Search NASA⌕ Search

SEARCH · Search NASA

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Integrase-On-Demand-Pipeline Data Set

Files needed to run the Integrase-On-Demand-Pipeline, a program designed to provide users with a list of putative attachment site and integrase pairs for a prokaryotic genome of interest. isles.pkl: Serialized python-object file, containing a dictionary of attachment site sequences and reference genomic island information extracted from the Genomic island database ints.gff: Gene format file containing annotations for all integrases referenced in isles.pkl. The source genome, gene coordinates, integrase name, protein IDs and amino acid sequence included. reps.msh: Binary file containing 1000 128-bit MurmurHash3 hashes for >80,000 genomes

McClain, Hannah Marie [Sandia National Laboratorie↗
DOE OSTI2022

Link Parser Library

Link Parser Library is a Python library for parsing HTTP Link header format. Link Parser extracts information about relationships to other resources from Link Header and translates it into an easy to use Json structure.

Balakireva, Lyudmila↗
DOE OSTI2022

LAVA

We introduce LAVA, a general-purpose python toolkit to provide user-friendly and high throughput calculations for material properties using both LAMMPS and VASP. It contains a set of classes as well as pre-processing and post-processing functions to prepare, execute and extract information from LAMMPS/VASP simulations. An overview of the program structure is provided. The current version contains modules to calculate elastic and mechanical properties such as lattice constant, cohesive energy, cold curve, elastic constants, bulk and shear modulus, volume conserving/non-conserving deformation path, vacancy/interstitial formation energy, surface energy, stacking fault energy, melting point, radial distribution function, and thermal expansion.

Dang, Khanh↗
DOE OSTI2020

Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems

Security-constrained unit commitment (SCUC) is a fundamental problem in power systems and electricity markets. In practical settings, SCUC is repeatedly solved via mixed-integer linear programming (MIP), sometimes multiple times per day, with only minor changes in input data. In this work, we propose a number of machine learning techniques to effectively extract information from previously solved instances in order to significantly improve the computational performance of MIP solvers when solving similar instances in the future. Based on statistical data, we predict redundant constraints in the formulation, good initial feasible solutions, and affine subspaces where the optimal solution is likely to lie, leading to a significant reduction in problem size. Computational results on a diverse set of realistic and large-scale instances show that using the proposed techniques, SCUC can be solved on average 4.3 times faster with optimality guarantees and 10.2 times faster without optimality guarantees, with no observed reduction in solution quality. Out-of-distribution experiments provide evidence that the method is somewhat robust against data-set shift. Summary of Contribution. The paper describes a novel computational method, based on a combination of mixed-integer linear programming (MILP) and machine learning (ML), to solve a challenging and fundamental optimization problem in the energy sector. The method advances the state-of-the-art, not only for this particular problem, but also, more generally, in solving discrete optimization problems via ML. We expect that the techniques presented can be readily used by practitioners in the energy sector and adapted, by researchers in other fields, to other challenging operations research problems that are solved routinely.

Machine Learning↗
DOE OSTI2024

Summit Darshan Archival Dataset

Summit Darshan Archival Dataset contains 2021 Summit Darshan log data for 25 applications and is grouped into science domains. The dataset is processed, and all the propriety fields are anonymized. The resultant data is converted into a tabular structure and saved in parquet file format. In this notebook, we demonstrate how to access the data. Data Organization: The data is organized into two directories: Darshan total (`darshan_total`): List all the high levels generated by the `darshan-parser --total` command on `.darshan` files. There is one parquet file for each application. Note: `uid` and `exe` field are masked Darshan detail (`darshan_detail`): This data contains detailed job level log information extracted by command `darshan-parser` on the raw `.darshan` files. The data is sorted by directory hierarchy in the order of `year/month/day (2021/12/07)`. For instance, to get the data for a `job_id` 3819766 of application `App11`, which was executed on `2021-12-07`can be accessed as follows. Note:`uid` and `filename` fields are masked

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Using data-science approaches to unravel insights for enhanced transport of lithium ions in single-ion conducting polymer electrolyte

