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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Metagenomic stable isotope probing reveals bacteriophage participation in soil carbon cycling

Soil viruses are important components of the carbon (C) cycle, yet we still know little about viral ecology in soils. We added diverse 13 C-labelled carbon sources to soil and we used metagenomic-SIP to detect 13 C assimilation by viruses and their putative bacterial hosts. These data allowed us to link a 13 C-labelled bacteriophage to its 13 C-labelled Streptomyces putative host, and we used qPCR to track the dynamics of the putative host and phage in response to C inputs. Following C addition, putative host numbers increased rapidly for 3 days, and then more gradually, reaching maximal abundance on Day 6. Viral abundance and virus:host ratio increased dramatically over 6 days, and remained high thereafter (8.42 ± 2.94). From Days 6 to 30, virus:host ratio remained high, while putative host numbers declined more than 50%. Putative host populations were 13 C-labelled on Days 3–30, while 13 C-labelling of phage was detected on Days 14 and 30. This dynamic suggests rapid growth and 13 C-labelling of the host fueled by new C inputs, followed by extensive host mortality driven by phage lysis. Furthermore, these findings indicate that the viral shunt promotes microbial turnover in soil following new C inputs, thereby altering microbial community dynamics, and facilitating soil organic matter production.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Pediatric dosing for locally acting drugs in submissions to the U.S. Food and Drug Administration between 2002 and 2020

Abstract Deriving pediatric doses for locally acting drugs (LADs) presents a unique challenge because limited systemic exposure hinders commonly used approaches such as pharmacokinetic matching to adults. This study systematically evaluated drug development practices used for pediatric dose selection of LADs approved by the U.S. Food and Drug Administration from 2002 to 2020. The three study objectives were: (1) to determine the dose selection approach for the labeled pediatric dose, (2) to examine the studied pediatric dose(s), and (3) to evaluate the characteristics of the pediatric clinical programs used to support the labeled pediatric dose. A total of 187 pediatric submissions were characterized for the labeled and studied pediatric doses of LADs. The pediatric dose was predominantly labeled as a flat dose (91%) and at a single‐dose level (67%) similar to adults. The majority (68.4%) of the submissions had the same labeled dose for pediatrics and adults. Independent pharmacodynamic/efficacy studies in pediatric patients commonly (64.2%) provided supportive evidence for the labeled pediatric dose. Inhalation, nasal, and injectable submissions had the highest number of clinical trials, lowest usage of an extrapolation of efficacy approach, and utilized diverse approaches in selecting the studied pediatric doses. This article highlights approaches for LAD dosing in pediatric patients and can be used to inform drug development of these products in the pediatric population.

Research & Experimental Medicine↗
DOE OSTI2020

Differential ultrastructural alterations in the Vglut2 glutamatergic input to the substantia nigra pars compacta/pars reticulata following nigrostriatal dopamine loss in a progressive mouse model of Parkinson’s disease

Abstract Loss of nigrostriatal dopamine (DA) in Parkinson's disease results in over‐activation/bursting of the subthalamic nucleus (STN). The STN projects to the substantia nigra (SN) pars compacta (SNpc) and pars reticulata (SNpr). The vesicular glutamate transporter 2 (Vglut2) is localized within at least STN terminals synapsing within the SN, but it is not known if there are differential changes in the Vglut2+ input to the SNpc versus SNpr following DA loss. The goal/rationale of this current study was to determine whether there were differential changes in the density/levels of glutamate immuno‐gold labeling within Vglut2+ nerve terminals synapsing in the SNpc/SNpr and in the proportion of Vglut2+ terminals contacting tyrosine hydroxylase (TH) positively(+) or negatively(−) labeled dendrites following DA loss. Within the SNpc, there was a significant increase (51.3%) in the density of nerve terminal glutamate immuno‐gold labeling within Vglut2+ terminals synapsing on TH(−) dendrites following MPTP versus the vehicle ( VEH ) group. There was a significant decrease (16%) in the percentage of Vglut2+ terminals contacting TH(+) labeled dendrites in the MPTP‐ versus VEH‐treated group within the SNpc. Within the SNpr, there was a significant decrease in the density of glutamate immuno‐gold labeling in Vglut2+ terminals contacting TH(+) (71.5%) and TH(−) (55.5%) labeled dendrites, suggesting an increase in glutamate release. There was no change in the percentage of Vglut2+ terminals contacting TH(+) or TH(−) dendrites in the SNpr. We conclude that there is a differential effect following DA loss on the glutamate input from Vglut2+ terminals synapsing within the SNpr versus SNpc.

