Search NASA⌕ Search

SEARCH · Search NASA

Results for “Labeled Datasets”

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 271 records · Page 15

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗

(NOICE) Neural Optical Image Categorizer for the E-log

The Fermilab Accelerator Division Electronic logbook (E-log) is a record of all the activities and events in the Division for the past 10 years and more. The E-log search function is a valuable resource and the institutional memory of the accelerator complex. About 300,000 files are stored in the E-log, of which the vast majority are images attached to entries and comments. The visual information contained in the images is not presently searchable. The goal of team NOICE (Neural Optical Image Categorizer for the E-log) was to design a neural network able to produce label categories for these images for use by searches. The group developed a dataset and trained a convolutional neural network (CNN) with optimized hyperparameter

43 PARTICLE ACCELERATORS↗

Microstructure Segmentation with Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset

This study examined the improvement of microscopy segmentation accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures, including VGG, Inception, and ResNet, were trained on over 100,000 labelled microscopy images from 54 classes. These pre-trained encoders were then embedded into multiple segmentation architectures including U-Net and DeepLabV3+ to evaluate segmentation performance on newly created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2 percent reduction in relative segmentation error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.

machine learning↗

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗

Identifying atmospheric rivers and their poleward latent heat transport with generalizable neural networks: ARCNNv1

Abstract. Atmospheric rivers (ARs) are extreme weather events that can alleviate drought or cause billions of US dollars in flood damage. By transporting significant amounts of latent energy towards the poles, they are crucial to maintaining the climate system's energy balance. Since there is no first-principle definition of an AR grounded in geophysical fluid mechanics, AR identification is currently performed by a multitude of expert-defined, threshold-based algorithms. The variety of AR detection algorithms has introduced uncertainty into the study of ARs, and the thresholds of the algorithms may not generalize to new climate datasets and resolutions. We train convolutional neural networks (CNNs) to detect ARs while representing this uncertainty; we name these models ARCNNs. To detect ARs without requiring new labeled data and labor-intensive AR detection campaigns, we present a semi-supervised learning framework based on image style transfer. This framework generalizes ARCNNs across climate datasets and input fields. Using idealized and realistic numerical models, together with observations, we assess the performance of the ARCNNs. We test the ARCNNs in an idealized simulation of a shallow-water fluid in which nearly all the tracer transport can be attributed to AR-like filamentary structures. In reanalysis and a high-resolution climate model, we use ARCNNs to calculate the contribution of ARs to meridional latent heat transport, and we demonstrate that this quantity varies considerably due to AR detection uncertainty.

54 ENVIRONMENTAL SCIENCES↗

Machine Learning Approaches to Predicting Induced Seismicity and Imaging Geothermal Reservoir Properties

This project developed machine learning (ML) methods, lab data sets, and field data to advance geothermal exploration and geothermal energy production. The work had three focus areas. One involved the development of ML methods to use microearthquakes (MEQs) for imaging geothermal reservoir properties and improving subsurface characterization – most importantly the evolution of permeability within the evolving reservoir. This part of the work included development of ML approaches for automated MEQ location, focal mechanism determination and identification of earthquake precursors. The second area focused on using MEQ signals generated by geothermal exploration and production to predict the relationship between fluid injection and seismicity. Here, we extended to reservoir scale our success in using ML to predict laboratory earthquakes and fault zone stress state. The third focus area was on lab experiments. Here, we developed new ML models for lab earthquake prediction and identification of precursors to failure to improve earthquake forecasting and early warning in geothermal settings. Major outcomes of our work include ML models that learn from MEQ signals during geothermal exploration and production to predict induced seismicity. MEQs occur naturally in connection with drilling and energy production. We developed ML methods to use the seismic waves from these events to characterize the elastic, hydraulic and poromechanical properties of reservoirs. Our work illuminated fracture geometry and the evolution of fracture permeability by incorporating seismic coda wave analysis and ML methods to relate fluid injection and seismicity. We significantly expanded laboratory earthquake prediction to include methods that use both passive measurements of microearthquakes within the lab fault zones and also active source acoustic measurements of fault zone elastic properties. These methods can now predict fault zone stress state, time to failure and the magnitude of lab earthquakes. Our work showed that repetitive stick- slip failure events during frictional sliding (the lab equivalent of earthquakes) are preceded by a cascade of micro-failure events that radiate energy in a manner that foretells unstable failure – manifest as laboratory MEQs. We documented a mapping between fracture properties and statistical attributes of elastic radiation. We extended existing works to geothermal reservoir scale and developed ML methods to determine reservoir permeability, fracture properties, and their evolution during geothermal energy production. An attractive feature of ML algorithms is their ability to handle big datasets and reveal patterns and correlations that may remain invisible to conventional analyses. Our work connected data from field, laboratory and intermediate scales to study permeability, stress, strength, fracture stiffness and geometry. At the field scale we used data from the Newberry Volcano field site, UtahFORGE, EGS Collab, and also the Bedretto underground research lab in Switzerland. These data sets are bridging the gap between the lab scale, theory, and reservoir scale. Our work produced plain language summaries to improve public understanding of DOE research. We also developed openly distributed ML and seismicity datasets for use by all researchers and we published connections between induced seismicity in geothermal areas and reservoir properties including permeability, fracture properties, and stress state. Our models are designed for the large data sets of induced seismicity typically associated with geothermal sites. We produced labeled event catalogs and used them on geothermal data to assess how ML can facilitate geothermal production and exploration. All datasets are available on the GDR Productivity: The project produced 32 publications in peer reviewed journals (two are in review). It supported the work of 6 PhD students, 40 conference presentations, 6 keynote talks at national meetings, and mentoring and professional development for 4 postdoctoral fellows.

