Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature importance”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Ranking Biological Features in Soil-Based Microbial Multi-Omics Data with Integration Modeling

Distinguishing the most important features (e.g. proteins, metabolites, etc.) per group (e.g. control and treatment) is a critical challenge in feature-rich multi-omics experiments, especially in soil data. Traditional feature identification and ranking approaches, such as differential expression, are based on single omics and thus not directly translatable to multi-omics experiments. Here, 5 multi-omics integration models (DIABLO, JACA, MOFA, MultiMLP, and SLIDE) that were not explicitly built for soil data applications were tested using a soil-based multi-omics experiment. The data were obtained from an experimental setup of an autoclaved soil system inoculated with 8 bacteria and using chitin as the carbon source and including samples collected at 0- (control), 4-, 8-, and 12-weeks post-inoculation. The omics data included metaproteomics, 16S rRNA sequencing, and LC-MS/MS metabolomics (in positive and negative mode). Each multi-omics integration model was implemented, and top features were compared to differential univariate statistics per omic type, demonstrating that integration approaches cut the potential number of top features from 2957 identified by differential statistics to 13-224 (a 99.6% to 92.4% reduction). Interestingly, most top features across integration models were not shared; though, scaling and averaging ranks across models shared similar patterns. This work highlights the usefulness of multi-omics integration models in soil-based microbial studies and the power of using multiple integration models together to interpret results.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1991

Helicity-Density And Normalized-Helicity Maps Of Flows

Maps of helicity density and normalized helicity useful as graphical representations of important features of three-dimensional flow fields containg vortexes. Emphasize complicated and important parts of flow field, identify vortexes, differentiate between primary and secondary vortexes, indicate sense of swirling motion, locate free singular points, and trace vortex-core streamlines emanating from these points.

Degani, David↗
NASA NTRS2000

Past, Present, and Future Capabilities of the Transonic Dynamics Tunnel from an Aeroelasticity Perspective

The NASA Langley Transonic Dynamics Tunnel (TDT) has provided a unique capability for aeroelastic testing for forty years. The facility has a rich history of significant contributions to the design of many United States commercial transports, military aircraft, launch vehicles, and spacecraft. The facility has many features that contribute to its uniqueness for aeroelasticity testing, perhaps the most important feature being the use of a heavy gas test medium to achieve higher test densities. Higher test medium densities substantially improve model-building requirements and therefore simplify the fabrication process for building aeroelastically scaled wind tunnel models. Aeroelastic scaling for the heavy gas results in lower model structural frequencies. Lower model frequencies tend to a make aeroelastic testing safer. This paper will describe major developments in the testing capabilities at the TDT throughout its history, the current status of the facility, and planned additions and improvements to its capabilities in the near future.

Cole, Stanley R.↗
NASA NTRS2003

Test Activities in the Langley Transonic Dynamics Tunnel and a Summary of Recent Facility Improvements

The Langley Transonic Dynamics Tunnel (TDT) has provided a unique capability for aeroelastic testing for over forty years. The facility has a rich history of significant contributions to the design of many United States commercial transports, military aircraft, launch vehicles, and spacecraft. The facility has many features that contribute to its uniqueness for aeroelasticity testing, perhaps the most important feature being the use of a heavy gas test medium to achieve higher test densities compared to testing in air. Higher test medium densities substantially improve model-building requirements and therefore simplify the fabrication process for building aeroelastically scaled wind tunnel models. This paper describes TDT capabilities that make it particularly suited for aeroelasticity testing. The paper also discusses the nature of recent test activities in the TDT, including summaries of several specific tests. Finally, the paper documents recent facility improvement projects and the continuous statistical quality assessment effort for the TDT.

Cole, Stanley R.↗
NASA NTRS1976

Characteristics of Antarctic sea ice as determined by satellite-borne microwave imagers

The electrically scanning microwave radiometers on Nimbus 5 (wavelengths of 1.55 cm) and Nimbus 6 (wavelengths of 0.81 cm) produce images with a resolution of about 30 km. Weekly maps of sea ice coverage are generated, showing the percent of open water in each 2.5 x 2.5 degree cell. More detailed studies of the dynamics and thermodynamics of the sea ice and its interaction with the ocean and the atmosphere are carried out, using 3-day average pseudo-color images and maps of ice boundaries. Features of the Antarctic ice discerned from microwave images are discussed, and the important features of Antarctic currents are illustrated.

