Search NASA⌕ Search

SEARCH · Search NASA

Results for “annotated data”

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 OSTI2024

Genome-wide profiling of histone (H3) lysine 4 (K4) tri-methylation (me3) under drought, heat, and combined stresses in switchgrass

Background: Switchgrass (Panicum virgatum L.) is a warm-season perennial (C4) grass identified as an important biofuel crop in the United States. It is well adapted to the marginal environment where heat and moisture stresses predominantly affect crop growth. However, the underlying molecular mechanisms associated with heat and drought stress tolerance still need to be fully understood in switchgrass. The methylation of H3K4 is often associated with transcriptional activation of genes, including stress-responsive. Therefore, this study aimed to analyze genome-wide histone H3K4-tri-methylation in switchgrass under heat, drought, and combined stress. Results: In total, ~ 1.3 million H3K4me3 peaks were identified in this study using SICER. Among them, 7,342; 6,510; and 8,536 peaks responded under drought (DT), drought and heat (DTHT), and heat (HT) stresses, respectively. Most DT and DTHT peaks spanned 0 to + 2000 bases from the transcription start site [TSS]. By comparing differentially marked peaks with RNA-Seq data, we identified peaks associated with genes: 155 DT-responsive peaks with 118 DT-responsive genes, 121 DTHT-responsive peaks with 110 DTHT-responsive genes, and 175 HT-responsive peaks with 136 HT-responsive genes. We have identified various transcription factors involved in DT, DTHT, and HT stresses. Gene Ontology analysis using the AgriGO revealed that most genes belonged to biological processes. Most annotated peaks belonged to metabolite interconversion, RNA metabolism, transporter, protein modifying, defense/immunity, membrane traffic protein, transmembrane signal receptor, and transcriptional regulator protein families. Further, we identified significant peaks associated with TFs, hormones, signaling, fatty acid and carbohydrate metabolism, and secondary metabolites. qRT-PCR analysis revealed the relative expressions of six abiotic stress-responsive genes (transketolase, chromatin remodeling factor-CDH3, fatty-acid desaturase A, transmembrane protein 14C, beta-amylase 1, and integrase-type DNA binding protein genes) that were significantly (P < 0.05) marked during drought, heat, and combined stresses by comparing stress-induced against un-stressed and input controls. Conclusion: Our study provides a comprehensive and reproducible epigenomic analysis of drought, heat, and combined stress responses in switchgrass. Significant enrichment of H3K4me3 peaks downstream of the TSS of protein-coding genes was observed. In addition, the cost-effective experimental design, modified ChIP-Seq approach, and analyses presented here can serve as a prototype for other non-model plant species for conducting stress studies.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Deeplasmid: deep learning accurately separates plasmids from bacterial chromosomes

Plasmids are mobile genetic elements that play a key role in microbial ecology and evolution by mediating horizontal transfer of important genes, such as antimicrobial resistance genes. Many microbial genomes have been sequenced by short read sequencers and have resulted in a mix of contigs that derive from plasmids or chromosomes. New tools that accurately identify plasmids are needed to elucidate new plasmid-borne genes of high biological importance. We have developed Deeplasmid, a deep learning tool for distinguishing plasmids from bacterial chromosomes based on the DNA sequence and its encoded biological data. It requires as input only assembled sequences generated by any sequencing platform and assembly algorithm and its runtime scales linearly with the number of assembled sequences. Deeplasmid achieves an AUC–ROC of over 89%, and it was more accurate than five other plasmid classification methods. Finally, as a proof of concept, we used Deeplasmid to predict new plasmids in the fish pathogen Yersinia ruckeri ATCC 29473 that has no annotated plasmids. Deeplasmid predicted with high reliability that a long assembled contig is part of a plasmid. Using long read sequencing we indeed validated the existence of a 102 kb long plasmid, demonstrating Deeplasmid's ability to detect novel plasmids.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Foldy: An open-source web application for interactive protein structure analysis

