Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “process mining”

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 577 records · Page 32

Simulation of Helium-3 Extraction from Lunar Ilmenite

Knowledge of the trapping mechanisms and diffusion characteristics of solar-wind implanted isotopes in the minerals of the lunar regolith will enable the optimization of the processes to extract solar wind gases from regolith particles. Extraction parameters include the temperature and duration of extraction, particle size, and gas yield. Diffusion data will increase the efficiency and profitability of future mining ventures. This data will also assist in optimizing the evaluations of various potential mining sites based on remote sensing data. For instance, if magnesian ilmenite (Mg,Fel.,Ti03) is found to retain He better than stoichiometric ilmenite (FeTi03), remote sensing data for Mg could be considered in addition to Ti and maturity data. The context of the currently discussed work is the mining of helium-3 for potential use as a fuel for fusion energy generation. However, the potential resources deposited by the solar wind include hydrogen (and derived water), helium-4, nitrogen and carbon. Implantation experiments such as those performed for helium isotopes in ilmenite are important for the optimized extraction of these additional resources. These experiments can easily be reproduced for most elements or isotopes of interest.

Kuhlman, K. R.↗

Intelligent Systems: Terrestrial Observation and Prediction Using Remote Sensing Data

NASA has made science and technology investments to better utilize its large space-borne remote sensing data holdings of the Earth. With the launch of Terra, NASA created a data-rich environment where the challenge is to fully utilize the data collected from EOS however, despite unprecedented amounts of observed data, there is a need for increasing the frequency, resolution, and diversity of observations. Current terrestrial models that use remote sensing data were constructed in a relatively data and compute limited era and do not take full advantage of on-line learning methods and assimilation techniques that can exploit these data. NASA has invested in visualization, data mining and knowledge discovery methods which have facilitated data exploitation, but these methods are insufficient for improving Earth science models that have extensive background knowledge nor do these methods refine understanding of complex processes. Investing in interdisciplinary teams that include computational scientists can lead to new models and systems for online operation and analysis of data that can autonomously improve in prediction skill over time.

Coughlan, Joseph C.↗

INDUCTIVE SYSTEM HEALTH MONITORING WITH STATISTICAL METRICS

Model-based reasoning is a powerful method for performing system monitoring and diagnosis. Building models for model-based reasoning is often a difficult and time consuming process. The Inductive Monitoring System (IMS) software was developed to provide a technique to automatically produce health monitoring knowledge bases for systems that are either difficult to model (simulate) with a computer or which require computer models that are too complex to use for real time monitoring. IMS processes nominal data sets collected either directly from the system or from simulations to build a knowledge base that can be used to detect anomalous behavior in the system. Machine learning and data mining techniques are used to characterize typical system behavior by extracting general classes of nominal data from archived data sets. In particular, a clustering algorithm forms groups of nominal values for sets of related parameters. This establishes constraints on those parameter values that should hold during nominal operation. During monitoring, IMS provides a statistically weighted measure of the deviation of current system behavior from the established normal baseline. If the deviation increases beyond the expected level, an anomaly is suspected, prompting further investigation by an operator or automated system. IMS has shown potential to be an effective, low cost technique to produce system monitoring capability for a variety of applications. We describe the training and system health monitoring techniques of IMS. We also present the application of IMS to a data set from the Space Shuttle Columbia STS-107 flight. IMS was able to detect an anomaly in the launch telemetry shortly after a foam impact damaged Columbia's thermal protection system.

Iverson, David L.↗

PILOT PLANT EVALUATIONS OF RARE EARTH ELEMENT RECOVERY AND CONCENTRATION FROM PRE-COMBUSTION BITUMINOUS COAL SOURCES

Rare earths and other critical elements are commonly associated with coal-based sources and sometimes at concentrations that may be attractive for recovery as a byproduct of coal production. The results obtained from laboratory research performed during the past five years have led to the design, construction and testing of a pilot plant that recovered rare earth elements from several bituminous coal-based materials including coarse refuse as well as solutions from a small heap leach and acid mine drainage. From this initial design, rare earth oxide (REO) concentrates having a purity greater than 90% have been produced using solvent extraction as the primary means of concentration. Following cost reduction and process intensification efforts, the circuit was revised to include feed calcination and several selective precipitation stages as a substitute for the original direct leach-solvent extraction circuit. Pilot test results revealed that the modified circuit was ideal for treating the relatively low-grade feedstocks and provided similar final REO purities at a significantly lower cost. This communication will present the flowsheets evaluated in the pilot plant along with technical and economic analyses for each circuit.

