Search NASA⌕ Search

SEARCH · Search NASA

Results for “Regression approach”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Efficient bifurcation and tabulation of multi-dimensional combustion manifolds using deep mixture of experts: An a priori study

This work describes and validates an approach for autonomously bifurcating turbulent combustion man-ifolds to divide regression tasks amongst specialized artificial neural networks (ANNs). This approach relies on the mixture of experts (MoE) framework, where each neural network is trained to be specialized in a given portion of the input space. The assignment of different input regions to the experts is determined by a gating network, which is a neural network classifier. In some previous studies, it has been demonstrated that bifurcation of a complex combustion manifold and fitting different ANNs for each part leads to better fits or faster inference speeds. However, the manner of bifurcation in these studies was based on heuristic approaches or clustering techniques. In contrast, the proposed technique enables automatic bifurcation using non-linear planes in high-dimensional turbulent combustion manifolds that are often associated with complex behavior due to different dominating physics in various zones. Furthermore, the proposed concept is validated using 4-dimensional (4D) and 5D flamelet tables, showing that the errors obtained with a given network size, or conversely the network size required to achieve a given accuracy, is considerably reduced. The effect of the number of experts on inference speed is also investigated, showing that by increasing the number of experts from 1 to 8, the inference time can be approximately reduced by a factor of two. Moreover, it is shown that the MoE approach divides the input manifold in a physically intuitive manner, suggesting that the MoE framework can elucidate high-dimensional datasets in a physically meaningful way.

42 ENGINEERING↗
DOE OSTI2022

ppdx : Automated modeling of protein–protein interaction descriptors for use with machine learning

This paper describes ppdx, a python workflow tool that combines protein sequence alignment, homology modeling, and structural refinement, to compute a broad array of descriptors for characterizing protein–protein interactions. The descriptors can be used to predict various properties of interest, such as protein–protein binding affinities, or inhibitory concentrations (IC 50 ), using approaches that range from simple regression to more complex machine learning models. The software is highly modular. It supports different protocols for generating structures, and 95 descriptors can be currently computed. More protocols and descriptors can be easily added. The implementation is highly parallel and can fully exploit the available cores in a single workstation, or multiple nodes on a supercomputer, allowing many systems to be analyzed simultaneously. As an illustrative application, ppdx is used to parametrize a model that predicts the IC 50 of a set of antigens and a class of antibodies directed to the influenza hemagglutinin stalk.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

A comparison of Gaussian processes and neural networks for computer model emulation and calibration

The Department of Energy relies on complex physics simulations for prediction in domains like cosmology, nuclear theory, and materials science. These simulations are often extremely computationally intensive, with some requiring days or weeks for a single simulation. In order to assure their accuracy, these models are calibrated against observational data in order to estimate inputs and systematic biases. Because of their great computational complexity, this process typically requires the construction of an emulator, a fast approximation to the simulation. In this paper, two emulator approaches are compared: Gaussian process regression and neural networks. Their emulation accuracy and calibration performance on three real problems of Department of Energy interest is considered. On these problems, the Gaussian process emulator tends to be more accurate with narrower, but still well-calibrated uncertainty estimates. The neural network emulator is accurate, but tends to have large uncertainty on its predictions. Finally, as a result, calibration with the Gaussian process emulator produces more constrained posteriors that still perform well in prediction.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Search for the associated production of charm quarks and a Higgs boson decaying into a photon pair with the ATLAS detector

A search for the production of a Higgs boson and one or more charm quarks, in which the Higgs boson decays into a photon pair, is presented. This search uses proton-proton collision data with a centre-of-mass energy of $\sqrt{s}$ = 13 TeV and an integrated luminosity of 140 fb −1 recorded by the ATLAS detector at the Large Hadron Collider. The analysis relies on the identification of charm-quark-containing jets, and adopts an approach based on Gaussian process regression to model the non-resonant di-photon background. The observed (expected, assuming the Standard Model signal) upper limit at the 95% confidence level on the cross-section for producing a Higgs boson and at least one charm-quark-containing jet that passes a fiducial selection is found to be 10.6 pb (8.8 pb). The observed (expected) measured cross-section for this process is 5.3 ± 3.2 pb (2.9 ± 3.1 pb).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Projecting Life-Cycle Environmental Impacts of Corn Production in the U.S. Midwest under Future Climate Scenarios using machine learning approach