Moore, Cynthia↗
DOE OSTI2024

Mycorrhizal associations of temperate forest seedlings mediate rhizodeposition, but not soil carbon storage, under elevated nitrogen availability

Abstract Tree‐mycorrhizal associations are associated with patterns in nitrogen (N) availability and soil organic matter storage; however, we still lack a mechanistic understanding of what tree and fungal traits drive these patterns and how they will respond to global changes in soil N availability. To address this knowledge gap, we investigated how arbuscular mycorrhizal (AM)‐ and ectomycorrhizal (EcM)‐associated seedlings alter rhizodeposition in response to increased seedling inorganic N acquisition. We grew four species each of EcM and AM seedlings from forests of the eastern United States in a continuously 13 C‐labeled atmosphere within an environmentally controlled chamber and subjected to three levels of 15 N‐labeled fertilizer. We traced seedling 15 N uptake from, and 13 C‐labeled inputs (net rhizodeposition) into, root‐excluded or ‐included soil over a 5‐month growing season. N uptake by seedlings was positively related to rhizodeposition for EcM‐ but not AM‐associated seedlings in root‐included soils. Despite this contrast in rhizodeposition, there was no difference in soil C storage between mycorrhizal types over the course of the experiment. Instead root‐inclusive soils lost C, while root‐exclusive soils gained C. Our findings suggest that mycorrhizal associations mediate tree belowground C investment in response to inorganic N availability, but these differences do not affect C storage. Continued soil warming and N deposition under global change will increase soil inorganic N availability and our seedling results indicate this could lead to greater belowground C investment by EcM‐associated trees. This potential for less efficient N uptake by EcM‐trees could contribute to AM‐tree success and a shift toward more AM‐dominated temperate forests.

Fitch, Amelia A.↗
DOE OSTI2020

Short-Term Stable Isotope Probing of Proteins Reveals Taxa Incorporating Inorganic Carbon in a Hot Spring Microbial Mat

The upper green layer of the chlorophototrophic microbial mats associated with the alkaline siliceous hot springs of Yellowstone National Park consists of oxygenic cyanobacteria ( Synechococcus spp.), anoxygenic Roseiflexus spp., and several other anoxygenic chlorophototrophs. Synechococcus spp. are believed to be the main fixers of inorganic carbon (C i ), but some evidence indicates that Roseiflexus spp. also contribute to inorganic carbon fixation during low-light, anoxic morning periods. Contributions of other phototrophic taxa have not been investigated. In order to follow the pathway of C i incorporation into different taxa, mat samples were incubated with [ 13 C]bicarbonate for 3 h during the early-morning, low-light anoxic period. Extracted proteins were treated with trypsin and analyzed by mass spectrometry, leading to peptide identifications and peptide isotopic profile signatures containing evidence of 13 C label incorporation. A total of 25,483 peptides, corresponding to 7,221 proteins, were identified from spectral features and associated with mat taxa by comparison to metagenomic assembly sequences. A total of 1,417 peptides, derived from 720 proteins, were detectably labeled with 13 C. Most 13 C-labeled peptides were derived from proteins of Synechococcus spp. and Roseiflexus spp. Chaperones and proteins of carbohydrate metabolism were most abundantly labeled. Proteins associated with photosynthesis, C i fixation, and N 2 fixation were also labeled in Synechococcus spp. Importantly, most proteins of the 3-hydroxypropionate bi-cycle for C i fixation in Roseiflexus spp. were labeled, establishing that members of this taxocene contribute to C i fixation. Other taxa showed much lower [ 13 C]bicarbonate incorporation. IMPORTANCE Yellowstone hot spring mats have been studied as natural models for understanding microbial community ecology and as modern analogs of stromatolites, the earliest community fossils on Earth. Stable-isotope probing of proteins (Pro-SIP) permitted short-term interrogation of the taxa that are involved in the important process of light-driven C i fixation in this highly active community and will be useful in linking other metabolic processes to mat taxa. Here, evidence is presented that Roseiflexus spp., which use the 3-hydroxypropionate bi-cycle, are active in C i fixation. Because this pathway imparts a lower degree of selection of isotopically heavy C i than does the Calvin-Benson-Bassham cycle, the results suggest a mechanism to explain why the natural abundance of 13 C in mat biomass is greater than expected if only the latter pathway were involved. Understanding how mat community members influence the 13 C/ 12 C ratios of mat biomass will help geochemists interpret the 13 C/ 12 C ratios of organic carbon in the fossil record.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Ultra-sensitive isotope probing to quantify activity and substrate assimilation in microbiomes