Coal↗

Evaluating a Semi-Quantitative, Spectrophotometric Method for the Rapid Determination of Total Rare Earth Element Concentrations in Citrate Leaching Solutions

Quick, reliable methods to measure the rare earth elements (REEs) in process streams are needed to support real-time parameterization and monitoring for a burgeoning number of REE extraction schemes. Such methods would ideally be fast, reproducible, and field-deployable. This study evaluates the feasibility of using a chromogenic indicator, arsenazo(III) (hereafter abbreviated as Arsz(III)) to detect the concentration of REEs in complex citrate leaching solutions using a spectrophotometer. Arsz(III) forms a chromogenic complex with the lanthanide elements that produces a blue/purple color detectable in the visible light range. Matrices of solutions containing varied concentrations of calcium, iron, and lanthanum were scanned in the presence of an Arsz(III) indicator to generate a modeled relationship that could be used to back calculate REE concentrations. While relatively quick (scan times on the order of seconds), the results indicated that the calcium and iron concentrations of typical mining solutions overwhelm the signal of the REEs, to the extent that sensitivity of the method is no less than 50 µM REEs. These results demonstrate the difficulties of accurately measuring trace metals in complex solutions, although the method may still hold utility for processes with significantly lower calcium and iron concentrations or REE concentrations much greater than 50 µM.

36 MATERIALS SCIENCE↗

Enriching the Twitter Stream Increasing Data Mining Yield and Quality Using Machine Learning

Social media data streams are important sources of real-time and historical global information for science applications. At the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC), we are exploring the Twitter data stream for its potential in augmenting the validation program of NASA Earth science missions, specifically the Global Precipitation Measurement (GPM) mission. We have implemented a tweet processing infrastructure that outputs classified precipitation tweets. Inputs are "passive" tweets, along with a smaller number of tweets from "active" participants, i.e., those knowingly contributing to our effort. The "active" tweets, presumably of higher quality, enrich the Twitter stream. "Active" sources include data scraped from other social media (e.g., public Facebook posts) and data from existing crowdsourcing programs (e.g., mPING reports). In addition, there is likely relevant precipitation information in images and documents that are the end points of links often included in tweets. Information derived from these "active" sources could then be tweeted into the Twitter stream, thus enriching its quality. The objective of our current work is to mine these tweet­ linked images and documents, using neural networks, to increase the information content and quality related to precipitation. For images, we classified them as either precipitation-related or not. For training and validation, we used images obtained via the Google custom search API. We created two models: (1) by training a simple Convolutional Neural Network and (2) by using transfer learning principles to adapt a pre-trained object recognition model. For documents, both those linked to tweets and the tweet contents, we trained Hierarchical Attention Networks to determine precipitation occurrence, type, and intensity. For training and validation, we used a keyword-filtered tweet data set labelled with ground truth data from Dark Sky (an API to retrieve weather-related labels) and the National Severe Storms Laboratory's Multi­ Radar/Multi-Sensor (MRMS) system. Our results demonstrated the efficacy of our machine learning approaches for enriching the Twitter stream, to derive information potentially useful for validation of earth science satellite data.

Albayrak, Arif↗

Targeted Biomining and Machine Learning Approaches in Critical Minerals Revealed by a Biogeochemical Survey of a Coal Mine Drainage Remediation System

Abandoned coal mine drainage (AMD) remediation systems in Pennsylvania can concentrate critical minerals and materials (CMM) at levels comparable to mining-grade ores. Remediation systems have varying engineering features and are open to the environment, resulting in diverse microbial colonization and seasonal climate influences that may impact CMM speciation. The location of CMMs, the types of bacterial communities tolerant of these pollutant conditions, and the influence of localized climate on CMM rich remediation systems are not well characterized. Through a one-year spatiotemporal survey of biogeochemistry at a remediation system, we have initiated the process to address these questions. Rare Earth Elements (REE) ranged 180-1,200 ppm and greater than 1,500 bacterial ASVs were classified via 16S sequencing. Analyses indicate biogeochemical differences are heavily influenced by engineering features. Additionally, REE precipitants correlate strongly with the elements Al, Cu, Zn, Be, and U. Unearthing these trends has refined our line of inquiry to explore biological mining opportunities more closely with these metals. Furthermore, we created a Machine Learning Model for predicting AMD REE content, with 89% accuracy, using the data from this study and several others. Further training data is required to create a more reputable model. Recently, global research efforts have prioritized modeling work or the use of the few historical surveys to design experiments. Through our data, we challenge this approach, emphasizing the importance of expanding fundamental survey efforts prior to advanced product design and experimentation.

