Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “information extraction”

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 163 records · Page 9

Landsat image interpretation aids

In the Large Area Crop Inventory Experiment, image interpretation aids were produced to assist in selecting and/or identifying representative samples of signatures in a given Landsat scene. The three methods employed are based on clustering techniques, information extraction, and aggregation of like spectral information on a two-dimensional spectral plot.

Abotteen, R. A.↗

Natural Language Processing Analysis of Notices to Airmen for Air Traffic Management Optimization

With new emerging technologies in the field of NLP, we explore their applications to digitize and analyze heritage Air Traffic Management (ATM) documents for planning and optimizing airspace operations. Specifically, this research focuses on harvesting semi-structured or un-structured information contained in Notices to Airmen (NOTAMs). Using NLP and other advanced data analytics, we will construct a data-driven framework which facilitates finding language patterns and the use of pretrained language models for classification and extraction of useful airspace constraints and restrictions. These may lead to tools that assist airspace users in understanding the constraints more efficiently, contributing to better route planning and safer execution. This paper explores three workflows entailing different NLP tasks. First, unsupervised techniques like word embedding and topic modeling are used for pattern finding and document classification. Second, a dataset is created by extracting information from the semi-structured NOTAM format as metadata for categorizing, visualizing, and extracting key entities driving NOTAM content. Third, modern pre-built deep learning based transformer models such as BERT, RoBERTa, and XLNet are evaluated on the question answering task, an even more robust approach to information extraction, as well as their respective fine-tuning tasks. In this work we include various performance metrics for the trained models to evaluate both accuracy and precision and we show that the models can be generalized for their respective tasks. The research work developed shows promise in uncovering trends in digital NOTAMs in the NAS and also offers a new framework for digitizing and inferring insights from free-form legacy NOTAMs, that are yet to be digitized.

Natural Language Processing↗

Natural Language Processing (NLP) Analysis of NOTAMs for Air Traffic Management Optimization

With new emerging technologies in the field of NLP, we explore their applications to digitize and analyze heritage Air Traffic Management (ATM) documents for planning and optimizing airspace operations. Specifically, this research focuses on harvesting semi-structured or un-structured information contained in Notices to Airmen (NOTAMs). Using NLP and other advanced data analytics, we will construct a data-driven framework which facilitates finding language patterns and the use of pretrained language models for classification and extraction of useful airspace constraints and restrictions. These may lead to tools that assist airspace users in understanding the constraints more efficiently, contributing to better route planning and safer execution. This paper explores three workflows entailing different NLP tasks. First, unsupervised techniques like word embedding and topic modeling are used for pattern finding and document classification. Second, a dataset is created by extracting information from the semi-structured NOTAM format as metadata for categorizing, visualizing, and extracting key entities driving NOTAM content. Third, modern pre-built deep learning based transformer models such as BERT, RoBERTa, and XLNet are evaluated on the question answering task, an even more robust approach to information extraction, as well as their respective fine-tuning tasks. In this work we include various performance metrics for the trained models to evaluate both accuracy and precision and we show that the models can be generalized for their respective tasks. The research work developed shows promise in uncovering trends in digital NOTAMs in the NAS and also offers a new framework for digitizing and inferring insights from free-form legacy NOTAMs, that are yet to be digitized. Video is an mp4 download, with a play time of 9 min 35 secs.

Natural Language Processing↗

Massive νs through the CNN lens: interpreting the field-level neutrino mass information in weak lensing

Modern cosmological surveys probe the Universe deep into the nonlinear regime, where massive neutrinos suppress cosmic structure. Traditional cosmological analyses, which use the 2-point correlation function to extract information, are no longer optimal in the nonlinear regime, and there is thus much interest in extracting beyond-2-point information to improve constraints on neutrino mass. Quantifying and interpreting the beyond-2-point information is thus a pressing task. We study the field-level information in weak lensing convergence maps using convolution neural networks. We find that the network performance increases as higher source redshifts and smaller scales are considered — investigating up to a source redshift of 2.5 and ℓ max ≃ 10 4 — verifying that massive neutrinos leave a distinct effect on weak lensing. However, the performance of the network significantly drops after scaling out the 2-point information from the maps, implying that most of the field-level information can be found in the 2-point correlation function alone. We quantify these findings in terms of the likelihood ratio and also use Integrated Gradient saliency maps to interpret which parts of the map the network is learning the most from. We find that, in the absence of noise, the network extracts a similar amount of information from the most overdense and underdense regions. However, upon adding noise, the information in underdense regions is distorted as noise disproportionately washes out void-like structures.

