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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Citation network datasets for benchmarking spiking graph neural networks on experimental neuromorphic hardware

Spiking neural networks (SNNs) running on neuromorphic computers offer an energy-efficient alternative for AI tasks. Recently, spiking graph neural networks (S-GNNs) have been shown to produce encouraging results on benchmark citation network datasets such as Cora, CiteSeer, and PubMed for node classification tasks. These S-GNNs were run on SNN simulators only because they contain up to tens of thousands of neurons and up to millions of synapses, translating poorly to neuromorphic hardware. Therefore, in this paper, we create a suite of benchmark datasets from the CiteSeer dataset that can be accommodated on current neuromorphic hardware platforms. Our contribution consists of a collection of three datasets. First, we have an induced subgraph of CiteSeer, which we call MiniSeer, containing 2110 papers, 3604 binary features, and 6 topics. Second, MicroSeer is a very small dataset consisting of 84 papers, 1227 features, and 6 topics. Lastly, BiteSeer is a collection of 15 binary classification datasets. We present creation of these datasets along with accuracies, running times, and spike counts when simulated. We believe that our results in this paper will be used by the neuromorphic community to benchmark, test, and develop neuromorphic hardware and simulators.

Zhu, Kevin [George Mason University, Virginia]↗
DOE OSTI2025

Antiviral discovery using sparse datasets by integrating experiments, molecular simulations, and machine learning

Computational methods have demonstrated success in identifying virucidal agents, effectively contributing to the discovery of novel virucidal molecules. In this study, we developed a machine learning (ML) model, trained on a small dataset, to predict inhibitors of human enterovirus 71 (EV71), a pathological agent that causes severe disease in children and immunocompromised adults. Despite the dataset’s limitation, comprising of only 36 compounds tested, our ML framework demonstrated significant predictive capability. Notably, experimental validation revealed that five out of the eight compounds predicted by our model from the Chinese cosmetic material list exhibited virucidal activity. The inhibitor effects displayed by the main active compounds were further confirmed by molecular dynamics simulation. This underscores the potential of our AI-driven approach to bypass data constraints in identifying active molecules against viral pathogens.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Deep active learning for classifying cancer pathology reports

Abstract Background Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. Results We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. Conclusions Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Scalable and efficient learning from crowds with Gaussian processes

Over the last few years, multiply-annotated data has become a very popular source of information. Online platforms such as Amazon Mechanical Turk have revolutionized the labelling process needed for any classification task, sharing the effort between a number of annotators (instead of the classical single expert). This crowdsourcing approach has introduced new challenging problems, such as handling disagreements on the annotated samples or combining the unknown expertise of the annotators. Probabilistic methods, such as Gaussian Processes (GP), have proven successful to model this new crowdsourcing scenario. However, GPs do not scale up well with the training set size, which makes them prohibitive for medium-to-large datasets (beyond 10K training instances). This constitutes a serious limitation for current real-world applications. In this work, we introduce two scalable and efficient GP-based crowdsourcing methods that allow for processing previously-prohibitive datasets. The first one is an efficient and fast approximation to GP with squared exponential (SE) kernel. The second allows for learning a more flexible kernel at the expense of a heavier training (but still scalable to large datasets). Since the latter is not a GP-SE approximation, it can be also considered as a whole new scalable and efficient crowdsourcing method, useful for any dataset size. Both methods use Fourier features and variational inference, can predict the class of new samples, and estimate the expertise of the involved annotators. A complete experimentation compares them with state-of-the-art probabilistic approaches in synthetic and real crowdsourcing datasets of different sizes. Finally, they stand out as the best performing approach for large scale problems. Moreover, the second method is competitive with the current state-of-the-art for small datasets.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2023

Large-scale analysis of structural brain asymmetries in schizophrenia via the ENIGMA consortium

Left–right asymmetry is an important organizing feature of the healthy brain that may be altered in schizophrenia, but most studies have used relatively small samples and heterogeneous approaches, resulting in equivocal findings. We carried out the largest case–control study of structural brain asymmetries in schizophrenia, with MRI data from 5,080 affected individuals and 6,015 controls across 46 datasets, using a single image analysis protocol. Asymmetry indexes were calculated for global and regional cortical thickness, surface area, and subcortical volume measures. Differences of asymmetry were calculated between affected individuals and controls per dataset, and effect sizes were meta-analyzed across datasets. Small average case–control differences were observed for thickness asymmetries of the rostral anterior cingulate and the middle temporal gyrus, both driven by thinner left-hemispheric cortices in schizophrenia. Analyses of these asymmetries with respect to the use of antipsychotic medication and other clinical variables did not show any significant associations. Assessment of age- and sex-specific effects revealed a stronger average leftward asymmetry of pallidum volume between older cases and controls. Case–control differences in a multivariate context were assessed in a subset of the data (N = 2,029), which revealed that 7% of the variance across all structural asymmetries was explained by case–control status. Subtle case–control differences of brain macrostructural asymmetry may reflect differences at the molecular, cytoarchitectonic, or circuit levels that have functional relevance for the disorder. Reduced left middle temporal cortical thickness is consistent with altered left-hemisphere language network organization in schizophrenia.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Foundation models for atomistic simulation of chemistry and materials

