Search NASA⌕ Search

SEARCH · Search NASA

Results for “feature selection”

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 937 records · Page 52

Seamless lateral graphene p–n junctions formed by selective in situ doping for high-performance photodetectors

Lateral graphene p–n junctions are important since they constitute the core components in a variety of electronic/photonic systems. However, formation of lateral graphene p–n junctions with a controllable doping levels is still a great challenge due to the monolayer feature of graphene. Herein, by performing selective ion implantation and in situ growth by dynamic chemical vapor deposition, direct formation of seamless lateral graphene p–n junctions with spatial control and tunable doping is demonstrated. Uniform lattice substitution with heteroatoms is achieved in both the boron-doped and nitrogen-doped regions and photoelectrical assessment reveals that the seamless lateral p–n junctions exhibit a distinct photocurrent response under ambient conditions. As ion implantation is a standard technique in microelectronics, our study suggests a simple and effective strategy for mass production of graphene p–n junctions with batch capability and spatial controllability, which can be readily integrated into the production of graphene-based electronics and photonics.

36 MATERIALS SCIENCE↗

Error modeling for surrogates of dynamical systems using machine learning: Machine-learning-based error model for surrogates of dynamical systems

A machine learning–based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (eg, random forests, and LASSO) to map a large set of inexpensively computed “error indicators” (ie, features) produced by the surrogate model at a given time instance to a prediction of the surrogate-model error in a quantity of interest (QoI). This eliminates the need for the user to hand-select a small number of informative features. The methodology requires a training set of parameter instances at which the time-dependent surrogate-model error is computed by simulating both the high-fidelity and surrogate models. Using these training data, the method first determines regression-model locality (via classification or clustering) and subsequently constructs a “local” regression model to predict the time-instantaneous error within each identified region of feature space. We consider 2 uses for the resulting error model: (1) as a correction to the surrogate-model QoI prediction at each time instance and (2) as a way to statistically model arbitrary functions of the time-dependent surrogate-model error (eg, time-integrated errors). We then apply the proposed framework to model errors in reduced-order models of nonlinear oil-water subsurface flow simulations, with time-varying well-control (bottom-hole pressure) parameters. The reduced-order models used in this work entail application of trajectory piecewise linearization in conjunction with proper orthogonal decomposition. Moreover, when the first use of the method is considered, numerical experiments demonstrate consistent improvement in accuracy in the time-instantaneous QoI prediction relative to the original surrogate model, across a large number of test cases. When the second use is considered, results show that the proposed method provides accurate statistical predictions of the time- and well-averaged errors.

97 MATHEMATICS AND COMPUTING↗

Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning

Background: We developed machine-learning (ML) models to estimate a patient’s risk of cardiac death based on adenosine myocardial perfusion SPECT (MPS) and associated clinical data, and compared their performance to baseline logistic regression (LR). We demonstrated an approach to visually convey the reasoning behind a patient’s risk to provide insight to clinicians beyond that of a “black box.” Methods: We trained multiple models using 122 potential clinical predictors (features) for 8321 patients, including 551 cases of subsequent cardiac death. Accuracy was measured by area under the ROC curve (AUC), computed within a cross-validation framework. We developed a method to display the model’s rationale to facilitate clinical interpretation. Results: The baseline LR (AUC = 0.76; 14 features) was outperformed by all other methods. A least absolute shrinkage and selection operator (LASSO) model (AUC = 0.77; p = .045; 6 features) required the fewest features. A support vector machine (SVM) model (AUC = 0.83; p < .0001; 49 features) provided the highest accuracy. Conclusions: LASSO outperformed LR in both accuracy and simplicity (number of features), with SVM yielding best AUC for prediction of cardiac death in patients undergoing MPS. Combined with presenting the reasoning behind the risk scores, our results suggest that ML can be more effective than LR for this application.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Method for rapid development of additive manufacturing parameter set

An apparatus includes a control system that defines a test part having multiple features of multiple feature types. The control system controls an additive manufacturing (AM) machine to print multiple copies of the test part, with each copy being printed according to a respective set of values used as printing parameters. A measurement system obtains a computed tomography (CT) image of each of the copies of the test part. An analysis system, for each of the plurality of feature types, analyzes the CT images to identify a selected set of values for the printing parameters. The analysis system identifies a portion of the CT image related to a first feature and assesses its density based on an average grayscale value. The AM machine is then controlled to print production parts according to, for each feature type of the production parts, the selected set of values for the printing parameters.