15 GEOTHERMAL ENERGY↗

Automated segmentation of soft X-ray tomography: Native cellular structure with submicron resolution at high-throughput for whole-cell quantitative imaging in yeast

Soft X-ray tomography (SXT) is an invaluable tool for quantitatively analyzing cellular structures at suboptical isotropic resolution. However, it has traditionally depended on manual segmentation, limiting its scalability for large datasets. Here, we leverage a deep learning-based autosegmentation pipeline to segment and label cellular structures in hundreds of cells across three Saccharomyces cerevisiae strains. This task-based pipeline uses manual iterative refinement to improve segmentation accuracy for key structures, including the cell body, nucleus, vacuole, and lipid droplets, enabling high-throughput and precise phenotypic analysis. Using this approach, we quantitatively compared the three-dimensional (3D) whole-cell morphometric characteristics of wild-type, VPH1-GFP, and vac14 strains, uncovering detailed strain-specific cell and organelle size and shape variations. We show the utility of SXT data for precise 3D curvature analysis of entire organelles and cells and detection of fine morphological features using surface meshes. Our approach facilitates comparative analyses with high spatial precision and statistical throughput, uncovering subtle morphological features at the single-cell and population level. This workflow significantly enhances our ability to characterize cell anatomy and supports scalable studies on the mesoscale, with applications in investigating cellular architecture, organelle biology, and genetic research across diverse biological contexts.

Chen, Jianhua [Lawrence Berkeley National Laborato↗

HangulFonts v1.0.0

The software creates the Hangul Fonts data set.The Hangul Fonts Datasets consists of all possible blocks for each font along with a set of labels and features for each block which are common across all fonts. We provide scripts to render each block and font into an image and store them together in an HDF5 file for each font and fontsize specified. Each font has 11,172 possible blocks and we have curated 35 fonts for a total of 391,020 possible images. The spoken consonants and vowel correspond to a set of "initial", "medial", and "final" labels for each block with 19, 21, and 28 classes respectively. In addition, each block can also be assigned a hierarchy label based on the block geometry. Finally, the individual glyphs (atoms) are composed across the initial, medial, and final locations along with potential scalings, translations, or rotations. These features of the data set make it uniquely positioned in the deep representation learning field because of its compositionally and hierarchical organization, while retaining diverse types of variation in the realizations.

Bouchard, Kristofer↗

A Cloud Detection Neural Network for Above-Aircraft Clouds Using Airborne Cameras

