Search NASA⌕ Search

SEARCH · Search NASA

Results for “LABELLING”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Light Regimes Shape Utilization of Extracellular Organic C and N in a Cyanobacterial Biofilm

ABSTRACT Although it is becoming clear that many microbial primary producers can also play a role as organic consumers, we know very little about the metabolic regulation of photoautotroph organic matter consumption. Cyanobacteria in phototrophic biofilms can reuse extracellular organic carbon, but the metabolic drivers of extracellular processes are surprisingly complex. We investigated the metabolic foundations of organic matter reuse by comparing exoproteome composition and incorporation of 13 C-labeled and 15 N-labeled cyanobacterial extracellular organic matter (EOM) in a unicyanobacterial biofilm incubated using different light regimes. In the light and the dark, cyanobacterial direct organic C assimilation accounted for 32% and 43%, respectively, of all organic C assimilation in the community. Under photosynthesis conditions, we measured increased excretion of extracellular polymeric substances (EPS) and proteins involved in micronutrient transport, suggesting that requirements for micronutrients may drive EOM assimilation during daylight hours. This interpretation was supported by photosynthesis inhibition experiments, in which cyanobacteria incorporated N-rich EOM-derived material. In contrast, under dark, C-starved conditions, cyanobacteria incorporated C-rich EOM-derived organic matter, decreased excretion of EPS, and showed an increased abundance of degradative exoproteins, demonstrating the use of the extracellular domain for C storage. Sequence-structure modeling of one of these exoproteins predicted a specific hydrolytic activity that was subsequently detected, confirming increased EOM degradation in the dark. Associated heterotrophic bacteria increased in abundance and upregulated transport proteins under dark relative to light conditions. Taken together, our results indicate that biofilm cyanobacteria are successful competitors for organic C and N and that cyanobacterial nutrient and energy requirements control the use of EOM. IMPORTANCE Cyanobacteria are globally distributed primary producers, and the fate of their fixed C influences microbial biogeochemical cycling. This fate is complicated by cyanobacterial degradation and assimilation of organic matter, but because cyanobacteria are assumed to be poor competitors for organic matter consumption, regulation of this process is not well tested. In mats and biofilms, this is especially relevant because cyanobacteria produce an extensive organic extracellular matrix, providing the community with a rich source of nutrients. Light is a well-known regulator of cyanobacterial metabolism, so we characterized the effects of light availability on the incorporation of organic matter. Using stable isotope tracing at the single-cell level, we quantified photoautotroph assimilation under different metabolic conditions and integrated the results with proteomics to elucidate metabolic status. We found that cyanobacteria effectively compete for organic matter in the light and the dark and that nutrient requirements and community interactions contribute to cycling of extracellular organic matter.

09 BIOMASS FUELS↗
DOE OSTI2021

Competitive Exclusion and Metabolic Dependency among Microorganisms Structure the Cellulose Economy of an Agricultural Soil

Microorganisms that degrade cellulose utilize extracellular reactions that yield free by-products which can promote interactions with noncellulolytic organisms. We hypothesized that these interactions determine the ecological and physiological traits governing the fate of cellulosic carbon (C) in soil. We performed comparative genomics with genome bins from a shotgun metagenomic-stable isotope probing experiment to characterize the attributes of cellulolytic and noncellulolytic taxa accessing 13 C from cellulose. We hypothesized that cellulolytic taxa would exhibit competitive traits that limit access, while noncellulolytic taxa would display greater metabolic dependency, such as signatures of adaptive gene loss. We tested our hypotheses by evaluating genomic traits indicative of competitive exclusion or metabolic dependency, such as antibiotic production, growth rate, surface attachment, biomass degrading potential, and auxotrophy. The most 13 C-enriched taxa were cellulolytic Cellvibrio (Gammaproteobacteria) and Chaetomium (Ascomycota), which exhibited a strategy of self-sufficiency (prototrophy), rapid growth, and competitive exclusion via antibiotic production. Auxotrophy was more prevalent in cellulolytic Actinobacteria than in cellulolytic Proteobacteria, demonstrating differences in dependency among cellulose degraders. Noncellulolytic taxa that accessed 13 C from cellulose (Planctomycetales, Verrucomicrobia, and Vampirovibrionales) were also more dependent, as indicated by patterns of auxotrophy and 13 C labeling (i.e., partial labeling or labeling at later stages). Major 13 C-labeled cellulolytic microbes (e.g., Sorangium, Actinomycetales, Rhizobiales, and Caulobacteraceae) possessed adaptations for surface colonization (e.g., gliding motility, hyphae, attachment structures) signifying the importance of surface ecology in decomposing particulate organic matter. Our results demonstrated that access to cellulosic C was accompanied by ecological trade-offs characterized by differing degrees of metabolic dependency and competitive exclusion.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A standardized quantitative analysis strategy for stable isotope probing metagenomics

