Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “label quality”

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 OSTI2024

A Data-Driven Framework for Power System Event Type Identification via Safe Semi-Supervised Techniques

Herein this paper investigates the use of phasor measurement unit (PMU) data with deep learning techniques to construct real-time event identification models for transmission networks. Increasing penetration of distributed energy resources represents a great opportunity to achieve decarbonization, as well as challenges in systematic situational awareness. When high-resolution PMU data and sufficient manually recorded event labels are available, the power event identification problem is defined as a statistical classification problem that can be solved by numerous cutting-edge classifiers. However, in real grids, collecting tremendous high-quality event labels is quite expensive. Utilities frequently have a large number of event records without in-depth details (i.e., unlabeled events). To bridge this gap, we propose a novel semi-supervised learning-based method to improve the performance of event classifiers trained with a limited number of labeled events by exploiting the information from massive unlabeled events. In other words, compared to existing data-driven methods, our method requires only a small portion of labeled data to achieve a similar level of accuracy. Meanwhile, this work discusses and addresses the performance degradation caused by class distribution mismatch between the training set and the real applications. Based on the proposed safe learning mechanism, our model does not directly use all unlabeled events during model training, but selectively uses them through a comprehensive evaluation procedure. Numerical studies on a sizable PMU dataset have been used to validate the performance of the proposed method.

42 ENGINEERING↗
DOE OSTI2024

High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling

We introduce a novel semi-supervised learning approach, named Teacher-Student Bayesian Optimization (TSBO ), integrating the teacher-student paradigm into BO to minimize expensive labeled data queries for the first time. TSBO incorporates a teacher model, an unlabeled data sampler, and a student model. The student is trained on unlabeled data locations generated by the sampler, with pseudo labels predicted by the teacher. The interplay between these three components implements a unique selective regularization to the teacher in the form of student feedback. This scheme enables the teacher to predict high-quality pseudo labels, enhancing the generalization of the GP surrogate model in the search space. To fully exploit TSBO , we propose two optimized unlabeled data samplers to construct effective student feedback that well aligns with the objective of Bayesian optimization. Furthermore, we quantify and leverage the uncertainty of the teacher-student model for the provision of reliable feedback to the teacher in the presence of risky pseudo-label predictions. TSBO demonstrates significantly improved sample-efficiency in several global optimization tasks under tight labeled data budgets. The implementation is available at https://github.com/reminiscenty/TSBO-Official.

Yin, Yuxuan↗
DOE OSTI2020

The Ontologies Community of Practice: A CGIAR Initiative for Big Data in Agrifood Systems

Heterogeneous and multidisciplinary data generated by research on sustainable global agriculture and agrifood systems requires quality data labeling or annotation in order to be interoperable. As recommended by the FAIR principles, data, labels, and metadata must use controlled vocabularies and ontologies that are popular in the knowledge domain and commonly used by the community. Despite the existence of robust ontologies in the Life Sciences, there is currently no comprehensive full set of ontologies recommended for data annotation across agricultural research disciplines. In this paper, we discuss the added value of the Ontologies Community of Practice (CoP) of the CGIAR Platform for Big Data in Agriculture for harnessing relevant expertise in ontology development and identifying innovative solutions that support quality data annotation. The Ontologies CoP stimulates knowledge sharing among stakeholders, such as researchers, data managers, domain experts, experts in ontology design, and platform development teams.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Online Power System Event Detection via Bidirectional Generative Adversarial Networks

Accurate and speedy detection of power system events is critical to enhancing the reliability and resiliency of power systems. Although supervised deep learning algorithms show great promise in identifying power system events, they require a large volume of high-quality event labels for training. This paper develops a bidirectional anomaly generative adversarial network (GAN)-based algorithm to detect power system events using streaming PMU data, which does not rely on a huge amount of event labels. By introducing conditional entropy constraint in the objective function of GAN and graph signal processing-based PMU sorting technique, our proposed algorithm significantly outperforms state-of-the-art event detection algorithms in terms of accuracy. To facilitate the adoption of the proposed algorithm, a prototype online platform is also developed using Apache Hadoop, Kafka, and Spark to enable real-time event detection. Here, the accuracy and computational efficiency of the proposed algorithm are validated using a large-scale real-world PMU dataset from the Eastern Interconnection of the United States.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Dynamic Reconfiguration of Switchgrass Proteomes in Response to Rust ( Puccinia novopanici ) Infection