We introduce a method convolutional neural networks to detect the presence of clouds in airborne camera images. We quantify the performance of this Cloud Detection Neural Network (CDNN) using human-labeled validation data where we report a 96% accuracy in detecting clouds in testing datasets for both Zenith- viewing and Forward-viewing models. We assess our performance by comparing the flight-averaged cloud fraction of zenith and forward CDNN retrievals, with that of the prototype hyperspectral total-diffuse Sunshine Pyranometer (SPN-S) instrument’s cloud optical depth data. Comparison of the CDNN with the SPN-S on time specific intervals resulted in 93% accuracy for the zenith- viewing CDNN and 84% for the forward- viewing CDNN. The comparison of the CDNNs with the SPN-S on flight-averaged cloud fraction resulted in an agreement of 0.15 for the Forward CDNN and 0.07 for the Zenith CDNN. We then quantify the ability of the CDNN to identify the presence of clouds above the aircraft using a forward- looking camera mounted inside the aircraft cockpit compared to the use of an All- Sky upward-looking camera that is mounted outside the fuselage on top of the aircraft. We present results from the CDNN based on airborne imagery from the NASA Aerosol Cloud Meteorology Interactions Over the Western Atlantic Experiment (ACTIVATE) and the Clouds, Aerosol and Monsoon Processes- Philippines Experiment (CAMP2Ex). For CAMP2Ex 53% of flight dates had above- aircraft cloud fraction above 50%, while for ACTIVATE 52% and 54% of flight dates observed above-aircraft cloud fraction above 50% for 2020 and 2021, respectively.

Joseph D Nied↗

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗

RiverPIXELS: paired Landsat images and expert-labeled sediment and water pixels for a selection of rivers v1.0

RiverPIXELS contains GeoTIFFs of hand-labeled water and sediment pixels from Landsat images containing rivers. Each of the 104 labeled patches contains 256 x 256 Landsat pixels (30 meter resolution). Our aim in releasing RiverPIXELS is to provide an "off-the-shelf" training and testing dataset for building machine-learned models to automatically identify rivers from multispectral imagery. While a number of trained models and/or surface water products already exist, RiverPIXELS aims for pixel-level accuracy in order to precisely identify river boundaries in particular. Our selection of rivers is heavily Arctic, but we include tropical and temperate rivers as well. Patches are provided for the Colville (7), Indigirka (6), Kolyma (4), Ucayali (54), Waitaki (21), and Yana (12) Rivers. For each patch, all surface water pixels are labeled (1) and all in-channel sediment pixels are labeled (2). Sediments not in-channel are considered part of the land (0) class. RiverPIXELS also includes paired surface water data from the Global Surface Water dataset that may be useful as additional features in machine learning models. Each patch therefore contains four aligned GeoTIFFs: labeled, landsat, gswmo, and gswocc.

54 ENVIRONMENTAL SCIENCES↗

Models and Processes to Extract Drug-like Molecules From Natural Language Text

Researchers worldwide are seeking to repurpose existing drugs or discover new drugs to counter the disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). A promising source of candidates for such studies is molecules that have been reported in the scientific literature to be drug-like in the context of viral research. However, this literature is too large for human review and features unusual vocabularies for which existing named entity recognition (NER) models are ineffective. We report here on a project that leverages both human and artificial intelligence to detect references to such molecules in free text. We present 1) a iterative model-in-the-loop method that makes judicious use of scarce human expertise in generating training data for a NER model, and 2) the application and evaluation of this method to the problem of identifying drug-like molecules in the COVID-19 Open Research Dataset Challenge (CORD-19) corpus of 198,875 papers. We show that by repeatedly presenting human labelers only with samples for which an evolving NER model is uncertain, our human-machine hybrid pipeline requires only modest amounts of non-expert human labeling time (tens of hours to label 1778 samples) to generate an NER model with an F-1 score of 80.5%—on par with that of non-expert humans—and when applied to CORD’19, identifies 10,912 putative drug-like molecules. This enriched the computational screening team’s targets by 3,591 molecules, of which 18 ranked in the top 0.1% of all 6.6 million molecules screened for docking against the 3CLPro protein.

60 APPLIED LIFE SCIENCES↗

Visual Analytics of Heterogeneous Data Using Hypergraph Learning

For real-world learning tasks (e.g., classification), graph-based models are commonly used to fuse the information distributed in diverse data sources, which can be heterogeneous, redundant, and incomplete. Thesemodels represent the relations in different datasets as pairwise links. However, these links cannot deal with high-order relations which connect multiple objects (e.g., in public health datasets, more than two patient groups admitted by the same hospital in 2014). In this article, we propose a visual analytics approach forthe classification on heterogeneous datasets using the hypergraph model. The hypergraph is an extension to traditional graphs in which a hyperedge connects multiple vertices instead of just two. We model various high-order relations in heterogeneous datasets as hyperedges and fuse different datasets with a unified hypergraph structure. We use the hypergraph learning algorithm for predicting missing labels in the datasets.To allow users to inject their domain knowledge into the model-learning process, we augment the traditional learning algorithm in a number of ways. In addition, we also propose a set of visualizations which enable the user to construct the hypergraph structure and the parameters of the learning model interactively during the analysis. Here, we demonstrate the capability of our approach via two real-world cases.