Bhattad, Pradeep↗

Importance of Engineered and Learned Molecular Representations in Predicting Organic Reactivity, Selectivity, and Chemical Properties

Machine-readable chemical structure representations are foundational in all attempts to harness machine learning for the prediction of reactivities, selectivities, and chemical properties directly from molecular structure. The featurization of discrete chemical structures into a continuous vector space is a critical phase undertaken before model selection, and the development of new ways to quantitatively encode molecules is an active area of research. Here, we highlight the application and suitability of different representations, from expert-guided “engineered” descriptors to automatically “learned” features, in different prediction tasks relevant to organic and organometallic chemistry, where differing amounts of training data are available. These tasks include statistical models of stereo- and enantioselectivity, thermochemistry, and kinetics developed using experimental and quantum chemical data. The use of expert-guided molecular descriptors provides an opportunity to incorporate chemical knowledge, domain expertise, and physical constraints into statistical modeling. In applications to stereoselective organic and organometallic catalysis, where data sets may be relatively small and 3D-geometries and conformations play an important role, mechanistically informed features can be used successfully to obtain predictive statistical models that are also chemically interpretable. We provide an overview of several recent applications of this approach to obtain quantitative models for reactivity and selectivity, where topological descriptors, quantum mechanical calculations of electronic and steric properties, along with conformational ensembles, all feature as essential ingredients of the molecular representations used. Alternatively, more flexible, general-purpose molecular representations such as attributed molecular graphs can be used with machine learning approaches to learn the complex relationship between a structure and prediction target. This approach has the potential to out-perform more traditional representation methods such as “hand-crafted” molecular descriptors, particularly as data set sizes grow. One area where this is particularly relevant is in the use of large sets of quantum mechanical data to train quantitative structure–property relationships. A general approach toward curating useful data sets and training highly accurate graph neural network models is discussed in the context of organic bond dissociation enthalpies, where this strategy outperforms regression using precomputed descriptors. Finally, we describe how graph neural network predictions can be incorporated into mechanistically informed statistical models of chemical reactivity and selectivity. Once trained, this approach avoids the expensive computational overhead associated with quantum mechanical calculations, while maintaining chemical interpretability. We illustrate examples for which fast predictions of bond dissociation enthalpy and of the identities of radicals formed through cleavage of a molecule’s weakest bond are used in simple physical models of site-selectivity and reactivity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Vanadium-substituted heteropolyacids immobilized on amine- functionalized mesoporous MCM-41: A recyclable catalyst for selective oxidation of alcohols with H{sub 2}O{sub 2}

Graphical abstract: Vanadium-substituted phosphotungstic acids are immobilized on amine- functionalized mesoporous MCM-41 and the hybrid catalyst is proved to be a highly efficient solid catalyst for the oxidation of aromatic alcohols to the corresponding carbonyl compounds with H{sub 2}O{sub 2}, featured by the high conversion and selectivity, easy recovery, and quite steady reuse. - Highlights: • Vanadium-substituted phosphotungstic acid immobilized on amine-functionalized mesoporous MCM-41 are prepared. • HPAs were fixed on the inner surface of mesoporous MCM-41 by chemical bonding to aminosilane groups. • The hybrid catalyst showed much higher catalytic activity than the pure HPAs. • The hybrid catalyst is a highly efficient recyclable solid catalyst for the selective oxidation of aromatic alcohols. - Abstract: New hybrid materials of vanadium-substituted phosphotungstic acids (VHPW) immobilized on amine-functionalized mesoporous MCM-41 (VHPW/MCM-41/NH{sub 2}) are prepared and characterized by FT-IR, XRD, N{sub 2} adsorption, elemental analysis, SEM and TEM for their structural integrity and physicochemical properties. It is found that the structure of the heteropolyacids is retained upon immobilization over mesoporous materials. The catalytic activities of these hybrid materials are tested in the selective oxidation of alcohols to the carbonyl products with 30% aqueous H{sub 2}O{sub 2} as oxidant in toluene. The catalytic activities of different number of vanadium-substituted phosphotungstic acid are investigated, and among the catalysts, H{sub 5}[PV{sub 2}W{sub 10}O{sub 40}] immobilized on amine-functionalized MCM-41 exhibits the highest activity with 97% conversion and 99% selectivity in the oxidation of benzyl alcohol to benzaldehyde. The hybrid catalyst is proved to be a highly efficient recyclable solid catalyst for the selective oxidation of aromatic alcohols to the corresponding aldehydes with H{sub 2}O{sub 2}.