Conventional computational methods for modeling chemical and materials systems are limited by system size and timescale, forcing a trade-off between quantum-mechanical accuracy and the sampling needed for realistic observables. Large language and vision foundation models — pre-trained on massive datasets using transformer architectures — have revolutionized many fields. It is thus interesting to ask whether a foundation model — subject to suitable data, parameter scaling and training — could enable learned simulations of chemistry and materials. Here, in this study, we review the field of machine-learned interatomic potentials (MLIPs) and posit that scaling up large and diverse chemical and materials datasets and highly expressive architectures using advanced training strategies should result in models that are: more efficient, transferable, robust to out-of-distribution scenarios, and easier to fine-tune to a variety of downstream physical observables than models trained from scratch on small datasets corresponding to specific, targeted atomistic simulation tasks. We provide specific criteria for creating such large-scale MLIP foundation models, coordinated strategies for their development, evaluation and deployment, and highlight potential emergent capabilities that could transform predictive simulations in chemistry and materials science and accelerate discovery across multiple technological domains.

Yuan, Eric C.-Y. [University of California, Berkel↗
DOE OSTI2025

Predicting the von Neumann entanglement entropy using a graph neural network

Calculating the von Neumann entanglement entropy from experimental data is challenging due to its dependence on the complete wavefunction, forcing reliance on approximations such as classical mutual information (MI). We propose a machine learning approach using a graph neural network to predict the von Neumann entropy directly from experimentally accessible bitstrings. We test this approach on a Rydberg ladder system and achieve a mean absolute error of $3.6\,\times 10^{-3}$ when evaluating within the training range on a dataset with entropy values ranging from 0 to 1.9. The model achieves a mean absolute percentage error of 1.44% and outperforms MI-based bounds. When tested beyond the training range, the model maintains reasonable accuracy. Furthermore, we demonstrate that fine-tuning the model with small datasets significantly improves performance on data outside the original training range.

graph neural networks↗
DOE OSTI2024

Enhancing Electron Microscopy Image Classification Using Data Augmentation

Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep learning applications are scarce and limited. While data augmentation techniques have shown promise for extending image datasets, very little work has been done to understand the impact of combining multiple augmentation methods sequentially or the limits of their effectiveness when combined. Our work addresses this gap by examining how standard and combinatorial data augmentation affects the performance of machine learning models when trained on small datasets for label classification tasks. For our analysis, we generate single, double and quadruple-augmented datasets for a microscopy image classification task using six standard augmentation methods, and compare the resultant improvements observed in binary classification accuracy with three standard image classification models (DenseNet169, MobileNetV2, ResNet101V2). Our experiments show a non-monotonic relationship between the number of simultaneous augmentation methods and classification accuracy, indicating that there is a trade-off between the degree of augmentation and the model performance. These findings suggest that the optimal number of augmentation methods will vary by domain and use case. We also find that the order in which augmentation methods are applied to a limited dataset matters when combining augmentation schemes, with our use case showing performance differences up to 2.6% when the augmentation order is reversed for double-augmented datasets. Our work offers insights to the limits of data augmentation when working on image classification tasks with limited datasets.

Welsman, Jordan A↗
DOE OSTI2024

Exploring electron-beam induced modifications of materials with machine-learning assisted high temporal resolution electron microscopy

Directed atomic fabrication using an aberration-corrected scanning transmission electron microscope (STEM) opens new pathways for atomic engineering of functional materials. In this approach, the electron beam is used to actively alter the atomic structure through electron beam induced irradiation processes. One of the impediments that has limited widespread use thus far has been the ability to understand the fundamental mechanisms of atomic transformation pathways at high spatiotemporal resolution. Here, we develop a workflow for obtaining and analyzing high-speed spiral scan STEM data, up to 100 fps, to track the atomic fabrication process during nanopore milling in monolayer MoS 2 . An automated feedback-controlled electron beam positioning system combined with deep convolution neural network (DCNN) was used to decipher fast but low signal-to-noise datasets and classify time-resolved atom positions and nature of their evolving atomic defect configurations. Through this automated decoding, the initial atomic disordering and reordering processes leading to nanopore formation was able to be studied across various timescales. Using these experimental workflows a greater degree of speed and information can be extracted from small datasets without compromising spatial resolution. This approach can be adapted to other 2D materials systems to gain further insights into the defect formation necessary to inform future automated fabrication techniques utilizing the STEM electron beam.