critical minerals↗

Distributed sustainable metals production: opportunities for intensifying separations & alternative feedstocks

Meeting the increased demand for rare earth elements and beyond primary mined ore. Secondary sources like phosphogypsum, coal fly ash, used nuclear fuel, and electronic waste are concentrated sources of critical minerals. One strategy for a resilient supply chain is to decentralize sourcing and hydrometallurgical processing of metals. Rotating packed beds (RPBs) for solid-phase extraction and liquid-liquid extraction are gaining momentum for their ability to increase process throughput by 5-10x the state of the art. In conclusion, this review discusses advances in hydrometallurgical RPB processes and opportunities for implementation in distributed metals production.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Rare earth elements from waste

Rare earth elements (REEs) are critical materials in electronics and clean technologies. With the diminishing of easily accessible minerals for mining, the REE recovery from waste is an alternative toward a circular economy. Present methods for REE recovery suffer from lengthy purifications, low extractability, and high wastewater streams. Here, we report an ultrafast electrothermal process (~3000°C, ~1 s) based on flash Joule heating (FJH) for activating wastes to improve REE extractability. FJH thermally degrades or reduces the hard-to-dissolve REE species to components with high thermodynamic solubility, leading to ~2× increase in leachability and high recovery yields using diluted acid (e.g., 0.1 M HCl). The activation strategy is feasible for various wastes including coal fly ash, bauxite residue, and electronic waste. The rapid FJH process is energy-efficient with a low electrical energy consumption of 600 kWh ton –1 . The potential for this route to be rapidly scaled is outlined.

01 COAL, LIGNITE, AND PEAT↗

Recovery of Rare Earth Elements from Bioleachates by Precipitation

Rare earth elements are essential components in electronic devices, however because of the limited imports and mining capabilities in the US, recycling these rare earths is crucial. Common practices used to recover REEs including hydrometallurgy and pyrometallurgy are harmful to the environment. Bioleaching, a form of biohydrometallurgy, is an emerging process that uses organic acids synthesized by microorganisms and can leach REEs at comparable efficiencies to less environmentally conscious processes. Once the REEs are leached by the bio-lixiviant produced by microorganisms, the REEs are suspended in the solution and need to precipitate out in order to be harvested for reuse. Common chemicals used for rare earth precipitation in hydrometallurgy processes include sodium sulfate and oxalic acid. These two reagents were tested at varying stoichiometric excess concentrations in bio-leachate derived from smart phone speaker magnets and bio-lixiviant. Following the precipitation reactions, it was observed that the oxalic acid reaction precipitated an abundance of iron (II) oxalate, an REE contaminate. This is most likely due to the bio-leachate having a higher pH compared to the hydrometallurgical leachates. Therefore, it was determined that sodium sulfate is a better candidate for REE precipitation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Mapping Support for Targeted Critical Minerals Exploration and Extraction

The United States’ dependency on imported minerals poses significant risks to economic stability and national security due to potential supply disruptions. Recognizing the strategic importance of critical minerals, the Department of Energy (DOE) emphasizes the need for a secure and resilient supply chain to support emissions reduction, technology development, and capitalization on clean energy opportunities. The DOE’s Office of Manufacturing and Energy Supply Chains (MESC), in collaboration with the Office of Policy (OP), addresses these vulnerabilities by focusing on upstream domestic critical minerals production, balancing extraction with social and environmental goals, including conservation, environmental justice, and respect for Tribal sovereignty. This report showcases a collaborative effort involving Idaho National Laboratory (INL), Argonne National Laboratory (Argonne), National Renewable Energy Laboratory (NREL), and the U.S. Geological Survey (USGS) to map mineral development potential along with key social and environmental datasets. A geographical information system (GIS)-based web map application was developed as a preliminary tool for environmental analysis, integrating 158 geospatial data layers such as critical habitat, land ownership, economic indicators, and environmental concerns. Data were sourced from agencies like the Bureau of Land Management (BLM) and USGS and processed using GIS technology to enhance visualization and analysis. The proposed analysis framework categorizes areas into high, mid, and low concern based on withdrawn lands, special status species, the Economic Development Capacity Index (EDCI) Mining Composite Index, and the Climate and Economic Justice Screening Tool (CEJST). While the application provides broad visualizations, it is not a substitute for detailed environmental reviews required under the National Environmental Policy Act (NEPA). Users must conduct further analyses and engage with tribal entities and other stakeholders for comprehensive planning. A case study of the Idaho Cobalt Belt (ICB) in Lemhi County, Idaho, has been provided in the report to illustrate the tool's practical use. This report introduces a GIS application and framework to support stakeholders in identifying and prioritizing areas for critical mineral exploration, promoting secure supply chains, and advancing the nation's energy independence through responsible resource stewardship.