Abstract Background Stable isotope probing (SIP) approaches are a critical tool in microbiome research to determine associations between species and substrates, as well as the activity of species. The application of these approaches ranges from studying microbial communities important for global biogeochemical cycling to host-microbiota interactions in the intestinal tract. Current SIP approaches, such as DNA-SIP or nanoSIMS allow to analyze incorporation of stable isotopes with high coverage of taxa in a community and at the single cell level, respectively, however they are limited in terms of sensitivity, resolution or throughput. Results Here, we present an ultra-sensitive, high-throughput protein-based stable isotope probing approach (Protein-SIP), which cuts cost for labeled substrates by 50–99% as compared to other SIP and Protein-SIP approaches and thus enables isotope labeling experiments on much larger scales and with higher replication. The approach allows for the determination of isotope incorporation into microbiome members with species level resolution using standard metaproteomics liquid chromatography-tandem mass spectrometry (LC–MS/MS) measurements. At the core of the approach are new algorithms to analyze the data, which have been implemented in an open-source software ( https://sourceforge.net/projects/calis-p/ ). We demonstrate sensitivity, precision and accuracy using bacterial cultures and mock communities with different labeling schemes. Furthermore, we benchmark our approach against two existing Protein-SIP approaches and show that in the low labeling range used our approach is the most sensitive and accurate. Finally, we measure translational activity using 18 O heavy water labeling in a 63-species community derived from human fecal samples grown on media simulating two different diets. Activity could be quantified on average for 27 species per sample, with 9 species showing significantly higher activity on a high protein diet, as compared to a high fiber diet. Surprisingly, among the species with increased activity on high protein were several Bacteroides species known as fiber consumers. Apparently, protein supply is a critical consideration when assessing growth of intestinal microbes on fiber, including fiber-based prebiotics. Conclusions We demonstrate that our Protein-SIP approach allows for the ultra-sensitive (0.01 to 10% label) detection of stable isotopes of elements found in proteins, using standard metaproteomics data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Underwater Target Detection Software Demonstration on the RivGen Turbine

This repository contains data and processing scripts necessary to train the object detection models utilized in the underwater target detection software demonstration on the RivGen turbine project and to produce performance metrics (precision, recall, mAP50, mAP50-95). - Contents - Data consist of "images" and "labels". Each image has an associated label, both share the same time string in its file name (e.g., 2024_05_25_09_01_57.98.jpg and 2024_05_25_09_01_57.98.txt). Time strings have the format %yyyy_%mm_%dd_%HH_%MM_%SS.%3f. Images and labels were curated from 2021 and 2024 smolt outmigration periods at the project site in Igiugig, AK. Images are monochrome 8-bit images of objects (smolt, debris, and other) passing through the field of view of the deployed cameras during various operational stages of the RivGen turbine. Labels are text files indicating the class and bounding polygon of each object in an image. The provided labels use the "YOLO" label format. - Requirements - Python3.8+ is required to install and run the train and validation script. The README.md provides instruction for installing the requirements from the requirements.py file. - Instructions - The "example_train.py" file ingests the provided data, trains a model, and produces model performance metrics at completion. NOTE: model performance metrics will vary from run to run as a consequence of the random selection of training and validation data.