Emission factors and process-based mechanism models are popular approaches used to estimate life-cycle environmental impacts. However, emission factors are often incapable of describing spatial and temporal heterogeneity of agricultural emissions, whereas process-based mechanism models, capable of capturing the heterogeneity, tend to be very complicated, and time-consuming. Efficient predictions of life-cycle environmental impacts from agricultural production are lacking. This study develops a rapid predictive model to quantify life-cycle global warming (GW), eutrophication (EU) and acidification (AD) impacts of corn production using a novel machine learning approach. We used the boosted regression tree (BRT) model to estimate current and future life-cycle environmental impacts of corn production in 12 U.S. Midwest at county scale under four Intergovernmental Panel on Climate Change (IPCC)’s climate scenarios (RCP2.6. 4.5, 6.0, and 8.5) for years 2009-2100. Results show that future life-cycle GW, EU and AD impacts of corn production will increase under all four scenarios, with the worst environmental impacts shown under the RCP 8.5 scenario. Significant spatial variation were estimated to be 3.6, 29.9 and 1.8-folds under the RCP4.5 scenario, and 6.6, 152.9 and 1.6-folds under the RCP8.5 scenario, respectively. Findings from this study demonstrate the importance of considering county-level life-cycle environmental impacts and the influences of climate change in future years to aid in developing potential adaptation and mitigation programs and policies.

Machine learning, climate change, projections, env↗
DOE OSTI2020

General Protocol for the Accurate Prediction of Molecular 13 C/ 1 H NMR Chemical Shifts via Machine Learning Augmented DFT

An accurate prediction of NMR chemical shifts at affordable computational cost is very important for different types of structural assignments in experimental studies. Density functional theory (DFT) and gauge-including atomic orbital (GIAO) are two of the most popular computational methods for NMR calculation, yet they often fail to resolve ambiguities in structural assignments. In this work, we present a new method that uses machine learning (ML) techniques (DFT + ML) that significantly increases the accuracy of 13 C/ 1 H NMR chemical shift prediction for a variety of organic molecules. The input of the generalizable DFT + ML model contains two critical parts: one is a vector providing insights into chemical environments, which can be evaluated without knowing the exact geometry of the molecule; the other one is the DFT-calculated isotropic shielding constant. The DFT + ML model was trained with a data set containing 476 13 C and 270 1 H experimental chemical shifts. For the DFT methods used here, the root mean square deviations (RMSDs) for the errors between predicted and experimental 13 C/ 1 H chemical shifts can be as small as 2.10/0.18 ppm, which is much lower than those from simple DFT (5.54/0.25 ppm), or DFT + linear regression (LR) (4.77/0.23 ppm) approaches. It also has a smaller maximum absolute error than two previously proposed NMR-predicting ML models. The robustness of the DFT + ML model is tested on two classes of organic molecules (TIC10 and hyacinthacines), where the correct isomers were unambiguously assigned to the experimental ones. Overall, the DFT + ML model shows promise for structural assignments in a variety of systems, including stereoisomers, that are often challenging to determine experimentally.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Bayesian Gaussian process inference for neutron spin echo measurement

Neutron spin echo (NSE) spectroscopy provides unique access to microscopic dynamics, but its application is often constrained by low neutron flux, long acquisition times, and significant noise. Here, we present a Bayesian inference approach based on Gaussian process regression (GPR) to reconstruct high-quality spin echo signals from sparse and noisy data by exploiting correlations in reciprocal space. Benchmarks on synthetic datasets and validation with experimental NSE measurements of dendrimers show that GPR suppresses noise, interpolates missing intensity values, and accommodates irregular observations. The method improves accuracy, shortens acquisition times, and enables high-throughput and real-time studies. Beyond NSE, the framework is broadly applicable to other low signal-to-noise ratio scattering techniques, thereby extending the scope of neutron spectroscopy.