Switchgrass (Panicum virgatum L.) can be infected by the rust pathogen (Puccinia novopanici) and results in lowering biomass yields and quality. Label-free quantitative proteomics was conducted on leaf extracts harvested from non-infected and infected plants from a susceptible cultivar (Summer) at 7, 11, and 18 days after inoculation (DAI) to follow the progression of disease and evaluate any plant compensatory mechanisms to infection. Some pustules were evident at 7 DAI, and their numbers increased with time. However, fungal DNA loads did not appreciably change over the course of this experiment in the infected plants. In total, 3830 proteins were identified at 1% false discovery rate, with 3632 mapped to the switchgrass proteome and 198 proteins mapped to different Puccinia proteomes. Across all comparisons, 1825 differentially accumulated switchgrass proteins were identified and subjected to a STRING analysis using Arabidopsis (A. thaliana L.) orthologs to deduce switchgrass cellular pathways impacted by rust infection. Proteins associated with plastid functions and primary metabolism were diminished in infected Summer plants at all harvest dates, whereas proteins associated with immunity, chaperone functions, and phenylpropanoid biosynthesis were significantly enriched. At 18 DAI, 1105 and 151 proteins were significantly enriched or diminished, respectively. Many of the enriched proteins were associated with mitigation of cellular stress and defense.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Assessment of TMT Labeling Efficiency in Large-Scale Quantitative Proteomics: The Critical Effect of Sample pH

Isobaric labeling via tandem mass tag (TMT) reagents enables sample multiplexing prior to LC–MS/MS, facilitating high-throughput large-scale quantitative proteomics. Consistent and efficient labeling reactions are essential to achieve robust quantification; therefore, embedded in our clinical proteomic protocol is a quality control (QC) sample that contains a small aliquot from each sample within a TMT set, referred to as “Mixing QC.” This Mixing QC enables the detection of TMT labeling issues by LC–MS/MS before combining the full samples to allow for salvaging of poor TMT labeling reactions. While TMT labeling is a valuable tool, factors leading to poor reactions are not fully studied. We observed that relabeling does not necessarily rescue TMT reactions and that peptide samples sometimes remained acidic after resuspending in 50 mM HEPES buffer (pH 8.5), which coincided with low labeling efficiency (LE) and relatively low median reporter ion intensities (MRIIs). To obtain a more resilient TMT labeling procedure, we investigated LE, reporter ion missingness, the ratio of mean TMT set MRII to individual channel MRII, and the distribution of log 2 reporter ion ratios of Mixing QC samples. We discovered that sample pH is a critical factor in LE, and increasing the buffer concentration in poorly labeled samples before relabeling resulted in the successful rescue of TMT labeling reactions. Moreover, resuspending peptides in 500 mM HEPES buffer for TMT labeling resulted in consistently higher LE and lower missing data. By better controlling the sample pH for labeling and implementing multiple methods for assessing labeling quality before combining samples, we demonstrate that robust TMT labeling for large-scale quantitative studies is achievable.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2020

A Machine Learning-Based Cloud Detection and Thermodynamic Phase Classification Algorithm using Passive Spectral Observations