16 TIDAL AND WAVE POWER↗
DOE OSTI2026

Custom-trained Machine-learning Interatomic Potentials: ZnCl2 Aqueous Solution

This dataset was generated using an iterative active-learning strategy implemented in the ArcaNN software package (https://github.com/arcann-chem/arcann_training) to train machine-learning interatomic potentials for aqueous ZnCl2 solutions. Each active-learning cycle consisted of three stages: training, exploration, and labeling. The initial training set combined configurations generated in this work from enhanced-sampling ab initio molecular dynamics simulations with configurations from a previously reported neural-network-potential study of aqueous ZnCl2. The enhanced-sampling ab initio molecular dynamics simulations involved Zn–Cl separation and the chloride coordination number around Zn²? as collective variables. These configurations served as the seed dataset. Subsequent active-learning cycles expanded the training set by identifying and labeling configurations that were poorly represented by the current models, thereby improving coverage of ion-association states and changes in local coordination and charge-state environments relevant to the solution free-energy landscape. For all selected configurations, single-point calculations of the total energies and atomic forces were performed within density functional theory using the CP2K Quickstep module. Reference calculations employed the revPBE-D3 and r2SCAN exchange-correlation functionals. Motivated by recent work on aqueous Zn²?, the main revPBE calculations omitted D3 dispersion contributions involving Zn²?, while retaining the D3 correction for water and chloride. For comparison, fully dispersion-corrected revPBE-D3 reference calculations were also performed, with D3 applied to all species, including Zn²?. Valence electrons were treated explicitly, while core electrons were represented using norm-conserving Goedecker–Teter–Hutter pseudopotentials. The wave functions were expanded using the mixed Gaussian-and-plane-wave scheme with TZV2P-MOLOPT basis sets for all elements and a 600 Ry auxiliary plane-wave cutoff for the electron density. Self-consistent-field convergence was accelerated using the orbital-transformation and Direct Inversion in the Iterative Subspace algorithms, with a convergence threshold of 10?6. All single-point calculations were performed in periodic orthorhombic cells. The CELL_REF keyword in CP2K was used to define a fixed reference cell with a box length of 25 Å. This treatment ensured a consistent reference for configurations extracted from NpT trajectories with fluctuating cell dimensions. The resulting DFT energies and atomic forces constitute the ground-truth labels used to train the MLIPs. The resulting MLIP was trained for aqueous ZnCl2 solutions spanning concentrations from 0 to 30 molal and a broad pH range, from strongly acidic to strongly basic conditions. Representative examples of configurations included in the MLIP training dataset are provided below. These include 1) Representative configurations from the dataset labeled at the revPBE-D3 level, with D3 dispersion interactions involving Zn2+ excluded (revPBE-wo-D3). 2) Representative configurations from the dataset labeled at the fully dispersion-corrected revPBE-D3 level, with D3 interactions applied to all species, including Zn2+ (revPBE-D3). 3) Representative configurations from the dataset labeled at the r2SCAN level of theory (r2SCAN).

Dinpajooh, Mohammadhasan [Pacific Northwest Nation↗
DOE OSTI2022

Automated Shift Detection in Sensor-Based PV Power and Irradiance Time Series

PV power and irradiance sensor-based measurements are prone to error, resulting in issues such as abrupt time series data shifts. These shifts, which are usually unintentional, may be caused by software or hardware configuration changes on a PV system, and do not reflect an actual change in overall system performance. Locating these shifts and segmenting the associated time series aids in more accurate future PV analysis. In this research, an offline changepoint detection (CPD) algorithm that automatically detects these abrupt data shifts in sensor-based time series is introduced. Data shift periods in 101 daily PV power and irradiance time series were labeled manually by two solar experts. These data streams represent sensor-based measurements, and display a variety of data shift behaviors. A changepoint detection algorithm was tuned using the 101 labeled data streams, with each model configuration's ability to detect labeled changepoints benchmarked using metrics such as F1-score, recall, and Rand Index. Best performing models on seasonality-corrected data streams include the Pruned Exact Linear (PELT) method, the Binary Segmentation method, and the Bottom-Up method, all scoring an average F1-score of 0.76 or greater at detecting labeled changepoints within a 30-day window for the labeled data sets. To promote further research in this space, we are releasing the labeled data shift sets on U.S. Department of Energy's (DOE) DuraMAT Data Hub, and the associated algorithm in the Python PVAnalytics package.