ABSTRACT Stable isotope probing (SIP) facilitates culture-independent identification of active microbial populations within complex ecosystems through isotopic enrichment of nucleic acids. Many DNA-SIP studies rely on 16S rRNA gene sequences to identify active taxa, but connecting these sequences to specific bacterial genomes is often challenging. Here, we describe a standardized laboratory and analysis framework to quantify isotopic enrichment on a per-genome basis using shotgun metagenomics instead of 16S rRNA gene sequencing. To develop this framework, we explored various sample processing and analysis approaches using a designed microbiome where the identity of labeled genomes and their level of isotopic enrichment were experimentally controlled. With this ground truth dataset, we empirically assessed the accuracy of different analytical models for identifying active taxa and examined how sequencing depth impacts the detection of isotopically labeled genomes. We also demonstrate that using synthetic DNA internal standards to measure absolute genome abundances in SIP density fractions improves estimates of isotopic enrichment. In addition, our study illustrates the utility of internal standards to reveal anomalies in sample handling that could negatively impact SIP metagenomic analyses if left undetected. Finally, we present SIPmg , an R package to facilitate the estimation of absolute abundances and perform statistical analyses for identifying labeled genomes within SIP metagenomic data. This experimentally validated analysis framework strengthens the foundation of DNA-SIP metagenomics as a tool for accurately measuring the in situ activity of environmental microbial populations and assessing their genomic potential. IMPORTANCE Answering the questions, “who is eating what?” and “who is active?” within complex microbial communities is paramount for our ability to model, predict, and modulate microbiomes for improved human and planetary health. These questions can be pursued using stable isotope probing to track the incorporation of labeled compounds into cellular DNA during microbial growth. However, with traditional stable isotope methods, it is challenging to establish links between an active microorganism’s taxonomic identity and genome composition while providing quantitative estimates of the microorganism’s isotope incorporation rate. Here, we report an experimental and analytical workflow that lays the foundation for improved detection of metabolically active microorganisms and better quantitative estimates of genome-resolved isotope incorporation, which can be used to further refine ecosystem-scale models for carbon and nutrient fluxes within microbiomes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters

Purpose: Pathology reports are the primary source of information concerning the millions of cancer cases across the United States. Cancer registries manually process the pathology reports to extract the pertinent information including primary tumor site, behavior, histology, laterality, and grade. Processing a large volume of the pathology reports in a timely manner is a continuing challenge for cancer registries. The purpose of this study is to develop an information extraction pipeline to reliably and efficiently extract reportable information. Method: We have developed a novel inverse-regression (IR) based information extraction pipeline. The inverse-regression based supervised filter has been successfully applied to many application domains. However, its application to the information extraction from unstructured text is hindered primarily by the extreme high-dimensionality of n-gram representations of text. In this study, we attempt to overcome the obstacles by a novel bootstrapping strategy. First, we use an information-theoretic mutual information based filter to discard the excessive and redundant n-gram features. This step reduces the size and improves the condition number of the sample covariance matrix, thus reducing the computational cost and improving the numerical stability of the subsequent inverse-regression step. Then we use localized sliced inverse-regression (LSIR) to learn a low-dimensional discriminatory subspace for information inference. In particular, we use the k-nearest neighbors of an unlabeled pathology report in the learned representation to infer the desired information from the labeled data in a supervised manner. Results: The experiments were conducted on a set of de-identified pathology reports with human expert labels as the ground truth. Our pipeline consistently performed better than or comparable to the best performing state-of-the-art methods while reducing the training and inference times substantially. Conclusion: Our results demonstrate the potential of inverse-regression based information extraction pipeline for reliable and efficient information extraction from unstructured text. The information extracted from the pathology reports can be used along with clinical information, medical imaging, and genomic information to instigate discoveries in cancer research.

