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 505 records · Page 28

Design, development and analysis of large-area industrial silicon solar cells featuring a full area polysilicon based passivating contact on the rear and selective passivating contacts on the front

We present SERIS’ biPoly™ technology platform on large-area (M2), n-type rear-junction silicon solar cells featuring selective poly-Si/SiOx based passivated contacts on the front side and full-area poly-Si/SiOx contacts on the rear. The selective poly-Si ‘fingers’ are formed using an industrial ink-jet masking process followed by wet-chemical etching. The metal contacts are formed by an industrial screen-printing process using high-temperature fire-though metal pastes. We obtain excellent passivation on the front and rear surfaces, resulting in iVoc values between 720 mV and 730 mV on unmetallized solar cells. After high-temperature metallization, we achieve 22% efficiency on solar cells with selective poly-Si fingers on the front. We further develop the model for biPoly™ solar cells and with the help of a detailed loss analysis and simulations, identify the various loss components to identify the device modifications required for efficiency improvements.

36 MATERIALS SCIENCE↗

Turbine component, turbine blade, and turbine component fabrication process

A turbine component, a turbine blade, and a turbine component fabrication process are disclosed. The turbine component includes ceramic matrix composite plies and a feature configured for preventing interlaminar tension of the ceramic matrix composite plies. The feature is selected from the group consisting of ceramic matrix composite tows or precast insert tows extending through at least a portion of the ceramic matrix composite plies, a woven fabric having fiber tows or a precast insert preventing contact between a first set of the ceramic matrix composite plies and a second set of the ceramic matrix composite plies, and combinations thereof. The process includes laying up ceramic matrix composite plies in a preselected arrangement and securing a feature configured for interlaminar tension.

42 ENGINEERING↗

Uncertainty Quantification of Machine Learning Predicted Creep Property of Alumina-Forming Austenitic Alloys

The development of machine learning (ML) approaches in materials science offers the opportunity to exploit existing engineering and developmental alloy datasets, such as Oak Ridge National Laboratory (ORNL)’s consistently measured creep-rupture dataset for alumina-forming austenitic (AFA) alloys, to accelerate their further development. As a first step toward achieving ML insights for improved alloy design, the potential sources of uncertainty and their impacts on ML output are examined. It is observed that the selection of algorithms and features as well as data sampling significantly affects the performance of ML models, either positively or negatively. Further, the performance of various ML models in predicting the creep properties of AFA alloys is compared, with further evaluation by assessment of a small set of new developmental AFA alloys that were not part of the training dataset. The present study demonstrates that uncertainty quantification (UQ) is essential in materials science for evaluating the performance of ML algorithms with specifically selected feature sets and obtaining a comprehensive understanding of their limitations and the resultant capability of effective prediction in complex materials systems.

36 MATERIALS SCIENCE↗

Effects of system size and cooling rate on the structure and properties of sodium borosilicate glasses from molecular dynamics simulations

We present that borosilicate glasses form an important glass forming system in both glass science and technologies. The structure and property changes of borosilicate glasses as a function of thermal history in terms of cooling rate during glass formation and simulation system sizes used in classical molecular dynamics (MD) simulation were investigated with recently developed composition dependent partial charge potentials. Short and medium range structural features such as boron coordination, Si and B Qn distributions, and ring size distributions were analyzed to elucidate the effects of cooling rate and simulation system size on these structure features and selected glass properties such as glass transition temperature, vibration density of states, and mechanical properties. Neutron structure factors, neutron broadened pair distribution functions, and vibrational density of states were calculated and compared with results from experiments as well as ab initio calculations to validate the structure models. The results clearly indicate that both cooling rate and system size play an important role on the structures of these glasses, mainly by affecting the 3B and 4B distributions and consequently properties of the glasses. It was also found that different structure features and properties converge at different sizes or cooling rates; thus convergence tests are needed in simulations of the borosilicate glasses depending on the targeted properties. Lastly, the results shed light on the complex thermal history dependence on structure and properties in borosilicate glasses and the protocols in MD simulations of these and other glass materials.

