Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Labeling”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

NaroNet: Discovery of tumor microenvironment elements from highly multiplexed images

Understanding the spatial interactions between the elements of the tumor microenvironment -i.e. tumor cells. fibroblasts, immune cells- and how these interactions relate to the diagnosis or prognosis of a tumor is one of the goals of computational pathology. We present NaroNet, a deep learning framework that models the multi-scale tumor microenvironment from multiplex-stained cancer tissue images and provides patient-level interpretable predictions using a seamless end-to-end learning pipeline. Trained only with multiplex-stained tissue images and their corresponding patient-level clinical labels, NaroNet unsupervisedly learns which cell phenotypes, cell neighborhoods, and neighborhood interactions have the highest influence to predict the correct label. To this end, NaroNet incorporates several novel and state-of-the-art deep learning techniques, such as patch-level contrastive learning, multi-level graph embeddings, a novel max-sum pooling operation, or a metric that quantifies the relevance that each microenvironment element has in the individual predictions. We validate NaroNet using synthetic data simulating multiplex-immunostained images where a patient label is artificially associated to the -adjustable- probabilistic incidence of different microenvironment elements. We then apply our model to two sets of images of human cancer tissues: 336 seven-color multiplex-immunostained images from 12 high-grade endometrial cancer patients; and 382 35-plex mass cytometry images from 215 breast cancer patients. In both synthetic and real datasets, NaroNet provides outstanding predictions of relevant clinical information while associating those predictions to the presence of specific microenvironment elements.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy

Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse experimental datasets. Simulations can mitigate this challenge, but the accuracy of models trained on simulated data can deteriorate substantially when deployed to an out-of-distribution operational environment. In this study, we demonstrate that unsupervised domain adaptation (UDA) can improve the ability of a model trained on synthetic data to generalize to a new testing domain, provided unlabeled data from the target domain are available. Conventional supervised techniques are unable to utilize this data because the absence of isotope labels precludes defining a supervised classification loss. Instead, we first pretrain a spectral classifier using labeled synthetic data and subsequently leverage unlabeled target data to align the learned feature representations between the source and target domains. We compare a range of different UDA techniques, finding that minimizing the maximum mean discrepancy (MMD) between source and target feature vectors yields the most consistent improvement to testing scores. For instance, using a custom transformer-based neural network, we achieved a testing accuracy of $0.904 \pm 0.022$ on an experimental LaBr test set after performing unsupervised feature alignment via MMD minimization, compared to $0.754 \pm 0.014$ before alignment. Overall, our results highlight the potential of using UDA to adapt a radioisotope classifier trained on synthetic data for real-world deployment.

Lalor, Peter W.↗
DOE OSTI2023

A transfer learning approach for acoustic emission zonal localization on steel plate-like structure using numerical simulation and unsupervised domain adaptation

The detection and localization of damage in metallic structures using acoustic emission (AE) monitoring and artificial intelligence technology such as deep learning has been widely studied. However, a current challenge of this approach is the difficulty of obtaining sufficient labeled historical AE signals for the training process of deep learning models. This problem can be approached through the implementation of transfer learning. The innovation of this paper lies in the development of a transfer learning approach for AE source localization on a stainless-steel structure when no historical labeled AE signals are available for training. A finite element model is developed to generate numerical AE signals for the training. Unsupervised domain adaptation (UDA) technology is utilized to reduce the distribution difference between the numerical and the realistic AE signals and to derive the localization results of the unlabeled realistic AE signals. Finally, the results suggest that the proposed approach is capable of localizing AE signals with high accuracy in the absence of labeled training data.

42 ENGINEERING↗
DOE OSTI2022

Recombination between 13 C and 2 H to Form Acetylide ( 13 C 2 2 H – ) Probes Nanoscale Interactions in Lipid Bilayers via Dynamic Secondary Ion Mass Spectrometry: Cholesterol and GM 1 Clustering

