SEARCH · Engineering Papers

Results for “Science Pipeline”

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.

SourceResearch connectionFrom yearThrough year

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

At least 793 records · Page 44

All sources NASA NTRS DOE OSTI

NASA NTRS2013

NASA Sounding Rocket Program Educational Outreach

Educational and public outreach is a major focus area for the National Aeronautics and Space Administration (NASA). The NASA Sounding Rocket Program (NSRP) shares in the belief that NASA plays a unique and vital role in inspiring future generations to pursue careers in science, mathematics, and technology. To fulfill this vision, the NSRP engages in a variety of educator training workshops and student flight projects that provide unique and exciting hands-on rocketry and space flight experiences. Specifically, the Wallops Rocket Academy for Teachers and Students (WRATS) is a one-week tutorial laboratory experience for high school teachers to learn the basics of rocketry, as well as build an instrumented model rocket for launch and data processing. The teachers are thus armed with the knowledge and experience to subsequently inspire the students at their home institution. Additionally, the NSRP has partnered with the Colorado Space Grant Consortium (COSGC) to provide a "pipeline" of space flight opportunities to university students and professors. Participants begin by enrolling in the RockOn! Workshop, which guides fledgling rocketeers through the construction and functional testing of an instrumentation kit. This is then integrated into a sealed canister and flown on a sounding rocket payload, which is recovered for the students to retrieve and process their data post flight. The next step in the "pipeline" involves unique, user-defined RockSat-C experiments in a sealed canister that allow participants more independence in developing, constructing, and testing spaceflight hardware. These experiments are flown and recovered on the same payload as the RockOn! Workshop kits. Ultimately, the "pipeline" culminates in the development of an advanced, user-defined RockSat-X experiment that is flown on a payload which provides full exposure to the space environment (not in a sealed canister), and includes telemetry and attitude control capability. The RockOn! and RockSat-C elements of the "pipeline" have been successfully demonstrated by five annual flights thus far from Wallops Flight Facility. RockSat-X has successfully flown twice, also from Wallops. The NSRP utilizes launch vehicles comprised of military surplus rocket motors (Terrier-Improved Orion and Terrier-Improved Malemute) to execute these missions. The NASA Sounding Rocket Program is proud of its role in inspiring the "next generation of explorers" and is working to expand its reach to all regions of the United States and the international community as well.

Rosanova, G.↗

NASA NTRSDate not supplied

Supporting Space Weather with the Geospace Dynamics Constellation

The Geospace Dynamics Constellation (GDC) mission, planned to launch at the end of the decade, is a six-satellite constellation that will fly through the ionosphere and thermosphere at around 400 km. While GDC is a science mission, its comprehensive instrumentation will not only contribute to our understanding of space weather phenomena in the ionosphere-thermosphere system, but will also provide valuable, space weather-relevant data. Data from GDC will be made available at low latency via real-time space weather data stream. We are working with operational partners to identify space weather data products and coordinate reception of the space weather beacon data. Alongside preparations for real-time GDC data streams, we are working to identify current model capabilities and needs, to ensure that space weather models that can make use of GDC measurements are moving along the Research-toOperations pipeline. Before GDC launch, Observing System Simulation Experiments (OSSEs) carried out with synthetic GDC data can be used to demonstrate the capabilities of models and to predict the impact of GDC data. Following launch, Observing System Experiments (OSEs) will demonstrate the impact of GDC space weather data. In preparation for GDC, the ITM space weather community should establish baseline metrics for space weather parameters of scientific and operational interest. These metrics, tracked over time before and after the launch of GDC, will allow us to track advancements in forecasting, nowcasting, and hindcasting of the ITM system and to trace the impact of scientific progress from space weather research into operations. By demonstrating the impact of real-time GDC data, specific data needs can be identified and prioritized for long term investment on future observing systems.

