Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “small dataset”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction

With access to large datasets, deep neural networks through representation learning have been able to identify patterns from raw data, achieving human-level accuracy in image and speech recognition tasks. However, in chemistry, availability of large standardized and labelled datasets is scarce, and with a multitude of chemical properties of interest, chemical data is inherently small and fragmented. In this work, we explore transfer learning techniques in conjunction with the existing Chemception CNN model, to create a transferable and generalizable deep neural network for small-molecule property prediction. Our latest model, ChemNet learns in a semi-supervised manner from inexpensive labels computed from the ChEMBL database. When fine-tuned to the Tox21, HIV and FreeSolv dataset, which are 3 separate chemical tasks that ChemNet was not originally trained on, we demonstrate that ChemNet exceeds the performance of existing Chemception models, contemporary MLP models that trains on molecular fingerprints, and it matches the performance of the ConvGraph algorithm, the current state-of-the-art. Furthermore, as ChemNet has been pre-trained on a large diverse chemical database, it can be used as a universal “plug-and-play” deep neural network, which accelerates the deployment of deep neural networks for the prediction of novel small-molecule chemical properties.

Artificial Intelligence↗
DOE OSTI2025

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
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 OSTI2018

A shock tube study of ignition delay times in diluted methane, ethylene, propene and their blends at elevated pressures

Ignition delay times (IDT) of small hydrocarbons at elevated pressures provide a valuable constraint for the refinement of the core small-hydrocarbon sub-mechanisms used in all combustion kinetics. Current knowledge of these core mechanisms is based largely on low-pressure data, with only limited high-pressure data available. To remedy this, here the present study focuses on ignition delay times in methane, ethylene, propene and their blends at elevated pressures. IDT measurements were performed in 4% O 2 , balance Ar mixtures, over the temperature range of 950–1800 K, at pressures of 14–60 atm and equivalence ratios of 1 and 2. IDT was determined from recorded sidewall pressure, OH* emission measurements and fuel time-histories measured using laser absorption at 3.39 μm. These measurements extend the test conditions of earlier studies, with the advantage that they have all been performed at similar conditions and with the same facility and should provide a uniform set of kinetics targets for the evaluation of core small-hydrocarbon mechanisms. This dataset also allowed the temperature variation of the pressure and equivalence ratio scaling for methane and ethylene IDT to be investigated.

42 ENGINEERING↗
DOE OSTI2021

A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media

This paper presents a new deep learning data-driven model for predicting structure dependent pore-fluid velocity fields in rock. The model is based on a Convolutional Auto-Encoder (CAE) artificial neural network capable of learning from image data generated by direct numerical simulations of fluid flow through pore-structures, such as by Lattice Boltzmann or molecular dynamics methods. The main novelty of the model in comparison to previous CAE-based data-driven approaches consists of three parts. The first is a methodology for decomposing the full-domain of the porous media into sub-regions, or “sub-domains”, in order to reduce the overall size of the CAE, batch process the sub-domains in parallel, and enable the CAE to learn local and generalizable nonlinear mappings of pore-fluid velocities. The second consists of embedding the finite difference solutions of the incompressible Navier-Stokes and continuity equations into convolutional layers prior to the CAE in order to provide the CAE with knowledge of fluid dynamics physics (PhyFlow). The third main novelty is that the training of the CAE is regularized with a hierarchical loss function that encourages the learning of fluid flow patterns (in a way similar to ranked modes in principal component analysis), ranking from most to least important. This is shown to increase the stability in learning, reduce over-fitting, and promote interpretability of the CAE neural network layers (HierCAE). The comprehensive new data-driven model, which we call the PhyFlow-HierCAE model, is shown to exhibit improved accuracy and generalizability of flow field predictions over conventional CAE models, attributable to the embedded physical knowledge and the hierarchical regularization, as well as realize orders of magnitude speed-ups in computation times as a surrogate for the direct numerical simulations. Examples of training and forward predictions on unseen pore-structures are provided and evaluated for data from Lattice Boltzmann and molecular dynamics simulations of pore-fluid flow. The model is shown to be a fast and accurate emulator (or “surrogate”) for predicting effective permeability of unseen pore-structures based on learning from relatively small direct numerical simulation datasets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

A machine learning approach for determining temperature-dependent bandgap of metal oxides utilizing Allen–Heine–Cardona theory and O’Donnell model parameterization

