Search NASA⌕ Search

SEARCH · Search NASA

Results for “LABELLING”

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 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Uncertainty-refined image segmentation under domain shift

A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Martinez, Carianne↗
DOE OSTI2025

AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis

The Main Control Room of the Fermilab accelerator complex continuously gathers extensive time-series data from thousands of sensors monitoring the beam. However, unplanned events such as trips or voltage fluctuations often result in beam outages, causing operational downtime. This downtime not only consumes operator effort in diagnosing and addressing the issue but also leads to unnecessary energy consumption by idle machines awaiting beam restoration. The current threshold-based alarm system is reactive and faces challenges including frequent false alarms and inconsistent outage-cause labeling. To address these limitations, we propose an AI-enabled framework that leverages predictive analytics and automated labeling. Using data from $2,703$ Linac devices and $80$ operator-labeled outages, we evaluate state-of-the-art deep learning architectures, including recurrent, attention-based, and linear models, for beam outage prediction. Additionally, we assess a Random Forest-based labeling system for providing consistent, confidence-scored outage annotations. Our findings highlight the strengths and weaknesses of these architectures for beam outage prediction and identify critical gaps that must be addressed to fully harness AI for transitioning downtime handling from reactive to predictive, ultimately reducing downtime and improving decision-making in accelerator management.

Jain, Milan [PNL, Richland] (ORCID:000000021676111↗
DOE OSTI2024

Uncertainty-refined image segmentation under domain shift

Digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. Uncertainty is resolved according to expected characteristics. The label of any image element with an uncertainty above a threshold is replaced with a new label corresponding to a segmentation class based on domain knowledge.

Martinez, Carianne↗
DOE OSTI2021

The value of human data annotation for machine learning based anomaly detection in environmental systems

Anomaly detection is the process of identifying unexpected data samples in datasets. Automated anomaly detection is either performed using supervised machine learning models, which require a labelled dataset for their calibration, or unsupervised models, which do not require labels. While academic research has produced a vast array of tools and machine learning models for automated anomaly detection, the research community focused on environmental systems still lacks a comparative analysis that is simultaneously comprehensive, objective, and systematic. This knowledge gap is addressed for the first time in this study, where 15 different supervised and unsupervised anomaly detection models are evaluated on 5 different environmental datasets from engineered and natural aquatic systems. To this end, anomaly detection performance, labelling efforts, as well as the impact of model and algorithm tuning are taken into account. As a result, our analysis reveals the relative strengths and weaknesses of the different approaches in an objective manner without bias for any particular paradigm in machine learning. Most importantly, our results show that expert-based data annotation is extremely valuable for anomaly detection based on machine learning.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Non-conventional pathways enable pennycress (Thlaspi arvense L.) embryos to achieve high efficiency of oil biosynthesis

Abstract Pennycress (Thlaspi arvense L.) accumulates oil up to 35% of the total seed biomass, and its overall fatty acid composition is suitable for aviation fuel. However, for this plant to become economically viable, its oil production needs to be improved. In vivo culture conditions that resemble the development of pennycress embryos in planta were developed based on the composition of the liquid endosperm. Then, substrate uptake rates and biomass accumulation were measured from cultured pennycress embryos, revealing a biosynthetic efficiency of 93%, which is one of the highest in comparison with other oilseeds to date. Additionally, the ratio of carbon in oil to CO2 indicated that non-conventional pathways are likely to be responsible for such a high carbon conversion efficiency. To identify the reactions enabling this phenomenon, parallel labeling experiments with 13C-labeled substrates were conducted in pennycress embryos. The main findings of these labeling experiments include: (i) the occurrence of the oxidative reactions of the pentose phosphate pathway in the cytosol; (ii) the reversibility of isocitrate dehydrogenase; (iii) the operation of the plastidic NADP-dependent malic enzyme; and (iv) the refixation of CO2 by Rubisco. These reactions are key providers of carbon and reductant for fatty acid synthesis and elongation.