Zwally, H. J.↗
DOE OSTI2025

Seismicity-constrained fault detection and characterization with a multitask machine learning model

Geological fault detection and characterization are crucial for understanding subsurface dynamics across scales. While methods for fault delineation based on either seismicity location analysis or seismic image reflector discontinuity are well-established, a systematic approach that integrates both data types remains absent. We develop a novel machine learning model that unifies seismic reflector images and seismicity location information to automatically identify geological faults and characterize their geometrical properties. The model encodes a seismic image and a seismicity location image separately, and fuses the encoded features with a spatial-channel attention fusion module to improve the learning of important features in both inputs. We design an automated strategy to generate high-quality synthetic training data and labels. To improve the realism of the seismicity location image, we include random seismicity noise and missing seismicity location associated with some of the faults. We validate the model’s efficacy and accuracy using synthetic data examples and two field data examples. Moreover, we show that fine-tuning the trained model with a small, domain-specific dataset enhances its fidelity for field data applications. The results demonstrate that integrating seismicity location and seismic images into a unified framework allows the end-to-end neural network to achieve higher fidelity and accuracy in delineating subsurface faults and their geometrical properties compared with image-only fault detection methods. Our approach offers an adaptive data-driven tool for geological fault characterization and seismic hazard mitigation, bridging the gap between seismicity location and image-based fault detection methods.

58 GEOSCIENCES↗
DOE OSTI2022

Impact of Ion–Ion Correlated Motion on Salt Transport in Solvated Ion Exchange Membranes

The influence of dynamical ion-ion correlations and ion pairing on salt transport in ion exchange membranes remain poorly understood. In this study, we use the framework of Onsager transport coefficients within atomistic molecular dynamics sim- ulations to study the impact of ion-ion correlated motion on salt transport in hydrated polystyrene sulfonate membranes and compare with the results from aqueous salt so- lutions. At sufficiently high salt concentrations, cation-anion dynamical correlations exert a significant influence on both salt diffusivities and conductivities. Anion-anion distinct correlations, arising from the imbalance between the concentration of free (mo- bile) cations and anions, and the retarding effect of the fixed charge groups on cations, proves to be an additional important feature for polymer membranes. Furthermore, our results demonstrate that dynamical correlations should become an important consideration in experimental measurements of salt diffusivities and conductivities for non-dilute salt solutions in polymer membranes.

36 MATERIALS SCIENCE↗
NASA NTRS1992

Venus tectonic styles and crustal differentiation

Two of the most important constraints are known from Pioneer Venus data: the lack of a system of spreading rises, indicating distributed deformation rather than plate tectonics; and the high gravity/topography ratio, indicating the absence of an asthenosphere. In addition, the high depth/diameter ratios of craters on Venus indicate that Venus probably has no more crust than Earth. The problems of the character of tectonics and crustal formation and recycling are closely coupled. Venus appears to lack a recycling mechanism as effective as subduction, but may also have a low rate of crustal differentiation because of a mantle convection pattern that is more distributed, less concentrated, than Earth's. Distributed convection, coupled with the nonlinear dependence of volcanism on heat flow, would lead to much less magmatism, despite only moderately less heat flow, compared to Earth. The plausible reason for this difference in convective style is the absence of water in the upper mantle of Venus. We have applied finite element modeling to problems of the interaction of mantle convection and crust on Venus. The main emphasis has been on the tectonic evolution of Ishtar Terra, as the consequence of convergent mantle flow. The early stage evolution is primarily mechanical, with crust being piled up on the down-stream side. Then the downflow migrates away from the center. In the later stages, after more than 100 m.y., thermal effects develop due to the insulating influence of the thickened crust. An important feature of this modeling is the entrainment of some crustal material in downflows. An important general theme in both convergent and divergent flows is that of mixing vs. stratification. Models of multicomponent solid-state flow obtain that lower-density crustal material can be entrained and recycled, provided that the ration of low-density to high-density material is small enough (as in subducted slabs on Earth). The same considerations should apply in upflows; a small percent of partial melt may be carried along with its matrix and never escape to the surface. Models that assume melt automatically rising to the crust and no entrainment or other mechanism of recycling lower-density material obtain oscillatory behavior, because it takes a long time for heat to build up enough to overcome a Mg-rich low-density residuum. However, these models develop much thicker crust than consistent with estimates from crater depth/diameter ratios.

