Automating Evidence Collection for Software Assurance from Existing Status Reports
No abstract available
text search↗
SEARCH · Search NASA
Results for “text 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.
Automated electrosynthesis reaction mining with multimodal large language models (MLLMs)
Leveraging the chemical data available in legacy formats such as publications and patents is a significant challenge for the community. Automated reaction mining offers a promising solution to unleash this knowledge into a learnable digital form and therefore help expedite materials and reaction discovery. However, existing reaction mining toolkits are limited to single input modalities (text or images) and cannot effectively integrate heterogeneous data that is scattered across text, tables, and figures. In this work, we go beyond single input modalities and explore multimodal large language models (MLLMs) for the analysis of diverse data inputs for automated electrosynthesis reaction mining. We compiled a test dataset of 65 articles (MERMES-T24 set) and employed it to benchmark five prominent MLLMs against two critical tasks: (i) reaction diagram parsing and (ii) resolving cross-modality data interdependencies. The frontrunner MLLM achieved ≥96% accuracy in both tasks, with the strategic integration of single-shot visual prompts and image pre-processing techniques. We integrate this capability into a toolkit named MERMES (multimodal reaction mining pipeline for electrosynthesis). Our toolkit functions as an end-to-end MLLM-powered pipeline that integrates article retrieval, information extraction and multimodal analysis for streamlining and automating knowledge extraction. This work lays the groundwork for the increased utilization of MLLMs to accelerate the digitization of chemistry knowledge for data-driven research.
Leong, Shi Xuan↗
Exaflops Biomedical Knowledge Graph Analytics
We are motivated by newly proposed methods for mining large-scale corpora of scholarly publications (e.g., full biomedical literature), which consists of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover relationships among concepts. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as an all-pairs shortest paths (APSP) and validate connective paths against curated biomedical knowledge graphs (e.g., Spoke). In this context, we present Coast (Exascale Communication-Optimized All-Pairs Shortest Path) and demonstrate 1.004 EF/s on 9,200 Frontier nodes (73,600 GCDs). We develop hyperbolic performance models (HYPERMOD), which guide optimizations and parametric tuning. The proposed Coast algorithm achieved the memory constant parallel efficiency of 99% in the single-precision tropical semiring. Looking forward, Coast will enable the integration of scholarly corpora like PubMed into the Spoke biomedical knowledge graph.
Kannan, Ramakrishnan {ramki}↗
Scalable Knowledge Graph Analytics at 136 Petaflop/s
We are motivated by newly proposed methods for data mining large-scale corpora of scholarly publications, such as the full biomedical literature, which may consist of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover how concepts relate to one another. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as one of computing all-pairs shortest paths (APSP), which becomes a significant bottleneck. In this context, we present a new high-performance algorithm and implementation of the Floyd-Warshall algorithm for distributed-memory parallel computers accelerated by GPUs, which we call DSNAPSHOT (Distributed Accelerated Semiring All-Pairs Shortest Path). For our largest experiments, we ran DSNAPSHOT on a connected input graph with millions of vertices using 4, 096nodes (24,576GPUs) of the Oak Ridge National Laboratory's Summit supercomputer system. We find DSNAPSHOT achieves a sustained performance of 136×1015 floating-point operations per second (136petaflop/s) at a parallel efficiency of 90% under weak scaling and, in absolute speed, 70% of the best possible performance given our computation (in the single-precision tropical semiring or “min-plus” algebra). Looking forward, we believe this novel capability will enable the mining of scholarly knowledge corpora when embedded and integrated into artificial intelligence-driven natural language processing workflows at scale.