Katherine Garcia-Sage↗

DOE OSTI2017

Draft genome sequence of Chryseobacterium limigenitum SUR2 T (LMG 28734 T ) isolated from dehydrated sludge

The type strain SUR2 of the novel species Chryseobacterium limigenitum was isolated from a dehydrated sludge of the municipal sewage treatment plant in Dogoše near Maribor in Slovenia. The draft genome, with 60 contigs, 4,697,725 bp, 34.4% of G+C content, was obtained using the Illumina HiSeq 2500-1 platform. Joint Genome Institute Microbial Genome Annotation Pipeline (MGAP v.4) has identified 4322 protein-coding sequences including resistance genes against arsenic and other heavy metals. In addition, a subclass B3 metallo-β-lactamase, which confers resistance to penicillins, cephalosporins and carbapenems, was also present in the genome. The genome sequence provides important information regarding bioremediation potential and pathogenic properties of this newly identified species.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

End-to-end learning of multiple sequence alignments with differentiable Smith–Waterman

Abstract Motivation Multiple sequence alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA generation is often treated as a separate pre-processing step, without any guidance from the application it will be used for. Results Here, we implement a smooth and differentiable version of the Smith–Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold2 and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of optimizing predictions of protein sequences with methods that are not fully understood. Availability and implementation Our code and examples are available at: https://github.com/spetti/SMURF. Supplementary information Supplementary data are available at Bioinformatics online.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Engineering Crassulacean Acid Metabolism in C 3 and C 4 Plants

Carbon dioxide (CO 2 ) is a major greenhouse gas contributing to changing climatic conditions, which is a grand challenge affecting the security of food, energy, and environment. Photosynthesis plays the central role in plant-based CO 2 reduction. Additionally, plants performing CAM (crassulacean acid metabolism) photosynthesis have a much higher water use efficiency than those performing C 3 or C 4 photosynthesis. Therefore, there is a great potential for engineering CAM in C 3 or C 4 crops to enhance food/biomass production and carbon sequestration on arid, semiarid, abandoned, or marginal lands. Recent progresses in CAM plant genomics and evolution research, along with new advances in plant biotechnology, have provided a solid foundation for bioengineering to convert C 3 /C 4 plants into CAM plants. Here, we first discuss the potential strategies for CAM engineering based on our current understanding of CAM evolution. Then we describe the technical approaches for engineering CAM in C 3 and C 4 plants, with a focus on an iterative four-step pipeline: (1) designing gene modules, (2) building the gene modules and transforming them into target plants, (3) testing the engineered plants through an integration of molecular biology, biochemistry, metabolism, and physiological approaches, and (4) learning to inform the next round of CAM engineering. Finally, we discuss the challenges and future opportunities for fully realizing the potential of CAM engineering.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

Structure-Aware Unsupervised, Transformational Machine Learning for Drug Discovery (DTRA Basic Research Final Report)

The major goal of this project is to develop machine learning (ML) methods to enable improved predictive power on real drug discovery for novel targets. More specifically, we planned to demonstrate the capability and effectiveness of ML tools utilizing unlabeled large-volume protein-ligand datasets. We investigated multiple pre-training approaches for 3D protein-ligand structure-based foundation models, without relying on experimental binding data. We also addressed scenarios in which crystal structures are unavailable or binding data are limited. We also planned to develop a complete pipeline to screen novel compounds as well as to demonstrate the capability and effectiveness of the developed methods by testing on a realistic drug discovery task such as SARS-CoV-2. While the major goals and milestones remain consistent with the original proposal, certain technical details have been adjusted, based on the experimental results and related outcomes.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

High-Throughput Field Plant Phenotyping: A Self-Supervised Sequential CNN Method to Segment Overlapping Plants

High-throughput plant phenotyping—the use of imaging and remote sensing to record plant growth dynamics—is becoming more widely used. The first step in this process is typically plant segmentation, which requires a well-labeled training dataset to enable accurate segmentation of overlapping plants. However, preparing such training data is both time and labor intensive. To solve this problem, we propose a plant image processing pipeline using a self-supervised sequential convolutional neural network method for in-field phenotyping systems. This first step uses plant pixels from greenhouse images to segment nonoverlapping in-field plants in an early growth stage and then applies the segmentation results from those early-stage images as training data for the separation of plants at later growth stages. The proposed pipeline is efficient and self-supervising in the sense that no human-labeled data are needed. We then combine this approach with functional principal components analysis to reveal the relationship between the growth dynamics of plants and genotypes. We show that the proposed pipeline can accurately separate the pixels of foreground plants and estimate their heights when foreground and background plants overlap and can thus be used to efficiently assess the impact of treatments and genotypes on plant growth in a field environment by computer vision techniques. This approach should be useful for answering important scientific questions in the area of high-throughput phenotyping.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRSDate not supplied