We trained two Random Forest (RF) machine-learning models for cloud mask and cloud thermodynamic phase detection using spectral observations from VIIRS on Suomi NPP (SNPP). Observations from CALIOP were carefully selected to provide reference labels. The two RF models were trained for all-day and daytime-only conditions using a 4-year collocated VIIRS/CALIOP dataset from 2013 to 2016. Due to the orbit difference, the collocated CALIOP and SNPP VIIRS training samples cover a broad viewing zenith angle range, which is a great benefit to overall model performance. The all-day model uses 3 VIIRS infrared (IR) bands (8.6,11, and 12 μm) and the daytime model uses 5 Near-IR (NIR) and Shortwave-IR (SWIR) bands (0.86, 1.24, 1.38, 1.64 and 2.25 μm) together with the 3 IR bands to detect clear, liquid water, and ice cloud pixels. Up to 7 surface types, namely, ocean/water, forest, cropland, grassland, snow/ice, barren/desert, and shrubland, were considered separately to enhance performance for both models. Detection of cloudy pixels and thermodynamic phase with the two RF models were compared against collocated CALIOP products from 2017. It is shown that, with a conservative screening process that excludes the most challenging cloudy pixels for passive remote sensing, the two RF models have high accuracy rates in comparison with the CALIOP reference for both cloud detection and thermodynamic phase. Other existing SNPP VIIRS and Aqua MODIS cloud mask and phase products are also evaluated, with results showing that the two RF models and the MODIS MYD06 optical property phase product are the top 3 algorithms with respect to lidar observations during the daytime. During the nighttime, the RF all-day model works best for both cloud detection and phase, in particular for pixels over snow/ice surfaces. The present RF models can be extended to other similar passive instruments if training samples can be collected from CALIOP or other lidars. However, the quality of reference labels and potential sampling issues that may impact model performance would need further attention.

cloud detection↗
NASA NTRSDate not supplied

In Situ Water Quality Data for the Chesapeake Bay

This paper examines in situ water quality datameasured during2020-2021in the Chesapeake Bay for comparison with optical satellite data. Thiscollection was performed as part of a NASA project aiming to develop new methods for water quality monitoring from satellite remote sensingusing artificial intelligence. Our objective is to use insitu data as ground-truth to provide water quality classifications, or labels,to their overlapping (in time and location)satellite imagery. Having such labeled data, can help us achieve our project’s longer-termgoal:to train artificial intelligencemodelsto recognize features in spectral informationfor monitoringwater qualityfrom satellites. Because routine monitoring by state agencies is conducted at discrete locations, we obtained a flow-through system operated from small boats to measure waterquality parameters along transects for comparison with two-dimensional maps collected from space, with an initial focus on low oxygenevents, due to their large spatial extent and regular occurrence each summer.We also evaluated similar in situ data collected during 1984-2021by the Chesapeake Program.

Nargess Memarsadeghi↗
NASA NTRS2021

AI4MARS: A Dataset for Terrain-Aware Autonomy on Mars

Deep learning has quickly become a necessity for selfdriving vehicles on Earth. In contrast, the self-driving vehicles on Mars, including NASA’s latest rover, Perseverance, which is planned to land on Mars in February 2021, are still driven by classical machine vision systems. Deep learning capabilities, such as semantic segmentation and object recognition, would substantially benefit the safety and productivity of ongoing and future missions to the red planet. To this end, we created the first large-scale dataset, AI4Mars, for training and validating terrain classification models for Mars, consisting of ~326K semantic segmentation full image labels on 35K images from Curiosity, Opportunity, and Spirit rovers, collected through crowdsourcing. Each image was labeled by ~10 people to ensure greater quality and agreement of the crowdsourced labels. It also includes ~1.5K validation labels annotated by the rover planners and scientists from NASA’s MSL (Mars Science Laboratory) mission, which operates the Curiosity rover, and MER (Mars Exploration Rovers) mission, which operated the Spirit and Opportunity rovers. We trained a DeepLabv3 model on the AI4Mars training dataset and achieved over 96% overall classification accuracy on the test set. The dataset is made publicly available.1