changepoint detection↗
DOE OSTI2022

Automated Shift Detection in Sensor-Based PV Power and Irradiance Time Series

PV power and irradiance sensor-based measurements are prone to error, resulting in issues such as time series data shifts. In this research, a changepoint detection (CPD) algorithm that automatically detects data shifts in sensor-based time series is introduced. Data shift periods in 101 daily PV power and irradiance time series were labeled manually by two solar experts. These data streams represent sensor-based measurements, and display a variety of data shift behaviors. A changepoint detection algorithm was tuned using the 101 labeled data streams, with each model configuration's ability to detect labeled changepoints benchmarked using metrics such as F1-score, recall, and Rand Index. Best performing models on seasonality-corrected data streams include the Pruned Exact Linear (PELT) method, the Binary Segmentation method, and the Bottom-Up method, all scoring an average F1-score of 0.76 or greater at detecting labeled changepoints within a 30-day window across the labeled data sets. Pending approval, we plan to release the labeled data sets for this research on NREL's DuraMAT Data Hub, and the associated algorithm in the Python PVAnalytics package. By supplying the training sets and algorithm, we hope to encourage further development in this research space.

data shift↗
DOE OSTI2020

Kinetics and Optimization of the Lysine–Isopeptide Bond Forming Sortase Enzyme from Corynebacterium diphtheriae

Site-specifically modified protein bioconjugates have important applications in biology, chemistry, and medicine. Functionalizing specific protein side chains with enzymes using mild reaction conditions is of significant interest, but remains challenging. Recently, the lysine–isopeptide bond forming activity of the sortase enzyme that builds surface pili in Corynebacterium diphtheriae ( Cd SrtA) has been reconstituted in vitro. A mutationally activated form of Cd SrtA was shown to be a promising bioconjugating enzyme that can attach Leu-Pro-Leu-Thr-Gly peptide fluorophores to a specific lysine residue within the N-terminal domain of the SpaA protein ( N SpaA), enabling the labeling of target proteins that are fused to N SpaA. Here we present a detailed analysis of the Cd SrtA catalyzed protein labeling reaction. We show that the first step in catalysis is rate limiting, which is the formation of the Cd SrtA-peptide thioacyl intermediate that subsequently reacts with a lysine ε-amine in N SpaA. This intermediate is surprisingly stable, limiting spurious proteolysis of the peptide substrate. We report the discovery of a new enzyme variant ( Cd SrtA Δ ) that has significantly improved transpeptidation activity, because it completely lacks an inhibitory polypeptide appendage (“lid”) that normally masks the active site. We show that the presence of the lid primarily impairs formation of the thioacyl intermediate and not the recognition of the N SpaA substrate. Quantitative measurements reveal that Cd SrtA Δ generates its cross-linked product with a catalytic turnover number of 1.4 ± 0.004 h –1 and that it has apparent K M values of 0.16 ± 0.04 and 1.6 ± 0.3 mM for its N SpaA and peptide substrates, respectively. Cd SrtA Δ is 7-fold more active than previously studied variants, labeling >90% of N SpaA with peptide within 6 h. The results of this study further improve the utility of Cd SrtA as a protein labeling tool and provide insight into the enzyme catalyzed reaction that underpins protein labeling and pilus biogenesis.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Increasing the Reproducibility and Replicability of Supervised AI/ML in the Earth Systems Science by Leveraging Social Science Methods

Artificial intelligence (AI) and machine learning (ML) pose a challenge for achieving science that is both reproducible and replicable. The challenge is compounded in supervised models that depend on manually labeled training data, as they introduce additional decision-making and processes that require thorough documentation and reporting. We address these limitations by providing an approach to hand labeling training data for supervised ML that integrates quantitative content analysis (QCA)—a method from social science research. The QCA approach provides a rigorous and well-documented hand labeling procedure to improve the replicability and reproducibility of supervised ML applications in Earth systems science (ESS), as well as the ability to evaluate them. Specifically, the approach requires (a) the articulation and documentation of the exact decision-making process used for assigning hand labels in a “codebook” and (b) an empirical evaluation of the reliability” of the hand labelers. In this paper, we outline the contributions of QCA to the field, along with an overview of the general approach. We then provide a case study to further demonstrate how this framework has and can be applied when developing supervised ML models for applications in ESS. With this approach, we provide an actionable path forward for addressing ethical considerations and goals outlined by recent AGU work on ML ethics in ESS.