36 MATERIALS SCIENCE↗

Selective electrified polyethylene upcycling by pore-modulated pyrolysis

Plastic waste is a increasing problem, accumulating in landfills and the environment. Pyrolysis is a promising and industrially relevant approach for transforming plastic waste into value-added chemicals. However, the selectivity and yield of traditional plastic pyrolysis are poor, with products featuring broad molar mass distributions. Here we report a highly selective, energy-efficient and catalyst-free pyrolysis method that can upcycle plastic into value-added chemicals via pore-modulated pyrolysis. Using a Joule-heated carbon column, we demonstrate the pivotal role of the reactor’s graded porous structure in decreasing the polydispersity of the reaction intermediates, enabling high product selectivity and yield. The decreasing pore size of the reactor modulates the mass transport in an apparent gating effect—preventing high-molar-mass species from exiting the reactor before sufficient pyrolysis has occurred. Using polyethylene as a model reactant, we demonstrate a high yield of 65.9 ± 5.2% and up to 80.8% selectivity toward value-added aviation fuel precursor (C8–C18 hydrocarbons) without the use of any catalysts.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Cosmological implications of the CMB large-scale structure

The Wilkinson Microwave Anisotropy Probe (WMAP) and Planck may have uncovered several anomalies in the full cosmic microwave background (CMB) sky that could indicate possible new physics driving the growth of density fluctuations in the early universe. These include an unusually low power at the largest scales and an apparent alignment of the quadrupole and octopole moments. In a ΛCDM model where the CMB is described by a Gaussian Random Field, the quadrupole and octopole moments should be statistically independent. The emergence of these low probability features may simply be due to posterior selections from many such possible effects, whose occurrence would therefore not be as unlikely as one might naively infer. If this is not the case, however, and if these features are not due to effects such as foreground contamination, their combined statistical significance would be equal to the product of their individual significances. In the absence of such extraneous factors, and ignoring the biasing due to posterior selection, the missing large-angle correlations would have a probability as low as ∼0.1% and the low-l multipole alignment would be unlikely at the ∼4.9% level; under the least favorable conditions, their simultaneous observation in the context of the standard model could then be likely at only the ∼0.005% level. In this paper, we explore the possibility that these features are indeed anomalous, and show that the corresponding probability of CMB multipole alignment in the R{sub h}=ct universe would then be ∼7–10%, depending on the number of large-scale Sachs–Wolfe induced fluctuations. Since the low power at the largest spatial scales is reproduced in this cosmology without the need to invoke cosmic variance, the overall likelihood of observing both of these features in the CMB is ⩾7%, much more likely than in ΛCDM, if the anomalies are real. The key physical ingredient responsible for this difference is the existence in the former of a maximum fluctuation size at the time of recombination, which is absent in the latter because of inflation.

79 ASTRONOMY AND ASTROPHYSICS↗

Structure and Reactivity of Single-Site Vanadium Catalysts Supported on Metal–Organic Frameworks

Single-site catalysts with active species anchored over metal–organic framework (MOF) supports have garnered significant interest in recent years. Catalysts with vanadium oxide (VO x ) species immobilized over Zr-NU-1000 and Hf-MOF-808 (which have nodes containing six Zr (IV) or Hf (IV) ions, respectively) were recently characterized experimentally and were reported to be active for the selective oxidation of benzyl alcohol to benzaldehyde. Here, we report a detailed computational investigation of these VO x -incorporated MOF catalysts (V-MOF) by employing density functional theory. Based on the mode of VO x attachment, various structures are explored, and their relative stabilities and computed IR spectral features are reported. Mechanisms for the selective oxidation reaction are investigated. The analysis of electron flow in the turnover-limiting C–H activation step shows that the hydrogen-atom abstraction process involves a concerted proton-coupled electron-transfer mechanism. Here, the results of this study suggest that in addition to the identity of the metal in the node, the MOF node architecture plays a crucial role in driving the catalytic activities of V-MOFs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Machine Learning Models of Plastic Flow Based on Representation Theory

We use machine learning (ML) to infer stress and plastic flow rules using data from representative polycrystalline simulations. In particular, we use so-called deep (multilayer) neural networks (NN) to represent the two response functions. The ML process does not choose appropriate inputs or outputs, rather it is trained on selected inputs and output. Likewise, its discrimination of features is crucially connected to the chosen input-output map. Furthermore, we draw upon classical constitutive modeling to select inputs and enforce well-accepted symmetries and other properties. With these developments, we enable rapid model building in real-time with experiments, and guide data collection and feature discovery.