54 ENVIRONMENTAL SCIENCES↗

Bacterial Bioleaching and Biorecovery for Biomining Unconventional Rare Earth Element Feedstocks

Bacterial metabolic interactions with rare earth elements (REEs) can be harnessed for biomining unconventional feedstocks like abandoned coal-mine drainage (AMD). Pennsylvania has ~500 AMD passive remediation systems that can precipitate REE rich solids. REEs include yttrium and the lanthanide series that are used in modern energy and technology. Bacteria that metabolically interact with REEs can be used for biomining in an affordable efficient process that does not require hazardous chemical additives. Currently, the microbial metal mechanisms that contribute to REE biorelease and biorecovery are poorly understood. Our work shows acidogenic bacterial isolates (Bacillus mycoides JR07 and Bacillus pseudomycoides KB7) successfully bioleach a mixed REE solution from AMD solids by their organic acid production and biofilm formation. Further, our work shows the potential for bacterial lanthanide-dependent enzymes to recover lanthanides from a mixed REE solution; here we have bacterial isolate Methylobacterium sp. B3 that can recover soluble lanthanum. Whole genome sequencing of Methylobacterium sp. B3 predict lanthanide-dependent methanol dehydrogenase XoxF. Understanding the microbial metabolism and genes involved in the REE release and recovery is crucial to optimize the biomining of AMD solids. Our work addresses the growing need to develop novel REE mining methods from unconventional feedstocks.

biogeochemistry↗

Understanding Machine Learning in Earth Science: A Natural Language Processing Approach

Machine learning (ML) is being increasingly utilized in Earth science research. Benefits of ML include efficiency, reduction of human error, and ability to extract hidden patterns within data. However, the mutual lack of each other’s domain knowledge by ML and Earth science stands as a barrier to timely and effective implementation. Earth science, in particular, faces challenges in generating sample data, compared to those of traditional ML problems such as face recognition or stock predictions, where data is abundant and not lacking in ground truth, which is necessary for labeling. Earth science data are more varying in formats, such as HDF5 and image resolutions, and are not standardized across instruments, even within a given Earth science discipline. Previous studies have been done to outline the specific challenges that Earth science faces with ML, while others have focused on using existing publications to mine information efficiently. Other resources such as Scikit-Learn have developed decision trees for choosing appropriate machine learning algorithms, but application within Earth science subjects becomes much more complex. For the current study, we propose a methodology and tool that aids in implementation of ML in Earth science using natural language processing (NLP). Our work comprises three main parts: (1) analyzing existing publications related to ML and Earth science, using natural language processing: (2) extracting from the publications information on ML models subjects in Earth Science: and (3) visualizing the extracted relationships as a network graph. The resulting network graph should aid the Earth science communities in applying optimal ML algorithms and guiding data preparation through visualization of similar studies. The network graph and analysis of document similarity will be the basis of our next step, which is to develop a decision tree for selecting optimal machine learning methodologies for specified Earth science applications.