58 GEOSCIENCES↗
DOE OSTI2020

Selective Sampling for Sensor Type Classification in Buildings

A key barrier to applying any smart technology to a building is the requirement of locating and connecting to the necessary resources among the thousands of sensing and control points, i.e., the metadata mapping problem. Existing solutions depend on exhaustive manual annotation of sensor metadata --- a laborious, costly, and hardly scalable process. To reduce the amount of manual effort required, this paper presents a multi-oracle selective sampling framework to leverage noisy labels from information sources with unknown reliability such as existing buildings, which we refer to as weak oracles, for metadata mapping. This framework involves an interactive process, where a small set of sensor instances are progressively selected and labeled for it to learn how to aggregate the noisy labels as well as to predict sensor types. Two key challenges arise in designing the framework, namely, weak oracle reliability estimation and instance selection for querying. To address the first challenge, we develop a clustering-based approach for weak oracle reliability estimation to capitalize on the observation that weak oracles perform differently in different groups of instances. For the second challenge, we propose a disagreement-based query selection strategy to combine the potential effect of a labeled instance on both reducing classifier uncertainty and improving the quality of label aggregation. We evaluate our solution on a large collection of real-world building sensor data from 5 buildings with more than 11,000 sensors of 18 different types. The experiment results validate the effectiveness of our solution, which outperforms a set of state-of-the-art baselines.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

The oxidative pentose phosphate pathway in photosynthesis: a tale of two shunts

CO 2 release in the light (R L ) and its presumed source, oxidative pentose phosphate pathways, were found to be insensitive to CO 2 concentration. The oxidative pentose phosphate pathways form glucose 6-phosphate (G6P) shunts that bypass the nonoxidative pentose phosphate reactions of the Calvin–Benson cycle. Using adenosine diphosphate glucose and uridine diphosphate glucose as proxies for labeling of G6P in the stroma and cytosol respectively, it was found that only the cytosolic shunt was active. Uridine diphosphate glucose, a proxy for cytosolic G6P, and 6-phosphogluconate (6PG) were significantly less labeled than Calvin–Benson cycle intermediates in the light. But ADP glucose, a proxy for stromal G6P, is labeled to the same degree as Calvin–Benson cycle intermediates and much greater than 6PG. A metabolically inert pool of sedoheptulose bisphosphate can slowly equilibrate keeping the label in sedoheptulose lower than in other stromal metabolites. Finally, phosphorylation of fructose 6-phosphate (F6P) in the cytosol can allow some unlabeled carbon in cytosolic F6P to dilute label in phosphenolpyruvate. The results clearly show that there is oxidative pentose phosphate pathway activity in the cytosol that provides a shunt around the nonoxidative pentose phosphate pathway reactions of the Calvin–Benson cycle and is not strongly CO 2 -sensitive.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Self-Supervised Cloud Classification

Abstract Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets. Significance Statement Marine clouds heavily influence Earth’s weather and climate, and improved understanding of marine clouds is required to improve our atmospheric modeling capabilities and physical understanding of the atmosphere. Recently, deep learning has emerged as a powerful research tool that can be used to identify and study specific marine cloud types in the vast number of images collected by Earth-observing satellites. While powerful, these approaches require hand-labeling of training data, which is prohibitively time intensive. This study evaluates a recently developed self-supervised deep learning method that does not require human-labeled training data for processing images of clouds. We show that the trained algorithm performs competitively with algorithms trained on hand-labeled data for image classification tasks. We also discuss potential downstream uses and demonstrate some exciting features of the approach including application to multiple satellite instruments, resilience against changing image brightness, and its learned internal representations of cloud types. The self-supervised technique removes one of the major hurdles for applying deep learning to very large atmospheric datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Soil and soil fraction radiocarbon, C and N from the Enriched Background Isotope Study, Oak Ridge National Laboratory, Tennessee, USA