13C-labeling↗
DOE OSTI2016

Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest

Purpose: To develop an automated system for mediastinal lymph node detection and station mapping for chest CT. Methods: The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifier for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node. Results: The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations. Conclusions: Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

Technical Note: PLASTIMATCH MABS, an open source tool for automatic image segmentation

Purpose: Multiatlas based segmentation is largely used in many clinical and research applications. Due to its good performances, it has recently been included in some commercial platforms for radiotherapy planning and surgery guidance. Anyway, to date, a software with no restrictions about the anatomical district and image modality is still missing. In this paper we introduce PLASTIMATCH MABS, an open source software that can be used with any image modality for automatic segmentation. Methods: PLASTIMATCH MABS workflow consists of two main parts: (1) an offline phase, where optimal registration and voting parameters are tuned and (2) an online phase, where a new patient is labeled from scratch by using the same parameters as identified in the former phase. Several registration strategies, as well as different voting criteria can be selected. A flexible atlas selection scheme is also available. To prove the effectiveness of the proposed software across anatomical districts and image modalities, it was tested on two very different scenarios: head and neck (H&N) CT segmentation for radiotherapy application, and magnetic resonance image brain labeling for neuroscience investigation. Results: For the neurological study, minimum dice was equal to 0.76 (investigated structures: left and right caudate, putamen, thalamus, and hippocampus). For head and neck case, minimum dice was 0.42 for the most challenging structures (optic nerves and submandibular glands) and 0.62 for the other ones (mandible, brainstem, and parotid glands). Time required to obtain the labels was compatible with a real clinical workflow (35 and 120 min). Conclusions: The proposed software fills a gap in the multiatlas based segmentation field, since all currently available tools (both for commercial and for research purposes) are restricted to a well specified application. Furthermore, it can be adopted as a platform for exploring MABS parameters and as a reference implementation for comparing against other segmentation algorithms.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Jefferson Laboratory C100 Superconducting Radio-Frequency Cavity Fault Data, 2020

The dataset was created to train machine learning models for the task of identifying the (1) cavity and (2) fault type from C100-type cryomodules at the Thomas Jefferson National Accelerator Facility (Jefferson Lab), thereby replacing the time-consuming efforts of a subject matter expert. Superconducting radio-frequency (SRF) cavity trips represent a significant source of accelerator downtime. Real-time – rather than post-mortem – identification of the offending cavity and classification of the fault type would give control room operators valuable feedback for corrective action planning. The anticipated benefit is increased beam-on-target time for users and provides performance metrics that can be used to improve future cavity designs. A series of 17 RF signals are recorded for each of the 8 cavities in a C100 cryomodule every time a cavity trips. These time-series signals are written to file using a specially designed data acquisition system. The dataset represents fault events recorded during Continuous Electron Beam Accelerator Facility (CEBAF) beam operations between January 18, 2019 and March 9, 2020. The following filtering steps were applied to collected data; (1) only 4 of the 17 signals per cavity are retained (GMES, GASK, CRFP, DETA2) (2) only events with data from each of the eight cavities in the cryomodule are kept, (3) only events that were sampled at 5 kHz were kept, (4) events from cryomodule 0L04 were neglected, (5) events occurring between February 4, 3PM and February 5, 12PM were neglected. As a result of preprocessing, the dataset is comprised of 2,375 unique events. The full dataset is comprised of three files: features.csv, cavity_labels.csv, fault_labels.csv. Each instance in faults.csv includes a timestamp (“date_time”), a label for the cryomodule which experienced the trip (“zone_label”), and 192 features (“feature_1”, “feature_2”... “feature_192”). The features correspond to 6 autoregressive features for each of 4 signals per cavity for each of the 8 cavities (6 × 4 signals/cavity × 8 cavities/cryomodule = 192). To deal with the large variation of signal amplitudes, time-series standardization via the z-score (standard score) function was applied prior to computing the features. For each instance, there is an associated label for the (1) cavity which faulted first (cavity_labels.csv) and (2) the type of fault that caused the trip (fault_labels.csv). The cavity identification can take values of [0, 1, 2, 3, 4, 5, 6, 7, 8] and the fault type can take values of [‘Microphonics’, ‘Quench_100ms’, ‘Controls_Fault’, ‘E_Quench’, ‘Quench_3ms’, ‘Single_Cav_Turn_Off’ , ‘Heat_Riser_Choke’, ‘Multi_Cav_Turn_Off’].

