Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data augmentation”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1982

The report of the Gravity Field Workshop

A Gravity Field Workshop was convened to review the actions which could be taken prior to a GRAVSAT mission to improve the Earth's gravity field model. This review focused on the potential improvements in the Earth's gravity field which could be obtained using the current satellite and surface gravity data base. In particular, actions to improve the quality of the gravity field determination through refined measurement corrections, selected data augmentation and a more accurate reprocessing of the data were considered. In addition, recommendations were formulated which define actions which NASA should take to develop the necessary theoretical and computation techniques for gravity model determination and to use these approaches to improve the accuracy of the Earth's gravity model.

Smith, D. E.↗
NASA NTRS1975

Comparison of model and flight test data for an augmented jet flap STOL research aircraft

Aerodynamic design data for the Augmented Jet Flap STOL Research Aircraft or commonly known as the Augmentor-Wing Jet-STOL Research Aircraft was based on results of tests carried out on a large scale research model in the NASA Ames 40- by 80-Foot Wind Tunnel. Since the model differs in some respects from the aircraft, precise correlation between tunnel and flight test is not expected, however the major areas of confidence derived from the wind tunnel tests are delineated, and for the most part, tunnel results compare favorably with flight experience. In some areas the model tests were known to be nonrepresentative so that a degree of uncertainty remained: these areas of greater uncertainty are identified, and discussed in the light of subsequent flight tests.

Cook, W. L.↗
NASA NTRS2010

HST WFC3 Early Release Science: Emission-Line Galaxies from IR Grism Observations

We present grism spectra of emission line galaxies (ELGs) from 0.6-1.6 microns from the Wide Field Camera 3 (WFC3) on the Hubble Space Telescope (HST). These new infrared grism data augment previous optical Advanced Camera for Surveys G800L (0.6-0.95 micron) grism data in GOODS South, extending the wavelength coverage well past the G800L red cutoff. The ERS grism field was observed at a depth of 2 orbits per grism, yielding spectra of hundreds of faint objects, a subset of which are presented here. ELGs are studied via the Ha, [O III ], and [OII] emission lines detected in the redshift ranges 0.2 less than or equal to z less than or equal to 1.6, 1.2 less than or equal to z less than or equal to 2.4 and 2.0 less than or equal to z less than or equal to 3.6 respectively in the G102 (0.8-1.1 microns; R approximately 210) and C141 (1.1-1.6 microns; R approximately 130) grisms. The higher spectral resolution afforded by the WFC3 grisms also reveals emission lines not detectable with the G800L grism (e.g., [S II] and [S III] lines). From these relatively shallow observations, line luminosities, star formation rates, and grism spectroscopic redshifts are determined for a total of 25 ELGs to M(sub AB)(F098M) approximately 25 mag. The faintest source in our sample with a strong but unidentified emission line--is MAB(F098M)=26.9 mag. We also detect the expected trend of lower specific star formation rates for the highest mass galaxies in the sample, indicative of downsizing and discovered previously from large surveys. These results demonstrate the remarkable efficiency and capability of the WFC3 NIR grisms for measuring galaxy properties to faint magnitudes.

Straughn, A. N.↗
NASA NTRS2021

CIF Report - Information Fusion and Data Analytics for Human Lunar Exploration

This project leverages the Concept Exploration Laboratory (CEL) to collect, warehouse, and augment data relevant to human lunar exploration as a platform for NA (S&MA) to develop operational data integration techniques. The project capitalizes on 16+ years of CEL experience applied to NASA, DoD, the City of Houston, the State of Texas, and private industry. The integrated data will be utilized in the two scenarios described in a definition of concept for development of a full scale data analysis suite and storage solution, useful to all JSC organizations engaged in real time operations and safety tasks, and may be useful as pathfinders for the Digital Transformation Program.

information fusion↗
DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗
DOE OSTI2025

2025 TEM Workshop

The TEM Data Management Workshop will take place on August 26 from 9 a.m. to 12 p.m. MT, and will be held virtually on TEAMS. The primary goal of this workshop is to engage NSUF users and stakeholders in discussions about the data needs for the utilization of AI and ML in the analysis of TEM data. Key topics to be covered include data storage, data sharing, data tagging, metadata inclusion, standardized data formats, data augmentation, and annotated training datasets. Additionally, the workshop will provide valuable insights into resources such as the Nuclear Research Data System (NRDS) for data storage and sharing, as well as open-source codes for data analysis.