Although it is thought that there is lateral heterogeneity of lipid and protein components within biological membranes, probing this heterogeneity has proven challenging. The difficulty in such experiments is due to both the small length scale over which such heterogeneity can occur, and the significant perturbation resulting from fluorescent or spin labeling on the delicate interactions within bilayers. Atomic recombination during dynamic nanoscale secondary ion imaging mass spectrometry (NanoSIMS) is a non-perturbative method for examining nanoscale bilayer interactions. Atomic recombination is a variation on conventional NanoSIMS imaging, whereby an isotope on one molecule combines with a different isotope on another molecule during the ionization process, forming an isotopically enriched polyatomic ion in a distance-dependent manner. In this work, we show that the recombinant ion, 13 C 2 2 H – , is formed in high yield from 13 C- and 2 H-labeled lipids. The low natural abundance of triply labeled acetylide also makes it an ideal ion to probe GM 1 clusters in model membranes and the effects of cholesterol on lipid–lipid interactions. We find evidence supporting the cholesterol condensation effect as well as the presence of nanoscale GM 1 clusters in model membranes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Enhancing Nanoparticle Detection in Interferometric Scattering (iSCAT) Microscopy Using a Mask R-CNN

Interferometric scattering microscopy (iSCAT) is a label-free optical microscopy technique that enables imaging of individual nano-objects such as nanoparticles, viruses, and proteins. Essential to this technique is the suppression of background scattering and identification of signals from nano-objects. In the presence of substrates with high roughness, scattering heterogeneities in the background, when coupled with tiny stage movements, cause features in the background to be manifested in background-suppressed iSCAT images. Traditional computer vision algorithms detect these background features as particles, limiting the accuracy of object detection in iSCAT experiments. Here, in this paper, we present a pathway to improve particle detection in such situations using supervised machine learning via a mask region-based convolutional neural network (mask R-CNN). Using a model iSCAT experiment of 19.2 nm gold nanoparticles adsorbing to a rough layer-by-layer polyelectrolyte film, we develop a method to generate labeled datasets using experimental background images and simulated particle signals and train the mask R-CNN using limited computational resources via transfer learning. We then compare the performance of the mask R-CNN trained with and without inclusion of experimental backgrounds in the dataset against that of a traditional computer vision object detection algorithm, Haar-like feature detection, by analyzing data from the model experiment. Results demonstrate that including representative backgrounds in training datasets improved the mask R-CNN in differentiating between background and particle signals and elevated performance by markedly reducing false positives. The methodology for creating a labeled dataset with representative experimental backgrounds and simulated signals facilitates the application of machine learning in iSCAT experiments with strong background scattering and thus provides a useful workflow for future researchers to improve their image processing capabilities.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Unraveling the convoluted and dynamic interphasial mechanisms on Li metal anode

Accurate understanding of the chemistry of solid-electrolyte interphase (SEI) is key to developing new electrolytes for high-energy batteries using lithium metal (Li-0) anodes(1). SEI is generally believed to be formed by the reactions between Li-0 and electrolyte(2,3). However, our new study shows this is not the whole story. Through synchrotron-based X-ray diffraction and pair distribution function analysis, we reveal a much more convoluted formation mechanism of SEI, which receives considerable contributions from electrolyte, cathode, moisture and native surface species on Li-0, with highly dynamic nature during cycling. Using isotope labelling, we traced the origin of LiH to electrolyte solvent, moisture and a new source: the native surface species (LiOH) on pristine Li-0. When lithium accessibility is very limited as in the case of anode-free cells, LiOH develops into plate-shaped large crystals during cycling. Alternatively, when the lithium source is abundant, as in the case of Li||NMC811 cells, LiOH reacts with Li-0 to form LiH and Li2O. While the desired anion-derived LiF-rich SEI is typically found in the concentrated electrolytes or their derivatives, we found it can also be formed in low-concentration electrolyte via the crosstalk effect, emphasizing the importance of formation cycle protocol and opening up opportunities for low-cost electrolyte development.

Polzin, Bryant J.↗
DOE OSTI2025

The effects of photosynthetic rate on respiration in light, starch/sucrose partitioning, and other metabolic fluxes within photosynthesis