Dubey, Abhishek↗
DOE OSTI2021

Few-shot Learning for Post-disaster Structure Damage Assessment

Automating post-disaster damage assessment with remote sensing data is critical for faster surveys of structures impacted by natural disasters. One significant obstacle to training state-of-the-art deep neural networks to support this automation is that large quantities of labelled data are often required. However, obtaining those labels is particularly unrealistic to support post-disaster damage assessment in a timely manner. Few-shot learning methods could help to mitigate this by reducing the amount of labelled data required to successfully train a model while achieving satisfactory results. To this end, we explore a feature reweighting method to the YOLOv3 object detection architecture to achieve few-shot learning of damage assessment models on the xBD dataset. Our results show that the feature reweighting approach yield improved mAP over the baseline with significantly fewer labelled samples. In addition, we use t-SNE to analyze the class-specific reweighting vectors generated by the reweighting module in order to evaluate their inter-class and intra-class similarity. We find that the vectors form clusters based on class, and that these clusters overlap with visually similar classes. Those results show the potential to employ this few-shot learning strategy for rapid damage assessment with post-event remote sensing images.

Bowman, Jordan↗
DOE OSTI2020

Simulating metagenomic stable isotope probing datasets with MetaSIPSim

DNA-stable isotope probing (DNA-SIP) links microorganisms to their in-situ function in diverse environmental samples. Combining DNA-SIP and metagenomics (metagenomic-SIP) allows us to link genomes from complex communities to their specific functions and improves the assembly and binning of these targeted genomes. However, empirical development of metagenomic-SIP methods is hindered by the complexity and cost of these studies. We developed a toolkit, ‘MetaSIPSim,’ to simulate sequencing read libraries for metagenomic-SIP experiments. MetaSIPSim is intended to generate datasets for method development and testing. To this end, we used MetaSIPSim generated data to demonstrate the advantages of metagenomic-SIP over a conventional shotgun metagenomic sequencing experiment. Through simulation we show that metagenomic-SIP improves the assembly and binning of isotopically labeled genomes relative to a conventional metagenomic approach. Improvements were dependent on experimental parameters and on sequencing depth. Community level G + C content impacted the assembly of labeled genomes and subsequent binning, where high community G + C generally reduced the benefits of metagenomic-SIP. Furthermore, when a high proportion of the community is isotopically labeled, the benefits of metagenomic-SIP decline. Finally, the choice of gradient fractions to sequence greatly influences method performance. Metagenomic-SIP is a valuable method for recovering isotopically labeled genomes from complex communities. We show that metagenomic-SIP performance depends on optimization of experimental parameters. MetaSIPSim allows for simulation of metagenomic-SIP datasets which facilitates the optimization and development of metagenomic-SIP experiments and analytical approaches for dealing with these data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Data for Selected Ion Monitoring for Orbitrap-Based Metabolomics

Orbitrap mass spectrometry in full scan mode enables the simultaneous detection of hundreds of metabolites and their isotope-labeled forms. Yet, sensitivity remains limiting for many metabolites, including low-concentration species, poor ionizers, and low-fractional-abundance isotope-labeled forms in isotope-tracing studies. Here, we explore selected ion monitoring (SIM) as a means of sensitivity enhancement. The analytes of interest are enriched in the orbitrap analyzer by using the quadrupole as a mass filter to select particular ions. In tissue extracts, SIM significantly enhances the detection of ions of low intensity, as indicated by improved signal-to-noise (S/N) ratios and measurement precision. In addition, SIM improves the accuracy of isotope-ratio measurements. SIM, however, must be deployed with care, as excessive accumulation in the orbitrap of similar m/z ions can lead, via space-charge effects, to decreased performance (signal loss, mass shift, and ion coalescence). Ion accumulation can be controlled by adjusting settings including injection time and target ion quantity. Overall, we suggest using a full scan to ensure broad metabolic coverage, in tandem with SIM, for the accurate quantitation of targeted low-intensity ions, and provide methods deploying this approach to enhance metabolome coverage.f

Mass Spectrometry↗
DOE OSTI2021

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Automatic Waveform Quality Control for Surface Waves Using Machine Learning