Artificial Intelligence (AI) Methods for Augmenting the IMPACT Tool Evidence Library

Development of the Evidence Library for use with the IMPACT probability risk assessment tool took several years and involved a staggering amount of effort from a multi-disciplinary team. A very significant amount of the labor effort to collect, assess and finalize the Clinical Finding Form (CliFF) for each of the 119 medical conditions was provided by physician subject matter experts from the Exploration Medical Capability (ExMC) Element Clinical and Science Team. Many AI tools such as ChatGPT are excellent at summarizing large amounts of information and the current project was initiated to determine how such tools might streamline laborious processes, e.g., review and summarization of many scientific research publications, to execute key steps more efficiently in the process of developing CliFFs. The process for collecting the evidence which is found in the CliFFs is well documented in the Evidence Library Methods document (ELM; HRP-48036*). Using ELM and the CliFF development instructions as a guideline, a team of developers is leveraging Microsoft Azure AI tools and services along with open-source frameworks, to construct an AI-assisted automated pipeline. This pipeline is designed to search, retrieve, and process the necessary data sources, and ultimately help generate the final version of a CliFF. Currently, the large language model evaluates the relevance of each source material to spaceflights, either as direct evidence or as an analog. Additionally, the model assists in extracting keywords and generating brief summaries to enhance augmented retrieval and search processes in later stages of CliFF development. Once the data is ready, the model can perform semantic search and retrieval, generating and extracting valuable information for the CliFF. For instance, it can handle epidemiological statistical data, such as incidence rates and the likelihood of best or worst-case scenarios. The steps that required reading and summarizing articles were viewed as providing the greatest return on investment since large language models are very efficient and accurate in summarizing large amounts of text. Since labor effort to complete the original CliFF was not recorded with sufficient granularity, comparisons with an AI tool-generated CliFF will provide merely an approximation of time saved. Upon completion of the process, the CliFF for the medical condition “appendicitis” generated with the support of AI-based methods will serve as a proof-of-concept and will be compared to the original appendicitis CliFF to determine if use of the tools resulted in content and conclusory similarity. Based upon the results from face validation of the two CliFFs, modifications to the process will be made if necessary and additional condition CliFFs will be evaluated. Ultimately, CliFFs for the entire set of medical conditions will be created with the assistance of AI tools. Depending on the cost savings realized, CliFFs for additional medical conditions can be created to expand the Evidence Library. Future direction includes specifying the characteristics of the reviewer (prompting the AI tools to generate output assuming the reviewer is a sub-specialist physician, or nurse or EMT/medic) to determine if the effects on AI-generated output are different based on knowledge, skills and abilities. *Exploration Medical Capability Evidence Library Methods, HRP-48036 Rev A, July 2022.

Ali Al↗

DOE OSTI2026

Untargeted, tandem mass spectrometry (LC/MS-MS) metaproteomes from soil samples in control and warming plots in Blodgett Forest, CA (2014-2021)