36 MATERIALS SCIENCE↗

Laser-induced selective local patterning of vanadium oxide phases

The same elements can form different compounds with widely different physical properties. Synthesis of a single-phase material is commonly achieved by controlling experimental conditions. Synthesizing materials that incorporate multiple specific spatially distributed chemical phases is often challenging, especially if different phases must be organized into well-defined spatial patterns. Here, we present an efficient solid reaction laser annealing (SRLA) approach to directly write regions of different local chemical compositions. We demonstrate the practical utility of our approach by locally writing microscale patterns of distinct chemical phases in vanadium oxide thin films. Specifically, we achieved the controlled local recrystallization of a uniform V 2 O 3 matrix into VO 2 , V 3 O 5 , and V 4 O 7 regions exhibiting sharp 1st- and 2nd-order metal–insulator phase transitions over a wide range of critical temperatures, i.e., a characteristic feature of select vanadium oxides that is extremely sensitive to even minute structural or compositional imperfections. We utilized the local chemical phase writing to pattern spiking oscillators with distinct electrical behavior directly in the thin film sample without employing elaborate lithography fabrication. Our laser tuning local chemical composition opens a pathway to synthesize a wide range of artificially micropatterned composite materials, with precision and control unattainable in conventional material synthesis methods.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Parsimonious Potential Energy Surface Expansions Using Dictionary Learning with Multipass Greedy Selection

Potential energy surfaces fit with basis set expansions have been shown to provide accurate representations of electronic energies and have enabled a variety of high-accuracy dynamics, kinetics, and spectroscopy applications. The number of terms in these expansions scales poorly with system size, a drawback that challenges their use for systems with more than similar to 10 atoms. A solution is presented here using dictionary learning. Subsets of the full set of conventional basis functions are optimized using a newly developed multipass greedy regression method inspired by forward and backward selection methods from the statistics, signal processing, and machine learning literatures. Here, the optimized representations have accuracies comparable to the full set but are 1 or more orders of magnitude smaller, and notably, the number of terms in the optimized multipass greedy expansions scales approximately linearly with the number of atoms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Fast Solution in Sparse LDA for Binary Classification

An algorithm that performs sparse linear discriminant analysis (Sparse-LDA) finds near-optimal solutions in far less time than the prior art when specialized to binary classification (of 2 classes). Sparse-LDA is a type of feature- or variable- selection problem with numerous applications in statistics, machine learning, computer vision, computational finance, operations research, and bio-informatics. Because of its combinatorial nature, feature- or variable-selection problems are NP-hard or computationally intractable in cases involving more than 30 variables or features. Therefore, one typically seeks approximate solutions by means of greedy search algorithms. The prior Sparse-LDA algorithm was a greedy algorithm that considered the best variable or feature to add/ delete to/ from its subsets in order to maximally discriminate between multiple classes of data. The present algorithm is designed for the special but prevalent case of 2-class or binary classification (e.g. 1 vs. 0, functioning vs. malfunctioning, or change versus no change). The present algorithm provides near-optimal solutions on large real-world datasets having hundreds or even thousands of variables or features (e.g. selecting the fewest wavelength bands in a hyperspectral sensor to do terrain classification) and does so in typical computation times of minutes as compared to days or weeks as taken by the prior art. Sparse LDA requires solving generalized eigenvalue problems for a large number of variable subsets (represented by the submatrices of the input within-class and between-class covariance matrices). In the general (fullrank) case, the amount of computation scales at least cubically with the number of variables and thus the size of the problems that can be solved is limited accordingly. However, in binary classification, the principal eigenvalues can be found using a special analytic formula, without resorting to costly iterative techniques. The present algorithm exploits this analytic form along with the inherent sequential nature of greedy search itself. Together this enables the use of highly-efficient partitioned-matrix-inverse techniques that result in large speedups of computation in both the forward-selection and backward-elimination stages of greedy algorithms in general.

Moghaddam, Baback↗

SU-E-J-242: Volume-Dependence of Quantitative Imaging Features From CT and CE-CT Images of NSCLC