Kannan, Ramakrishnan {ramki}↗
Dynamic Network Analysis of Nuclear Science Literature for Research Influence Assessment
Analyzing nuclear science literature via data-driven methods is a critical step for assessing research influence and technology advancements. Indicators of scholarly activities may be buried in large volumes of nuclear research publications and collaboration networks over time. Mining for relevant scholarly influence trends in large volumes of text can be computationally challenging; however, open-source information on research collaborations over time can offer opportunities to extract meaningful insights. While network centrality analysis of scholarly research provides topology-based insights, additional emphasis on dynamics associated with the diffusion of information through these networks is important. Here this paper represents a step in that direction through the development of a novel dynamic network analysis framework and computational engine to identify key entities and capabilities over time within global scholarly nuclear science collaboration networks. Network theoretic, stochastic simulation, and optimization methods are leveraged to address variability in scholarly interactions, influence propagation, and collaboration patterns via network connections. A topic-aware influence maximization algorithm is developed to address the goal of identifying key influential authors in diverse research topics over time. Efficient parallelized implementation of the algorithm is applied to reduce computational costs. A proof-of-concept case study using open-source Scopus data with 33,517 published nuclear research papers from 2000-2019 is presented and representative analytic insights are generated. Broad implications of these insights are discussed and future research directions are also identified.
98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
Using a Knowledge Graph to Discover Earth Science Information
Knowledge graphs link key entities within a specific domain to other entities via relationships. Researchers are able to mine these relationships from numerous sources to infer new knowledge. Text extraction from peer-reviewed papers and scientific reports are untapped resources that can be leveraged by knowledge graphs to accelerate scientific discovery.
Freitag, Brian↗
Visual Detection with Context for Document Layout Analysis
We present 1) a work in progress method to visually segment key regions of scientific articles using an object detection technique augmented with contextual features, and 2) a novel dataset of region-labeled articles. A continuing challenge in scientific literature mining is the difficulty of consistently extracting high-quality text from formatted PDFs. To address this, we adapt the object-detection technique Faster R-CNN for document layout detection, and incorporate contextual information that leverages the inherently localized nature of article contents to improve the region detection performance. Due to the limited availability of region-labels for scientific articles, we also contribute a novel dataset of region annotations, the first version of which covers 9 region classes and 822 article pages. Initial experimental results demonstrate a 23.9% absolute improvement in mean average precision over the baseline by incorporating contextual features, and a processing speed 14x faster than a text-based technique. Ongoing work on further improvements is also discussed.
97 MATHEMATICS AND COMPUTING↗
Nanomaterial Synthesis Insights from Machine Learning of Scientific Articles by Extracting, Structuring, and Visualizing Knowledge
Nanomaterials of varying compositions and morphologies are of interest for many applications from catalysis to optics, but the synthesis of nanomaterials and their scale-up are most often time-consuming and Edisonian processes. Information gleaned from the scientific literature can help inform and accelerate nanomaterials development, but again, searching the literature and digesting the information are time-consuming manual processes for researchers. To help address these challenges, here we developed scientific article-processing tools that extract and structure information from the text and figures of nanomaterials articles, thereby enabling the creation of a personalized knowledgebase for nanomaterials synthesis that can be mined to help inform further nanomaterials development. Starting with a corpus of ~35k nanomaterials-related articles, we developed models to classify articles according to the nanomaterial composition and morphology, extract synthesis protocols from within the articles’ text, and extract, normalize, and categorize chemical terms within synthesis protocols. We demonstrate the efficiency of the proposed pipeline on an expert-labeled set of nanomaterials synthesis articles, achieving 100% accuracy on composition prediction, 95% accuracy on morphology prediction, 0.99 AUC on protocol identification, and up to a 0.87 F1-score on chemical entity recognition. In addition to processing articles’ text, microscopy images of nanomaterials within the articles are also automatically identified and analyzed to determine the nanomaterials’ morphologies and size distributions. To enable users to easily explore the database, we developed a complementary browser-based visualization tool that provides flexibility in comparing across subsets of articles of interest. We use these tools and information to identify trends in nanomaterials synthesis, such as the correlation of certain reagents with various nanomaterial morphologies, which is useful in guiding hypotheses and reducing the potential parameter space during experimental design.