The pathways of carbon transport and loss through and from soils—soil organic matter (SOM) depolymerization to dissolved organic carbon and mineralization to carbon dioxide (CO2)—are fundamentally driven by microbial activity, which is strongly regulated by environmental conditions. As part of Lawrence Berkeley National Laboratory (LBNL) Terrestrial Ecosystem Science (TES) Belowground Biogeochemistry Science Focus Area (SFA), we have established a novel whole-soil long-term warming experiment at the University of California (UC) Blodgett Forest Research Station (Sierra Nevada) in 2014, where we study the role of biogeochemical, microbial and geochemical process interactions in SOM decomposition and stabilization. This package contains soil metaproteomics data in the context of site specific metagenomes from soil depth profiles in three paired control and warming plots from a temperate mixed forest in Northern California. Each paired plot had been subjected to experimental warming since June 2014 to simulate a predicted climate change scenario for northern California. These metaproteomes were collected in 2018 after 4.5 years of warming from five depth intervals (0-10 cm, 10-30 cm, 30-45 cm, 45-60 cm, 60-80 cm). For protein identification, the collected spectra were searched following a target-decoy search strategy against a database of metagenome predicted proteins (covering 96 samples from 2014 to 2021) representing the complete sequence diversity at the site. Data was searched with mass spectrometry database search tool (MS-GF+) using Pacific Northwest National Laboratory (PNNL)'s Data Management System (DMS) Processing pipeline. The metagenomes are published as part of another data package. Raw metaproteomic data and the data products from MS-GF+ are deposited in the Mass Spectrometry Interactive Virtual Environment (MassIVE) database under accession no. MSV000097826. Here we present a dataset that includes spectral counts for the detected proteins across samples (EMSL50964_BrodieAllMAGs_Globals_SC.txt), the sequences of the detected proteins, and sample metadata file that contains site information for the soil metaproteome samples.

Belowground Biogeochemistry Science Focus Area↗

DOE OSTI2020

Corrosion protection of steel pipelines with metal-polymer composite barrier liners

Pipelines are efficient in transporting natural gas over large distances. Wet carbon dioxide present in pipelines can create an environment that is corrosive to steel. Polymer liners made from either polyethylene or polyamide (nylon) are presently used to mitigate internal corrosion in natural gas pipelines. Gas diffuses through all polymers over time, and polymer-only liners lower the steel corrosion rate by reducing the reactive gas flux to the internal surface of a pipeline. Composite liners, which incorporate one or more metallic layers that are impermeable to corrosive gases, offer better protection than polymer-only liners. In this study, we measured the methane, water vapor, and carbon dioxide permeability of a multi-layer barrier film and found it to be more effective in resisting gas permeation than polyethylene and nylon-11 films.

03 NATURAL GAS↗

DOE OSTI2020

Automated pipeline framework for processing of large-scale building energy time series data

Commercial buildings account for one third of the total electricity consumption in the United States and a significant amount of this energy is wasted. Therefore, there is a need for “virtual” energy audits, to identify energy inefficiencies and their associated savings opportunities using methods that can be non-intrusive and automated for application to large populations of buildings. Here we demonstrate virtual energy audits applied to large populations of buildings’ time-series smart-meter data using a systematic approach and a fully automated Building Energy Analytics (BEA) Pipeline that unifies, cleans, stores and analyzes building energy datasets in a non-relational data warehouse for efficient insights and results. This BEA pipeline is based on a custom compute job scheduler for a high performance computing cluster to enable parallel processing of Slurm jobs. Within the analytics pipeline, we introduced a data qualification tool that enhances data quality by fixing common errors, while also detecting abnormalities in a building’s daily operation using hierarchical clustering. We analyze the HVAC scheduling of a population of 816 buildings, using this analytics pipeline, as part of a cross-sectional study. With our approach, this sample of 816 buildings is improved in data quality and is efficiently analyzed in 34 minutes, which is 85 times faster than the time taken by a sequential processing. The analytical results for the HVAC operational hours of these buildings show that among 10 building use types, food sales buildings with 17.75 hours of daily HVAC cooling operation are decent targets for HVAC savings. Overall, this analytics pipeline enables the identification of statistically significant results from population based studies of large numbers of building energy time-series datasets with robust results. These types of BEA studies can explore numerous factors impacting building energy efficiency and virtual building energy audits. This approach enables a new generation of data-driven buildings energy analysis at scale.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Quality Guidelines for Energy System Studies: CO 2 Impurity Design Parameters

This section of the Quality Guidelines for Energy System Studies (QGESS) provides recommended impurity limits for carbon dioxide (CO 2 ) stream components for use in conceptual studies of CO 2 carbon capture, utilization, and storage systems. These limits were developed from information consolidated from numerous studies and are presented by component and application. Impurity levels are provided for carbon steel pipelines, sequestration through enhanced oil recovery (EOR), saline aquifer sequestration (SAS), and co-sequestration of CO 2 and hydrogen sulfide (H2S) in saline reservoirs. This QGESS is intended as a guideline only for conceptual studies under a generic scenario and should not be used for actual projects, which are likely to have requirements that differ from the generic scenario assumed herein.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Cell to Ecosystem: Understanding Methane and Associated Nutrient Cycling by Sediment Hosted Syntrophic Consortia and Their Viral Predators