To evaluate the high temperature sensing properties of metal oxide and perovskite materials suitable for use in combustion environments, it is necessary to understand the temperature dependence of their bandgaps. Although such temperature-driven changes can be calculated via the Allen–Heine–Cardona (AHC) theory, which assesses electron–phonon coupling for the bandgap correction at given temperatures, this approach is computationally demanding. Another approach to predict bandgap temperature-dependence is the O’Donnell model, which uses analytical expressions with multiple fitting parameters that require bandgap information at 0 K. This work employs data-driven Gaussian process regression (GPR) to predict the parameters employed in the O’Donnell model from a set of physical features. We use a sample of 54 metal oxides for which density functional theory has been performed to calculate the bandgap at 0 K, and the AHC calculations have been carried out to determine the shift in the bandgap at non-zero temperatures. As the AHC calculations are impractical for high-throughput screening of materials, the developed GPR model attempts to alleviate this issue by predicting the O'Donnell parameters purely from physical features. To mitigate the reliability issues arising from the very small size of the dataset, we apply a Bayesian technique to improve the generalizability of the data-driven models as well as quantify the uncertainty associated with the predictions. The method captures well the overall trend of the O’Donnell parameters with respect to a reduced feature set obtained by transforming the available physical features. Quantifying the associated uncertainty helps us understand the reliability of the predictions of the O’Donnell parameters and, therefore, the bandgap as a function of temperature for any novel material.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Characterizing the acceleration time of laser-driven ion acceleration with data-informed neural networks

Peak ion energy is an important figure-of-merit in short-pulse, laser-driven ion acceleration and is dependent on an associated acceleration time. Standard metrics for these quantities depend on analytical results such as the self-similar fluid model or empirical models based on relatively small experimental and simulation datasets. In this work we attempt to use a data-informed neural network (NN) as a surrogate model for a large ensemble of PIC simulations to investigate an effective acceleration time. We explore the application of a stacked convolutional and recurrent NN architecture for improved regression by incorporating the time dependencies of the data into the training process. Of particular note is how pretraining a network on lower fidelity data, e.g. 1D analytical results, greatly improves the network's ability to learn more complex, higher fidelity data. Finally, the dependency of the acceleration time on various laser and plasma parameters is explored.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Neural networks for estimation of divertor conditions in DIII-D using C III imaging

Deep learning approaches have been applied to images of C III emission in the lower divertor of DIII-D to develop models for estimating the level of detachment and magnetic configuration (X-point location and strike point radial location). The poloidal distance from the target to the C III emission front is used to represent the level of detachment. The models perform well on a test dataset not used in training, achieving $F_1$ scores as high as 0.99 for detachment state classification and root mean squared error (RMSE) as low as 2cm for front location regression. Predictions for shots with intermittent reattachment are studied, with class activation mapping used to aid in interpretation of the model predictions. Based on the success of these models, a third model was trained to predict the X-point location and strike point radial position from C III images. Though the dataset covers only a small range of possible magnetic configurations, the model shows promising results, achieving RMSE around 1cm for the test data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

AGS-GNN: Attribute-guided Sampling for Graph Neural Networks

We propose AGS-GNN, a novel attribute-guided sampling algorithm for Graph Neural Networks (GNNs) that exploits node features and connectivity structure of a graph while simultaneously adapting for both homophily and heterophily in graphs. (In homophilic graphs vertices of the same class are more likely to be connected, and vertices of different classes tend to be linked in heterophilic graphs.) While GNNs have been successfully applied to homophilic graphs, their application to heterophilic graphs remains challenging. The best-performing GNNs for heterophilic graphs do not fit the sampling paradigm, suffer high computational costs, and are not inductive. We employ samplers based on feature-similarity and feature-diversity to select subsets of neighbors for a node, and adaptively capture information from homophilic and heterophilic neighborhoods using dual channels. Currently, AGS-GNN is the only algorithm that we know of that explicitly controls homophily in the sampled subgraph through similar and diverse neighborhood samples. For diverse neighborhood sampling, we employ submodularity, which was not used in this context prior to our work. The sampling distribution is pre-computed and highly parallel, achieving the desired scalability. Using an extensive dataset consisting of 35 small (<=100K nodes) and large (>100K nodes) homophilic and heterophilic graphs, we demonstrate the superiority of AGS-GNN compare to the current approaches in the literature. AGS-GNN achieves comparable test accuracy to the best-performing heterophilic GNNs, even outperforming methods using the entire graph for node classification. AGS-GNN also converges faster compared to methods that sample neighborhoods randomly, and can be incorporated into existing GNN models that employ node or graph sampling.

artificial intelligence↗
DOE OSTI2019

Understanding the Effects of Tapering on Gaussian Process Regression

Gaussian process regression is a computationally expensive machine learning algorithm that requires the solution of a system of linear equations with a dense covariance matrix. We propose a modification that uses tapering to introduce sparsity into the covariance matrix followed by matrix reordering schemes to reduce the bandwidth of the sparse matrix. We also apply iterative refinement to our approximate solution in order to recover some of the accuracy lost to tapering. Our numerical tests showed that this modification works best with datasets that have many small values in the covariance matrix. This restricts the usefulness of the modification, so other techniques to reduce computational time may be worth considering in the future.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Multi-INT Signature Collection and Exploitation for Security Los Alamos LDRD Report