36 MATERIALS SCIENCE↗
Data Mining SIAM Presentation
This viewgraph document describes the data mining system developed at NASA Ames. Many NASA programs have large numbers (and types) of problem reports.These free text reports are written by a number of different people, thus the emphasis and wording vary considerably With so much data to sift through, analysts (subject experts) need help identifying any possible safety issues or concerns and help them confirm that they haven't missed important problems. Unsupervised clustering is the initial step to accomplish this; We think we can go much farther, specifically, identify possible recurring anomalies. Recurring anomalies may be indicators of larger systemic problems. The requirement to identify these anomalies has led to the development of Recurring Anomaly Discovery System (ReADS).
Srivastava, Ashok↗
Searching for 'Unknown Unknowns'
The NASA Engineering and Safety Center (NESC) was established to improve safety through engineering excellence within NASA programs and projects. As part of this goal, methods are being investigated to enable the NESC to become proactive in identifying areas that may be precursors to future problems. The goal is to find unknown indicators of future problems, not to duplicate the program-specific trending efforts. The data that is critical for detecting these indicators exist in a plethora of dissimilar non-conformance and other databases (without a common format or taxonomy). In fact, much of the data is unstructured text. However, one common database is not required if the right standards and electronic tools are employed. Electronic data mining is a particularly promising tool for this effort into unsupervised learning of common factors. This work in progress began with a systematic evaluation of available data mining software packages, based on documented decision techniques using weighted criteria. The four packages, which were perceived to have the most promise for NASA applications, are being benchmarked and evaluated by independent contractors. Preliminary recommendations for "best practices" in data mining and trending are provided. Final results and recommendations should be available in the Fall 2005. This critical first step in identifying "unknown unknowns" before they become problems is applicable to any set of engineering or programmatic data.
Parsons, Vickie S.↗
Exploration Clinical Decision Support System: Medical Data Architecture
The Exploration Clinical Decision Support (ECDS) System project is intended to enhance the Exploration Medical Capability (ExMC) Element for extended duration, deep-space mission planning in HRP. A major development guideline is the Risk of "Adverse Health Outcomes & Decrements in Performance due to Limitations of In-flight Medical Conditions". ECDS attempts to mitigate that Risk by providing crew-specific health information, actionable insight, crew guidance and advice based on computational algorithmic analysis. The availability of inflight health diagnostic computational methods has been identified as an essential capability for human exploration missions. Inflight electronic health data sources are often heterogeneous, and thus may be isolated or not examined as an aggregate whole. The ECDS System objective provides both a data architecture that collects and manages disparate health data, and an active knowledge system that analyzes health evidence to deliver case-specific advice. A single, cohesive space-ready decision support capability that considers all exploration clinical measurements is not commercially available at present. Hence, this Task is a newly coordinated development effort by which ECDS and its supporting data infrastructure will demonstrate the feasibility of intelligent data mining and predictive modeling as a biomedical diagnostic support mechanism on manned exploration missions. The initial step towards ground and flight demonstrations has been the research and development of both image and clinical text-based computer-aided patient diagnosis. Human anatomical images displaying abnormal/pathological features have been annotated using controlled terminology templates, marked-up, and then stored in compliance with the AIM standard. These images have been filtered and disease characterized based on machine learning of semantic and quantitative feature vectors. The next phase will evaluate disease treatment response via quantitative linear dimension biomarkers that enable image content-based retrieval and criteria assessment. In addition, a data mining engine (DME) is applied to cross-sectional adult surveys for predicting occurrence of renal calculi, ranked by statistical significance of demographics and specific food ingestion. In addition to this precursor space flight algorithm training, the DME will utilize a feature-engineering capability for unstructured clinical text classification health discovery. The ECDS backbone is a proposed multi-tier modular architecture providing data messaging protocols, storage, management and real-time patient data access. Technology demonstrations and success metrics will be finalized in FY16.