Purpose: To determine whether tumor volume plays a significant role in the values obtained for texture features when they are extracted from computed tomography (CT) images of non-small cell lung cancer (NSCLC). We also sought to identify whether features can be reliably measured at all volumes or if a minimum volume threshold should be recommended. Methods: Eleven features were measured on 40 CT and 32 contrast-enhanced CT (CECT) patient images for this study. Features were selected for their prognostic/diagnostic value in previous publications. Direct correlations between these textures and volume were evaluated using the Spearman correlation coefficient. Any texture that the Wilcoxon rank-sum test was used to compare the variation above and below a volume cutoff. Four different volume thresholds (5, 10, 15, and 20 cm{sup 3}) were tested. Results: Four textures were found to be significantly correlated with volume in both the CT and CE-CT images. These were busyness, coarseness, gray-level nonuniformity, and run-length nonuniformity with correlation coefficients of 0.92, −0.96, 0.94, and 0.98 for the CT images and 0.95, −0.97, 0.98, and 0.98 for the CE-CT images. After volume normalization, the correlation coefficients decreased substantially. For the data obtained from the CT images, the results of the Wilcoxon rank-sum test were significant when volume thresholds of 5–15 cm3 were used. No volume threshold was shown to be significant for the CE-CT data. Conclusion: Equations for four features that have been used in several published studies were found to be volume-dependent. Future studies should consider implementing normalization factors or removing these features entirely to prevent this potential source of redundancy or bias. This work was supported in part by National Cancer Institute grant R03CA178495-01. Xenia Fave is a recipient of the American Association of Physicists in Medicine Graduate Fellowship.

60 APPLIED LIFE SCIENCES↗

Influence of particle size on NIR spectroscopic characterization of sorghum biomass for the biofuel industry

NIR spectroscopy is a rapid and accurate green technology for high-throughput biomass characterization, including sorghum (Sorghum bicolor), a promising energy crop for the biofuel industry. This study assessed the influence of particle size on NIR spectroscopic analysis (wavelength range: 867–2535 nm) of sorghum biomass composition. Grown under field conditions, a total of 113 types of genetically diverse sorghum accessions were dried, ground, and sieved (<250, 250–600, 600–850, and > 850 µm particle size) for developing partial least square regression (PLSR) prediction models for moisture, ash, extractive, glucan, xylan, acid-soluble lignin (ASL), acid-insoluble lignin (AIL), and total lignin (ASL + AIL). Overall, smaller particle sizes provided better model performance, while no single particle size provided the best performance for all the selected components. With only 9 selected bands and 4 latent variables (LVs), the best PLSR model was obtained for moisture with particle size of 600–850 µm with the square root of the coefficient of determination (R) of 0.85, the ratio of prediction to deviation (RPD) of 2.2, and the root mean square error (RMSE) of 0.46 % in external validation. Similar model performances were also obtained for ash, extractive, glucan, and xylan. This study showed that size reduction could effectively improve NIR spectroscopic analysis for lipid-producing sorghum biomass for the biofuel industry.

09 BIOMASS FUELS↗

Data-Centric Development of Lignin Structure–Solubility Relationships in Deep Eutectic Solvents Using Molecular Simulations

Lignin is a natural source of aromatic chemicals with significant potential as an abundant, renewable feedstock for value-added products. Deep eutectic solvents (DES)–solvents composed of a hydrogen bond donor (HBD) and acceptor (HBA) in varying ratios–have emerged as a highly tunable class of solvents for lignin solubilization. However, the variety of possible DES compositions and limited molecular-scale understanding of lignin solubility makes solvent selection a challenge without laborious trial-and-error experimentation. To address these challenges, we use classical molecular dynamics (MD) simulations to study the interactions of lignin model compounds with various DES–water systems. Quantitative parameters (descriptors) were calculated by postprocessing the MD results and used to train a regression model that predicts experimentally determined solubilities of lignin model compounds. This approach revealed that the most important descriptors of solubility are the system temperature, solute hydrophilicity, and metrics quantifying hydrogen bonding. Maximizing the interactions between solute–HBD (hydrophobic group), water–HBD (hydrophilic group), and water–HBA molecules led to the highest model compound solubility. Our results support a hydrotropic mechanism in which extensive DES–water hydrogen bonding and favorable HBD interactions with the solute promote high solubility. We applied the regression model derived using model compounds to predict the solubility of representative lignin oligomers. The model predicted lignin oligomers’ solubilities in good agreement with experiments, indicating that the simulations of model compounds can be extended to predict the solubility of larger lignin compounds across a range of solvent compositions and temperatures. Furthermore, these findings provide new molecular-scale insight into lignin solubilization mechanisms and a new method for computationally screening potential solvent systems for lignin valorization.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Manipulating the Assembly and Architecture of Fibrillar Silk