Golshan, Malika [University of California, Berkele↗

Automatic Labeling for Entity Extraction in Cyber Security

Timely analysis of cyber-security information necessitates automated information extraction from unstructured text. While state-of-the-art extraction methods produce extremely accurate results, they require ample training data, which is generally unavailable for specialized applications, such as detecting security related entities; moreover, manual annotation of corpora is very costly and often not a viable solution. In response, we develop a very precise method to automatically label text from several data sources by leveraging related, domain-specific, structured data and provide public access to a corpus annotated with cyber-security entities. Next, we implement a Maximum Entropy Model trained with the average perceptron on a portion of our corpus (~750,000 words) and achieve near perfect precision, recall, and accuracy, with training times under 17 seconds.

Automatic Labeling↗

Adaptive Classification of Landscape Process and Function: An Integration of Geoinformatics and Self-Organizing Maps

The advanced geospatial information extraction and analysis capabilities of a Geographic Information System (GISs) and Artificial Neural Networks (ANNs), particularly Self-Organizing Maps (SOMs), provide a topology-preserving means for reducing and understanding complex data relationships in the landscape. The Adaptive Landscape Classification Procedure (ALCP) is presented as an adaptive and evolutionary capability where varying types of data can be assimilated to address different management needs such as hydrologic response, erosion potential, habitat structure, instrumentation placement, and various forecast or what-if scenarios. This paper defines how the evaluation and analysis of spatial and/or temporal patterns in the landscape can provide insight into complex ecological, hydrological, climatic, and other natural and anthropogenic-influenced processes. Establishing relationships among high-dimensional datasets through neurocomputing based pattern recognition methods can help 1) resolve large volumes of data into a structured and meaningful form; 2) provide an approach for inferring landscape processes in areas that have limited data available but exhibit similar landscape characteristics; and 3) discover the value of individual variables or groups of variables that contribute to specific processes in the landscape. Classification of hydrologic patterns in the landscape is demonstrated.

58 GEOSCIENCES↗

X-ray photoelectron spectroscopy of epitaxial films and heterostructures

X-ray photoelectron spectroscopy is a powerful experimental technique that yields invaluable information on a range of phenomena that occur in solids, liquids, and gasses. The binding energy and shape of a photoemission peak is sensitive not only to the atomic number, valence and orbital from which the electron is ejected, but also to complex many-body effects that accompany photoemission. Provided the influences of these different drivers of spectral line shapes can be disentangled, a great deal can be learned about the electronic structures of specific atoms in the material of interest. In addition to these largely local effects, the long-range electrostatic environment and resulting electric potential at the emitting atom have a direct effect on the measured binding energies. Furthermore, this fact opens the door to extracting information about the dependence of the valence and conduction band minima on depth below the surface, which in turn allows both vertical and lateral electrical transport data to be better understood. One purpose of this Report is to describe how the different physical forces described above impact spectral properties of complex oxide epitaxial films. This class of materials typically incorporates transition metal cations in different valences and of all the elements, these exhibit the most complex core-level spectra. A second purpose is to show how a comprehensive understanding of local physical effects in x-ray photoemission allows one to extract detailed information on internal electric fields and band edge discontinuities in heterostructures involving complex oxides from core-level line shapes.

47 OTHER INSTRUMENTATION↗

ABM Drag_Pass Report Generator

dragREPORT software was developed in parallel with abmREPORT, which is described in the preceding article. Both programs were built on the capabilities created during that process. This tool generates a drag_pass report that summarizes vital information from the MRO aerobreaking drag_pass build process to facilitate both sequence reviews and provide a high-level summarization of the sequence for mission management. The script extracts information from the ENV, SSF, FRF, SCMFmax, and OPTG files, presenting them in a single, easy-to-check report providing the majority of parameters needed for cross check and verification as part of the sequence review process. Prior to dragReport, all the needed information was spread across a number of different files, each in a different format. This software is a Perl script that extracts vital summarization information and build-process details from a number of source files into a single, concise report format used to aid the MPST sequence review process and to provide a high-level summarization of the sequence for mission management reference. This software could be adapted for future aerobraking missions to provide similar reports, review and summarization information.

