatic instrumentation instead of requiring manual region annotations in the source code. In this work, we design and demonstrate a study for classification of parallel sorting algorithms using parallel performance data collected from automatic instrumentation, and evaluate the performance of our new methodology on classification. We leverage Caliper to collect the performance data, Thicket for our exploratory data analysis (EDA), and PyTorch and Scikit-learn to evaluate the effectiveness of random forests, support vector machines (SVMs), decision trees, neural networks, and logistic regressions on parallel performance data. Additionally, we study noise in parallel performance data, whether the removal of noise and pre-processing of the data is necessary to accurately classify parallel sorting algorithms, and determine the effectiveness of features created from performance data. In conclusion, we demonstrate classification accuracy for these five different models of up to 97.7% across four different parallel algorithm classes.

Algorithm Classification↗
DOE OSTI2016

SU-C-207B-05: Tissue Segmentation of Computed Tomography Images Using a Random Forest Algorithm: A Feasibility Study

Purpose: Develop an automated Random Forest algorithm for tissue segmentation of CT examinations. Methods: Seven materials were classified for segmentation: background, lung/internal gas, fat, muscle, solid organ parenchyma, blood/contrast, and bone using Matlab and the Trainable Weka Segmentation (TWS) plugin of FIJI. The following classifier feature filters of TWS were investigated: minimum, maximum, mean, and variance each evaluated over a pixel radius of 2n, (n = 0–4). Also noise reduction and edge preserving filters, Gaussian, bilateral, Kuwahara, and anisotropic diffusion, were evaluated. The algorithm used 200 trees with 2 features per node. A training data set was established using an anonymized patient’s (male, 20 yr, 72 kg) chest-abdomen-pelvis CT examination. To establish segmentation ground truth, the training data were manually segmented using Eclipse planning software, and an intra-observer reproducibility test was conducted. Six additional patient data sets were segmented based on classifier data generated from the training data. Accuracy of segmentation was determined by calculating the Dice similarity coefficient (DSC) between manual and auto segmented images. Results: The optimized autosegmentation algorithm resulted in 16 features calculated using maximum, mean, variance, and Gaussian blur filters with kernel radii of 1, 2, and 4 pixels, in addition to the original CT number, and Kuwahara filter (linear kernel of 19 pixels). Ground truth had a DSC of 0.94 (range: 0.90–0.99) for adult and 0.92 (range: 0.85–0.99) for pediatric data sets across all seven segmentation classes. The automated algorithm produced segmentation with an average DSC of 0.85 ± 0.04 (range: 0.81–1.00) for the adult patients, and 0.86 ± 0.03 (range: 0.80–0.99) for the pediatric patients. Conclusion: The TWS Random Forest auto-segmentation algorithm was optimized for CT environment, and able to segment seven material classes over a range of body habitus and CT protocol parameters with an average DSC of 0.86 ± 0.04 (range: 0.80–0.99).

60 APPLIED LIFE SCIENCES↗
DOE OSTI2018

Climate sensitive size-dependent survival in tropical trees

Survival rates of large trees determine forest biomass dynamics. Survival rates of small trees are linked to mechanisms that maintain biodiversity across tropical forests. How species survival rates change with size offers insight into the links between biodiversity and ecosystem function across tropical forests. We tested patterns of size-dependent tree survival across the tropics using data from 1781 species and over two million individuals to assess whether tropical forests can be characterized by size-dependent life-history survival strategies. We found species were classifiable into four “survival modes” that explain life-history variation that shapes carbon-cycling and the relative abundances within forests. Frequently collected functional traits, such as wood density, leaf mass per area, and seed mass, were not generally predictive of species’ survival modes. Mean annual temperature and cumulative water deficit predicted the proportion of biomass of survival modes, indicating important links between evolutionary strategies, climate, and carbon cycling. The application of survival modes in demographic simulations predicted biomass change across forest sites. Our results reveal globally identifiable size-dependent survival strategies that differ across diverse systems in a consistent way. The abundance of survival modes and interaction with climate ultimately determine forest structure, carbon storage in biomass, and future forest trajectories.

Johnson, Daniel J.↗
DOE OSTI2021

A k-mer based approach for classifying viruses without taxonomy identifies viral associations in human autism and plant microbiomes

Viruses are an underrepresented taxa in the study and identification of microbiome constituents; however, they play an essential role in health, microbiome regulation, and transfer of genetic material. Only a few thousand viruses have been isolated, sequenced, and assigned a taxonomy, which limits the ability to identify and quantify viruses in the microbiome. Additionally, the vast diversity of viruses represents a challenge for classification, not only in constructing a viral taxonomy, but also in identifying similarities between a virus’ genotype and its phenotype. However, the diversity of viral sequences can be leveraged to classify their sequences in metagenomic and metatranscriptomic samples, even if they do not have a taxonomy. To identify and quantify viruses in transcriptomic and genomic samples, we developed a dynamic programming algorithm for creating a classification tree out of 715,672 metagenome viruses. To create the classification tree, we clustered proportional similarity scores generated from the k-mer profiles of each of the metagenome viruses to create a database of metagenomic viruses. The resulting Kraken2 database of the metagenomic viruses can be found here: https://www.osti.gov/biblio/1615774 and is compatible with Kraken2. We then integrated the viral classification database with databases created with genomes from NCBI for use with ParaKraken (a parallelized version of Kraken provided in Supplemental Zip 1), a metagenomic/transcriptomic classifier. To illustrate the breadth of our utility for classifying metagenome viruses, we analyzed data from a plant metagenome study identifying genotypic and compartment specific differences between two Populus genotypes in three different compartments. We also identified a significant increase in abundance of eight viral sequences in post mortem brains in a human metatranscriptome study comparing Autism Spectrum Disorder patients and controls. We also show the potential accuracy for classifying viruses by utilizing both the JGI and NCBI viral databases to identify the uniqueness of viral sequences. Finally, we validate the accuracy of viral classification with NCBI databases containing viruses with taxonomy to identify pathogenic viruses in known COVID-19 and cassava brown streak virus infection samples. Our method represents the compulsory first step in better understanding the role of viruses in the microbiome by allowing for a more complete identification of sequences without taxonomy. Better classification of viruses will improve identifying associations between viruses and their hosts as well as viruses and other microbiome members. Despite the lack of taxonomy, this database of metagenomic viruses can be used with any tool that utilizes a taxonomy, such as Kraken, for accurate classification of viruses.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2018