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Structure‐Aware Representation Learning for Effective Performance Prediction

ABSTRACT Application performance is a function of several unknowns stemming from the interactions between the application, runtime, OS, and underlying hardware, making it challenging to model performance using deep learning techniques, especially without a large labeled dataset. Collecting such labeled longitudinal datasets can take weeks. Intuitively, developers could save analysis time during code development by taking a comparative approach between multiple applications. However, the unknown dynamic interactions between applications and execution environments make it difficult for deep learning‐based models to predict the performance of new applications. In this paper, we address these problems by presenting a labeled dataset for the community and taking a comparative analysis approach to explore the source code differences between different correct implementations of the same problem. This paper assesses the feasibility of using purely static information, for example, Abstract Syntax Tree (AST), of applications to predict performance change based on code structure. We evaluate several deep learning‐based representation learning techniques for source code and propose an architecture for the tree‐based Long Short‐Term Memory (LSTM) models to discover latent representations for a source code's hierarchical structure. We demonstrate that our proposed architecture enables feed‐forward predictive models to predict change in performance using source code with up to 84% accuracy.

Ramadan, Tarek [Department of Computer Science Tex↗
DOE OSTI2020

A Systematic Assessment of US Food and Drug Administration Dosing Recommendations For Drug Development Programs Amenable to Response‐Guided Titration

A key goal in drug development is optimized dosing for patients. Interactions between drug developers and regulatory scientists throughout development are important for the optimization of dosing and serve as a forum to discuss approaches for optimal dosing, such as precision or individualized dosing. To date, there has not been a systematic assessment of the advice provided by the US Food and Drug Administration (FDA) to drug developers from an individualized dosing perspective. Here, we reviewed FDA recommendations on dose selection for efficacy trials at end‐of‐phase meetings between the FDA and drug developers for 76 new molecular entities approved between 2013 and 2017 that are considered amenable for an individualized dosing method, response‐guided titration. Forty FDA dosing recommendations were identified as specific to dose selection and design of the respective efficacy trials and subsequently: (i) characterized based on if they were supportive of individualized dosing and (ii) compared with dosing regimens used in efficacy trials and labeling at approval to evaluate if FDA recommendations were implemented. Of these 40 recommendations for efficacy trials, 35 (88%) were considered supportive of individualized dosing. Eighteen of these 40 recommendations (45%) were incorporated into efficacy trials and 11 (28%) were incorporated into labeling. This research suggests that early FDA‐sponsor interactions can support the study of doses in efficacy trials that may lead to individualized dosing strategies in labeling.

Wang, Lingshan↗
DOE OSTI2019

Bound and mobile soil water isotope ratios are affected by soil texture and mineralogy, whereas extraction method influences their measurement

Questions persist about interpreting isotope ratios of bound and mobile soil water pools, particularly relative to clay content and extraction conditions. Interactions between pools and resulting extracted water isotope composition are presumably related to soil texture, yet few studies have manipulated the bound pool to understand its influence on soil water processes. Using a series of drying and spiking experiments, we effectively labelled bound and mobile water pools in soils with varying clay content. Soils were first vacuum dried to remove residual water, which was then replaced with heavy isotope-enriched water prior to oven drying and spiking with heavy isotope-depleted water. Water was extracted via centrifugation or cryogenic vacuum distillation (at four temperatures) and analysed for oxygen and hydrogen isotope ratios via isotope ratio mass spectrometry. Water from centrifuged samples fell along a mixing line between the two added waters but was more enriched in heavy isotopes than the depleted label, demonstrating that despite oven drying, a residual pool remains and mixes with the mobile water. Soils with higher clay + silt content appeared to have a larger bound pool. Water from vacuum distillation samples have a significant temperature effect, with high temperature extractions yielding progressively more heavy isotope-enriched values, suggesting that Rayleigh fractionation occurred at low temperatures in the vacuum line. By distinctly labelling bound and mobile soil water pools, we detected interactions between the two that were dependent on soil texture. Although neither extraction method appeared to completely extract the combined bound and mobile (total water) pool, centrifugation and high temperature cryogenic vacuum distillations were comparable for both δ 2 H and δ 18 O of soil water isotope ratios.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Spatially tracking carbon through the root-rhizosphere-soil system using laser ablation-IRMS