Foldy is a cloud-based application that allows non-computational biologists to easily utilize advanced AI-based structural biology tools, including AlphaFold and DiffDock. With many deployment options, it can be employed by individuals, labs, universities, and companies in the cloud without requiring hardware resources, but it can also be configured to utilize locally available computers. Foldy enables scientists to predict the structure of proteins and complexes up to 6000 amino acids with AlphaFold, visualize Pfam annotations, and dock ligands with AutoDock Vina and DiffDock. In our manuscript, we detail Foldy’s interface design, deployment strategies, and optimization for various user scenarios. We demonstrate its application through case studies including rational enzyme design and analyzing proteins with domains of unknown function. Furthermore, we compare Foldy’s interface and management capabilities with other open and closed source tools in the field, illustrating its practicality in managing complex data and computation tasks. Our manuscript underlines the benefits of Foldy as a day-to-day tool for life science researchers, and shows how Foldy can make modern tools more accessible and efficient.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Knowledge Graph for End-to-End Traceability of an Integrated Human-Earth System Model

Integrated human-Earth system models inform energy-water-land system dynamics and policies, yet their results are difficult to trace through input-data, model structure, scenario configurations, and solved outputs. Because this information is siloed across disconnected artifacts, process-based IAMs have historically lacked a unified, queryable representation. Such lack of traceability prevents researchers from systematically isolating the multi-sector drivers of complex outcomes (such as tracing water-scarcity results back to distant energy-system dynamics) or conducting holistic uncertainty attribution across hundreds of interacting parameters. To address this concern, our work documents the software engineering process of a knowledge graph that unifies these four layers for the Global Change Analysis Model (GCAM-USA_Reference scenario, GCAM v9.1). The graph was built as a relational property graph in DuckDB from the run’s own artifacts: the input-preparation dependency map (gcamdata chunk map), the model’s XML input files, the run configuration, and the results database (BaseX), successfully mapping the model’s declared structure. The resulting graph comprises 204,321 nodes and 1,687,814 edges across 16 node types and 15 edge types, with approximately 16.3 million time-series values stored separately to maintain structural efficiency. To ensure representation fidelity, every edge carries an epistemic-status annotation recording the warrant for the relationship (structural, provenance, dependency, or model-derived), and a machine-readable provenance ledger classifying the origin of every schema element. Evaluation against a fixed five-benchmark suite with locked baselines reports zero structural orphans, zero dangling edge endpoints, and 100% of output-producing technologies traceable to raw input files. Two interactive interfaces present the graph, including a serverless browser application built on DuckDB-Wasm. By establishing the first end-to-end provenance framework for an IAM, this work enables researchers and scientists to systematically audit complex policy scenarios, debug model structures, and trace policy-relevant outputs to their data origins in real time.

Artifical Intelligence↗
NASA NTRS2025

Navigating Team Dynamics: Automated Detection of Micro-Behaviors Between Team Members Through Longitudinal Interaction Data

The success in future long term space exploration missions will depend on the cooperation, coordination, and mutual understanding among the crew members. Micro-behaviors are momentary, subtle linguistic and paralinguistic indicators of thinking and feeling toward another member of the team (Cortina et al., 2001; Smith & Griffiths, 2022) that can significantly impact team dynamics and influence the overall team performance (Paromita & Chaspari, 2024). Due to their interactive nature, micro-behaviors have a sender (i.e., the team member expressing the micro-behavior) and a target (the team member impacted by the micro-behavior). Detection of these behaviors can assist in avoiding possible conflict among crew members and promoting the overall team success. Our prior research focused on an initial proof of concept of machine learning (ML) models and natural language processing (NLP) techniques that were used for automatically detect micro-behaviors among crew members of the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA) Campaigns 4 and 5 missions (Paromita et al., 2023). Results underscored the importance of incorporating contextual information in the ML models in the form of sentiment analysis, type of task, and dyadic interaction among team members. Here, we expand the scope of our prior work in two ways. First, we assess ML/NLP methods on new behavioral annotations coded using an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). Second, we expand the design of the ML model to preserve information about the role of each team member within the occurrence of the micro-behavior (in contrast to the previous model that only considered the sender and the target without determining the team member role). This allows to consider all team members' contributions in the conversation and model long-term dependencies in the dialogue. Our experiments for this study are conducted on data from 5 teams of the NASA HERA C4 (NASA grant NNX16AQ48G (PI: Bell)). Conversations were extracted from the 1.5 hour Team Interaction Battery (TIB) task that occurred 5 times in-mission per crew. This resulted in a total of 13,058 conversational turns (i.e., 17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls). Our findings with the revised behavioral coding and ML/NLP models indicate a 43.66% macro F1-score (i.e., 38.29% precision (P), 50.8% recall (R)) for a dialog state-tracking model that includes information from the sender only, and a 40.9% F1-score (i.e., 38.7% P, 43.36% R) for the same model that includes information from both the sender and the target of the micro-behavior. These are significantly higher compared to simple random forest models that classify behaviors strictly based on speech content and do not consider iterative team dynamics, achieving a 36.07% F1-score (i.e., 39.04% R, 33.53% P). Our findings demonstrate potential ways to leverage large conversational datasets to better capture complex team dynamics. We will discuss future directions including proposed models that can incorporate additional mission days and tasks beyond the TIB for objectively quantifying team behavior at high temporal resolution in space exploration missions.