Tung, Chi-Huan [Oak Ridge National Laboratory (ORN↗
DOE OSTI2024

Exploration of Novel Neuromorphic Methodologies for Materials Applications

Many of today's most interesting questions involve understanding and interpreting complex relationships within graph-based structures. For instance, in materials science, predicting material properties often relies on analyzing the intricate network of atomic interactions. Graph neural networks (GNNs) have emerged as a popular approach for these tasks; however, they suffer from limitations such as inefficient hardware utilization and over-smoothing. Recent advancements in neuromorphic computing offer promising solutions to these challenges. In this work, we evaluate two such neuromorphic strategies known as reservoir computing and hyperdimensional computing. We compare the performance of both approaches for bandgap classification and regression using a subset of the Materials Project dataset. Our results indicate recent advances in hyperdimensional computing can be applied effectively to better represent molecular graphs.

Gobin, Derek [George Mason University, Virginia]↗
DOE OSTI2022

Denoising Convolutional Networks to Accelerate Detector Simulation

The high accuracy of detector simulation is crucial for modern particle physics experiments. However, this accuracy comes with a high computational cost, which will be exacerbated by the large datasets and complex detector upgrades associated with next-generation facilities such as the High Luminosity LHC. We explore the viability of regression-based machine learning (ML) approaches using convolutional neural networks (CNNs) to "denoise" faster, lower-quality detector simulations, augmenting them to produce a higher-quality final result with a reduced computational burden. The denoising CNN works in concert with classical detector simulation software rather than replacing it entirely, increasing its reliability compared to other ML approaches to simulation. We obtain promising results from a prototype based on photon showers in the CMS electromagnetic calorimeter. Future directions are also discussed.

Banerjee, Sunanda↗
DOE OSTI2021

Denoising Convolutional Networks to Accelerate Detector Simulation [Poster]

The high accuracy of detector simulation is crucial for modern particle physics experiments. However, this accuracy comes with a high computational cost, which will be exacerbated by the large datasets and complex detector upgrades associated with next-generation facilities such as the High Luminosity LHC. We explore the viability of regression-based machine learning (ML) approaches using convolutional neural networks (CNN) to ``denoise'' faster, lower-quality detector simulations, augmenting them to produce a higher-quality final result with a reduced computational burden. The denoising CNN works in concert with classical detector simulation software rather than replacing it entirely, increasing its reliability compared to other ML approaches to simulation. We obtain promising results from a prototype based on photon showers in the CMS electromagnetic calorimeter. Future directions are also discussed.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Biomass Resources and Emission Reduction Potential of Agricultural and Livestock Residues in Mainland China from 2013 to 2022

Controlling carbon emissions is a global goal, and China is actively implementing carbon reduction measures. As a major agricultural nation, China has considerable potential for developing agricultural residues as renewable and environmentally friendly biomass energy. In this study, we obtained data on crop yields, crop-to-grain ratios, and livestock excretion coefficients to calculate the biomass resources of agricultural and livestock residues in Chinese provinces from 2013 to 2022. Crop residue biomass resources showed a distribution pattern with higher levels in the north than in the south and the east than in the west. Henan and Heilongjiang provinces consistently had the highest resource levels, exceeding 35 million tons annually for 10 years. The biomass resources from livestock residues were relatively abundant in Sichuan, Henan, Yunnan, Shandong, Hunan, and Inner Mongolia. Inner Mongolia, Sichuan, Shandong, and Henan had the greatest potential for CO2 emission reductions, primarily located in regions abundant in biomass resources and with high traditional energy consumption levels. ArcGIS was used to apply natural break classification to categorize the potential for emission reductions from agricultural and livestock residues across China from 2013 to 2022 into five classes. Based on factors such as crop planting area and livestock numbers, the spatiotemporal distribution of factors influencing the quantity of biomass resources was examined using Geographically and Temporally Weighted Regression. A tailored and integrated approach should be used for biomass, and the development of biomass energy should be promoted through policy support and technological innovation.