The anaerobic oxidation of methane (AOM) is a significant worldwide microbial process in anoxic lake and ocean sediments, responsible for sequestering up to 80% of this greenhouse gas. Often considered a metabolism on the edge of thermodynamic probability, the impact of ANaerobic MEthane-oxidizing ‘ANME’ archaea on carbon and nutrient cycling in sediment ecosystems is far reaching. They not only serve as a sink for methane coupled to diverse electron acceptors, but also catalyze the transformation of many important nutrients including nitrogen, phosphate, and iron. While information about the potential mechanisms supporting metabolism in AOM is now available, remarkably little has been learned about their nutritional requirements, their dependencies on bacterial partners, and consequentially their ultimate impact on nutrient transformation and bioavailability within sedimentary ecosystems, and beyond. Further, the role of viruses within sediment ecosystems represents an essential but vastly understudied aspect of the transformation of carbon and nutrients by AOM. Viruses are now widely appreciated as central players in biogeochemical cycles across diverse ecosystems. These nanoscale predators have been shown to enhance the turnover of essential nutrients, thus stimulating microbial growth and environmental viruses themselves may constitute an important reservoir of nitrogen and phosphorous. Little is known about the role of viruses in methane-impacted sedimentary ecosystems, however prior genomic and microscopy evidence suggests that AOM consortia are susceptible to phage infection. The overarching scientific goal of this multi-disciplinary research proposal is to build on these recent discoveries and expand our understanding of interactions and fundamental activities involved in cycling of carbon and nutrients by syntrophic methanotrophic archaeal-bacterial consortia and associated viruses in anoxic sedimentary environments. Our three specific objectives are to 1) Quantify energy and nutrient exchange (e.g. N, P, Fe and vitamins) within AOM consortia and between ANME-bacterial partners; 2) Identify virus-host interactions associated with AOM and assess C and N transfer through viruses in methane-impacted sediment ecosystems; 3) Model energy and nutrient exchange in AOM consortia and viral-host interactions (i.e. viral activity), and their environmental distribution patterns. Our experimental emphasis cuts across scales that are important for understanding microbial and viral interactions and activities within their habitats, as well as community wide biogeochemical transformations. These research goals will be accomplished through the application of novel molecular techniques targeting DNA, RNA, proteins, and metabolites combined with a unique multi-modal analytical imaging pipeline. We will then model the ecophysiological capabilities of diverse sediment-hosted methanotrophic consortia to develop a more comprehensive understanding of the energetic and nutritional interactions between different AOM partner couplings that occur in sediments.

03 NATURAL GAS↗

DOE OSTI2026

Expanding the Domain of Applicability of Machine Learning Models with Limited Data for Drug Property Prediction

Accurate machine learning models for predicting small molecule interactions with biological targets are essential for therapeutic discovery, biothreat response, and computational drug design, but their performance is often limited for understudied targets with sparse experimental data. To address this challenge, we developed and evaluated methods to improve molecular property prediction under low-data conditions, using the NimA-related kinase (NEK) family as a proof-of-concept. This work focused on two complementary goals within the ATOM Modeling PipeLine (AMPL) and the Generative Molecular Design (GMD) loop: expanding model applicability through transfer learning, representation learning, feature scaling, sampling strategies, and active-learning-inspired compound selection; and enabling efficient virtual screening to prioritize compounds that balance predicted activity, design objectives, and synthetic accessibility.

organic↗

DOE OSTI2020

Empirical Evidence for the Potential Climate Benefits of Decarbonizing Light Vehicle Transport in the U.S. with Bioenergy from Purpose-Grown Biomass with and without BECCS