Projna Paromita↗
DOE OSTI2023

The Human Phenotype Ontology in 2024: phenotypes around the world

The Human Phenotype Ontology (HPO) is a widely used resource that comprehensively organizes and defines the phenotypic features of human disease, enabling computational inference and supporting genomic and phenotypic analyses through semantic similarity and machine learning algorithms. The HPO has widespread applications in clinical diagnostics and translational research, including genomic diagnostics, gene-disease discovery, and cohort analytics. In recent years, groups around the world have developed translations of the HPO from English to other languages, and the HPO browser has been internationalized, allowing users to view HPO term labels and in many cases synonyms and definitions in ten languages in addition to English. Since our last report, a total of 2239 new HPO terms and 49235 new HPO annotations were developed, many in collaboration with external groups in the fields of psychiatry, arthrogryposis, immunology and cardiology. The Medical Action Ontology (MAxO) is a new effort to model treatments and other measures taken for clinical management. Finally, the HPO consortium is contributing to efforts to integrate the HPO and the GA4GH Phenopacket Schema into electronic health records (EHRs) with the goal of more standardized and computable integration of rare disease data in EHRs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Evolution and comparative genomics of the most common Trichoderma species

Background: The growing importance of the ubiquitous fungal genus Trichoderma (Hypocreales, Ascomycota) requires understanding of its biology and evolution. Many Trichoderma species are used as biofertilizers and biofungicides and T. reesei is the model organism for industrial production of cellulolytic enzymes. In addition, some highly opportunistic species devastate mushroom farms and can become pathogens of humans. A comparative analysis of the first three whole genomes revealed mycoparasitism as the innate feature of Trichoderma. However, the evolution of these traits is not yet understood. Results: We selected 12 most commonly occurring Trichoderma species and studied the evolution of their genome sequences. Trichoderma evolved in the time of the Cretaceous-Palaeogene extinction event 66 (±15) mya, but the formation of extant sections (Longibrachiatum, Trichoderma) or clades (Harzianum/Virens) happened in Oligocene. The evolution of the Harzianum clade and section Trichoderma was accompanied by significant gene gain, but the ancestor of section Longibrachiatum experienced rapid gene loss. The highest number of genes gained encoded ankyrins, HET domain proteins and transcription factors. We also identified the Trichoderma core genome, completely curated its annotation, investigated several gene families in detail and compared the results to those of other fungi. Eighty percent of those genes for which a function could be predicted were also found in other fungi, but only 67% of those without a predictable function. Conclusions: Our study presents a time scaled pattern of genome evolution in 12 Trichoderma species from three phylogenetically distant clades/sections and a comprehensive analysis of their genes. The data offer insights in the evolution of a mycoparasite towards a generalist.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Evaluation of a Reference-Free Collision Cross Section Calibration Strategy for Proteomics Using SLIM-Based High-Resolution Ion Mobility Spectrometry–Mass Spectrometry