Surface-wave seismograms are widely used by researchers to study Earth’s interior and earthquakes. To extract information reliably and robustly from a suite of surface waveforms, the signals require quality control screening to reduce artifacts from signal complexity and noise. This process has usually been completed by human experts labeling each waveform visually, which is time consuming and tedious for large data sets. We explore automated approaches to improve the efficiency of waveform quality control processing by investigating logistic regression, support vector machines, K-nearest neighbors, random forests (RF), and artificial neural networks (ANN) algorithms. To speed up signal quality assessment, we trained these five machine learning (ML) methods using nearly 400,000 human-labeled waveforms. The ANN and RF models outperformed other algorithms and achieved a test accuracy of 92%. We evaluated these two best-performing models using seismic events from geographic regions not used for training. The results show that the two trained models agree with labels from human analysts but required only 0.4% of the time. Although the original (human) quality assignments assessed general waveform signal-to-noise, the ANN or RF labels can help facilitate detailed waveform analysis. Our investigations demonstrate the capability of the automated processing using these two ML models to reduce outliers in surface-wave-related measurements without human quality control screening.

58 GEOSCIENCES↗
DOE OSTI2016

Laboratory Experiments to Evaluate Matrix Diffusion of Dissolved Organic Carbon Carbon-14 in Southern Nevada Fractured-rock Aquifers

Dissolved inorganic carbon (DIC) carbon-14 ( 14 C) is used to estimate groundwater ages by comparing the DIC 14 C content in groundwater in the recharge area to the DIC 14 C content in the downgradient sampling point. However, because of chemical reactions and physical processes between groundwater and aquifer rocks, the amount of DIC 14 C in groundwater can change and result in 14 C loss that is not because of radioactive decay. This loss of DIC 14 C results in groundwater ages that are older than the actual groundwater ages. Alternatively, dissolved organic carbon (DOC) 14 C in groundwater does not react chemically with aquifer rocks, so DOC 14 C ages are generally younger than DIC 14 C ages. In addition to chemical reactions, 14 C ages may also be altered by the physical process of matrix diffusion. The net effect of a continuous loss of 14 C to the aquifer matrix by matrix diffusion and then radioactive decay is that groundwater appears to be older than it actually is. Laboratory experiments were conducted to measure matrix diffusion coefficients for DOC 14 C in volcanic and carbonate aquifer rocks from southern Nevada. Experiments were conducted using bromide (Br-) as a conservative tracer and 14 C-labeled trimesic acid (TMA) as a surrogate for groundwater DOC. Outcrop samples from six volcanic aquifers and five carbonate aquifers in southern Nevada were used. The average DOC 14 C matrix diffusion coefficient for volcanic rocks was 2.9 x 10 -7 cm 2 /s, whereas the average for carbonate rocks was approximately the same at 1.7 x 10 -7 cm 2 /s. The average Br- matrix diffusion coefficient for volcanic rocks was 10.4 x 10 -7 cm 2 /s, whereas the average for carbonate rocks was less at 6.5 x 10 -7 cm 2 /s. Carbonate rocks exhibited greater variability in DOC 14 C and Br- matrix diffusion coefficients than volcanic rocks. These results confirmed, at the laboratory scale, that the diffusion of DOC 14 C into southern Nevada volcanic and carbonate aquifers is slower than DIC 14 C. Because of the apparent sorption of 14 C-labeled TMA in the experiments, matrix diffusion coefficients are likely even lower. The reasons for the higher than expected Br-/ 14 C-labeled TMA are unknown. Because the molecular size of TMA is on the low end of the range in molecular size for typical humic substances, the matrix diffusion coefficients for the 14 C-labeled TMA likely represent close to the maximum diffusion rates for DOC 14 C in the volcanic and carbonate aquifers in southern Nevada.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

Temporal Cyber Attack Detection.

Rigorous characterization of the performance and generalization ability of cyber defense systems is extremely difficult, making it hard to gauge uncertainty, and thus, confidence. This difficulty largely stems from a lack of labeled attack data that fully explores the potential adversarial space. Currently, performance of cyber defense systems is typically evaluated in a qualitative manner by manually inspecting the results of the system on live data and adjusting as needed. Additionally, machine learning has shown promise in deriving models that automatically learn indicators of compromise that are more robust than analyst-derived detectors. However, to generate these models, most algorithms require large amounts of labeled data (i.e., examples of attacks). Algorithms that do not require annotated data to derive models are similarly at a disadvantage, because labeled data is still necessary when evaluating performance. In this work, we explore the use of temporal generative models to learn cyber attack graph representations and automatically generate data for experimentation and evaluation. Training and evaluating cyber systems and machine learning models requires significant, annotated data, which is typically collected and labeled by hand for one-off experiments. Automatically generating such data helps derive/evaluate detection models and ensures reproducibility of results. Experimentally, we demonstrate the efficacy of generative sequence analysis techniques on learning the structure of attack graphs, based on a realistic example. These derived models can then be used to generate more data. Additionally, we provide a roadmap for future research efforts in this area.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