Fisher, Forest↗

A Comparative Study on Emerging Electric Vehicle Technology Assessments

Numerous organizations have published reports in recent years that investigate the ever changing world of electric vehicle (EV) technologies and their potential effects on society. Specifically, projections have been made on greenhouse gas (GHG) emissions associated with these vehicles and how they compare to conventional vehicles or hybrid electric vehicles (HEVs). Similar projections have been made on the volumes of oil that these vehicles can displace by consuming large amounts of grid electricity instead of petroleum-based fuels. Finally, the projected rate that these new vehicle fleets will enter the market varies significantly among organizations. New ideas, technologies, and possibilities are introduced often, and projected values are likely to be refined as industry announcements continue to be made. As a result, over time, a multitude of projections for GHG emissions, oil displacement, and market penetration associated with various EV technologies has resulted in a wide range of possible future outcomes. This leaves the reader with two key questions: (1) Why does such a collective range in projected values exist in these reports? (2) What assumptions have the greatest impact on the outcomes presented in these reports? Since it is impractical for an average reader to review and interpret all the various vehicle technology reports published to date, Sentech Inc. and the Oak Ridge National Laboratory have conducted a comparative study to make these interpretations. The primary objective of this comparative study is to present a snapshot of all major projections made on GHG emissions, oil displacement, or market penetration rates of EV technologies. From the extensive data found in relevant publications, the key assumptions that drive each report's analysis are identified and 'apples-to-apples' comparisons between all major report conclusions are attempted. The general approach that was taken in this comparative study is comprised of six primary steps: (1) Search Relevant Literature - An extensive search of recent analyses that address the environmental impacts, market penetration rates, and oil displacement potential of various EV technologies was conducted; (2) Consolidate Studies - Upon completion of the literature search, a list of analyses that have sufficient data for comparison and that should be included in the study was compiled; (3) Identify Key Assumptions - Disparity in conclusions very likely originates from disparity in simple assumptions. In order to compare 'apples-to-apples,' key assumptions were identified in each study to provide the basis for comparing analyses; (4) Extract Information - Each selected report was reviewed, and information on key assumptions and data points was extracted; (5) Overlay Data Points - Visual representations of the comprehensive conclusions were prepared to identify general trends and outliers; and (6) Draw Final Conclusions - Once all comparisons are made to the greatest possible extent, the final conclusions were draw on what major factors lead to the variation in results among studies.

54 ENVIRONMENTAL SCIENCES↗

Proposed Test of the Two Beam BPM at RHIC

The essence of the ERL operation implies that at least two beams (accelerated and decelerated) are co-propagating in the same vacuum vessel and each beam has its own trajectory. The existing beam position monitors measure only “average” trajectory but not that of an individual beam, unless the time separation between bunches is so large that one can resolve individual bunches. It was proposed to use phase information of the pick-up signal to extract information on the orbit “difference”. We are planning to conduct experiments at RHIC to test the proposed idea. The approach and experiment set-up are described in the paper.

43 PARTICLE ACCELERATORS↗

Velocity Extraction Using Complete Time-Domain Waveform Data and Audio Machine Learning

We developed a new machine learning-based tool for extracting information from interferometry measurements: MIDWAZE (Modular Interferometry Direct Waveform AnalyZEr). This paper showcases MIDWAZE’s ability to extract an object’s velocity information from Photonic Doppler Velocimetry (PDV) data at near-human accuracy with little to no human intervention. MIDWAZE can extract velocities roughly 350 times as fast as a human analyst "rushing" to complete their extractions, with similar extraction accuracy. MIDWAZE’s most outstanding feature is that it operates directly in waveform/temporal space, freeing analysis from certain limitations imposed by traditional spectrogram-based approaches and opening the way to "phase aware" PDV analysis. MIDWAZE also has limited ability to discriminate between different solid objects, which we develop as a first step towards automated discrimination of different kinds of objects such as ejecta clouds.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Web-based wide-area monitoring platform for ringdown and clustering analytics in power systems

This paper introduces an open-source research platform for monitoring the Mexican interconnected power grid, allowing real-time processing and information extraction of the grid’s dynamic condition. Moreover, the platform is a Python-based development that embeds different ringdown and clustering analytics tools. In the case of ringdown analysis, the modal information can be extracted using some of the most known algorithms, i.e., Prony analysis, eigensystem realization algorithm (ERA), and matrix pencil (MP). For clustering analysis, the coherent behaviour of generator and non-generator buses is provided by applying recent state-of-the-art techniques such as affinity propagation, K-means, hierarchical agglomerative clustering, and typicality data analysis. The results of up to 93 PMUs show that this open-source platform suits researchers’ and engineers’ power system dynamic analysis requirements.