Zheng, Laura↗

Thermal Characterization and Exhumation of Northwest San Juan Basin Area, NM

The San Juan Basin (SJB), located in southwestern Colorado northwestern New Mexico, containing Paleozoic through middle Cenozoic strata, formed as a partitioned basin approximately 80 Ma in response to the Laramide orogeny. The SJB is a commercially mature, petroleum-producing basin, and currently being explored for CCUS and geothermal resources. Modern heat flow within the SJB is spatially variable with higher geothermal gradients in its northern and eastern portions. The temporal history of the basin thermal history is essential for understanding capacity for carbon storage and geothermal exploration. We present thermochronometric analyses of two surface and two subsurface samples to constrain spatial-temporal thermal evolution of the northwestern San Juan Basin. Apatite (U-Th)/He thermochronometric analyses were conducted on Cliff House and Kirtland Formation outcrops and subsurface samples of the Ojo Alamo and Pictured Cliffs Formations from a DOE funded, CCUS project pilot-well. In addition, vitrinite reflectance data and 1D basin modelling constrain possible time-temperature pathways of the samples in an area where no previous studies have constrained the uplift/exhumation of the Hogback Monocline using thermochronometry. Modeling suggests that elevated subsurface temperatures developed simultaneously with regional late Oligiocene volcanism in the San Juan Volcanic field and timing of maximum burial in the SJB. Late Miocene to Pliocene cooling/exhumation through the apatite (U-Th)/He partial retention zone support stratigraphic evidence of the Colorado Plateau uplift, possibly regional epeirogenic uplift driven by mantle processes.

02 PETROLEUM↗

NASA Lunar Mining and Construction Activities and Plans

The Space Exploration Policy enacted by the US Congress in 2005 calls for the US National Aeronautics and Space Administration (NASA) to implement a sustained and affordable human and robotic program to explore the solar system and beyond; Extend human presence across the solar system, starting with a human return to the Moon by the year 2020, in preparation for human exploration of Mars and other destinations; Develop the innovative technologies, knowledge, and infrastructures both to explore and to support decisions about the destinations for human exploration; and Promote international and commercial participation in exploration to further U.S. scientific, security, and economic interests. In 2006, NASA released the Lunar Architecture Study, which proposed establishing a lunar Outpost on the Moon with international participation to extend human presence beyond Earth's orbit, pursue scientific activities, use the Moon to prepare for future human missions to Mars, and expand Earth s economic sphere. The establishment of sustained human presence on the Moon for science and exploration combines the design, integration, and operation challenges experienced from both the short Apollo lunar missions and the build-up and sustained crew operations of the International Space Station (ISS). Apollo experience reminds developers and mission planners that hardware must operate under extremely harsh environmental and abrasive conditions and every kilogram of mass and payload must be critical to achieve the mission s objectives due to the difficulty and cost of reaching the lunar surface. Experience from the ISS reminds developers and mission planners that integration of all hardware must be designed and planned from the start of the program, operations and evolution of capabilities on a continuous basis are important, and long-term life-cycle costs and logistical needs are equally or more important than minimizing early development and test costs. Overarching all of this is the need to implement efforts that are sustainable and affordable. One area NASA is developing that can significantly change how systems required for sustained human presence are designed and integrated, as well as potentially break our reliance on Earth supplied logistics, is In-Situ Resource Utilization (ISRU). ISRU, also known living off the land, involves the extraction and processing of local resources into useful products. In particular, the ability to make propellants, life support consumables, fuel cell reagents, and radiation shielding can significantly reduce the cost, mass, and risk of sustained human activities beyond Earth. Also, the ability to modify the lunar landscape for safer landing, transfer of payloads from the lander an outpost, dust generation mitigation, and infrastructure placement and buildup are also extremely important for long-term lunar operations. While extra-terrestrial excavation, material handling and processing, and site preparation and construction may be new to NASA and other space agencies, there is extensive terrestrial hardware and commercial experience that can be leveraged. This paper will provide an overview of current NASA activities in lunar ISRU mining and construction and how terrestrial experience in these areas are important to achieving the goal of affordable and sustainable human exploration.

Sanders, Gerald B.↗

AI-powered topic modeling: comparing LDA and BERTopic in analyzing opioid-related cardiovascular risks in women