Ono, Hiro↗
DOE OSTI2025

Using Temporal Information from Human Mobility Data to Detect Anchor Points

Spatiotemporal mobility data are available in massive quantities, but large quantities of data typically include fewer variables or data fields. Often, the only available fields are User ID, Longitude, Latitude, Timestamp (ULLT). This raises an important question: how much can we infer about human mobility patterns using only these four fields? With ULLT data, we do not know individuals' socioeconomic status information or when they are visiting their anchor points (AP) or locations (such as homes, places of employment, or schools), and it is a modern challenge to use this data to infer these characteristics. When detecting anchor locations with limited input information, verification and validation (VV) are significant challenges. This paper addresses the problem of identifying individuals' anchor locations using only temporal information from spatiotemporal datasets with limited attributes. Our approach does not explicitly use latitude and longitude during analysis. Locationbased information is only employed in the preprocessing stage to identify periods of movement (trips) and stops (dwelling). Beyond this step, all analysis is based on temporal patterns. In theory, if stops and dwell times could be detected through alternative means, our method could function entirely without location-based input. We demonstrate this methodology on the 2017 National Household Travel Survey (NHTS) data, because it includes a carefully designed and collected time use survey with representative sampling and labeled ground truth. The high-quality survey data allows us to test the accuracy of our methods because NHTS contains intended place labels and agent/user characteristics. We have also applied our validated AP identification algorithm on very large-scale GPS based trajectory data for Patterns-of-Life (PoL) assessment and other applications, but due to space limit that could not be presented here.

McBride, Liz [ORNL] (ORCID:0000000286925869)↗
DOE OSTI2024

From Simple Labels to Time-Use Integrations: Supporting the Spectrum of Qualitative Travel Behavior Data

In transportation research, applications of travel behavior data collection are context-specific and require different types of qualitative inputs. These inputs can be viewed as spanning a spectrum of user burden and data quality, from simple trip labels to complex time-use surveys. However, each currently active smartphone-based travel diary platform appears to only support one type of qualitative input, and the effort required for customization is unclear. In this paper, we characterize the spectrum by defining four canonical use cases: (i) trip labels, (ii) trip questionnaire, (iii) counterfactual trips, and (iv) time-use surveys. We then outline a mechanism for supporting configurable user inputs on the same underlying smartphone-based sensing mechanism and demonstrate that it can support all the use cases without any code changes. We further demonstrate that the flexible data model that underpins this mechanism can enable real-time monitoring and analysis. Finally, we evaluate per-user data collection and engagement metrics for large-scale deployments of three canonical use cases, spanning 10 programs, 435 users, and 251,041 trips, and a maximum duration of 800 days. Future efforts may support additional use cases through an expanded configuration and provide greater insight into user engagement. We hope that these insights enable the research community to look at qualitative inputs through a new lens and experiment with novel use cases to fill in the spectrum.

ADVANCED PROPULSION SYSTEMS,POWER TRANSMISSION AND↗
DOE OSTI2023

Towards Geospatial Knowledge Graph Infused Neuro-Symbolic AI for Remote Sensing Scene Understanding

Deep learning has proven its effectiveness in numerous tasks for remote sensing scene understanding. However there is an increasing interest to explore fusion of domain-specific background information to the deep neural network to further improve its performance. Remote sensing researchers are also working towards developing models that generalize and adapt to multiple applications. Generalization challenges coupled with the scarcity of large corpora of high-quality noise-free labelled data, have together fueled an interest for leveraging background information. Knowledge graphs serve as excellent choice to represent domain-specific information in a structured, standardized and extensible manner. Integrating symbolic knowledge representations in the form of Knowledge Graph Embedding (KGE) to perform neuro-symbolic reasoning is an emerging research direction promising significant impacts. This vision paper seeks to position ideas and provoke early thoughts toward advancing neuro-symbolic artificial intelligence in the context of geospatial challenges. Specifically, it conceptualizes and elaborates on an architecture for infusing geospatial knowledge from knowledge graph in a deep neural network pipeline. As guiding case studies - land-use land-cover classification, object detection and instance segmentation can benefit from infusing spatio-contextual information with remote sensing imagery. The discussion further reflects on and articulates the challenges and explainable AI opportunities anticipated when scaling and maintaining large-scale geospatial knowledge graphs.