Biomedical support↗
First Measurement of Charged Current Muon Neutrino-Induced Kaon Production on Argon
The Micro Booster Neutrino Experiment (MicroBooNE) is a liquid argon time projection chamber (LArTPC) neutrino detector with an 85-ton active volume, located on-axis to the Booster Neutrino Beamline (BNB) at Fermilab. The detector is exposed to a neutrino flux with average energy of 800 MeV and was designed to study neutrino interactions on argon, particularly in the 1 GeV energy range. Among its main goals is the investigation of neutrino-induced strange particle production at final-state, with a specific interest on charged kaons ($K^{+}$). The understanding of this neutrino interaction is crucial for refining background models in future nucleon decay searches on others LArTPCs experiments such as the Deep Underground Neutrino Experiment (DUNE). Additionally, the techniques developed for the identification of neutrino-induced $K^{+}$ will contribute to improving particle identification methods in LArTPC-based detectors. This thesis is reporting the first-ever measurement of the flux-integrated cross section for charged-current muon neutrino-induced $K^{+}$ production on argon, determined to be $7.93 \pm 3.27(\text{stat.}) \pm 2.92(\text{syst.}) \times 10^{-42}$ cm$^2$/nucleon, based on the MicroBooNE dataset corresponding to $6.88 \times 10^{20}$ Protons on Target (POT).
Rodriguez Rondon, Jairo H. [South Dakota Sch. Mine↗
Extract useful information from building permits data to profile a city’s building retrofit history
Building retrofit is one of the key strategies for cities to reduce energy use and GHG emissions. The historical information about changes to buildings is crucial to infer the buildings’ current energy system efficiency levels and to identify candidate buildings for retrofit. In general, a building permit is required before the start of any construction activity of a building, such as changing building structure, remodeling, or installing new equipment. Moreover, many large cities provide public datasets of building permits in history. Therefore, the permits are a potentially good resource for mining information on the city’s retrofit history. In this study, we use the permit dataset from the city of San Francisco as a case study. Location and time information from the dataset is also used to depict the retrofit timeline of each building and the whole building stock. The type of work of the permit is inferred from the descriptive text by a machine learning model. At last, the limitations of the current permit dataset and potential improvements on the permit data management are discussed to better utilize the information in the future.
Zhang, Wanni↗
Mining Product Reviews for Important Product Features of Refurbished iPhones
Problem: Remanufacturers want to increase consumer interest in refurbished products, which motivates the need to understand which product features are important to buyers of refurbished products such as mobile phones. Research Questions: This study addresses two questions. First, which product features are most important for buyers of refurbished iPhones? Second, how do those preferences differ from the preferences of buyers of new iPhones? Methods: Online reviews of iPhones are obtained and converted into a document–term matrix. Using this text model, three subsets of features are identified using statistical analysis of frequency of mention: most frequent, average, and least frequent. A logistic regression (LR) model is then used to identify which features are most predictive of whether a review is for a new or refurbished phone. Results: Buyers of refurbished phones mention battery health, screen/display, shell condition, and brand significantly more often than other features. Directly contrasting reviews of refurbished versus new phones shows that shell condition, brand, speaker, and charger are found to be the most predictive product features indicated in reviews for refurbished phones. Of those, the shell condition is significantly more predictive than the others. Implications: The results identify product features that remanufacturers of iPhones can emphasize to increase customer demand.
Anisi, Atefeh↗
A High-Throughput Computing Infrastructure to Generate Custom, Open Community Geothermal Datasets
The most significant challenge facing geothermal research, development, and deployment is a lack of comprehensive datasets describing the geological and economical properties of North America. Automated knowledge base construction, the process of designing algorithms to analyze text and images to programmatically build new datasets, is one possible solution to this problem. The xDD library of full-text scientific articles (https://xdd.wisc.edu) is one of the largest collections of open and controlled-access scientific documents available for knowledge base construction in the world, but it has been underutilized by experts in geothermal research. The xDD development team attributed the lack of engagement by software developers and geothermal researchers to two perceived shortcomings of the system. First, the workflow for obtaining data from xDD for local development and testing of data mining applications was unnecessarily abstruse and required significant manual intervention by xDD systems administrators. Second, although xDD already held articles from a broad cross-section of scientific literature with an emphasis on the geosciences, it did not have an explicit set of geothermal research documents that could serve as the nucleus of a geothermal data mining application. To address these issues, the Automated Data Extraction PlaTform (ADEPT) was proposed to extend the data distribution capabilities of the xDD system. The ADEPT extension added the following four key features to xDD: 1) integration of National Geothermal Data System (NGDS) documents into the xDD library to provide an explicitly geothermally-themed collection; 2) improved RESTful (i.e., https-protocol driven) web services for external partners to access xDD data for machine learning application development; 3) a web platform for end-users and xDD administrators to coordinate the development of data mining applications from the initial step of browsing available documents to the final stage of deploying a production-quality machine learning application on high-throughput computing infrastructure; and 4) the development of demonstration data mining applications to illustrate the new workflow to potential collaborators. A total of 21,674 geothermal documents from NGDS were fully ingested into the xDD library and the associated metadata is publicly available through the xDD web services; furthermore, the ADEPT web platform is now publicly accessible and fully live at https://xdd.wisc.edu/adept/.