Bachhav, Mukesh↗
NASA NTRS1992

Detecting change as it occurs

Traditionally climate changes have been detected from long series of observations and long after they have happened. Our 'inverse sequential' procedure, for detecting change as soon as it occurs, describes the existing or most recent data by their frequency distribution. Its parameter(s) are estimated both from the existing set of observations and from the same set augmented by 1,2,....j new observations. Individual-value probability products ('likelihoods') are used to form ratios which yield two probabilities for erroneously accepting the existing parameter(s) as valid for the augmented data set, and vice versa. A genuine parameter change is signaled when these probabilities (or a more stable compound probability) show a progressive decrease. New parameter values can then be estimated from the new observations alone using standard statistical techniques. The inverse sequential procedure will be illustrated for global annual mean temperatures (assumed normally distributed), and for annual numbers of North Atlantic hurricanes (assumed to represent Poisson distributions). The procedure was developed, but not yet tested, for linear or exponential trends, and for chi-squared means or degrees of freedom, a special measure of autocorrelation.

Radok, Uwe↗
DOE OSTI2026

Transplatformer: translating toxicogenomic profiles between generations of platforms

Background Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources. Results We present TransPlatformer a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. TransPlatformer employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, TransPlatformer achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation ( ≈ 0.71 vs. 0.37) relative to baseline methods. Importantly, TransPlatformer preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra Conclusions TransPlatformer provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Roadmap for transforming heterogeneous catalysis with artificial intelligence

Artificial intelligence (AI) is poised to transform heterogeneous catalysis, opening avenues for catalytic materials discovery. By uncovering intricate patterns in high-dimensional data, AI has been reshaping our pursuit of sustainable catalytic processes across the energy, environmental and chemical sectors. This promise, however, hinges on overcoming fundamental barriers, including limitations in data availability and quality, challenges in the generalizability and interpretability of data-augmented decisions, and the persistent gap between in silico predictions and experiments. Furthermore, we outline a forward-looking roadmap for deeply integrating AI into heterogeneous catalysis with an AI-ready data ecosystem, multimodal foundation models, and ultimately autonomous laboratories to accelerate the development of next-generation catalytic technologies via AI-empowered human–machine collaboration.

Computational methods↗
NASA NTRS2020

Names Don't Fly: Smart Filters for Profanity Detection and Classification in User-Generated Content

Generally, names associate with a person’s identity. But what if in the pretext of a legitimate name and given the opportunity, users of software provide names to online web forms that carry along offensive language, slurs, and other profanity that is then sent to Mars ? The answer is simple: they don’t fly. In this paper,we perform model explorations to detect and classify inappropriate content in the names submitted from people across the world to ‘Send Your Names to MARS’ public engagement campaign.We propose a novel pipeline approach, that can effectively overcome the issues of lack of negative samples, noisy labels by gathering expert knowledge over time with human(s) in the loop and data augmentation, and achieve high accuracy in classifying inappropriate names with very little or no context. We describe cloud-based infrastructure to deploy our application and run predictions on large-scale data through our pipeline and achieve significant speedup over offline processes, with enhanced reliability and security.

Soderstrom, Tomas↗
NASA NTRS2016

Hybrid Reality Lab Capabilities - Video 2

Our Hybrid Reality and Advanced Operations Lab is developing incredibly realistic and immersive systems that could be used to provide training, support engineering analysis, and augment data collection for various human performance metrics at NASA. To get a better understanding of what Hybrid Reality is, let's go through the two most commonly known types of immersive realities: Virtual Reality, and Augmented Reality. Virtual Reality creates immersive scenes that are completely made up of digital information. This technology has been used to train astronauts at NASA, used during teleoperation of remote assets (arms, rovers, robots, etc.) and other activities. One challenge with Virtual Reality is that if you are using it for real time-applications (like landing an airplane) then the information used to create the virtual scenes can be old (i.e. visualized long after physical objects moved in the scene) and not accurate enough to land the airplane safely. This is where Augmented Reality comes in. Augmented Reality takes real-time environment information (from a camera, or see through window, and places digitally created information into the scene so that it matches with the video/glass information). Augmented Reality enhances real environment information collected with a live sensor or viewport (e.g. camera, window, etc.) with the information-rich visualization provided by Virtual Reality. Hybrid Reality takes Augmented Reality even further, by creating a higher level of immersion where interactivity can take place. Hybrid Reality takes Virtual Reality objects and a trackable, physical representation of those objects, places them in the same coordinate system, and allows people to interact with both objects' representations (virtual and physical) simultaneously. After a short period of adjustment, the individuals begin to interact with all the objects in the scene as if they were real-life objects. The ability to physically touch and interact with digitally created objects that have the same shape, size, location to their physical object counterpart in virtual reality environment can be a game changer when it comes to training, planning, engineering analysis, science, entertainment, etc. Our Project is developing such capabilities for various types of environments. The video outlined with this abstract is a representation of an ISS Hybrid Reality experience. In the video you can see various Hybrid Reality elements that provide immersion beyond just standard Virtual Reality or Augmented Reality.