97 MATHEMATICS AND COMPUTING↗

S. elongatus PCC 7942 Carbon Metabolism Proteomics (MC-DP2)

The purpose of this experiment was to examine the redox proteome of S. elongatus PCC 7942 CscB/SPS under different light conditions (light and dark) and culture conditions (dense and dilute optical density). Samples were processed using a resin-assisted capture (RAC) workflow with TMT labeling to enrich and quantify protein cysteines which were differentially oxidized under four conditions. The datasets were generated by a Q Exactive Plus Orbitrap Mass Spectrometer coupled with a Waters nanoAcquity UPLC, then searched by MSGF+ for downstream redox PTM analysis.

59 BASIC BIOLOGICAL SCIENCES↗

Enhancing Docking Accuracy with PECAN2, a 3D Atomic Neural Network Trained without Co-Complex Crystal Structures

Decades of drug development research have explored a vast chemical space for highly active compounds. The exponential growth of virtual libraries enables easy access to billions of synthesizable molecules. Computational modeling, particularly molecular docking, utilizes physics-based calculations to prioritize molecules for synthesis and testing. Nevertheless, the molecular docking process often yields docking poses with favorable scores that prove to be inaccurate with experimental testing. To address these issues, several approaches using machine learning (ML) have been proposed to filter incorrect poses based on the crystal structures. However, most of the methods are limited by the availability of structure data. Here, we propose a new pose classification approach, PECAN2 (Pose Classification with 3D Atomic Network 2), without the need for crystal structures, based on a 3D atomic neural network with Point Cloud Network (PCN). The new approach uses the correlation between docking scores and experimental data to assign labels, instead of relying on the crystal structures. We validate the proposed classifier on multiple datasets including human mu, delta, and kappa opioid receptors and SARS-CoV-2 Mpro. Our results demonstrate that leveraging the correlation between docking scores and experimental data alone enhances molecular docking performance by filtering out false positives and false negatives.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Power System Waveform Datasets for Machine Learning

The desire for increased visibility across the electricity grid will necessarily increase the deployment of sensing and measurement devices and associated data management needs to unprecedented levels. For the existing sensing and measurement infrastructure, there remains a great amount of “value” yet to be extracted through advanced data management and analytics. Availability of more data will not, by itself, lead to changes in grid visibility, security, and resiliency. To create the predictive and prescriptive environment required to enable new markets and transactions for customer revenue and a reliable grid, the data must be collected, organized, evaluated, and analyzed using sophisticated algorithms to provide actionable information allowing operators and customers to reliably manage an increasingly complex grid. Progress in artificial intelligence (AI) has been largely driven by large, publicly available datasets that can be used to train AI algorithms such as MNIST, a database of handwritten images of digits, and ImageNet, an image database of everyday objects. These types of publicly available databases of real-world training datasets have been largely credited for advancement of image processing, computer vision, and deep learning algorithms that these use cases deploy. However, in the power systems industry to date, there are few databases with proper event labeling, and data access to a publicly available collection of power system event waveforms that will allow users to interact with grid signature data. Publicly available datasets of power system event waveforms, such as the DOE/EPRI dataset, often lack critical metadata or contain limited examples of each event type, and data formats vary widely across these datasets.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗

BUTTER - Empirical Deep Learning Dataset

The BUTTER Empirical Deep Learning Dataset represents an empirical study of the deep learning phenomena on dense fully connected networks, scanning across thirteen datasets, eight network shapes, fourteen depths, twenty-three network sizes (number of trainable parameters), four learning rates, six minibatch sizes, four levels of label noise, and fourteen levels of L1 and L2 regularization each. Multiple repetitions (typically 30, sometimes 10) of each combination of hyperparameters were preformed, and statistics including training and test loss (using a 80% / 20% shuffled train-test split) are recorded at the end of each training epoch. In total, this dataset covers 178 thousand distinct hyperparameter settings ("experiments"), 3.55 million individual training runs (an average of 20 repetitions of each experiments), and a total of 13.3 billion training epochs (three thousand epochs were covered by most runs). Accumulating this dataset consumed 5,448.4 CPU core-years, 17.8 GPU-years, and 111.2 node-years.

Array↗