Potnis, Abhishek↗
DOE OSTI2023

Machine learning-based inversion for acoustic impedance with large synthetic training data: Workflow and data characterization

Where wells are sparse or training data are difficult to label with high-quality wireline-derived impedance logs, machine learning (ML)-based inversion of acoustic impedance typically depends on small training data sets, leading to biased prediction. We have advanced a novel workflow that applies large synthetic seismic training data to reduce facies-related bias. Using a geologically realistic model as the truth model, we randomly select sparse seed wells to perform sequential Gaussian simulation (SGS) for impedance models of the same geometry and simulate facies variability. We implement random forest regression on 30 features extracted from the synthetic volume. We observe that more seed wells tend to reduce facies-induced bias by sampling more types of facies, resulting in a better prediction. We then focus on the responses of SGS models to facies changes, the number of seed wells necessary for a useful synthetic model, and how much a synthetic model can help ML-based inversion. Here, we observe that the SGS synthetic training model outperforms well-direct training in general. For modeled clastic shore-zone systems in Miocene Gulf of Mexico, two or more seed wells are necessary for a significant reduction of root-mean-square error and outliners, and improvement of facies imaging. In a field-data test, we apply a similar workflow to quantitatively predict acoustic impedance, which is then converted to a sand-volume map at a high-frequency sequence (10–100 m), revealing detailed facies and sandstone patterns. Such results are valuable in many geologic and engineering applications, such as hydrocarbon and CO 2 reservoir prospecting, reserve estimation, simulation, etc.

3D seismic↗
NASA NTRS2004

Fluorescent Approaches to High Throughput Crystallography

X-ray crystallography remains the primary method for determining the structure of macromolecules. The first requirement is to have crystals, and obtaining them is often the rate-limiting step. The numbers of crystallization trials that are set up for any one protein for structural genomics, and the rate at which they are being set up, now overwhelm the ability for strictly human analysis of the results. Automated analysis methods are now being implemented with varying degrees of success, but these typically cannot reliably extract intermediate results. By covalently modifying a subpopulation, less than or = 1%, of a macromolecule solution with a fluorescent probe, the labeled material will add to a growing crystal as a microheterogeneous growth unit. Labeling procedures can be readily incorporated into the final stages of a macromolecules purification. The covalently attached probe will concentrate in the crystal relative to the solution, and under fluorescent illumination the crystals will show up as bright objects against a dark background. As crystalline packing is more dense than amorphous precipitate, the fluorescence intensity can be used as a guide in distinguishing different types of precipitated phases, even in the absence of obvious crystalline features, widening the available potential lead conditions in the absence of clear "bits." Non-protein structures, such as salt crystals, will not incorporate the probe and will not show up under fluorescent illumination. Also, brightly fluorescent crystals are readily found against less fluorescent precipitated phases, which under white light illumination may serve to obscure the crystals. Automated image analysis to find crystals should be greatly facilitated, without having to first define crystallization drop boundaries and by having the protein or protein structures all that show up. The trace fluorescently labeled crystals will also emit with sufficient intensity to aid in the automation of crystal alignment using relatively low cost optics, further increasing throughput at synchrotrons. This presentation will focus on the methodology for fluorescent labeling, the crystallization results, and the effects of the trace labeling on the crystal quality.