Solid polymer electrolytes have yet to achieve the an ionic conductivity > 1 mS/cm at room temperature for realistic applications. This target implies the need to reduce the effective energy barriers of ion transport in polymer electrolytes to around 20 kJ/mol. In this work, we combine information extracted from existing experimental results with theoretical calculations to provide insights into ion transport in single-ion conductors (SICs) with a focus on lithium ion SICs. Through the analysis of temperature-dependent ionic conductivity data obtained from the literature, we evaluate different methods of extracting energy barriers for lithium transport. The traditional Arrhenius fit to the temperature-dependent ionic conductivity data indicates that the Meyer-Neldel rule holds for SICs. However, the values of the fitting parameters remain unphysical. Our modified approach based on recent work (Macromolecules, 56, 15, 6051(2023)), which incorporates a fixed pre-exponential factor, reveals that the energy barriers exhibit temperature dependence over a wide range of temperatures. Using this approach, we identify a series of anions leading to the energy barriers less than 30 kJ/mol, which include trifluoromethane sulfonimide (TFSI), fluoromethane sulfonimide (FSI), and boron-based organic anions. In our efforts to design the next generation of anions, which can exhibit the energy barriers less than 20 kJ/mol, we focused on boron-containing SICs, and performed density functional theory (DFT) based calculations to connect the chemical structures via the binding energy of cation (lithium)-anion pairs with the experimentally derived effective energy barriers for ion transport. Not only have we identified a correlation between the binding energy and the energy barriers, but we also propose a strategy to design new boron-based anions by using the correlation. This combined approach involving experiments and theoretical calculations is capable of facilitating the identification of promising new anions, which can exhibit ionic conductivity $> 1$ mS/cm near room temperature, thereby expediting the development of novel superionic single-ion conducting polymer electrolytes. The published datasets include all the temperature-dependent ionic conductivity collected from the literature with literature DOIs, DFT calculated binding energies, and python scripts to analyze data, construct statistical models, and generate plots.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Using case-level context to classify cancer pathology reports

Individual electronic health records (EHRs) and clinical reports are often part of a larger sequence—for example, a single patient may generate multiple reports over the trajectory of a disease. In applications such as cancer pathology reports, it is necessary not only to extract information from individual reports, but also to capture aggregate information regarding the entire cancer case based off case-level context from all reports in the sequence. In this paper, we introduce a simple modular add-on for capturing case-level context that is designed to be compatible with most existing deep learning architectures for text classification on individual reports. We test our approach on a corpus of 431,433 cancer pathology reports, and we show that incorporating case-level context significantly boosts classification accuracy across six classification tasks—site, subsite, laterality, histology, behavior, and grade. We expect that with minimal modifications, our add-on can be applied towards a wide range of other clinical text-based tasks.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2026

Truck Platooning Performance with ADAS and Onboard Camera Data Describing Traffic Interactions

This project was part of the Characterizing Behaviors and Capabilities for Emerging Connected and Automated Vehicle Technologies, Sensors, and Connectivity project. The National Laboratory of the Rockies partnered with Cummins Inc. to collect data from Class 8 tractor trailer combinations in platoon (cooperative adaptive cruise control) operations on public roads in southern Indiana. Data collected include J1939 CAN bus, radar, intervehicle position, and video data. The video data could not be shared in the raw form, so they were processed to extract information on the other vehicles on the road, their relative positions, and intrusion events. This information was then columnized for modeling use and further enhanced by appending road information including road type, speed limit, altitude, and grade. The test route included free-flowing traffic, highway interchanges, and construction zones, as well as low-, medium-, and high-grade sections. Individual test conditions varied by day, with advanced driver-assistance system (ADAS) features engaged or disengaged and different combined vehicle masses tested in addition to uncontrolled variables such as weather and traffic interactions.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Automatic Waveform Quality Control for Surface Waves Using Machine Learning

Surface-wave seismograms are widely used by researchers to study Earth’s interior and earthquakes. To extract information reliably and robustly from a suite of surface waveforms, the signals require quality control screening to reduce artifacts from signal complexity and noise. This process has usually been completed by human experts labeling each waveform visually, which is time consuming and tedious for large data sets. We explore automated approaches to improve the efficiency of waveform quality control processing by investigating logistic regression, support vector machines, K-nearest neighbors, random forests (RF), and artificial neural networks (ANN) algorithms. To speed up signal quality assessment, we trained these five machine learning (ML) methods using nearly 400,000 human-labeled waveforms. The ANN and RF models outperformed other algorithms and achieved a test accuracy of 92%. We evaluated these two best-performing models using seismic events from geographic regions not used for training. The results show that the two trained models agree with labels from human analysts but required only 0.4% of the time. Although the original (human) quality assignments assessed general waveform signal-to-noise, the ANN or RF labels can help facilitate detailed waveform analysis. Our investigations demonstrate the capability of the automated processing using these two ML models to reduce outliers in surface-wave-related measurements without human quality control screening.