Environmental Sciences & Ecology↗
NASA NTRS1980

Predicting major element mineral/melt equilibria - A statistical approach

Empirical equations have been developed for calculating the mole fractions of NaO0.5, MgO, AlO1.5, SiO2, KO0.5, CaO, TiO2, and FeO in a solid phase of initially unknown identity given only the composition of the coexisting silicate melt. The approach involves a linear multivariate regression analysis in which solid composition is expressed as a Taylor series expansion of the liquid compositions. An internally consistent precision of approximately 0.94 is obtained, that is, the nature of the liquidus phase in the input data set can be correctly predicted for approximately 94% of the entries. The composition of the liquidus phase may be calculated to better than 5 mol % absolute. An important feature of this 'generalized solid' model is its reversibility; that is, the dependent and independent variables in the linear multivariate regression may be inverted to permit prediction of the composition of a silicate liquid produced by equilibrium partial melting of a polymineralic source assemblage.

Hostetler, C. J.↗
NASA NTRS1983

Creep fatigue life prediction for engine hot section materials (isotropic)

The Hot Section Technology (HOST) program, creep fatigue life prediction for engine hot section materials (isotropic), is reviewed. The program is aimed at improving the high temperature crack initiation life prediction technology for gas turbine hot section components. Significant results include: (1) cast B1900 and wrought IN 718 selected as the base and alternative materials respectively; (2) fatigue test specimens indicated that measurable surface cracks appear early in the specimen lives, i.e., 15% of total life at 871 C and 50% of life at 538 c; (3) observed crack initiation sites are all surface initiated and are associated with either grain boundary carbides or local porosity, transgrannular cracking is observed at the initiation site for all conditions tested; and (4) an initial evaluation of two life prediction models, representative of macroscopic (Coffin-Mason) and more microscopic (damage rate) approaches, was conducted using limited data generated at 871 C and 538 C. It is found that the microscopic approach provides a more accurate regression of the data used to determine crack initiation model constants, but overpredicts the effect of strain rate on crack initiation life for the conditions tested.

Moreno, V.↗
NASA NTRS1990

Threshold altitude resulting in decompression sickness

A review of case reports, hypobaric chamber training data, and experimental evidence indicated that the threshold for incidence of altitude decompression sickness (DCS) was influenced by various factors such as prior denitrogenation, exercise or rest, and period of exposure, in addition to individual susceptibility. Fitting these data with appropriate statistical models makes it possible to examine the influence of various factors on the threshold for DCS. This approach was illustrated by logistic regression analysis on the incidence of DCS below 9144 m. Estimations using these regressions showed that, under a noprebreathe, 6-h exposure, simulated EVA profile, the threshold for symptoms occurred at approximately 3353 m; while under a noprebreathe, 2-h exposure profile with knee-bends exercise, the threshold occurred at 7925 m.

Kumar, K. V.↗
NASA NTRS2007

Aeroelastic Model Structure Computation for Envelope Expansion

Structure detection is a procedure for selecting a subset of candidate terms, from a full model description, that best describes the observed output. This is a necessary procedure to compute an efficient system description which may afford greater insight into the functionality of the system or a simpler controller design. Structure computation as a tool for black-box modeling may be of critical importance in the development of robust, parsimonious models for the flight-test community. Moreover, this approach may lead to efficient strategies for rapid envelope expansion that may save significant development time and costs. In this study, a least absolute shrinkage and selection operator (LASSO) technique is investigated for computing efficient model descriptions of non-linear aeroelastic systems. The LASSO minimises the residual sum of squares with the addition of an l(Sub 1) penalty term on the parameter vector of the traditional l(sub 2) minimisation problem. Its use for structure detection is a natural extension of this constrained minimisation approach to pseudo-linear regression problems which produces some model parameters that are exactly zero and, therefore, yields a parsimonious system description. Applicability of this technique for model structure computation for the F/A-18 (McDonnell Douglas, now The Boeing Company, Chicago, Illinois) Active Aeroelastic Wing project using flight test data is shown for several flight conditions (Mach numbers) by identifying a parsimonious system description with a high percent fit for cross-validated data.