Minamitani, Elizabeth Forsythe↗
NASA NTRS2004

Fluorescent Approaches to High Throughput Crystallography

X-ray crystallography remains the primary method for determining the structure of macromolecules. The first requirement is to have crystals, and obtaining them is often the rate-limiting step. The numbers of crystallization trials that are set up for any one protein for structural genomics, and the rate at which they are being set up, now overwhelm the ability for strictly human analysis of the results. Automated analysis methods are now being implemented with varying degrees of success, but these typically can not reliably extract intermediate results. By covalently modifying a subpopulation, less than or = 1%, of a macromolecule solution with a fluorescent probe, the labeled material will add to a growing crystal as a microheterogeneous growth unit. Labeling procedures can be readily incorporated into the final stages of purification. The covalently attached probe will concentrate in the crystal relative to the solution, and under fluorescent illumination the crystals show up as bright objects against a dark background. As crystalline packing is more dense than amorphous precipitate, the fluorescence intensity can be used as a guide in distinguishing different types of precipitated phases, even in the absence of obvious crystalline features, widening the available potential lead conditions in the absence of clear "hits." Non-protein structures, such as salt crystals, will not incorporate the probe and will not show up under fluorescent illumination. Also, brightly fluorescent crystals are readily found against less fluorescent precipitated phases, which under white light illumination may serve to obscure the crystals. Automated image analysis to find crystals should be greatly facilitated, without having to first define crystallization drop boundaries and by having the protein or protein structures all that show up. The trace fluorescently labeled crystals will also emit with sufficient intensity to aid in the automation of crystal alignment using relatively low cost optics, further increasing throughput at synchrotrons. This presentation will focus on the methodology for fluorescent labeling, the crystallization results, and the effects of the trace labeling on the crystal quality.

Pusey, Marc L.↗
NASA NTRS2005

Fluorescent Approaches to High Throughput Crystallography

X-ray crystallography remains the primary method for determining the structure of macromolecules. The first requirement is to have crystals, and obtaining them is often the rate-limiting step. The numbers of crystallization trials that are set up for any one protein for structural genomics, and the rate at which they are being set up, now overwhelm the ability for strictly human analysis of the results. Automated analysis methods are now being implemented with varying degrees of success, but these typically cannot reliably extract intermediate results. By covalently modifying a subpopulation, 51%, of a macromolecule solution with a fluorescent probe, the labeled material will add to a growing crystal as a microheterogeneous growth unit. Labeling procedures can be readily incorporated into the final stages of purification. The covalently attached probe will concentrate in the crystal relative to the solution, and under fluorescent illumination the crystals show up as bright objects against a dark background. As crystalline packing is more dense than amorphous precipitate, the fluorescence intensity can be used as a guide in distinguishing different types of precipitated phases, even in the absence of obvious crystalline features, widening the available potential lead conditions in the absence of clear hits. Non-protein structures, such as salt crystals, will not incorporate the probe and will not show up under fluorescent illumination. Also, brightly fluorescent crystals are readily found against less fluorescent precipitated phases, which under white light illumination may serve to obscure the crystals. Automated image analysis to find crystals should be greatly facilitated, without having to first define crystallization drop boundaries and by having the protein or protein structures all that show up. The trace fluorescently labeled crystals will also emit with sufficient intensity to aid in the automation of crystal alignment using relatively low cost optics, further increasing throughput at synchrotrons. This presentation will focus on the methodology for fluorescent labeling, the crystallization results, and the effects of the trace labeling on the crystal quality.

Pusey, Marc L.↗
DOE OSTI2023

Model Agnostic Bayesian Framework for Online Anomaly/Event Detection in PMU Data

Phasor measurement units (PMU) are integral to the modernization and automation plan of the electric power industry. A PMU data signature contains system-level events (e.g., faults, generation/load change, etc.) and any measurement/device-related errors. Therefore, the reliable and resilient operation of power systems is equivalent to the quality of the PMU data and the situation awareness provided by its data signature. Despite recent progress, current state-of-the-art methods are not fool-proof and have certain limitations tracing an error/abnormality to sensor sub-components and grid systems. This is because of technical challenges imposed by the scarcity of the labeled information, loss of data quality, and non-stationarity of data. In this paper, we consider the online PMU data stream as an output of a stochastic process and pose the anomaly/event detection as a changepoint detection problem dealing with detecting parameter changes in the underlying stochastic processes. The proposed model-agnostic framework relies on: (a) feature extraction utilizing the minimum volume enclosing ellipsoids (MVEE) method from raw PMU observations and (b) a Bayesian framework of changepoint detection. The validity of the proposed methodology is discussed through numerical experiments on real-world utility-scale PMU data.

Hossain, Ramij Raja↗