225 Ac/ 213 Bi Generator Based on Millifluidics Controlled Electrodeposition

Radioisotopes provide both diagnostic tools and therapeutic treatments for cancer and other diseases. In the US, millions of radioisotope doses are given to patients per year. Radiopharmaceutical generators are widely used to provide such short-lived medical radioisotopes in a clinical setting. These generators work by exploiting chemical differences in a parent/daughter isotope relationship. Actinium-225 (half-life 10 d) is used to provide clinically useful amounts of daughter isotopes 213 Bi (46 m). An integrated millifluidic 225 Ac/ 213 Bi radiopharmaceutical generator device was engineered to produce 213 Bi labeled biomolecules. Using recent LANL successes in additive manufacturing of small-scale fluidic devices, a disposable device was developed that integrates three steps for the production of 213 Bi labeled antibodies: 1) 213 Bi separation from 225 Ac parent, 2) 213 Bi antibody labeling, and 3) purification of the labelled antibody.

213Bi↗
DOE OSTI2021

FY21 Progress Report: SRNL Analysis of ICCWR LCM and WAMS data for Corrosion and Cracking

The development of algorithms for machine learning and data analysis for the 3013 Surveillance Program is a collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). For corrosion detection, Laser Confocal Microscope (LCM) or Wide Area 3D Measurement System (WAMS) data is extracted from large binary files, with software written to convert the data to physical attributes (e.g., height, color and grayscale values; all as functions of a location in a plane projection). A user-friendly Matlab Graphical User Interface (GUI) that reads data from either LCM or WAMS files was developed to integrate input data with software developed for processing and evaluation. The GUI can selectively download binary data, interrogate data attributes, label data, flag significant features, execute Machine Learning (ML) algorithms, output parameters for trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. Features can be called out by user-specified thresholds, manual labeling or machine learning algorithms when they have been completed. The ability to rapidly label data is important because of the volume of data required for training machine learning algorithms. The GUI has the flexibility to allow addition of improved ML algorithms, methods for data visualization, and statistical computations. Statistical analyses via the GUI include areas of pits within a defined range of pit depths, correlations between Red-Green-Blue (RGB) or grayscale intensity and relative surface height, covariances between values associated with features, and feature histograms. The development of supervised machine learning algorithms, however, has been hindered by a lack of training data. The machine learning algorithms for crack identification are being refined but require improvements to the true positive rate for crack detection. This shortcoming is an artifact of the limited training data currently available, perhaps more so than the structure of the neural networks. At present, the best results are had from a consensus over an ensemble of randomly generated Deep Neural Network (DNN) or Convolutional Neural Network (CNN) algorithms. Although the consensus accuracy method has yielded optimum true positive and true negative rates in excess of 80%, additional validation testing is necessary. In addition to the suite of LCM data that was initially used, and which represents the majority of the work presented in this report, WAMS image data was also reviewed at a preliminary level. The review included a comparison between image resolution and dynamic range for each method. WAMS (ZON file) image data was found to have a pixel pitch of 3.69μm compared to 1 μm for the LCM (vk4 file) data, which implies a lower resolution for the WAMS images. Conversely, the ratio of dynamic range of the WAMS data to the LCM data was approximately 41:20 for height data, suggesting that information from WAMS should more accurately determine the depth of pits. At present, the significance of the greater dynamic range of the WAMS data relative to the LCM data has not yet been evaluated.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

FY22 Progress Report: SRNL Analysis of ICCWR LCM and WAMS Data for Corrosion and Cracking

Algorithms for machine learning and data analysis for the 3013 Surveillance Program are being developed in an ongoing collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). To detect the presence of corrosion and cracking, data is collected from large binary files generated by a Laser Confocal Microscope (LCM) or Wide Area 3D Measurement System (WAMS). Software is being developed to use the physical attributes in the data files (e.g., height, color, and grayscale values; all as functions of a location in a plane projection) to detect the presence of surface corrosion and cracking. A user-friendly Matlab Graphical User Interface (GUI) that reads data from either LCM or WAMS files was developed to integrate input data with software developed for processing and evaluation. The GUI can selectively download binary data, interrogate data attributes, label data for training ML algorithms, flag significant features, execute Machine Learning (ML) algorithms, output parameters from trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. Surface defects can be called out by setting user-specified thresholds, feature based analysis or machine learning algorithms. 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 very large volume of data required to train ML algorithms.