The intimate relationships between plant roots, rhizosphere, and soil are fostered by the release of organic compounds from the plant into soil through various forms of rhizodeposition and the simultaneous harvestingof inorganic nutrients from the soil to the plant. Here we present a method to spatially track and map the migration of plant-derived carbon (C) through roots into the rhizosphere and surrounding soil using laser ablation-isotope ratio mass spectrometry (LA-IRMS). Weused switchgrass microcosms containing soil from field plots at the Kellogg Biological Station (Hickory Corners, Michigan, USA), which have been cropped with switchgrass since 2008. We used a 13 CO 2 tracerto isotopically label switchgrass plants for two diel cycles and tracked subsequent movement of labeled C using the spatially specific (<100 µm resolution) δ 13 C analysis enabled by LA-IRMS.This approach permitted assessment of variable C flow through different roots and enabled mapping of spatial variability of C allocation to the rhizosphere. Highly 13 C-enriched C (consistent with production during the 13 CO 2 application period) extended ~0.5 – 1 mm from the root into the soil, suggesting that the majority of recent plant-derived C was within this distance of the root after 48 hours. Tracking the physical extent of root exudation into the rhizosphere can help evaluate the localization of plant-microbe interactions in highly variable subsurface environments,and the use of the isotopic label can differentiate freshly fixed C (presumably from root exudates) from other types of subsurface C (e.g., plant necromass and microbial turnover). The LA-IRMS technique mayalso serve as a valuable screening technique to identify areas of high activity for additional microbial or geochemicalassays.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Enhanced detection of paramagnetic fluorine-19 magnetic resonance imaging agents using zero echo time sequence and compressed sensing

Fluorine-19 ( 19 F) magnetic resonance imaging (MRI) is an emerging technique offering specific detection of labeled cells in vivo. Lengthy acquisition times and modest signal-to-noise ratio (SNR) makes three-dimensional spin-density–weighted 19 F imaging challenging. Recent advances in tracer paramagnetic metallo-perfluorocarbon (MPFC) nanoemulsion probes have shown multifold SNR improvements due to an accelerated 19 F T 1 relaxation rate and a commensurate gain in imaging speed and averages. However, 19 F T 2 -reduction and increased linewidth limit the amount of metal additive in MPFC probes, thus constraining the ultimate SNR. To overcome these barriers, we describe a compressed sampling (CS) scheme, implemented using a “zero” echo time (ZTE) sequence, with data reconstructed via a sparsity-promoting algorithm. Our CS-ZTE scheme acquires k-space data using an undersampled spherical radial pattern and signal averaging. Image reconstruction employs off-the-shelf sparse solvers to solve a joint total variation and -norm regularized least square problem. To evaluate CS-ZTE, we performed simulations and acquired 19 F MRI data at 11.7 T in phantoms and mice receiving MPFC-labeled dendritic cells. For MPFC-labeled cells in vivo, we show SNR gains of ~6.3 × with 8-fold undersampling. We show that this enhancement is due to three mechanisms including undersampling and commensurate increase in signal averaging in a fixed scan time, denoising attributes from the CS algorithm, and paramagnetic reduction of T 1 . Importantly, 19 F image intensity analyses yield accurate estimates of absolute quantification of 19 F spins. Overall, the CS-ZTE method using MPFC probes achieves ultrafast imaging, a substantial boost in detection sensitivity, accurate 19 F spin quantification, and minimal image artifacts.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

BdGT43B2 functions in xylan biosynthesis and is essential for seedling survival in Brachypodium distachyon

Abstract Xylan is the predominant hemicellulose in the primary cell walls of grasses, but its synthesis and interactions with other wall polysaccharides are complex and incompletely understood. To probe xylan biosynthesis, we generated CRISPR/Cas9 knockout and amiRNA knockdown lines of BdGT43B2 , an ortholog of the wheat TaGT43‐4 xylan synthase scaffolding protein in the IRX14 clade, in Brachypodium distachyon . Knockout of BdGT43B2 caused stunting and premature death in Brachypodium seedlings. Immunofluorescence labeling of xylans was greatly reduced in homozygous knockout BdGT43B2 mutants, whereas cellulose labeling was unchanged or slightly increased. Biochemical analysis showed reductions in digestible xylan in knockout mutant walls, and cell size was smaller in knockout leaves. BdGT43B2 knockdown plants appeared morphologically normal as adults, but showed slight reductions in seedling growth and small decreases in xylose content in isolated cell walls. Immunofluorescence labeling of xylan and cellulose staining was both reduced in BdGT43B2 knockdown plants. Together, these data indicate that BdGT43B2 functions in the synthesis of a form of xylan that is required for seedling growth and survival in Brachypodium distachyon .