Silk is a unique and exceptionally strong biological material. However, no synthetic method has yet come close to replicating the properties of natural silk. This shortfall is attributed to an insufficient understanding of both silk nanofibril structure and the mechanism of formation. Here in situ atomic force microscopy (AFM) and photo-induced force microscopy (PiFM) is utilized to investigate the formation process and define the basic structural paradigm of individual silk nanofibrils. By visualizing the multistage process of silk nanofibril formation, the importance of conformational transformations along the assembly pathway is revealed. Unfolded silk structures initially accumulate into amorphous clusters, which then evolve into crystal nuclei via conformational transformation into β-crystallites. Nanofibril elongation then occurs through the attachment of silk molecules at a single end of the nanofibril tip; this is facilitated through the formation of a new amorphous cluster that then repeats the aforementioned conformational transformation. However, enzymatic digestion of the amorphous regions leads to direct, rapid elongation of β-crystalline fibers. These findings imply that the energy landscape is characterized by shallow minima associated with intermediate states, which can be eliminated by introducing β-crystallites, and motivate research into the directed modification of the silk assembly pathway to select for features beneficial to specific applications.

36 MATERIALS SCIENCE↗

Three-dimensional dendritic needle network model for alloy solidification

Here, we present a three-dimensional (3D) formulation of the multiscale Dendritic Needle Network (DNN) model for dendritic microstructure growth. This approach is aimed at simulating quantitatively the solidification dynamics of complex hierarchical networks in spatially extended dendritic arrays, hence bridging the scale gap between phase-field simulations at the scale of a few dendrites and coarse-grained simulations on the larger scale of entire polycrystalline structures. In the DNN model, the dendritic network is represented by a network of branches that interact through the solutal diffusion field. The tip velocity V(t) and tip radius ρ(t) of each needle is determined by combining a standard solvability condition that fixes the product ρ 2 V and a solute flux conservation condition that fixes the product ρV 2 in 2D and ρV in 3D as a function of a solutal flux intensity factor ℱ(t). The latter measures the intensity of the solute flux in the dendrite tip region and can be calculated by contour (2D) or surface (3D) integration around the tip of each needle. We first present an extended formulation of the 2D DNN model where needles have a finite thickness and parabolic tips. This formulation remains valid for a larger range of tip Péclet number than the original thin needle formulation and is readily extended to 3D needles with paraboloidal tips. The 3D DNN model based on this thick-needle formulation is developed for both isothermal and directional solidification. Model predictions are validated by comparisons with known analytical solutions that describe the early transient and steady-state growth regimes. We exploit the power of the DNN model to characterize the competitive growth of well-developed secondary branches in 3D on the scale of the diffusion length. The results show that the length of active secondary branches increases as a power law of distance behind the tip with an exponent in good quantitative agreement with experimental measurements. Finally, we apply the model to simulate the three-dimensional directional solidification of an Al-7wt% Si alloy, which we directly compare to observed microstructures from microgravity experiments onboard the International Space Station. The predictions of selected microstructural features, such as dendrite arm spacings, show a good agreement with experiments. The computationally-efficient DNN model opens new avenues for investigating the dynamics of large dendritic arrays at length and time scales relevant to solidification experiments and processes.

36 MATERIALS SCIENCE↗

Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering

Fusing various sensing data sources can significantly improve the accuracy and reliability of building occupancy detection. Fusing environmental sensors and wireless network signals are seldom studied for its computational and technical complexity. Here, this study aims to propose an integrated adaptive lasso model that is able to extract critical data features for environmental and Wi-Fi probe dual sensing sources. Through rapid feature extraction and process simplification, the proposed method aims to improve the computational efficiency of occupancy detecting models. To validate the proposed model, an onsite experiment was conducted to examine two occupancy data resolutions, (real-time and four-level occupancy resolutions). The results suggested that, among all twelve features, eight features are most relevant. The mean absolute error of the real-time occupancy can be reduced to 2.18 and F1_accuracy is about 84.36% for the four-level occupancy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Insight into ideal shear strength of Ni-based dilute alloys using first-principles calculations and correlational analysis

Here the present work examines the effect of alloying elements (denoted X) on the ideal shear strength for 26 dilute Ni-based alloys, Ni11X, as determined by first-principles calculations of pure alias shear deformations. The variations in ideal shear strength are quantitatively explored with correlational analysis techniques, showing the importance of atomic properties such as size and electronegativity. The shear moduli of the alloys are affirmed to show a strong linear relationship with their ideal shear strengths, while the shear moduli of the individual alloying elements were not indicative of alloy shear strength. Through combination with available ideal shear strength data on Mg alloys, a potential application of the Ni alloy data is demonstrated in the search for a set of atomic features suitable for machine learning applications to mechanical properties. As another illustration, the calculated Ni ideal shear strengths play a key role in a predictive multiscale framework for deformation behavior of single crystal alloys at large strains, as shown by simulated stress–strain curves.