Delgado, Francisco J.↗
DOE OSTI2026

Data‐Efficient Generation of Synthetic Microstructures of Polymer‐Bonded Energetic Material With Fine‐Tuned Stable Diffusion

Among current deep learning approaches for synthetic image generation, diffusion-based models stand out in terms of algorithmic stability and ability to retain high-fidelity image features with detailed resolution. Here, in this work, we employ Dreambooth, a method for fine-tuning Stable Diffusion, on X-ray CT images of microstructure of the polymer-bonded form (PBX) of a commonly used high explosive, Pentaerythritol tetranitrate (PETN), which yields generative models for creating synthetic PBX images. The models developed here represent five classes (or ‘lots’) of microstructures and demonstrate successful generation of images of each class with high fidelity, as verified by computed classification accuracy of ∼ 94% or higher. Data augmentation afforded by such image synthesis can be used to more reliably decipher underlying statistics, build processing-structure correlations, recognize off-normal structural anomalies, and identify age-related changes. Ideas related to converting image data into appropriate density mapping and performing mesoscale simulation or surrogate modeling of detonation are also discussed.

Dreambooth↗
NASA NTRSDate not supplied

Developing Natural Language Processing and Supervised Learning Techniques to Classify Mars Tasks

As NASA's Human Research Program (HRP) prepares for long-duration Mars missions, understanding astronaut tasks is crucial. This study, conducted at NASA Glenn Research Center (GRC), employed Natural Language Processing (NLP) and machine learning techniques to analyze and classify Mars tasks. A list of 1,058 Mars tasks was provided by HRP experts including binary labeling of 18 Human System Task Categories (HSTCs). We developed an NLP model using Google's BERT language model to capture the semantic and syntactic nuances of these tasks. Supervised training was initially applied to a subset of the NLP-analyzed tasks to assess the model's effectiveness in classifying the remaining tasks. Incorporating HSTC descriptions significantly enhanced the classification accuracy for 9 out of the 18 HSTCs and reduced training time. To address the issue of severe class imbalance in the HSTC data, we introduced innovative weighting and sampling techniques for data augmentation. We then fine-tune BERT to implement a pairwise relatedness scoring method, allowing us to cluster tasks based on their relatedness and similarity, getting a step closer to labeling the tasks without supervision. In this presentation we guide you through data preprocessing, deciphering key syntax components using BERT, and performing supervised classification of the Mars tasks. This work showcases the potential use of advanced NLP techniques to analyze Mars missions to be incorporated into various crew health and performance analyses.

GenAI↗
DOE OSTI2025

Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model's foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research.

Generative Adversarial Networks↗
DOE OSTI2025

Sparse-Data Deep Learning Strategies for Radiographic Non-Destructive Testing

Radiography is an imaging technique used in a variety of applications, such as medical diagnosis, airport security, and nondestructive testing. We present a deep learning system for extracting information from radiographic images. We perform various prediction tasks using our system, including material classification and regression on the dimensions of a given object that is being radiographed. Our system is designed to address the sparse-data issue for radiographic nondestructive testing applications. It uses a radiographic simulation tool for synthetic data augmentation, and it uses transfer learning with a pre-trained convolutional neural network model. Using this system, our preliminary results indicate that the object geometry regression task saw an improvement of 70% in the R-squared value when using a multi-regime model. In addition, we increase the performance of the object material classification tasks by utilizing data from different imaging systems. In particular, using neutron imaging improved the material classification accuracy by 20% when compared to x-ray imaging.

convolutional neural networks↗
DOE OSTI2026

Benchmarking the performance of uncertainty quantification methods for neural network-based interatomic potentials

Machine-learned interatomic potentials (ML-IAPs) continue to gain popularity as accurate, computationally efficient replacements for traditional, physics-based interatomic potentials and expensive ab initio methods. Uncertainty quantification (UQ) of ML-IAPs is a growing area of research as UQ is critical in many applications of IAPs, such as developing curated datasets, active learning-based data augmentation, self-improving models, and estimating the uncertainty of molecular dynamics simulations. In this paper, we construct and benchmark a series of different neural network potentials (NNPs) with varying network architectures to determine the performance of these models with respect to both the mean and uncertainty calibration error. Each NNP method is specifically designed to predict either epistemic or aleatoric uncertainty with particular focus on the differences in behavior between the epistemic and aleatoric uncertainty estimates. We benchmark these methods using multiple datasets common in the ML-IAP literature. The results show that the aleatoric uncertainty from single-shot model architectures is a competitive alternative to ensemble-based epistemic uncertainty predictions in regions of sufficient data-density. However, in regions where the representative data is sparse, aleatoric uncertainty models tend to overpredict and epistemic methods tend to underpredict the actual model error. We conclude that the type of UQ is crucial when discussing performance of probabilistic model results as different methods have different performance characteristics depending on the regime in which they are evaluated. Therefore, the type of UQ method should be carefully evaluated against both the data characteristics and requirements for the intended application.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
DOE OSTI2025

Quantum adversarial learning for kernel methods

We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defense strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