Topic modeling is a crucial technique in natural language processing (NLP), enabling the extraction of latent themes from large text corpora. Traditional topic modeling, such as Latent Dirichlet Allocation (LDA), faces limitations in capturing the semantic relationships in the text document although it has been widely applied in text mining. BERTopic, created in 2022, leveraged advances in deep learning and can capture the contextual relationships between words. In this work, we integrated Artificial Intelligence (AI) modules to LDA and BERTopic and provided a comprehensive comparison on the analysis of prescription opioid-related cardiovascular risks in women. Opioid use can increase the risk of cardiovascular problems in women such as arrhythmia, hypotension etc. 1,837 abstracts were retrieved and downloaded from PubMed as of April 2024 using three Medical Subject Headings (MeSH) words: “opioid,” “cardiovascular,” and “women.” Machine Learning of Language Toolkit (MALLET) was employed for the implementation of LDA. BioBERT was used for document embedding in BERTopic. Eighteen was selected as the optimal topic number for MALLET and 23 for BERTopic. ChatGPT-4-Turbo was integrated to interpret and compare the results. The short descriptions created by ChatGPT for each topic from LDA and BERTopic were highly correlated, and the performance accuracies of LDA and BERTopic were similar as determined by expert manual reviews of the abstracts grouped by their predominant topics. The results of the t-SNE (t-distributed Stochastic Neighbor Embedding) plots showed that the clusters created from BERTopic were more compact and well-separated, representing improved coherence and distinctiveness between the topics. Our findings indicated that AI algorithms could augment both traditional and contemporary topic modeling techniques. In addition, BERTopic has the connection port for ChatGPT-4-Turbo or other large language models in its algorithm for automatic interpretation, while with LDA interpretation must be manually, and needs special procedures for data pre-processing and stop words exclusion. Therefore, while LDA remains valuable for large-scale text analysis with resource constraints, AI-assisted BERTopic offers significant advantages in providing the enhanced interpretability and the improved semantic coherence for extracting valuable insights from textual data.

Research & Experimental Medicine↗

Machine learning the metastable phase diagram of covalently bonded carbon

Abstract Conventional phase diagram generation involves experimentation to provide an initial estimate of the set of thermodynamically accessible phases and their boundaries, followed by use of phenomenological models to interpolate between the available experimental data points and extrapolate to experimentally inaccessible regions. Such an approach, combined with high throughput first-principles calculations and data-mining techniques, has led to exhaustive thermodynamic databases (e.g. compatible with the CALPHAD method), albeit focused on the reduced set of phases observed at distinct thermodynamic equilibria. In contrast, materials during their synthesis, operation, or processing, may not reach their thermodynamic equilibrium state but, instead, remain trapped in a local (metastable) free energy minimum, which may exhibit desirable properties. Here, we introduce an automated workflow that integrates first-principles physics and atomistic simulations with machine learning (ML), and high-performance computing to allow rapid exploration of the metastable phases to construct “metastable” phase diagrams for materials far-from-equilibrium. Using carbon as a prototypical system, we demonstrate automated metastable phase diagram construction to map hundreds of metastable states ranging from near equilibrium to far-from-equilibrium (400 meV/atom). We incorporate the free energy calculations into a neural-network-based learning of the equations of state that allows for efficient construction of metastable phase diagrams. We use the metastable phase diagram and identify domains of relative stability and synthesizability of metastable materials. High temperature high pressure experiments using a diamond anvil cell on graphite sample coupled with high-resolution transmission electron microscopy (HRTEM) confirm our metastable phase predictions. In particular, we identify the previously ambiguous structure of n -diamond as a cubic-analog of diaphite-like lonsdaelite phase.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Automated annotation of scientific texts for ML-based keyphrase extraction and validation

Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lack the essential metadata required for researchers to find, curate, and search them effectively. The lack of metadata poses a significant challenge in the utilization of these data sets. Machine learning (ML)–based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific data sets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata. However, manual labeling is time-consuming and not always feasible; thus, there is a need to develop automated text labeling techniques in order to accelerate the process of scientific innovation. This need is particularly urgent in fields such as environmental genomics and microbiome science, which have historically received less attention in terms of metadata curation and creation of gold-standard text mining data sets. In this paper, we present two novel automated text labeling approaches for the validation of ML-generated metadata for unlabeled texts, with specific applications in environmental genomics. Our techniques show the potential of two new ways to leverage existing information that is only available for select documents within a corpus to validate ML models, which can then be used to describe the remaining documents in the corpus. The first technique exploits relationships between different types of data sources related to the same research study, such as publications and proposals. The second technique takes advantage of domain-specific controlled vocabularies or ontologies. In this paper, we detail applying these approaches in the context of environmental genomics research for ML-generated metadata validation. Our results show that the proposed label assignment approaches can generate both generic and highly specific text labels for the unlabeled texts, with up to 44% of the labels matching with those suggested by a ML keyword extraction algorithm.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