Climate mitigation scenarios limiting global temperature increases to 1.5 °C rely on decarbonizing vehicle transport with bioenergy production plus carbon capture and storage (BECCS), but climate impacts for producing different bioenergy feedstocks have not been directly compared experimentally or for ethanol vs electric light-duty vehicles. A field experiment at two Midwest U.S. sites on contrasting soils revealed that feedstock yields of seven potential bioenergy cropping systems varied substantially within sites but little between. Bioenergy produced per hectare reflected yields: miscanthus > poplar > switchgrass > native grasses ≈ maize stover (residue) > restored prairie ≈ early successional. Greenhouse gas emission intensities for ethanol vehicles ranged from 20 to -179 g CO 2 e MJ –1 : maize stover $\gg$ miscanthus ≈ switchgrass ≈ native grasses ≈ poplar > early successional ≥ restored prairie; direct climate benefits ranged from ~80% (stover) to 290% (restored prairie) reductions in CO 2 e compared to petroleum and were similar for electric vehicles. With carbon capture and storage (CCS), reductions in emission intensities ranged from 204% (stover) to 416% (restored prairie) for ethanol vehicles and from 329 to 558% for electric vehicles, declining 27 and 15%, respectively, once soil carbon equilibrates within several decades of establishment. Extrapolation based on expected U.S. transportation energy use suggests that, once CCS potential is maximized with CO 2 pipeline infrastructure, negative emissions from bioenergy with CCS for light-duty electric vehicles could capture >900 Tg CO 2 e year –1 in the U.S. In the future, as other renewable electricity sources become more important, electricity production from biomass would offset less fossil fuel electricity, and the advantage of electric over ethanol vehicles would decrease proportionately.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Hypermut 3: identifying specific mutational patterns in a defined nucleotide context that allows multistate characters

Abstract Motivation The detection of APOBEC3F- and APOBEC3G-induced mutations in virus sequences is useful for identifying hypermutated sequences. These sequences are not representative of viral evolution and can therefore alter the results of downstream sequence analyses if included. We previously published the software Hypermut, which detects hypermutation events in sequences relative to a reference. Two versions of this method are available as a webtool. Neither of these methods consider multistate characters or gaps in the sequence alignment. Results Here, we present an updated, user-friendly web and command-line version of Hypermut with functionality to handle multistate characters and gaps in the sequence alignment. This tool allows for straightforward integration of hypermutation detection into sequence analysis pipelines. As with the previous tool, while the main purpose is to identify G to A hypermutation events, any mutational pattern and context can be specified. Availability and implementation Hypermut 3 is written in Python 3. It is available as a command-line tool at https://github.com/MolEvolEpid/hypermut3 and as a webtool at https://www.hiv.lanl.gov/content/sequence/HYPERMUT/hypermutv3.html.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2016

Holistic Interactions of Shallow Clouds, Aerosols, and Land-Ecosystems (HI-SCALE): National Geospatial-Intelligence Agency Calibration Target Placements Field Campaign Report

The purpose of our research has been to develop a capability of simulating image collection from any sensor so as to account for sensor configuration, ground spectral radiance, and atmospheric contributions. Atmosphere is arguably the most difficult aspect of the image pipeline to accurately characterize and integrate into an image simulation. Some of the reasons for this include the highly variable spatial content of different absorbing and scattering species in the atmosphere. Additionally, the interaction of land and atmosphere can significantly impact the total radiation budget, especially in the southern Great Plains.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Constructing Self-Labeled Materials Imaging Datasets from Open Access Scientific Journals with EXSCLAIM!

Due to recent improvements in image resolution and acquisition speeds, materials microscopy is experiencing an explosion in imaging data. Yet, despite the volume of images generated, the overall accessibility landscape is highly fragmented, as researchers who do release images to the public, often only do so as snapshots of their larger private dataset in context of scientific journal publications. The effort to automatically consolidate images and descriptive information from web-based platforms has garnered broad attention from the computer vision, language technologies, and chemistry/materials informatics communities. However, these methods are problematic for scientific figures because over 30% of figures are compound in nature, and it is the individual images themselves, paired with relevant context, that are necessary for construction a proper labeled dataset. To this end, we outline in this paper the design of a software pipeline for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific figures (EXSCLAIM!). Successful consolidation of materials imaging across literature sources will enhance navigation and searchability of materials microscopy images for both novice and experienced researchers, as well as establish the framework necessary for users to search by images, text, or some combination of both.

36 MATERIALS SCIENCE↗