In the future, plants may encounter increased light and elevated CO 2 levels. How consequent alterations in photosynthetic rates will impact fluxes in photosynthetic carbon metabolism remains uncertain. Respiration in light ( R L ) is pivotal in plant carbon balance and a key parameter in photosynthesis models. Understanding the dynamics of photosynthetic metabolism and R L under varying environmental conditions is essential for optimizing plant growth and agricultural productivity. However, measuring R L under high light and high CO 2 (HLHC) conditions poses challenges using traditional gas exchange methods. In this study, we employed isotopically nonstationary metabolic flux analysis (INST-MFA) to estimate RL and investigate photosynthetic carbon flux, unveiling nuanced adjustments in Camelina sativa under HLHC. Despite numerous flux alterations in HLHC, RL remained stable. HLHC affects several factors influencing RL, such as starch and sucrose partitioning, v o /v c ratio, triose phosphate partitioning, and hexose kinase activity. Analysis of A/C i curve operational points reveals that HLHC’s major changes primarily stem from CO 2 suppressing photorespiration. Integration of these fluxes into a simplified model predicts changes in CBC labeling under HLHC. This study extends our prior discovery that incomplete CBC labeling is due to unlabeled carbon reimported during R L , offering insights into manipulating labeling through adjustments in photosynthetic rates.

Elevated CO2↗
DOE OSTI2023

Enabling quantitative analysis of complex polymer blends by infrared nanospectroscopy and isotopic deuteration

Atomic-force microscopy coupled with infrared spectroscopy (AFM-IR) deciphers surface morphology of thin-film polymer blends and composites by simultaneously mapping physical topography and chemical composition. However, acquiring quantitative phase and composition information from multi-component blends can be challenging using AFM-IR due to the possible overlapping infrared absorption bands between different species. Isotope labeling one of the blend components introduces a new type of bond (carbon-deuterium vibration) that can be targeted using AFM-IR and responds at wavelengths sufficiently shifted toward unoccupied regions (around 2200 cm –1 ). In this project, AFM-IR was used to probe the surface morphology and chemical composition of three polymer blends containing deuterated polystyrene; each blend is expected to exhibit various degrees of miscibility. AFM-IR results successfully demonstrated that deuterium labeling prevents infrared spectral overlap and enables the visualization of blend phases that could not normally be distinguished by other scanning probe techniques. The nanoscale domain composition was resolved by fast infrared spectrum analysis. Overall, we presented isotope labeling as a robust approach for circumventing obstacles preventing the quantitative analysis of multiphase systems by AFM-IR.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Ti- and Fe-related charge transition levels in $β$ – Ga 2 O 3

Here, deep-level transient spectroscopy measurements on $β$ – Ga 2 O 3 crystals reveal the presence of three defect signatures labeled $E$ 2a , $E$ 2b , and $E$ 3 with activation energies at around 0.66 eV, 0.73 eV, and 0.95 eV below the conduction band edge. Using secondary ion mass spectrometry, a correlation between the defect concentration associated with $E$ 3 and the Ti concentration present in the samples was found. Particularly, it is found that $E$ 3 is the dominant Ti-related defect in $β$ – Ga 2 O 3 and is associated with a single Ti atom. This finding is further corroborated by hybrid functional calculations that predict Ti substituting on an octahedral Ga site, denoted as Ti GaII , to be a good candidate for $E$ 3 . Moreover, the deep level transient spectroscopy results show that the level previously labeled $E$ 2 and attributed to Fe substituting on a gallium site (FeGa) consists of two overlapping signatures labeled E2a and E2b. We tentatively assign $E$ 2a and $E$ 2b to Fe substituting for Ga on a tetrahedral or an octahedral site, respectively.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Automatic identification of edge localized modes in the DIII-D tokamak

Fusion power production in tokamaks uses discharge configurations that risk producing strong type I edge localized modes. The largest of these modes will likely increase impurities in the plasma and potentially damage plasma facing components, such as the protective heat and particle divertor. Machine learning-based prediction and control may provide for the automatic detection and mitigation of these damaging modes before they grow too large to suppress. To that end, large labeled datasets are required for the supervised training of machine learning models. We present an algorithm that achieves 97.7% precision when automatically labeling edge localized modes in the large DIII-D tokamak discharge database. The algorithm has no user controlled parameters and is largely robust to tokamak and plasma configuration changes. This automatically labeled database of events can subsequently feed future training of machine learning models aimed at autonomous edge localized mode control and suppression.