Kaula, W. M.↗
NASA NTRS1977

A study of key features of random atmospheric disturbance models for the approach flight phase

An analysis and brief simulator experiment were performed to identify and classify important features of random turbulence for the landing approach flight phase. The analysis of various wind models was carried out within the context of the longitudinal closed-loop pilot/vehicle system. The analysis demonstrated the relative importance of atmospheric disturbance scale lengths, horizontal versus vertical gust components, decreasing altitude, and spectral forms of disturbances versus the pilot/vehicle system. Among certain competing wind models, the analysis predicted no significant difference in pilot performance. This was confirmed by a moving base simulator experiment which evaluated the two most extreme models. A number of conclusions were reached: attitude constrained equations do provide a simple but effective approach to describing the closed-loop pilot/vehicle. At low altitudes the horizontal gust component dominates pilot/vehicle performance.

Heffley, R. K.↗
NASA NTRS1993

An overview on development of neural network technology

The study has been to obtain a bird's-eye view of the current neural network technology and the neural network research activities in NASA. The purpose was two fold. One was to provide a reference document for NASA researchers who want to apply neural network techniques to solve their problems. Another one was to report out survey results regarding NASA research activities and provide a view on what NASA is doing, what potential difficulty exists and what NASA can/should do. In a ten week study period, we interviewed ten neural network researchers in the Langley Research Center and sent out 36 survey forms to researchers at the Johnson Space Center, Lewis Research Center, Ames Research Center and Jet Propulsion Laboratory. We also sent out 60 similar forms to educators and corporation researchers to collect general opinions regarding this field. Twenty-eight survey forms, 11 from NASA researchers and 17 from outside, were returned. Survey results were reported in our final report. In the final report, we first provided an overview on the neural network technology. We reviewed ten neural network structures, discussed the applications in five major areas, and compared the analog, digital and hybrid electronic implementation of neural networks. In the second part, we summarized known NASA neural network research studies and reported the results of the questionnaire survey. Survey results show that most studies are still in the development and feasibility study stage. We compared the techniques, application areas, researchers' opinions on this technology, and many aspects between NASA and non-NASA groups. We also summarized their opinions on difficulties encountered. Applications are considered the top research priority by most researchers. Hardware development and learning algorithm improvement are the next. The lack of financial and management support is among the difficulties in research study. All researchers agree that the use of neural networks could result in cost saving. Fault tolerance has been claimed as one important feature of neural computing. However, the survey indicates that very few studies address this issue. Fault tolerance is important in space mission and aircraft control. We believe that it is worthy for NASA to devote more efforts into the utilization of this feature.

Lin, Chun-Shin↗
DOE OSTI2021

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

Abstract The class of 9–12% Cr ferritic-martensitic alloys (FMA) and austenitic stainless steels have received considerable attention due to their numerous applications in high temperature power generation industries. To design high strength steels with prolonged service life requires a thorough understanding of the long-term properties, e.g., creep rupture strength, rupture life, etc., as a function of the chemical composition and processing parameters that govern the microstructural characteristics. In this article, the creep rupture strength of both 9–12% Cr FMA and austenitic stainless steel has been parameterized using curated experimental datasets with a gradient boosting machine. The trained model has been cross validated against unseen test data and achieved high predictive performance in terms of correlation coefficient ( $$R^{2} > 0.98 $$ R 2 > 0.98 for 9–12% Cr FMA and $$R^{2} > 0.95 $$ R 2 > 0.95 for austenitic stainless steel) thus bypassing the need for additional comprehensive tensile test campaigns or physical theoretical calculations. Furthermore, the feature importance has been computed using the Shapley value analysis to understand the complex interplay of different features.

36 MATERIALS SCIENCE↗
NASA NTRS1992

Geology and distribution of impact craters on Venus - What are they telling us?

Data on the distribution of impact craters on Venus are analyzed in relation to the geologic history of Venus and the effects of high ambient pressures and temperatures on the cratering process itself. The cratering record of Venus is discussed in terms of size, number, spatial distribution, and state of preservation of craters. The morphology of Venusian craters is examined as a function of the diameter, and features unique to these craters are discussed. Attention is also given to several craters that illustrate important features of Venusian crater; surface 'splotches' that are closely related in origin to impact craters; and implications of the distribution of severely modified craters for Venus' recent geologic history.

Schaber, G. G.↗
NASA NTRS1983

The materials processing research base of the Materials Processing Center. Report for FY 1982

The work described, while involving research in the broad field of materials processing, has two common features: the problems are closed related to space precessing of materials and have both practical and fundamental significance. An interesting and important feature of many of the projects is that the interdisciplinary nature of the problem mandates complementary analytical modeling/experimental approaches. An other important aspect of many of the projects is the increasing use of mathematical modeling techniques as one of the research tools. The predictive capability of these models, when tested against measurements, plays a very important role in both the planning of experimental programs and in the rational interpretation of the results. Many of the projects described have a space experiment as their ultimate objective. Mathematical models are proving to be extremely valuable in projecting the findings of ground - based experiments to microgravity conditions.