Ion mobility spectrometry (IMS) is a gas-phase analytical technique that separates ions with different sizes and shapes and is compatible with mass spectrometry (MS) to provide an additional separation dimension. The rapid nature of the IMS separation combined with the high sensitivity of MS-based detection and the ability to derive structural information on analytes in the form of the property collision cross section (CCS) makes IMS particularly well-suited for characterizing complex samples in -omics applications. In such applications, the quality of CCS from IMS measurements is critical to confident annotation of the detected components in the complex -omics samples. However, most IMS instrumentation in mainstream use requires calibration to calculate CCS from measured arrival times, with the most notable exception being drift tube IMS measurements using multifield methods. The strategy for calibrating CCS values, particularly selection of appropriate calibrants, has important implications for CCS accuracy, reproducibility, and transferability between laboratories. The conventional approach to CCS calibration involves explicitly defining calibrants ahead of data acquisition and crucially relies upon availability of reference CCS values. In this work, we present a novel reference-free approach to CCS calibration which leverages trends among putatively identified features and computational CCS prediction to conduct calibrations post-data acquisition and without relying on explicitly defined calibrants. We demonstrated the utility of this reference-free CCS calibration strategy for proteomics application using high-resolution structures for lossless ion manipulations (SLIM)-based IMS-MS. In conclusion, we first validated the accuracy of CCS values using a set of synthetic peptides and then demonstrated using a complex peptide sample from cell lysate.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2018

The ATLAS Event Index: The Architecture of the Core Engine

The global view of the ATLAS Event Index system has been presented in the 17th ACAT Conference. This article concentrates on the architecture of the system core component. This component handles the final stage of the event metadata import. It organizes its storage and provides a fast and feature-rich access to all information. A user is able to interrogate metadata in various ways, including by executing user-provided code on the data to make selections and to interpret the results. A wide spectrum of clients is available, from a set of Linux-like commands to an interactive graphical Web Service. The stored event metadata contain the basic description of the related events, the references to the experiment event storage and the full trigger record and can be extended with other event characteristics. Derived collections of events can be created. Such collections can be annotated and tagged with further information.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2026

UCB-GLOBES: An open-access mass spectral database of identified and unidentified atmospheric organic compounds

Chemical characterization of atmospheric organic aerosols using gas chromatography with 70 eV electron ionization mass spectrometry (GC/EI-MS) has been used for decades in advancing molecular marker detection and identification, though primarily through suspect screening and/or targeted analyses. To advance non-targeted analyses of environmental samples, we have catalogued approximately 27 000 mass spectra (MS) of the trimethylsilyl derivatives of semi-volatile organic aerosol (OA) analytes in the open-access University of California Berkeley Goldstein Library of Organic Biogenic Environmental Spectra (UCB-GLOBES). Analytes were observed in ambient samples from the U.S. and the Central Amazon and/or laboratory simulations of secondary OA (SOA) formation. These samples are representative of OA under urban and biomass burning influences as well as SOA derived from biogenic precursors (e.g., isoprene, monoterpenes, sesquiterpenes) and biomass burning intermediates. MS are documented in UCB-GLOBES without regard to known chemical identity, annotated with extensive metadata such as sample source/experimental conditions, any structural information gained from MS analyses, and predicted chemical properties such as average carbon oxidation state and carbon number. UCB-GLOBES MS are compatible for importing into the NIST MS Search program, and we have also provided a Jupyter Notebook for MS visualization and comparisons. We demonstrate the utility of UCB-GLOBES through MS reanalyses of prior analytes observed in ambient data, finding a 20 % reduction in the number of analytes assigned to OA source categories reliant solely on time series correlation and an overall 11 % increase in new MS-based OA source categorization for the Southeast U.S. For 1513 analytes observed previously in the Central Amazon, we found 375 MS matches using UCB-GLOBES vs. 136 MS matches during prior analyses, representing a 14 % gain in newly confirmed or newly categorized OA species. While OA from laboratory oxidation experiments in UCB-GLOBES are highly diverse chemically, on average only 29 % of UCB-GLOBES MS have a mass spectral match to another MS entry in UCB-GLOBES and/or in databases of known compounds (i.e. NIST MS Database, Adams Essential Oil, MANE Flavor and Fragrance Company). This indicates that roughly 70 % of UCB-GLOBES MS are unique thus far, not observed more than once among the laboratory oxidation samples and ambient data in UCB-GLOBES MS. Further, only 18 % can be positively identified using these databases or known authentic standards. This points to a large gap between these laboratory simulations and ambient OA. Overall, the UCB-GLOBES database can be utilized for improving confidence in OA source categorization and/or identification, novel chemical marker discovery, tracking chemical diversity, de novo structure and properties prediction, and improving MS search and matching algorithms. This can ultimately inform future research priorities for the chemical characterization of atmospheric organic samples.