Clustering↗

Extracting heading and temporal range from optic flow: Human performance issues

Pilots are able to extract information about their vehicle motion and environmental structure from dynamic transformations in the out-the-window scene. In this presentation, we focus on the information in the optic flow which specifies vehicle heading and distance to objects in the environment, scaled to a temporal metric. In particular, we are concerned with modeling how the human operators extract the necessary information, and what factors impact their ability to utilize the critical information. In general, the psychophysical data suggest that the human visual system is fairly robust to degradations in the visual display, e.g., reduced contrast and resolution or restricted field of view. However, extraneous motion flow, i.e., introduced by sensor rotation, greatly compromises human performance. The implications of these models and data for enhanced/synthetic vision systems are discussed.

Kaiser, Mary K.↗

Integration of AIRSAR and AVIRIS data for Trail Canyon alluvial fan, Death Valley, California

Combining quantitative geophysical information extracted from the optical and microwave wavelengths provides complementary information about both the surface mineralogy and morphology. This study combines inversion results from two remote sensing instruments, a polarimetric synthetic aperture radar, AIRSAR, and an imaging spectrometer, AVIRIS, for Trail Canyon alluvial fan in Death Valley, California. The NASA/JPL Airborne Synthetic Aperture Radar (AIRSAR) is a quad-polarization, three frequency instrument. AIRSAR collects data at C-band = 5.66 cm, L-band = 23.98 cm, and P-band = 68.13 cm. The data are processed to four-looks and have a spatial resolution of 10 m and a swath width of 12 km. The AIRSAR data used in this study were collected as part of the Geologic Remote Sensing Field Experiment (GRSFE) over Death Valley on 9/14/89. The Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) is a NASA/JPL instrument that flies in an ER-2 aircraft at an altitude of 20 km. AVIRIS uses four spectrometers to collect data in 224 spectral channels from 0.4 micrometer to 2.45 micrometer. The width of each spectral band is approximately 10 nm. AVIRIS collects data with a swath width of 11 km and a pixel size of 20 m. The AVIRIS data used in this study were collected over Death Valley on 5/31/92.

Kierein-Young, Kathryn S.↗

Quantification of Arctic Soil and Permafrost Properties Using Ground-Penetrating Radar and Electrical Resistivity Tomography Datasets

Improving understanding of Arctic ecosystem climate feedback and parameterization of models that simulate freeze-Thaw dynamics require advances in quantifying soil and snow properties. Due to the significant spatiotemporal variability of soil properties and the limited information provided by point-scale measurements (e.g., cores), geophysical methods hold potential for improving soil and permafrost characterization. In this study, we evaluate the use of a ground-penetrating radar (GPR) to estimate thaw layer thickness, snow depth, and ice-wedge characteristics in an ice-wedge-dominated tundra region near Barrow, AK, USA. To this end, we analyze GPR and point-scale measurements collected along several parallel transects at the end of the growing season and the end of frozen season. In addition, we compare the structural information extracted from the GPR data with electrical resistivity tomography (ERT) information about ice-wedge characteristics. Our study generally highlights the value of GPR data collected in the frozen season, when conditions lead to the improved GPR signal-To-noise ratio, facilitate data acquisition, and reduce acquisition-related ecosystem disturbance relative to growing season. We document for the first time that GPR data collected during the frozen season can provide reliable estimates of active layer thickness and geometry of ice wedges. We find that the ice-wedge geometry extracted from GPR data collected during the frozen season is consistent with ERT data, and that GPR data can be used to constrain the ERT inversion. Consistent with recent studies, we also find that GPR data collected during the frozen season can provide good estimates of snow thickness, and that GPR data collected during the growing season can provide reliable estimate thaw depth. As a result, our quantification of the value of the GPR and ERT data collected during growing and frozen seasons paves the way for coupled inversion of the datasets to improve understanding of permafrost variability.

54 ENVIRONMENTAL SCIENCES↗

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks. Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗

Bridging the Gap between Cosmological Simulations with Graph Neural Networks and Domain Adaptation

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross dataset tasks (up to 28% better relative error and up to almost an order of magnitude better χ 2 ). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

97 MATHEMATICS AND COMPUTING↗

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