O’Shea, Finn H. (ORCID:0000000323987381)↗
DOE OSTI2021

Iterative self-organizing SCEne-LEvel sampling (ISOSCELES) for large-scale building extraction

Convolutional neural networks (CNN) provide state-of-the-art performance in many computer vision tasks, including those related to remote-sensing image analysis. Successfully training a CNN to generalize well to unseen data, however, requires training on samples that represent the full distribution of variation of both the target classes and their surrounding contexts. With remote sensing data, acquiring a sufficiently representative training set is a challenge due to both the inherent multi-modal variability of satellite or aerial imagery and the general high cost of labeling data. To address this challenge, we have developed ISOSCELES, an Iterative Self-Organizing SCEne LEvel Sampling method for hierarchical sampling of large image sets. Using affinity propagation, ISOSCELES automates the selection of highly representative training images. Compared to random sampling or using available reference data, the distribution of the training is principally data driven, reducing the chance of oversampling uninformative areas or undersampling informative ones. In comparison to manual sample selection by an analyst, ISOSCELES exploits descriptive features, spectral and/or textural, and eliminates human bias in sample selection. Using a hierarchical sampling approach, ISOSCELES can obtain a training set that reflects both between-scene variability, such as in viewing angle and time of day, and within-scene variability at the level of individual training samples. We verify the method by demonstrating its superiority to stratified random sampling in the challenging task of adapting a pre-trained model to a new image and spatial domain for country-scale building extraction. Using a pair of hand-labeled training sets comprising 1,987 sample image chips, a total of 496,000,000 individually labeled pixels, we show, across three distinct model architectures, an increase in accuracy, as measured by F1-score, of 2.2–4.2%.

42 ENGINEERING↗
DOE OSTI2023

Sneaking in SpyCatcher using cell penetrating peptides for in vivo imaging

Abstract In vivo imaging of protein complexes is a powerful method for understanding the underlying biological function of these key biomolecules. Though the engineering of small, high affinity nanobodies have become more prevalent, the off-rates of these tags may result in incomplete or partial labeling of proteins in live cells. The SpyCatcher003 and SpyTag split protein system allow for irreversible, covalent binding to a short target peptide unlike nanobody-affinity based probes. However, delivering these tags into a cell without disrupting its normal function is a key challenge. Cell penetrating peptides (CPPs) are short peptide sequences that facilitate the transduction of otherwise membrane-impermeable ‘cargo’ , such as proteins, into cells. Here we report on our efforts to engineer and characterize CPP-SpyCatcher003 fusions as modular imaging probes. We selected three CPPs, CUPID, Pentratin, and pVEC, to engineer fusion protein probes for superresolution microscopy, with the aim to eliminate prior permeabilization treatments that could introduce imaging artifacts. We find that fusing the CPP sequences to SpyCatcher003 resulted in dimer and multimer formation as determined by size exclusion chromatography, dynamic light scattering, and SDS resistant dimers on SDS-PAGE gels. By isolating and labeling the monomeric forms of the engineered protein, we show these constructs retained their ability to bind SpyTag and all three CPP sequences remain membrane active, as assessed by CD spectroscopy in the presence of SDS detergent. Using fluorescence and super resolution Lattice structured illumination microscopy (Lattice SIM) imaging we show that the CPPs did not enhance uptake of SpyCatcher by E. coli, however with Caulobacter crescentus cells, we show that Penetratin, and to a lesser degree CUPID, does enhance uptake. Our results demonstrate the ability of the CPP-SpyCatcher003 to label targets within living cells, providing the groundwork for using split protein systems for targeted in vivo imaging.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Coincidence anomaly detection for unsupervised locating of edge localized modes in the DIII-D tokamak dataset

Using supervised learning to train a machine learning model to predict an on-coming edge localized mode (ELM) requires a large number of labeled samples. Creating an appropriate data set from the very large database of discharges at a long-running tokamak, such as DIII-D, would be a very time-consuming process for a human. Considering this need and difficulty, we use coincidence anomaly detection, an unsupervised learning technique, to train an ELM-identifier to identify and label ELMs in the DIII-D discharge database. This ELM-identifier shows, simultaneously, a precision of 0.68 and a recall of 0.63 (AUC is 0.73) on identifying ELMs in example time series pulled from thousands of discharges spanning five years. In a test set of 50 discharges, the algorithm finds over 26 thousand ELM candidates, more than 5 times the existing catalog of ELMs labeled by humans.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task