Mass spectrometry↗
DOE OSTI2024

Signature analysis of high-throughput transcriptomics screening data for mechanistic inference and chemical grouping

Abstract High-throughput transcriptomics (HTTr) uses gene expression profiling to characterize the biological activity of chemicals in in vitro cell-based test systems. As an extension of a previous study testing 44 chemicals, HTTr was used to screen an additional 1,751 unique chemicals from the EPA’s ToxCast collection in MCF7 cells using 8 concentrations and an exposure duration of 6 h. We hypothesized that concentration-response modeling of signature scores could be used to identify putative molecular targets and cluster chemicals with similar bioactivity. Clustering and enrichment analyses were conducted based on signature catalog annotations and ToxPrint chemotypes to facilitate molecular target prediction and grouping of chemicals with similar bioactivity profiles. Enrichment analysis based on signature catalog annotation identified known mechanisms of action (MeOAs) associated with well-studied chemicals and generated putative MeOAs for other active chemicals. Chemicals with predicted MeOAs included those targeting estrogen receptor (ER), glucocorticoid receptor (GR), retinoic acid receptor (RAR), the NRF2/KEAP/ARE pathway, AP-1 activation, and others. Using reference chemicals for ER modulation, the study demonstrated that HTTr in MCF7 cells was able to stratify chemicals in terms of agonist potency, distinguish ER agonists from antagonists, and cluster chemicals with similar activities as predicted by the ToxCast ER Pathway model. Uniform manifold approximation and projection (UMAP) embedding of signature-level results identified novel ER modulators with no ToxCast ER Pathway model predictions. Finally, UMAP combined with ToxPrint chemotype enrichment was used to explore the biological activity of structurally related chemicals. The study demonstrates that HTTr can be used to inform chemical risk assessment by determining in vitro points of departure, predicting chemicals’ MeOA and grouping chemicals with similar bioactivity profiles.

Toxicology↗
DOE OSTI2022

Identifying Disinformation Using Rhetorical Devices in Natural Language Models

Foreign disinformation campaigns are strategically organized, extended efforts using disinformation – false or misleading information deliberately placed by an adversary – to achieve some goal. Disinformation campaigns pose severe threats to our nation’s security by misinforming decision makers and negatively influencing their actions when they are operating on limited amounts of evidence. Current efforts rely on subject matter experts to manually identify disinformation, or on computers and traditional natural language processing algorithms to identify patterns in data to calculate the probability that something is disinformation or not. While both have their merits and successes, subject matter experts are unable to keep up with the high volumes of global information and traditional natural language algorithms do not do well in identifying “why” something is disinformation or not. Our hypothesis is that we can identify disinformation by looking at the way someone speaks, in the rhetorical devices they use. We have curated and annotated a dataset designed for multiple natural language processing tasks, but specifically useful for disinformation detection algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Poplar: a phylogenomics pipeline

Motivation Generating phylogenomic trees from the genomic data is essential in understanding biological systems. Each step of this complex process has received extensive attention and has been significantly streamlined over the years. Given the public availability of data, obtaining genomes for a wide selection of species is straightforward. However, analyzing that data to generate a phylogenomic tree is a multistep process with legitimate scientific and technical challenges, often requiring a significant input from a domain-area scientist. Results We present Poplar, a new, streamlined computational pipeline, to address the computational logistical issues that arise when constructing the phylogenomic trees. It provides a framework that runs state-of-the-art software for essential steps in the phylogenomic pipeline, beginning from a genome with or without an annotation, and resulting in a species tree. Running Poplar requires no external databases. In the execution, it enables parallelism for execution for clusters and cloud computing. The trees generated by Poplar match closely with state-of-the-art published trees. The usage and performance of Poplar is far simpler and quicker than manually running a phylogenomic pipeline. Availability and implementation Freely available on GitHub at https://github.com/sandialabs/poplar. Implemented using Python and supported on Linux.