36 MATERIALS SCIENCE↗
DOE OSTI2018

Two-Scale 13 C Metabolic Flux Analysis for Metabolic Engineering

Accelerating the Design-Build-Test-Learn (DBTL) cycle in synthetic biology is critical to achieving rapid and facile bioengineering of organisms for the production of, e.g., biofuels and other chemicals. The Learn phase involves using data obtained from the Test phase to inform the next Design phase. As part of the Learn phase, mathematical models of metabolic fluxes give a mechanistic level of comprehension to cellular metabolism, isolating the principle drivers of metabolic behavior from the peripheral ones, and directing future experimental designs and engineering methodologies. Furthermore, the measurement of intracellular metabolic fluxes is specifically noteworthy as providing a rapid and easy-to-understand picture of how carbon and energy flow throughout the cell. Here, we present a detailed guide to performing metabolic flux analysis in the Learn phase of the DBTL cycle, where we show how one can take the isotope labeling data from a 13 C labeling experiment and immediately turn it into a determination of cellular fluxes that points in the direction of genetic engineering strategies that will advance the metabolic engineering process.For our modeling purposes we use the Joint BioEnergy Institute (JBEI) Quantitative Metabolic Modeling (jQMM) library, which provides an open-source, python-based framework for modeling internal metabolic fluxes and making actionable predictions on how to modify cellular metabolism for specific bioengineering goals. It presents a complete toolbox for performing different types of flux analysis such as Flux Balance Analysis, 13 C Metabolic Flux Analysis, and it introduces the capability to use 13 C labeling experimental data to constrain comprehensive genome-scale models through a technique called two-scale 13 C Metabolic Flux Analysis (2S- 13 C MFA) [1]. In addition to several other capabilities, the jQMM is also able to predict the effects of knockouts using the MoMA and ROOM methodologies. The use of the jQMM library is illustrated through a step-by-step demonstration, which is also contained in a digital Jupyter Notebook format that enhances reproducibility and provides the capability to be adopted to the user's specific needs. As an open-source software project, users can modify and extend the code base and make improvements at will, providing a base for future modeling efforts.

13C Metabolic flux analysis↗
DOE OSTI2019

Creating Training Data for Scientific Named Entity Recognition with Minimal Human Effort

Scientific Named Entity Referent Extraction is often more complicated than traditional Named Entity Recognition (NER). For example, in polymer science, chemical structure may be encoded in a variety of nonstandard naming conventions, and authors may refer to polymers with conventional names, commonly used names, labels (in lieu of longer names), synonyms, and acronyms. As a result, accurate scientific NER methods are often based on task-specific rules, which are difficult to develop and maintain, and are not easily generalized to other tasks and fields. Machine learning models require substantial expert-annotated data for training. Here we propose polyNER: a semi-automated system for efficient identification of scientific entities in text. PolyNER applies word embedding models to generate entity-rich corpora for productive expert labeling, and then uses the resulting labeled data to bootstrap a context-based word vector classifier. Evaluation on materials science publications shows that the polyNER approach enables improved precision or recall relative to a state-of-the-art chemical entity extraction system at a dramatically lower cost: it required just two hours of expert time, rather than extensive and expensive rule engineering, to achieve that result. This result highlights the potential for human-computer partnership for constructing domain-specific scientific NER systems.

Crowdsourcing↗
DOE OSTI2021

Flame stability analysis of flame spray pyrolysis by artificial intelligence

Flame spray pyrolysis (FSP) is a process used to synthesize nanoparticles through the combustion of an atomized precursor solution; this process has applications in catalysts, battery materials, and pigments. Current limitations revolve around understanding how to consistently achieve a stable flame and the reliable production of nanoparticles. Machine learning and artificial intelligence algorithms that detect unstable flame conditions in real time may be a means of streamlining the synthesis process and improving FSP efficiency. In this study, the FSP flame stability is first quantified by analyzing the brightness of the flame's anchor point. This analysis is then used to label data for both unsupervised and supervised machine learning approaches. The unsupervised learning approach allows for autonomous labeling and classification of new data by representing data in a reduced dimensional space and identifying combinations of features that most effectively cluster it. The supervised learning approach, on the other hand, requires human labeling of training and test data but is able to classify multiple objects of interest (such as the burner and pilot flames) within the video feed. The accuracy of each of these techniques is compared against the evaluations of human experts. Both the unsupervised and supervised approaches can track and classify FSP flame conditions in real time to alert users of unstable flame conditions. This research has the potential to autonomously track and manage flame spray pyrolysis as well as other flame technologies by monitoring and classifying the flame stability.

42 ENGINEERING↗