Flemings, M. C.↗
DOE OSTI2021

ENSO Dynamics in the E3SM-1-0, CESM2, and GFDL-CM4 Climate Models

We report that this study examines historical simulations of ENSO in the E3SM-1-0, CESM2, and GFDL-CM4 climate models, provided by three leading U.S. modeling centers as part of the Coupled Model Intercomparison Project phase 6 (CMIP6). These new models have made substantial progress in simulating ENSO’s key features, including: amplitude; timescale; spatial patterns; phase-locking; spring persistence barrier; and recharge oscillator dynamics. However, some important features of ENSO are still a challenge to simulate. In the central and eastern equatorial Pacific, the models’ weaker-than-observed subsurface zonal current anomalies and zonal temperature gradient anomalies serve to weaken the nonlinear zonal advection of subsurface temperatures, leading to insufficient warm/cold asymmetry of ENSO’s sea surface temperature anomalies (SSTA). In the western equatorial Pacific, the models’ excessive simulated zonal SST gradients amplify their zonal temperature advection, causing their SSTA to extend farther west than observed. The models underestimate both ENSO’s positive dynamic feedbacks (due to insufficient zonal wind stress responses to SSTA) and its thermodynamic damping (due to insufficient convective cloud shading of eastern Pacific SSTA during warm events); compensation between these biases leads to realistic linear growth rates for ENSO, but for somewhat unrealistic reasons. The models also exhibit stronger-than-observed feedbacks onto eastern equatorial Pacific SSTAs from thermocline depth anomalies, which accelerates the transitions between events and shortens the simulated ENSO period relative to observations. Implications for diagnosing and simulating ENSO in climate models are discussed.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle S.↗
NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle↗
DOE OSTI2022

Golgi-localized putative S-adenosyl methionine transporters required for plant cell wall polysaccharide methylation

Polysaccharide methylation, especially that of pectin, is a common and important feature of land plant cell walls. Polysaccharide methylation takes place in the Golgi apparatus and therefore relies on the import of S-adenosyl methionine (SAM) from the cytosol into the Golgi. However, so far, no Golgi SAM transporter has been identified in plants. Here we studied major facilitator superfamily members in Arabidopsis that we identified as putative Golgi SAM transporters (GoSAMTs). Knockout of the two most highly expressed GoSAMTs led to a strong reduction in Golgi-synthesized polysaccharide methylation. Furthermore, solid-state NMR experiments revealed that reduced methylation changed cell wall polysaccharide conformations, interactions and mobilities. Notably, NMR revealed the existence of pectin ‘egg-box’ structures in intact cell walls and showed that their formation is enhanced by reduced methyl esterification. Here, these changes in wall architecture were linked to substantial growth and developmental phenotypes. In particular, anisotropic growth was strongly impaired in the double mutant. The identification of putative transporters involved in import of SAM into the Golgi lumen in plants provides new insights into the paramount importance of polysaccharide methylation for plant cell wall structure and function.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Global River Topology (GRIT): A Bifurcating River Hydrography

Existing global river networks underpin a wide range of hydrological applications but do not represent channels with divergent river flows (bifurcations, multi‐threaded channels, canals), as these features defy the convergent flow assumption that elevation‐derived networks (e.g., HydroSHEDS, MERIT Hydro) are based on. Yet, bifurcations are important features of the global river drainage system, especially on large floodplains and river deltas, and are also often found in densely populated regions. Here we developed the first raster and vector‐based Global RIver Topology that not only represents the tributaries of the global drainage network but also the distributaries, including multi‐threaded rivers, canals and deltas. We achieve this by merging a 30 m Landsat‐based river mask with elevation‐generated streams to ensure a homogeneous drainage density outside of the river mask for rivers narrower than approximately 30 m. Crucially, we employ the new 30 m digital terrain model, FABDEM, based on TanDEM‐X, which shows greater accuracy over the traditionally used SRTM derivatives. After vectorization and pruning, directionality is assigned by a series of elevation, flow angle and continuity approaches. The new global network and its attributes are validated using gauging stations, comparison with existing networks, and randomized manual checks. The new network represents 19.6 million km of streams and rivers with drainage areas greater than 50 km 2 and includes 67,495 bifurcations. With the advent of hyper‐resolution modeling and artificial intelligence, GRIT is expected to greatly improve the accuracy of many river‐based applications such as flood forecasting, water availability and quality simulations, or riverine habitat mapping.

54 ENVIRONMENTAL SCIENCES↗