36 MATERIALS SCIENCE↗
NASA NTRS2018

Augmented Reality Data Generation for Training Deep Learning Neural Network

One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a highquality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.

Torres, Gil↗
DOE OSTI2021

EpitopeVec: linear epitope prediction using deep protein sequence embeddings

Motivation: B-cell epitopes (BCEs) play a pivotal role in the development of peptide vaccines, immuno-diagnostic reagents and antibody production, and thus in infectious disease prevention and diagnostics in general. Experimental methods used to determine BCEs are costly and time-consuming. Therefore, it is essential to develop computational methods for the rapid identification of BCEs. Although several computational methods have been developed for this task, generalizability is still a major concern, where cross-testing of the classifiers trained and tested on different datasets has revealed accuracies of 51–53%. Results: We describe a new method called EpitopeVec, which uses a combination of residue properties, modified antigenicity scales, and protein language model-based representations (protein vectors) as features of peptides for linear BCE predictions. Extensive benchmarking of EpitopeVec and other state-of-the-art methods for linear BCE prediction on several large and small datasets, as well as cross-testing, demonstrated an improvement in the performance of EpitopeVec over other methods in terms of accuracy and area under the curve. As the predictive performance depended on the species origin of the respective antigens (viral, bacterial and eukaryotic), we also trained our method on a large viral dataset to create a dedicated linear viral BCE predictor with improved cross-testing performance.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Paw-Net: Stacking ensemble deep learning for segmenting scanning electron microscopy images of fine-grained shale samples

Segmentation of scanning electron microscopy (SEM) images is critical yet time-consuming for geological analyses, as it needs to differentiate the boundaries for different mineral objects to facilitate subsequent analyses, such as porosity calculation. Recently, various machine learning methods, especially convolutional neural networks (CNNs), have been explored to segment SEM images of fine-grained shale samples. However, we found that general CNNs do not yield optimal performance due to insufficient training data and imbalanced objects in SEM images. This work has revised the U-Net architecture, a popular approach for biomedical image analyses, by incorporating a loss function that addresses the imbalance issue. Furthermore, we used the ensemble learning method to train multiple models and combined the results to improve the overall performance of segmentation. We prepared 2162 sub-images from raw SEM images in our experiments and divided them into training, validation, and testing datasets. The overall results show that our method improves the average Intersection over Union (IOU) of mineral objects from 0.49 to 0.58, compared to the original U-Net model. Our method can clearly distinguish each object from others with boundaries, even in highly imbalanced images. Training our models takes less than three minutes using a single GPU, while manual labeling can take up to three hours for each image. Furthermore, the method helps geoscientists gain insights quickly and effectively by building neural network models from a small dataset of SEM images.

58 GEOSCIENCES↗
NASA NTRSDate not supplied

Developing and Testing a Physics Guided Machine Learning NeuralNetwork to Predict Tonal Noise Emitted by a Propeller

Artificial neural networks offer a highly nonlinear and adaptive model for predicting complex interactions between input-output parameters. However, these networks require large datasets which often exceed practical considerations in modeling experimental results. To alleviate the dataset size requirement, a method known as physics guided machine learning has been applied to construct several neural networks for predicting propeller tonal noise in the time domain over a broad range of flight conditions. Three space-filling designs, namely, Latin-Hypercube, Sphere-Packing, and Grid-Space, were used to distribute points throughout the input parameter space encompassing nondimensional flight conditions and observer geometry. Each neural network’s performance was validated by conditions outside of the training set and compared to the Propeller Analysis System tool from the NASA Aircraft Noise Prediction Program. Compared to the Grid-Space input design, the Latin-Hypercube and the Sphere-Packing designs provided a better representation of the domain for training. Regarding the network archetype, a fully connected perceptron was found to outperform the partially connected perceptron in their ability to predict tonal noise for small datasets. The black-box nature of these neural networks was also explored to understand how the networks constructed the waveform and understand why some network designs produce better models.

Propeller noise↗
DOE OSTI2024

Interpretable Machine Learning Models for Practical Antimonate Electrocatalyst Performance

Computationally predicting the performance of catalysts under reaction conditions is a challenging task due to the complexity of catalytic surfaces and their evolution in situ, different reaction paths, and the presence of solid-liquid interfaces in the case of electrochemistry. We demonstrate here how relatively simple machine learning models can be found that enable prediction of experimentally observed onset potentials. Inputs to our model are comprised of data from the oxygen reduction reaction on non-precious transition-metal antimony oxide nanoparticulate catalysts with a combination of experimental conditions and computationally affordable bulk atomic and electronic structural descriptors from density functional theory simulations. From human-interpretable genetic programming models, we identify key experimental descriptors and key supplemental bulk electronic and atomic structural descriptors that govern trends in onset potentials for these oxides and deduce how these descriptors should be tuned to increase onset potentials. Here, we finally validate these machine learning predictions by experimentally confirming that scandium as a dopant in nickel antimony oxide leads to a desired onset potential increase. Macroscopic experimental factors are found to be crucially important descriptors to be considered for models of catalytic performance, highlighting the important role machine learning can play here even in the presence of small datasets.