This project demonstrates the feasibility of a 2-D passive tracking capability for ground-based and airborne moving sources using multi-INT signal processing of acoustic and seismic signals. We leveraged the recent DDSTE-supported investment in rapid deployable sensors (the Los Alamos Rapid-deployable Sensor Array—LARSA), and used uncrewed aerial vehicles (UAV) as a data source. Moving source types are characterized by their variability with time (exemplified but not limited to the Doppler shift of a passing vehicle) and the signatures used for detection should have similar characteristics. We have demonstrated that time-varying sensor signatures (TVS) combined with time-stable sensor signatures provide a more complete understanding of moving source behavior and drive towards path prediction. Importantly, we have collected a new, relevant LANL dataset of moving sources (small UAV flights and vehicle movement), developed new signatures, and demonstrated a capability to identify, track and forecast the position of TVS.

42 ENGINEERING↗
DOE OSTI2021

Multi-INT Signature Collection and Exploitation for Security: Improving Discrimination, Analyses, and Passive Tracking Capabilities for Time- and Distance-Varying Signatures in the Seismoacoustic Regime

This project demonstrates the feasibility of a passive tracking capability for ground-based and airborne moving sources using multiple information streams from acoustic and seismic signals. These moving source types are characterized by their variability with time and distance (exemplified but not limited to the familiar doppler shift of a passing vehicle) and the signatures used for detection should have similar characteristics. We have demonstrated that time-varying sensor signatures (TVS) combined with time-stable sensor signatures provide a more complete understanding of moving source behavior. Importantly, we have collected a new, relevant LANL dataset of moving sources (small uncrewed aerial vehicle flights and ground vehicle movement), developed new signatures, and demonstrated the capability to identify, track and forecast the position of these moving sources.

42 ENGINEERING↗
DOE OSTI2025

High-Temperature Gas Sensor Materials with Properties Predicted via First-Principles Calculations with Machine Learning Modeling and Experimental Corroboration

Understanding the temperature dependence of functional properties of sensing materials is vital for their applications in combustion environments. The electron-phonon coupling that derives the electronic structure change with temperatures is a key property of interest as it affects other sensing responses. Herein, we first assess the temperature dependence of band gap renormalization in sensing materials by employing Allen-Heine-Cardona (AHC) theory with density functional theory (DFT) simulations corroborated with experimental observation. As the AHC calculations are impractical for high-throughput screening of materials, we employ data-driven Gaussian process regression to predict the parameters employed in the O’Donnell empirical model from a set of physical features. To mitigate the reliability issues arising from the small size of the dataset, we apply a Bayesian technique to improve the generalizability of the data-driven models as well as to quantify the uncertainty associated with theoretical predictions. These models capture well the overall trend of the O’Donnell parameters with respect to a reduced feature set obtained by transforming the available physical features. Quantifying the associated uncertainty helps us understand the reliability of the predictions and, therefore, the variation of bandgap as a function of temperature for other novel materials. The predicted candidates from machine learning models are further validated by experiments and DFT calculations.

bandgap renormalization↗
DOE OSTI2021

A hybrid data–model approach to map soil thickness in mountain hillslopes

Abstract. Soil thickness plays a central role in the interactions between vegetation, soils, and topography, where it controls the retention and release of water, carbon, nitrogen, and metals. However, mapping soil thickness, here defined as the mobile regolith layer, at high spatial resolution remains challenging. Here, we develop a hybrid model that combines a process-based model and empirical relationships to estimate the spatial heterogeneity of soil thickness with fine spatial resolution (0.5 m). We apply this model to two aspects of hillslopes (southwest- and northeast-facing, respectively) in the East River watershed in Colorado. Two independent measurement methods – auger and cone penetrometer – are used to sample soil thickness at 78 locations to calibrate the local value of unconstrained parameters within the hybrid model. Sensitivity analysis using the hybrid model reveals that the diffusion coefficient used in hillslope diffusion modeling has the largest sensitivity among all input parameters. In addition, our results from both sampling and modeling show that, in general, the northeast-facing hillslope has a deeper soil layer than the southwest-facing hillslope. By comparing the soil thickness estimated between a machine-learning approach and this hybrid model, the hybrid model provides higher accuracy and requires less sampling data. Modeling results further reveal that the southwest-facing hillslope has a slightly faster surface soil erosion rate and soil production rate than the northeast-facing hillslope, which suggests that the relatively less dense vegetation cover and drier surface soils on the southwest-facing slopes influence soil properties. With seven parameters in total for calibration, this hybrid model can provide a realistic soil thickness map with a relatively small amount of sampling dataset comparing to machine-learning approach. Integrating process-based modeling and statistical analysis not only provides a thorough understanding of the fundamental mechanisms for soil thickness prediction but also integrates the strengths of both statistical approaches and process-based modeling approaches.