58 GEOSCIENCES↗
DOE OSTI2020

Cosmic Growth Rate as Probe of Dark Matter and Gravity. Final Report

Some 95% of the energy content of the universe lies outside the standard model of particle physics, with approximately 70% arising from physics that accelerates cosmic expansion in opposition to normal gravity and about 25% dark matter that clusters under gravity but does not interact directly with light. This project made significant advances in developing methods to extract information on the former – dark energy or modified gravity – and latter – dark matter through their effects on the expansion history of the universe and the cosmic growth of large scale structures under the influence of gravity and dark energy. These results directly benefit experimental/observational cosmic surveys of large scale structure imaging hundreds of millions of galaxies and mapping spectroscopically the 3D positions of tens of millions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

HAIMOS Ensemble Forecasts for Intra-day and Day- Ahead GHI, DNI and Ramps

The objective of this research is to develop a hybrid physics-based/data-driven forecast model to improve direct normal and global horizontal irradiance (DNI and GHI) prediction for horizons ranging from 1 to 72 hours. Project objectives also address key gaps in state-of-the-art solar forecasting: accurate probabilistic solar forecasts and the forecasting of large irradiance ramps (ramp onset and magnitude). The proposed model ensembles Numerical Weather Prediction (NWP) forecasts, determinist physics-based algorithms, and new-generation cloud cover products (high-resolution rapid refresh satellite images and Large Eddy Simulations). The result is the Hybrid Adaptive Input Model Objective Selection (HAIMOS) ensemble model. HAIMOS blends state of the art machine learning methodologies with physics-based models for cloud cover and cloud optical depth forecasts. The technical activities followed a two-pronged strategy. First, the preprocessing of data, the selection of inputs to the nonlinear approximators, the type of approximator and objective functions, and post-processing ensembling techniques included in HAIMOS were all optimized adaptively to find the best model for a specific goal (reduce DNI/GHI forecast error, improve the prediction of ramp onset, etc.). Second, a large effort was put in improving cloud identification and the forecast of cloud cover and cloud optical depth. To this end, new-generation cloud parametrization products were developed in this work. These include improved algorithms to assist in cloud identification, cloud classification and cloud parametrization from satellite images – three key factors in the accuracy of 1 to 6-hours irradiance forecasts and prediction of ramp onset. Furthermore, we also included cloud information extracted from high resolution rapid refresh satellite images (GOES-16) and Large Eddy Simulations (LES). LES was used to model the atmosphere in detail over locations of interest and produce cloud optical depth forecasts. Once these data streams were validated, they were used as input data to the HAIMOS forecast. The model was developed using data from several climatologically distinct locations with potential for high solar penetration. In the last year of the project, we conducted a validation campaign according to the guidelines stipulated by the Topic Area 1 project as described in the FOA. This effort brings, for the first time, proven machine-learning methodologies for generating state-of-the-art solar forecasts interweaved with detailed physics-based models for cloud detection, and cloud optical depth forecasts. HAIMOS will generate accurate irradiance probabilistic forecast to assist in reducing solar generation prediction error. Globally optimized solar forecast models are more likely to impact solar energy stakeholders. The goal of this project was to increase the state-of-the-art forecast skill from their present values of 10 to 35%. At the end of the project, we achieved between 30% and 50% forecast skill across a wide range of horizons for both GHI and DNI.

14 SOLAR ENERGY↗
DOE OSTI2022

Accelerating Multiscale Materials Modeling with Machine Learning

The focus of this project is to accelerate and transform the workflow of multiscale materials modeling by developing an integrated toolchain seamlessly combining DFT, SNAP, LAMMPS, (shown in Figure 1-1) and a machine-learning (ML) model that will more efficiently extract information from a smaller set of first-principles calculations. Our ML model enables us to accelerate first-principles data generation by interpolating existing high fidelity data, and extend the simulation scale by extrapolating high fidelity data (10 2 atoms) to the mesoscale (10 4 atoms). It encodes the underlying physics of atomic interactions on the microscopic scale by adapting a variety of ML techniques such as deep neural networks (DNNs), and graph neural networks (GNNs). We developed a new surrogate model for density functional theory using deep neural networks. The developed ML surrogate is demonstrated in a workflow to generate accurate band energies, total energies, and density of the 298K and 933K Aluminum systems. Furthermore, the models can be used to predict the quantities of interest for systems with more number of atoms than the training data set. We have demonstrated that the ML model can be used to compute the quantities of interest for systems with 100,000 Al atoms. When compared with 2000 Al system the new surrogate model is as accurate as DFT, but three orders of magnitude faster. We also explored optimal experimental design techniques to choose the training data and novel Graph Neural Networks to train on smaller data sets. These are promising methods that need to be explored in the future.

36 MATERIALS SCIENCE↗
DOE OSTI2022

MVP-CTL Fellowship for Suicide Intervention (CRADA Final Report)

Research conducted with Crisis Text Line (CTL) served as an important stepping stone in the group’s ongoing work of developing natural language processing (NLP) methodologies to discover indicators of suicide factors in the U.S. veteran population. With rising cases of suicide, detecting risk factors among veterans is of growing concern. Socio-economic factors are often under-reported along structured medical variables, and extracting information through NLP methods may improve the sensitivity of suicide prediction models. The research explored through the CTL collaboration provided insights on suicide crisis detection and de-escalation, experience in applying scalable data analysis on real world datasets, contributions to study designs for detecting rare-event and produced transferable methods applicable to the domain of veteran suicide mitigation. Tools developed during this research directly benefits ongoing work on the Million Veteran Project (MVP) collaboration with the Department of Veteran Affairs (VA).