Koning, Elizabeth [Sandia National Laboratories (S↗
DOE OSTI2022

Genome Sequence and Analysis of the Flavinogenic Yeast Candida membranifaciens IST 626

The ascomycetous yeast Candida membranifaciens has been isolated from diverse habitats, including humans, insects, and environmental sources, exhibiting a remarkable ability to use different carbon sources that include pentoses, melibiose, and inulin. In this study, we isolated four C. membranifaciens strains from soil and investigated their potential to overproduce riboflavin. C. membranifaciens IST 626 was found to produce the highest concentrations of riboflavin. The volumetric production of this vitamin was higher when C. membranifaciens IST 626 cells were cultured in a commercial medium without iron and when xylose was the available carbon source compared to the same basal medium with glucose. Supplementation of the growth medium with 2 g/L glycine favored the metabolization of xylose, leading to biomass increase and consequent enhancement of riboflavin volumetric production that reached 120 mg/L after 216 h of cultivation. To gain new insights into the molecular basis of riboflavin production and carbon source utilization in this species, the first annotated genome sequence of C. membranifaciens is reported in this article, as well as the result of a comparative genomic analysis with other relevant yeast species. A total of 5619 genes were predicted to be present in C. membranifaciens IST 626 genome sequence (11.5 Mbp). Among them are genes involved in riboflavin biosynthesis, iron homeostasis, and sugar uptake and metabolism. This work put forward C. membranifaciens IST 626 as a riboflavin overproducer and provides valuable molecular data for future development of superior producing strains capable of using the wide range of carbon sources, which is a characteristic trait of the species.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1991

Annotated bibliography of Software Engineering Laboratory literature

An annotated bibliography of technical papers, documents, and memorandums produced by or related to the Software Engineering Laboratory is given. More than 100 publications are summarized. These publications cover many areas of software engineering and range from research reports to software documentation. All materials have been grouped into eight general subject areas for easy reference: The Software Engineering Laboratory; The Software Engineering Laboratory: Software Development Documents; Software Tools; Software Models; Software Measurement; Technology Evaluations; Ada Technology; and Data Collection. Subject and author indexes further classify these documents by specific topic and individual author.

Morusiewicz, Linda↗
NASA NTRS1989

Annotated bibliography of software engineering laboratory literature

An annotated bibliography is presented of technical papers, documents, and memorandums produced by or related to the Software Engineering Laboratory. The bibliography was updated and reorganized substantially since the original version (SEL-82-006, November 1982). All materials were grouped into eight general subject areas for easy reference: (1) The Software Engineering Laboratory; (2) The Software Engineering Laboratory: Software Development Documents; (3) Software Tools; (4) Software Models; (5) Software Measurement; (6) Technology Evaluations; (7) Ada Technology; and (8) Data Collection. Subject and author indexes further classify these documents by specific topic and individual author.

Buhler, Melanie↗
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 OSTI2020

Compiler and Runtime Approaches to Enable Large-Scale Irregular Programs. Final report, July 2013 - July 2019

While regular algorithms, characterized by operations on dense matrices and arrays, have long been the mainstay of scientific, high-performance computing, irregular algorithms, which feature unpredictable accesses to pointer-based data structures, are becoming increasingly common in high performance computing, arising in graph analysis, data mining and visualization, among other domains. Unfortunately, the defining characteristics of irregular applications, their dynamic, unpredictable, data-dependent access patterns and data layouts, make achieving high performance on large scale systems difficult. Scaling applications to peta- and exa-scale requires carefully controlling communication and data movement and placement, an inherently difficult task when access patterns and data layouts are unpredictable! Most irregular applications that attain high performance must be painstakingly hand-written and hand-tuned, with few common principles or paradigms uniting various implementations and easing future development. Despite the increasing importance of irregular applications, there is little programmer knowledge, and even less compiler ability, devoted to optimizing them. This project aims to solve these problems. By allowing programmers to write irregular applications in high level forms, with at most a few annotations highlighting key structural properties, programmers can focus on developing their algorithms and methods. The compiler and run-time system can take on the tedious task of optimizing the application for execution at large scales, and can automatically provide efficient implementations. This will provide portability and ease maintenance for existing irregular applications, but, more importantly, open up whole new domains of computational science to large-scale, high-performance simulation codes.

97 MATHEMATICS AND COMPUTING↗