Differences in Pre and Post Vascular Patterning of Retinas from ISS Crew Members and HDT Subjects by VESGEN Analysis

Accelerated research by NASA [1] has investigated the significant risks for visual and ocular impairments Spaceflight Associated Neuro-Ocular Syndrome /Visual Impairment/Intracranial Pressure (SANS/VIIP) incurred by microgravity spaceflight, especially long-duration missions. Our study investigates the role of blood vessels in the incidence and etiology of SANS/VIIP within the retinas of Astronaut crewmembers pre-and post-flight to the International Space Station (ISS) by NASA's VESsel GENeration Analysis (VESGEN). The response of retinal vessels in crewmembers to microgravity was compared to that of retinal vessels to Head-Down Tilt (HDT) in subjects undergoing 70-Day Bed Rest. The study tests the proposed hypothesis that cephalad fluid shifts missions, resulting in ocular and visual impairments, are necessarily mediated in part by retinal blood vessels, and are therefore accompanied by significant remodeling of retinal vasculature.Vascular patterns in the retinas of crew members and HDTBR subjects extracted from 30° infrared (IR) Heidelberg Spectralis® images collected pre/postflight and pre/post HDTBR, respectively, were analyzed by VESGEN (patent pending). a mature, automated software developed as a research discovery tool for progressive vascular diseases in the retina and other tissues [2]. The weighted, multi-parametric VESGEN analysis generates maps of branching arterial and venous trees and quantification by parameters such as the fractal dimension (Df, a modern measure of vascular space-filling capacity), vessel diameters, and densities of vessel length and number classified into specific branching generations by vascular physiological branching rules [2,3]. The retrospective study approved by NASA’s Institutional Review Board included six HDT subjects (NASA Flight Analogs Research Unit [FARU] Campaign 11; for example, [4]) and eight ISS crewmembers monitored by routine occupational surveillance who provided their study consents to NASA’s Lifetime Surveillance of Astronaut Health (LSAH). For the initial blinded VESGEN phase, ophthalmic retinal images were masked as to subject identity and pre- and post-status. In the second unblinded phase, VESGEN results were analyzed according to the pre- and post-status of left and right retinas matched to each subject. To complete our study, vascular results will be subjected to NASA biostatistical analysis and correlated with other ophthalmic and medical findings. Preliminary results for changes in the pre- to post-status of vascular patterning in the retinas of crewmembers and HDT subjects are strikingly opposite. By Df and other vascular branching measures, the space-filling capacity of arterial and venous trees decreased in a substantial subset of crewmembers (11/16 retinas). In contrast, vascular densities increased in a substantial subset of HDT subjects by the same parameters (6/10 retinas, currently excluding one anomalous subject). To conclude the study, biostatistical and medical analyses will be of critical importance for investigating the validity of these vascular findings. Vascular densities appeared to decrease in the retinas of crewmembers following ISS Missions, and increase in subjects after HDT. The vascular increases and decreases most likely derive primarily from limits of resolution to the ophthalmic imaging that does not capture the smallest vessels, rather than from vessel growth or atrophy. Differences in arterial and venous response to cephalad fluid shifts induced by ISS and HDT may have resulted from a long-duration conditioning phenomenon (for example, 6-month ISS missions compared to 70-day HDT), or the presence of gravity in HDT compared to microgravity onboard the ISS. To conclude our study, the biostatistical and medical analyses will be of critical importance for investigating the validity and significance of the VESGEN findings.

Murray, M. C.↗
DOE OSTI2018

Jet charge and machine learning

Modern machine learning techniques, such as convolutional, recurrent and recursive neural networks, have shown promise for jet substructure at the Large Hadron Collider. For example, they have demonstrated effectiveness at boosted top or W boson identification or for quark/gluon discrimination. We explore these methods for the purpose of classifying jets according to their electric charge. We find that both neural networks that incorporate distance within the jet as an input and boosted decision trees including radial distance information can provide significant improvement in jet charge extraction over current methods. Specifically, convolutional, recurrent, and recursive networks can provide the largest improvement over traditional methods, in part by effectively utilizing distance within the jet or clustering history. Furthermore, the advantages of using a fixed-size input representation (as with the CNN) or a small input representation (as with the RNN) suggest that both convolutional and recurrent networks will be essential to the future of modern machine learning at colliders.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