ABSTRACT Motivation Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model’s performance. Results We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets—BioASQ-7b, BioASQ-8b and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets. Availability and implementation BioADAPT-MRC is freely available as an open-source project at https://github.com/mmahbub/BioADAPT-MRC. Supplementary information Supplementary data are available at Bioinformatics online.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Escherichia coli amino acid auxotrophic expression host strains for investigating protein structure–function relationships

Abstract A set of C43(DE3) and BL21(DE3) Escherichia coli host strains that are auxotrophic for various amino acids is briefly reviewed. These strains require the addition of a defined set of one or more amino acids in the growth medium, and have been specifically designed for overproduction of membrane or water-soluble proteins selectively labelled with stable isotopes, such as 2H, 13C and 15N. The strains described here are available for use and have been deposited into public strain banks. Although they cannot fully eliminate the possibility of isotope dilution and mixing, metabolic scrambling of the different amino acid types can be minimized through a careful consideration of the bacterial metabolic pathways. The use of a suitable auxotrophic expression host strain with an appropriately isotopically labelled growth medium ensures high levels of isotope labelling efficiency as well as selectivity for providing deeper insight into protein structure–function relationships.

Biochemistry & Molecular Biology↗
DOE OSTI2022

Practical galaxy morphology tools from deep supervised representation learning

Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful semantic representations of galaxies that are useful for new tasks on which the models were never trained. We exploit these representations to outperform several recent approaches at practical tasks crucial for investigating large galaxy samples. The first task is identifying galaxies of similar morphology to a query galaxy. Given a single galaxy assigned a free text tag by humans (e.g. ‘#diffuse’), we can find galaxies matching that tag for most tags. The second task is identifying the most interesting anomalies to a particular researcher. Our approach is 100 per cent accurate at identifying the most interesting 100 anomalies (as judged by Galaxy Zoo 2 volunteers). The third task is adapting a model to solve a new task using only a small number of newly labelled galaxies. Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch. We solve each task with very few new labels; either one (for the similarity search) or several hundred (for anomaly detection or fine-tuning). This challenges the longstanding view that deep supervised methods require new large labelled data sets for practical use in astronomy. To help the community benefit from our pretrained models, we release our fine-tuning code zoobot. Zoobot is accessible to researchers with no prior experience in deep learning.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Monomer-dimer tensor-network basis for qubit-regularized lattice gauge theories

Traditional SU⁡(𝑁) lattice gauge theories (LGTs) can be formulated using an orthonormal basis constructed from the irreducible representations (irreps) 𝑉 𝜆 of the SU⁡(𝑁) gauge symmetry. On a lattice, the elements of this basis are tensor networks comprising dimer tensors on the links labeled by a set of irreps {𝜆 ℓ } and monomer tensors on sites labeled by {𝜆 𝑠 }. These tensors naturally define a local site Hilbert space, ℋ$^𝑔_𝑠$, on which gauge transformations act. Gauss’s law introduces an additional index 𝛼 𝑠 =1,2,…,𝒟⁡(ℋ$^𝑔_𝑠$) that labels an orthonormal basis of the gauge-invariant subspace of ℋ$^𝑔_𝑠$. This monomer-dimer tensor-network (MDTN) basis, |{𝜆 𝑠 },{𝜆 ℓ },{𝛼 𝑠 }⟩, of the physical Hilbert space enables the construction of new qubit-regularized SU⁡(𝑁) gauge theories that are free of sign problems while preserving key features of traditional LGTs. Here, we investigate finite-temperature confinement-deconfinement transitions in a simple qubit-regularized SU(2) and SU(3) gauge theory in 𝑑 =2 and 𝑑 =3 spatial dimensions, formulated using the MDTN basis, and show that they reproduce the universal results of traditional LGTs at these transitions. Additionally, in 𝑑 =1, we demonstrate using a plaquette chain that the string tension at zero temperature can be continuously tuned to zero by adjusting a model parameter that plays the role of the gauge coupling in traditional LGTs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Convolutional Variational Autoencoder-based Unsupervised Learning for Power Systems Faults

Classification of power system event data is a growing need, particularly where non-protective relaying-based sensors are used to monitor grid performance. Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to obtain. This paper presents an unsupervised learning method to classify and label transients observed in the distribution grid. A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations. The simulation data is used to train the CVAE that identifies different faults as different clusters in the latent space. The clusters are then used as the foundation model to categorize the real-world data.

Alam, Maksudul↗