A large accidental 14CO2 release at the Oak Ridge Reservation in Tennessee, USA provided a strong label pulse into adjacent, well-studied oak forests, resulting in highly elevated Δ14C values in leaf litter (~1000‰) and roots (~260–450‰). A four-year manipulative study was conducted to provide insight into mechanisms underlying soil Organic matter dynamics, specifically to determine the relative contribution of litter versus roots to the bulk mineral soil C pool, as well as to free light, occluded light and heavy fractions. The heavy fraction was further split into fractions with densities of 1.7–2.4 g cm-3 and >2.4 g cm-3 to test the homogeneity of the mineral-associated fraction of C. Substantial concentrations of label were detected in all soil fractions within a year of the 14CO2 release, indicating rapid incorporation of newly fixed photosynthates in all fractions of soil organic C, regardless of differences in stability inferred by previous work. This rapid incorporation of label occurred only in treatments where roots were labeled, indicating that roots are the major source of inputs to mineral soil C stocks at these sites. Separation of the heavy fraction into subfractions of intermediate (1.7–2.4 g cm -3) and high (>2.4 g cm-3) density indicated that both subfractions incorporated label at similar rates, despite significant differences in degree of microbial processing.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Identifying Vehicle Signals in Continuous Seismic Data Using Unsupervised Machine-Learning Techniques

Seismic sensors deployed near roadways effectively capture ground vibrations generated by passing vehicles. Although both traditional and machine‐learning algorithms have been utilized for analyzing such signals, independent validation of detected vehicle events remains limited. We applied two unsupervised machine‐learning algorithms, uniform manifold approximation and projection for dimension reduction, and hierarchical density‐based spatial clustering of applications with noise, to continuous seismic data collected along a road on the main campus of Oak Ridge National Laboratory. The algorithms identified seven distinct cluster labels across the entire dataset. By comparing these cluster labels with precipitation records from a nearby weather station and image‐derived labels from a local camera system, we identified one cluster associated with rainfall and another with vehicle activity. Our algorithms identified a greater number of vehicle‐related labels compared to the camera‐derived labels because seismic data are unaffected by poor lighting conditions. The arrival times of the newly detected vehicle signals corresponded well with the road’s speed limit, supporting our findings. Our algorithm outperformed the short‐term average/long‐term average method and k‐means clustering. Our results suggest that seismic data, when analyzed with machine‐learning algorithms, can complement existing vehicle monitoring systems, particularly under challenging environmental conditions.

Chai, Chengping [Oak Ridge National Laboratory (OR↗
DOE OSTI2024

FY24 Progress Report: SRNL Analysis of ICCWR LCM and WAMS data for Corrosion and Cracking

Algorithms for Machine Learning (ML) and data analysis for the 3013 Surveillance Program have been developed in an ongoing collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). The objective of the algorithms is to automate the identification of corrosion and crack formation in the Inner Container Closure Weld Region (ICCWR) of the canister system used to store Pu-bearing material. Data for corrosion and cracking is collected from large binary files generated by a Laser Confocal Microscope (LCM), the Wide Area 3D Measurement System (WAMS), or,in a recent proposal, by a Scanning Electron Microscope (SEM). The ML software uses the physical attributes in the data files (e.g., one or more of: height, color, and 16-bit grayscale values as functions of position in a plane projection) to detect signs of surface corrosion and cracking after being trained on similar data, with the features to be detected. Although the initial scope included screening for broader indicators of corrosion, e.g., pitting, identification of potential cracks was prioritized for the past several years at the request of program leadership. Labeled training data is essential to developing the ML algorithm, and enhancements to data labeling capability have been developed to address this essential precursor to application of ML routines. Efficient labeling is particularly important in view of the large volume of data required to train ML algorithms and the relative rarity of cracks in the ICCWR data set. The updated program will read binary data from either LCM, WAMS or SEM files, interrogate data attributes, facilitate user labeling of data for training ML algorithms, execute ML algorithms, output parameters from trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. In FY24, hourglass neural networks (HNNs) that were initiated in FY22 were further developed and tested using available LCM data, and their performance was tested against that of the alternative U-Net Neural Network algorithm structure. HNNs along with previously developed Convolutional Neural Networks (CNNs) and Deep Neural Networks (DNNs) comprise a suite of ML tools for identification of cracks in the ICCWR

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