42 ENGINEERING↗

Deformable, Programmable, and Shape-Memorizing Micro-Optics

The use of shape memory polymers is demonstrated for deformable, programmable, and shape-memorizing micro-optical devices. A semi-crystalline shape memory elastomer, crosslinked poly(ethylene-co-vinyl acetate), is used to prepare various micro-optic components, ranging from microlens and microprism arrays to diffraction gratings and holograms. Here, the precise replication of surface features at the micro- and nanoscale and the formation of crosslinked shape memory polymer networks can be achieved in a single step via compression molding. Further deformation via hot pressing or stretching of micro-optics formed in this manner allows manipulation of the microscopic surface features, and thus the corresponding optical properties. Due to the shape memory effect, the original surface structures and the optical properties can be recovered and the devices be reprogrammed, with excellent reversibility in the optical properties. Furthermore, arrays of transparent resistive microheaters can be integrated with deformed micro-optical devices to selectively trigger the recovery of surface features in a spatially programmable manner, thereby providing additional capabilities in user-definable optics.

36 MATERIALS SCIENCE↗

Earth Observing Scanning Polarimeter (EOSP), phase B

Evaluations performed during a Phase B study directed towards defining an optimal design for the Earth Observing Scanning Polarimeter (EOSP) instrument is summarized. An overview of the experiment approach is included which provides a summary of the scientific objectives, the background of the measurement approach, and the measurement method. In the instrumentation section, details of the design are discussed starting with the key instrument features required to accomplish the scientific objectives and a system characterization in terms of the Stokes vector/Mueller matrix formalism. This is followed by a detailing of the instrument design concept, the design of the individual elements of the system, the predicted performance, and a summary of appropriate instrument testing and calibration. The selected design makes use of key features of predecessor polarimeters and is fully compatible with the Earth Observing System spacecraft requirements.

Source record↗

Accelerating Solvent Selection for Type II Porous Liquids

Type II porous liquids, comprising intrinsically porous molecules dissolved in a liquid solvent, potentially combine the adsorption properties of porous adsorbents with the handling advantages of liquids. Previously, discovery of appropriate solvents to make porous liquids had been limited to direct experimental tests. We demonstrate an efficient screening approach for this task that uses COSMO-RS calculations, predictions of solvent pK a values from a machine-learning model, and several other features and apply this approach to select solvents from a library of more than 11,000 compounds. Additionally, this method is shown to give qualitative agreement with experimental observations for two molecular cages, CC13 and TG-TFB-CHEDA, identifying solvents with higher solubility for these molecules than had previously been known. Ultimately, the algorithm streamlines the downselection of suitable solvents for porous organic cages to enable more rapid discovery of Type II porous liquids.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Performance analysis and comparison of data-driven models for predicting indoor temperature in multi-zone commercial buildings

Building thermal models, which characterize the properties of a building’s envelope and thermal mass, are essential for accurate indoor temperature and cooling/heating demand prediction. Because of their flexibility and ease of use, data-driven models are increasingly used. Here, this study compared and analyzed the performance of gray-box (resistance-capacitance) and black-box (recurrent neural network) models for predicting indoor air temperature in a real multi-zone commercial building. The developed resistance-capacitance model served as a benchmark model for which full sets of temporal data and building information were used as inputs. The recurrent neural network models were trained and tested assuming various available types and amounts of temporal data and known building physical information to investigate the effects of data and information availability. Feature importance analysis was conducted to select the key variables for different prediction targets under different scenarios. This research provides guidance in selecting an appropriate building thermal response modeling method based on the measured data availability, building physical information, and application.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

An Accuracy-Maximization Approach for Claims Classifiers in Document Content Analytics for Cybersecurity

This paper presents our research approach and findings towards maximizing the accuracy of our classifier of feature claims for cybersecurity literature analytics, and introduces the resulting model ClaimsBERT. Its architecture, after extensive evaluations of different approaches, introduces a feature map concatenated with a Bidirectional Encoder Representation from Transformers (BERT) model. We discuss deployment of this new concept and the research insights that resulted in the selection of Convolution Neural Networks for its feature mapping aspects. We also present our results showing ClaimsBERT to outperform all other evaluated approaches. This new claims classifier represents an essential processing stage within our vetting framework aiming to improve the cybersecurity of industrial control systems (ICS). Furthermore, in order to maximize the accuracy of our new ClaimsBERT classifier, we propose an approach for optimal architecture selection and determination of optimized hyperparameters, in particular the best learning rate, number of convolutions, filter sizes, activation function, the number of dense layers, as well as the number of neurons and the drop-out rate for each layer. Fine-tuning these hyperparameters within our model led to an increase in classification accuracy from 76% obtained with BertForSequenceClassification’s original model to a 97% accuracy obtained with ClaimsBERT.