Kukreja, Sunil L.↗
NASA NTRS2011

Prognostics of Power MOSFET

This paper demonstrates how to apply prognostics to power MOSFETs (metal oxide field effect transistor). The methodology uses thermal cycling to age devices and Gaussian process regression to perform prognostics. The approach is validated with experiments on 100V power MOSFETs. The failure mechanism for the stress conditions is determined to be die-attachment degradation. Change in ON-state resistance is used as a precursor of failure due to its dependence on junction temperature. The experimental data is augmented with a finite element analysis simulation that is based on a two-transistor model. The simulation assists in the interpretation of the degradation phenomena and SOA (safe operation area) change.

Celaya, Jose Ramon↗
NASA NTRS2021

First Measurements of Ambient PM2.5 in Kinshasa, Democratic Republic of Congo and Brazzaville, Republic of Congo Using Field-calibrated Low-cost Sensors

Estimates of air pollution mortality in sub-Saharan Africa are limited by a lack of surface observations of fine particulate matter (PM2.5). Despite being large metropolises, Kinshasa, Democratic Republic of the Congo (DRC), population 14.3 million, and Brazzaville, Republic of the Congo (ROC), population 2.4 million, have no reference air pollution monitors at the time of writing. Recently, a few reference monitors have been deployed in other parts of sub-Saharan Africa, including Kampala, Uganda. A low-cost PurpleAir PM2.5 monitor was collocated next to the Kampala US Embassy BAM-1020 (Met One Beta Attenuation Monitor) starting in August 2019. Raw PurpleAir data are strongly correlated with the BAM (r(exp 2) = 0.88), but have a mean absolute error of approximately 14 μg/cu.m. Two calibration models, multiple linear regression and a random forest approach, decrease mean absolute error (MAE) from 14.3 μg/cu.m to 3.4 µg/cu.m or less and improve the the r(exp 2) from 0.88 to 0.96. Given )the similarity in climate and emissions in Kampala, we apply the collocated field correction factors to four PurpleAir sensors in Kinshasa, DRC and one in neighboring Brazzaville, ROC deployed beginning April 2018. Annual average PM2.5 for 2019 in Kinshasa is estimated at 43.5 µg/cu.m, more than 4 times higher than WHO Interim Target 1 of 10 µg/cu.m. Surface PM2.5 and aerosol optical depth were each about 40% lower during the 2020 COVID19 lockdown period compared to the same time period in 2019, which cannot be explained by changes in meteorology or wildfire emissions alone. Our results highlight the need for clean air solutions implementation in the Congo.

Celeste McFarlane↗
NASA NTRS1999

Canopy Cover Predictions using Ground Observations and Remotely Sensed Data

Maps of vegetation status are needed at many scales, from the field level to monitor ecosystem condition to the global level to understand the carbon cycle. Status is quantified by such variables as leaf area index, biomass, and fraction of canopy cover. Current methods of predicting vegetation variables use remote sensing data to provide a spatially exhaustive data source. In a study in western Montana, several hundred ground observations made by the US Forest Service on tenth-acre conifer plots were used to develop aspatial regression and geostatistical prediction models. Normalized Difference Vegetation Index (NDVI) values from Landsat Thematic Mapper images were used as ancillary data. These models were then used to predict canopy cover at unsampled locations in a 97 square kilometer region on the boundary of the Flathead National Forest and the Bob Marshall Wilderness. Independent data from two dates six years apart were used for validation. Given the assumption that actual canopy cover remained relatively unchanged within this time period, partial validation can be achieved by measuring the correspondence of the two maps. This criterion results in ranking the aspatial regression maps as less accurate than the geostatistically generated maps. The geostatistical approach emphasizes ground measurements more heavily than does aspatid regression. Geostatistical simulations of canopy cover also provide a means of describing uncertainty about the patterns of canopy cover.

Dungan, Jennifer L.↗