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

The soil health assessment protocol and evaluation applied to soil organic carbon

The concept of soil health has evolved over the past several decades, recognizing that dynamic soil property response to management and land use is highly dependent on site-specific factors that must be considered when interpreting soil health measurements. Initially, the Soil Management Assessment Framework (SMAF) and Comprehensive Assessment of Soil Health (CASH) were developed and used globally for scoring soil health indicators. However, both SMAF and CASH frameworks were developed using a relatively small dataset and their interpretation curves were not validated at the nationwide scale. Expanding upon these concepts, we propose the Soil Health Assessment Protocol and Evaluation (SHAPE) tool. The SHAPE was developed using 14,680 soil organic C (SOC) observations from across the United States, and accounts for edaphic and climate factors at the continental scale. Data were compiled from the literature, the Cornell Soil Health Laboratory, and the Kellogg Soil Survey Laboratory. In this approach, scoring curves are Bayesian model-based estimates of the conditional cumulative distribution function (CDF) for defined soil peer groups reflecting five soil texture and five soil suborder classes adjusted for mean annual temperature and precipitation. Specifically, SHAPE produces scores between 0 and 1 (0–100%) for measured SOC values that reflect the quantile or position within the conditional CDF along with measures of uncertainty. Herein, we focus on development of the SHAPE scoring curve for SOC with our case studies. SHAPE is a flexible, quantitative tool that provides a regionally relevant interpretation of this key soil health indicator.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Analysis of phase stability and chemical segregation in the Mo-V alloys using a generalized embedded atom method potential

A new interatomic potential for the Mo-V system is introduced to facilitate the study of phase stability and mechanical properties at lower temperatures. This potential is based on a generalization of the embedded atom method and includes contributions from embedding energy, explicit two- and three-body interactions and nonlocal many-body interaction terms. The parameters of the potential are optimized by using data from ab initio density functional theory (DFT) calculations. The potential is rigorously validated across a range of physical properties, such as elastic constants, equation of states, phonon dispersion curves, point defect properties and melting temperatures for different compositions. Even though our potential is trained on a small dataset, its accuracy is comparable to available machine learning potentials for Mo and V. Furthermore, our results show that an ordered B2 phase is stable at low temperatures in alloys containing 50% V, but the solid solution phase is stable above 800 K. However, such long-range ordering is not observed in V-rich or Mo-rich alloys. In addition, our results show that V segregates to dislocation cores and grain boundaries.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Development of an interatomic potential for the Ta–Li system

A new interatomic potential for the Ta–Li system is introduced to facilitate the study of phase stability, mechanical properties and non-equilibrium dynamics after Li implantation in Ta. Here, this potential is based on a generalization of the embedded atom method (GEAM) and includes contributions from embedding energy, explicit two- and three-body interactions, and nonlocal many-body interaction terms. The parameters of the potential are optimized using energies and atomic forces for a wide range of configurations obtained from ab initio density functional theory (DFT) calculations. The potential is rigorously validated across a range of physical properties, including elastic constants, equations of state, phonon dispersion curves, point defect properties, and melting temperatures for different compositions. Although our potential is trained on a small dataset, its accuracy is comparable to that of available machine learning potentials for Li and Ta. Our simulations show that at temperatures below 500 K, Li atoms in Ta–Li alloys form clusters separated by Ta-rich domains, and we find no evidence of ordered phase formation. For Li concentrations below a few percent, Li atoms preferentially segregate to surfaces and grain boundaries. However, in alloys containing more than ~10% Li, the accumulation of Li in symmetric-tilt grain boundaries can lead to one of the following effects: formation of amorphous-like regions, changes in grain boundary structural units, or lateral movement of the grain boundary.

GEAM potential↗
DOE OSTI2023

Neural networks for parameter estimation in intractable models

The goal is to use deep learning models to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible. For instance, inference for max-stable processes is exceptionally challenging even with small datasets, but simulation is straightforward. Data from model simulations are used to train deep neural networks and learn statistical parameters from max-stable models. The proposed neural network-based method provides a competitive alternative to current approaches, as demonstrated by considerable accuracy and computational time improvements. Finally, it serves as a proof of concept for deep learning in statistical parameter estimation and can be extended to other estimation problems.

97 MATHEMATICS AND COMPUTING↗