15 GEOTHERMAL ENERGY↗
Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types
In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.
60 APPLIED LIFE SCIENCES↗
Complete Decoding and Reporting of Aviation Routine Weather Reports (METARs)
Aviation Routine Weather Report (METAR) provides surface weather information at and around observation stations, including airport terminals. These weather observations are used by pilots for flight planning and by air traffic service providers for managing departure and arrival flights. The METARs are also an important source of weather data for Air Traffic Management (ATM) analysts and researchers at NASA and elsewhere. These researchers use METAR to correlate severe weather events with local or national air traffic actions that restrict air traffic, as one example. A METAR is made up of multiple groups of coded text, each with a specific standard coding format. These groups of coded text are located in two sections of a report: Body and Remarks. The coded text groups in a U.S. METAR are intended to follow the coding standards set by National Oceanic and Atmospheric Administration (NOAA). However, manual data entry and edits made by a human report observer may result in coded text elements that do not follow the standards, especially in the Remarks section. And contrary to the standards, some significant weather observations are noted only in the Remarks section and not in the Body section of the reports. While human readers can infer the intended meaning of non-standard coding of weather conditions, doing so with a computer program is far more challenging. However such programmatic pre-processing is necessary to enable efficient and faster database query when researchers need to perform any significant historical weather analysis. Therefore, to support such analysis, a computer algorithm was developed to identify groups of coded text anywhere in a report and to perform subsequent decoding in software. The algorithm considers common deviations from the standards and data entry mistakes made by observers. The implemented software code was tested to decode 12 million reports and the decoding process was able to completely interpret 99.93 of the reports. This document presents the deviations from the standards and the decoding algorithm. Storing all decoded data in a database allows users to quickly query a large amount of data and to perform data mining on the data. Users can specify complex query criteria not only on date or airport but also on weather condition. This document also describes the design of a database schema for storing the decoded data, and a Data Warehouse web application that allows users to perform reporting and analysis on the decoded data. Finally, this document presents a case study correlating dust storms reported in METARs from the Phoenix International airport with Ground Stops issued by Air Route Traffic Control Centers (ATCSCC). Blowing widespread dust is one of the weather conditions when dust storm occurs. By querying the database, 294 METARs were found to report blowing widespread dust at the Phoenix airport and 41 of them reported such condition only in the Remarks section of the reports. When METAR is a data source for an ATM research, it is important to include weather conditions not only from the Body section but also from the Remarks section of METARs.
METAR Decoder/Parser↗
Kaona: Deep Searching and Curating Data from Aviation Safety Reporting Systems
Context: Several works in the literature have examined how safety narrative databases can be leveraged to share lessons learned. However, less attention has been given to augmenting existing processes for mining these safety reporting system databases. Aim: In this work, we introduce Kaona: An interface that weaves machine learning in existing aviation safety database mining activities. Method: We provide a use case of search, curation and newsletter writing to showcase how Kaona features build on existing processes and on its own to enhance information retrieval, curation and synthesis of narratives. Results: We created two instances of Kaona internally for evaluation, one using publicly available NASA’s ASRS narratives and another using publicly available C3RS narratives. Data ranged from 1998 to 2024. Conclusion: Our tool provides a new way to explore safety narratives, serving to re-imagine how text databases can benefit of novel information retrieval mechanisms in the era of large language models.
ASRS↗