36 MATERIALS SCIENCE↗

Multimodal sensor fusion framework for residential building occupancy detection

For several years now, smart building energy systems have been a research area of intensive activity. In light of the increasing need for sustainable buildings and energy systems, this trend motivates an increasing need for a solution to reduce carbon dioxide emissions and improve energy efficiency. This work proposes a high-performing and transferable occupancy detection framework that combines sensor data from different data modalities, including time series environmental data (temperature, humidity, and illuminance), image data, and acoustic energy data using ensemble method. To draw out the best prediction performance in each modality, the proposed framework was developed, including various models that were designed to learn the occupancy patterns reflected in the physical data streams. To tackle the time series environmental data, we designed two variants of an occupancy detection spatiotemporal pattern network (Occ-STPN) that performs both feature level and decision level fusion, respectively. We also propose a new metric; the fading memory mean square error (FMMSE), that provides a fair evaluation and penalization of delayed occupancy predictions. Multiple open-sourced datasets, including the Electricity Consumption and Occupancy and the University of California, Irvine's (UCI) building occupancy detection dataset, along with our own real data collected from six different houses, were used to validate the algorithms' performance. The experimental results presented herein break down the performance for each sensing modality, and a detailed analysis of the performance is also discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Filament-induced breakdown spectroscopy signal enhancement using optical wavefront control

Filament-induced breakdown spectroscopy (FIBS) is an analytical method that holds significant promise for remote sensing. In FIBS, it is desirable to maximize the intensity and improve the reproducibility of a selected spectroscopic feature. Here, we demonstrate the use of wavefront control in conjunction with a genetic algorithm in FIBS of metallic copper and show that this approach can increase the efficacy of filament-induced breakdown signal production. Through wavefront optimization, we enhance the intensity of a chosen characteristic spectroscopic feature of copper by a factor of approximately 3 when performing filamentation over a 1-meter distance. The relative standard deviation of signal intensity is reduced from ~17% to ~12% after optimization. We find that modification of the wavefront by introduction of astigmatism and coma maximizes the signal intensity, and these aberrations appear in two distinct trials of the genetic algorithm. We compare these findings to previous work on multiple filament control and discuss the possible mechanisms that lead to signal enhancement associated with both the beam amplitude and phase profile. A broader use of wavefront control with feedback may improve the performance of FIBS in remote sensing applications.

42 ENGINEERING↗

Comparing Sensor Fusion and Multimodal Chemometric Models for Monitoring U(VI) in Complex Environments Representative of Irradiated Nuclear Fuel

Optical sensors and chemometric models were leveraged for the quantification of uranium(VI) (0–100 μg mL –1 ), europium (0–150 μg mL –1 ), samarium (0–250 μg mL –1 ), praseodymium (0–350 μg mL –1 ), neodymium (0–1000 μg mL –1 ), and HNO 3 (2–4 M) with varying corrosion product (iron, nickel, and chromium) levels using laser fluorescence, Raman scattering, and ultraviolet–visible–near-infrared absorption spectra. In this paper, an efficient approach to developing and evaluating tens of thousands of partial least-squares regression (PLSR) models, built from fused optical spectra or multimodal acquisitions, is discussed. Each PLSR model was optimized with unique preprocessing combinations, and features were selected using genetic algorithm filters. The 7-factor D-optimal design training set contained just 55 samples to minimize the number of samples. The performance of PLSR models was evaluated by using an automated latent variable selection script. PLS1 regression models tailored to each species outperformed a global PLS2 model. PLS1 models built using fused spectra data and a multimodal (i.e., analyzed separately) approach yielded similar information, resulting in percent root-mean-square error of prediction values of 0.9–5.7% for the seven factors. Further, the optical techniques and data processing strategies established in this study allow for the direct analysis of numerous species without measuring luminescence lifetimes or relying on a standard addition approach, making it optimal for near-real-time, in situ measurements. Nuclear reactor modeling helped bound training set conditions and identified elemental ratios of lanthanide fission products to characterize the burnup of irradiated nuclear fuel. Leveraging fluorescence, spectrophotometry, experimental design, and chemometrics can enable the remote quantification and characterization of complex systems with numerous species, monitor system performance, help identify the source of materials, and enable rapid high-throughput experiments in a variety of industrial processes and fundamental studies.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