3013 Corrosion↗
DOE OSTI2022

Oxidation of p-[125I]Iodobenzoic Acid and p-[211At]Astatobenzoic Acid Derivatives and Evaluation In Vivo

The alpha particle-emitting radionuclide astatine-211 (211At) is of interest for targeted radiotherapy; however, low in vivo stability of many 211At-labeled cancer-targeting molecules has limited its potential. As an alternative labeling method, we evaluated whether a specific type of astatinated aryl compound that has the At atom in a higher oxidation state might be stable to in vivo deastatination. In the research effort, para-iodobenzoic acid methyl ester and dPEG4-amino acid methyl ester derivatives were prepared as HPLC standards. The corresponding para-stannylbenzoic acid derivatives were also prepared and labeled with 125I and 211At. Oxidization of the [125I]iodo- and [211At]astato-benzamidyl-dPEG4-acid methyl ester derivatives provided materials for in vivo evaluation. A biodistribution was conducted in mice with coinjected oxidized 125I- and 211At-labeled compounds. The oxidized radioiodinated derivative was stable to in vivo deiodination, but unfortunately the oxidized [211At]astatinated benzamide derivative was found to be unstable under the conditions of isolation by radio-HPLC (post animal injection). Another biodistribution study in mice evaluated the tissue concentrations of coinjected [211At]NaAtO3 and [125I]NaIO3. Comparison of the tissue concentrations of the isolated material from the oxidized [211At]benzamide derivative with those of [211At]astatate indicated the species obtained after isolation was likely [211At]astatate.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Self-supervised Representation Learning for Astronomical Images

Sky surveys are the largest data generators in astronomy, making automated tools for extracting meaningful scientific information an absolute necessity. We show that, without the need for labels, self-supervised learning recovers representations of sky survey images that are semantically useful for a variety of scientific tasks. These representations can be directly used as features, or fine-tuned, to outperform supervised methods trained only on labeled data. We apply a contrastive learning framework on multiband galaxy photometry from the Sloan Digital Sky Survey (SDSS), to learn image representations. We then use them for galaxy morphology classification and fine-tune them for photometric redshift estimation, using labels from the Galaxy Zoo 2 data set and SDSS spectroscopy. In both downstream tasks, using the same learned representations, we outperform the supervised state-of-the-art results, and we show that our approach can achieve the accuracy of supervised models while using 2-4 times fewer labels for training. The codes, trained models, and data can be found at https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

A semi-supervised machine learning detector for physics events in tokamak discharges

Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (>85%) for H-L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only 3 discharges are initially labeled by the user. Lower yet reasonable performance (~75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. This suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelity as the user strategically adds manually labeled examples. Detections on Alcator C-Mod and EAST are also shown, demonstrating the potential for this to be used on a multi-tokamak dataset.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1981

AgRISTARS: Foreign commodity production forecasting. The 1980 US corn and soybeans exploratory experiment

The U.S. corn and soybeans exploratory experiment is described which consisted of evaluations of two technology components of a production forecasting system: classification procedures (crop labeling and proportion estimation at the level of a sampling unit) and sampling and aggregation procedures. The results from the labeling evaluations indicate that the corn and soybeans labeling procedure works very well in the U.S. corn belt with full season (after tasseling) LANDSAT data. The procedure should be readily adaptable to corn and soybeans labeling required for subsequent exploratory experiments or pilot tests. The machine classification procedures evaluated in this experiment were not effective in improving the proportion estimates. The corn proportions produced by the machine procedures had a large bias when the bias correction was not performed. This bias was caused by the manner in which the machine procedures handled spectrally impure pixels. The simulation test indicated that the weighted aggregation procedure performed quite well. Although further work can be done to improve both the simulation tests and the aggregation procedure, the results of this test show that the procedure should serve as a useful baseline procedure in future exploratory experiments and pilot tests.

Malin, J. T.↗