Ameri, Kimia (ORCID:0000000328791871)↗

A Photographic Atlas of Rock Breakdown Features in Geomorphic Environments

A primary goal of geomorphological enquiry is to make genetic associations between process and form. In rock breakdown studies, the links between process, inheritance and lithology are not well constrained. In particular, there is a need to establish an understanding of feature persistence. That is, to determine the extent to which in situ rock breakdown (e.g., aeolian abrasion or salt weathering) masks signatures of earlier geomorphic transport processes (e.g., fluvial transport or crater ejecta). Equally important is the extent to which breakdown during geomorphic transport masks the imprint of past weathering. The use of rock features in this way raises the important question: Can features on the surface of a rock reliably indicate its geomorphic history? This has not been determined for rock surfaces on Earth or other planets. A first step towards constraining the links between process, inheritance, and morphology is to identify pristine features produced by different process regimes. The purpose of this atlas is to provide a comprehensive image collection of breakdown features commonly observed on boulders in different geomorphic environments. The atlas is intended as a tool for planetary geoscientists and their students to assist in identifying features found on rocks on planetary surfaces. In compiling this atlas, we have attempted to include features that have formed 'recently' and where the potential for modification by another geomorphic process is low. However, we acknowledge that this is, in fact, difficult to achieve when selecting rocks in their natural environment. We group breakdown features according to their formative environment and process. In selecting images for inclusion in the atlas we were mindful to cover a wide range of climatic zones. For example, in the weathering chapter, clast features are shown from locations such as the hyper-arid polar desert of Antarctica and the semi-arid canyons of central Australia. This is important as some features (e.g., alveoli) occur across climate regimes. We have drawn on the published geomorphological literature and our own field experience. We use, where possible, images of extrusive igneous rocks as the data returned from Mars, Venus and the Moon indicates that this is the predominant rock type. One of the purposes of this atlas is to expand the range of surface features that are known to indicate a particular geomorphic environment or process history. The surface features on boulders in some environments such as aeolian and weathering are well understood. In contrast, those in fluvial or ejecta environments are not. Therefore we have presented a comprehensive assemblage of features that are likely to be produced in each of the geomorphic environments. We hope that this atlas will trigger more research on diagnostic features, particularly their morphometry and detailed morphology, their persistence and rates of formation. In this first edition of the atlas we detail the features found on clasts in three geomorphic environments: aeolian, fluvial and weathering. Future editions of the atlas will include chapters on ejecta, micro-impacts, coastal, colluvial, glacial and structural features.

Bourke, Mary C.↗

ON THE NATURE OF THE FIRST GALAXIES SELECTED AT 350 mum

We present constraints on the nature of the first galaxies selected at 350 mum. The sample includes galaxies discovered in the deepest blank-field survey at 350 mum (in the Booetes Deep Field) and also later serendipitous detections in the Lockman Hole. In determining multiwavelength identifications, the 350 mum position and map resolution of the second generation Submillimeter High Angular Resolution Camera are critical, especially in the cases where multiple radio sources exist and the 24 mum counterparts are unresolved. Spectral energy distribution templates are fitted to identified counterparts, and the sample is found to comprise IR-luminous galaxies at 1 < z < 3 predominantly powered by star formation. The first spectrum of a 350 mum selected galaxy provides an additional confirmation, showing prominent dust grain features typically associated with star-forming galaxies. Compared to submillimeter galaxies selected at 850 and 1100 mum, galaxies selected at 350 mum have a similar range of far-infrared color temperatures. However, no 350 mum selected sources are reliably detected at 850 or 1100 mum. Galaxies in our sample with redshifts 1 < z < 2 show a tight correlation between the far- and mid-infrared flux densities, but galaxies at higher redshifts show a large dispersion in their mid- to far-infrared colors. This implies a limit to which the mid-IR emission traces the far-IR emission in star-forming galaxies. The 350 mum flux densities (15 < S{sub 350} < 40 mJy) place these objects near the Herschel/SPIRE 350 mum confusion threshold, with the lower limit on the star formation rate density suggesting the bulk of the 350 mum contribution will come from less luminous infrared sources and normal galaxies. Therefore, the nature of the dominant source of the 350 mum background-star-forming galaxies in the epoch of peak star formation in the universe-could be more effectively probed using ground-based instruments with their angular resolution and sensitivity offering significant advantages over space-based imaging.

79 ASTRONOMY AND ASTROPHYSICS↗