58 GEOSCIENCES↗
NASA NTRS2016

GeneLab for High Schools: Data Mining for the Next Generation

Modern biological sciences have become increasingly based on molecular biology and high-throughput molecular techniques, such as genomics, transcriptomics, and proteomics. NASA Scientists and the NASA Space Biology Program have aimed to examine the fundamental building blocks of life (RNA, DNA and protein) in order to understand the response of living organisms to space and aid in fundamental research discoveries on Earth. In an effort to enable NASA funded science to be available to everyone, NASA has collected the data from omics studies and curated them in a data system called GeneLab. Whilst most college-level interns, academics and other scientists have had some interaction with omics data sets and analysis tools, high school students often have not. Therefore, the Space Biology Program is implementing a new Summer Program for high-school students that aims to inspire the next generation of scientists to learn about and get involved in space research using GeneLabs Data System. The program consists of three main components core learning modules, focused on developing students knowledge on the Space Biology Program and Space Biology research, Genelab and the data system, and previous research conducted on model organisms in space; networking and team work, enabling students to interact with guest lecturers from local universities and their fellow peers, and also enabling them to visit local universities and genomics centers around the Bay area; and finally an independent learning project, whereby students will be required to form small groups, analyze a dataset on the Genelab platform, generate a hypothesis and develop a research plan to test their hypothesis. This program will not only help inspire high-school students to become involved in space-based research but will also help them develop key critical thinking and bioinformatics skills required for most college degrees and furthermore, will enable them to establish networks with their peers and connections with university Professors that may help them achieve their educational goals.

genelab↗
NASA NTRSDate not supplied

Open Science for Life in Space: Data Sharing and Tools for Knowledge Discovery

The fast-growing array of space biological data, which in the past was simply archived after minimal analysis, holds great potential if it can be reorganized and formatted for Open Science. Organizing the data for such analysis is a challenge because of its diverse nature (molecular, cellular, tissue, whole organism, behavior; tabular, imagery). Open Science is the concept that the more people have access to scientifically curated data, the more knowledge will be gained. This led NASA to start the development of GeneLab in 2015. GeneLab houses spaceflight and space-analog multi-omics datasets from plant, rodent, small animal, and microbial experiments. The success and knowledge gained from GeneLab led to a new alliance of NASA “Open Science Data Repositories” (OSDR), which include the Ames Life Sciences Data Archive (ALSDA) and the NASA Biological Institutional Scientific Collection (NBISC). Both are adopting the GeneLab data system, so data are more findable, accessible, interoperable, and reusable (FAIR). OSDR systems provide users the ability to upload, download, search, share, analyze, and visualize. Open Science also needs strong confidence in the data, which is gained through building science communities. With ~400 current members, GeneLab and ALSDA formed Analysis Working Groups (AWGs) to provide feedback on processing pipelines, metadata curation standards (for ‘omics and phenotypic-physiological-behavioral assays), and to collaborate in effectively reusing data. The AWG also led to the development of the Radiation Biology Ontology (RBO), ensuring radiation metadata are efficiently captured, connected, and interoperable. Feedback from the AWG provided design input toward the new single point-of-entry data submission portal for all investigators to submit, curate, and share their research data. Space biological data is now maximally open access, collected-curated with rich metadata, and formatted for interoperability to enable systems biology, meta-analysis, knowledge graphs, machine learning, modeling, and other reuse approaches. With potential for further federation of OSDR for data mining with traditional biological and medical databases (NIH, NCI, EBI, etc.), a new era for space biology has begun to support the knowledge discovery necessary for Lunar and Martian missions.

Ryan T Scott↗
DOE OSTI2013

Genetic Algorithms and Classification Trees in Feature Discovery: Diabetes and the NHANES database

This paper presents a feature selection methodology that can be applied to datasets containing a mixture of continuous and categorical variables. Using a Genetic Algorithm (GA), this method explores a dataset and selects a small set of features relevant for the prediction of a binary (1/0) response. Binary classification trees and an objective function based on conditional probabilities are used to measure the fitness of a given subset of features. The method is applied to health data in order to find factors useful for the prediction of diabetes. Results show that our algorithm is capable of narrowing down the set of predictors to around 8 factors that can be validated using reputable medical and public health resources.

Heredia-Langner, Alejandro↗