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2022

Estimating Channel Width for the Middle Green River Using Remote Sensing

Channel geometry can affect the abundance and quality of fish habitats along rivers in the Colorado River basin. However, previous analyses of sediment transport and channel narrowing in the middle Green River have focused on very limited reaches of the river and have used techniques with varying degrees of resolution, leading to potential problems with interpretation and generalization to the overall reach. The goal of this study is to develop comprehensive baseline information for channel width estimation along the Green River by combining a high-resolution digital elevation model (DEM) derived from Light Detection and Ranging (LiDAR) data and Sentinel-2 multispectral satellite imagery. The objectives are to (1) estimate channel width using Sentinel-2 satellite imagery alone, (2) estimate channel width using the high-resolution DEM with ancillary information extracted from the multispectral imagery, and (3) examine the agreement in channel width estimates between the products derived from the two methods to gain insights for cost effective channel-width monitoring.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Triton Field Trials - Changes in Habitats, a Literature Review of Monitoring Technologies

Marine energy devices are installed in highly dynamic environments and have the potential to affect benthic and pelagic habitats around them. Regulatory bodies often require baseline characterization and/or post-installation monitoring to determine whether changes in these habitats are being observed. However, a great diversity of technologies is available for surveying and sampling marine habitats. Selecting the most suitable instrument to identify and measure changes in habitats at marine energy sites can become a daunting task. We conducted a thorough review of journal articles, survey reports, and grey literature to extract information about the technologies used, the data collection and processing methods, and the performance and effectiveness of these instruments. We examined documents related to marine energy development, offshore wind farms, oil and gas offshore sites, and other marine industries around the world over the last 20 years, as well as national and international guidelines for surveying habitats around offshore activities. A total of 120 different technologies were identified across six main habitat categories: seafloor, sediment, infauna, epifauna, pelagic, and biofouling. The technologies were organized into 12 broad technology classes: acoustic, corer, dredge, grab, hook and line, net and trawl, plate, remote sensing, scrape samples, trap, visual, and others. Visual was the most common and the most diverse technology class, with applications across all six habitat categories. Sampling designs varied considerably among the reviewed studies but transect was the predominant design for surveying seafloor, epifauna, and pelagic habitats. The most common data analyses were univariate and multivariate statistical analyses aimed at calculating and comparing biodiversity indices, characterizing faunal assemblages or sediment classes, or modeling the distribution of animals related to abiotic parameters. Technologies and sampling methods adaptable and designed to work efficiently in energetic environments have greater success at marine energy sites. In addition, sampling designs and statistical analyses should be carefully thought through to identify differences in faunal assemblages and spatiotemporal changes in habitats.

16 TIDAL AND WAVE POWER↗
DOE OSTI2024

Are Marine Low Cloud Droplet Concentrations Buffered by Entrained Aitken‐Mode Aerosol (Final Technical Report)

During the summertime, the high-latitude oceans come to life with green phytoplankton, which gain their energy from sunlight and are food for sea creatures small and large. When the phytoplankton are eaten or die, sulfur-rich gases are released under the ocean surface and mix into the air. Observations suggest that, over the Southern Ocean, frequent storms lift this air high into the atmosphere while raining out particulates like salt. As a result, the sulfur-rich air then spawns high concentrations of small ‘Aitken-mode’ aerosol particles. We hypothesize that these particles work their way down into the marine boundary layer, where they can replenish the supply of cloud-condensation nuclei scavenged by frequent precipitation. Further, this process maintains high concentrations of liquid cloud droplets in austral summer, promoting more sunlight to be reflected to space. We call this ‘Aitken buffering’. The primary objective of this project has been to document and test what role Aitken-mode aerosols play in clouds over the Southern Ocean and elsewhere. This effort has included three main components: 1) developing a computer model that realistically simulates the aerosol processes and the small-scale turbulent air motions that move aerosols around and create the clouds, 2) using that model to interpret and extend these observations for process understanding, by allowing different factors that contribute to the aerosol budget, such as surface wind speed, precipitation, surface gas exchange, etc. to be separated, and 3) studying Aitken-mode aerosol and its variability with a focus over the Southern Ocean and Antarctica, using data from Atmospheric Radiation Measurement (ARM) sites and other available observations. Initial computer studies in more idealized conditions found that elevated concentrations of Aitken-mode aerosols above the clouds could help prevent the breakup of those clouds by acting as cloud-condensation nuclei after they were entrained into the cloudy boundary layer. Simulations of a day during the ACE-ENA field campaign showed that Aitken-mode aerosols could also prevent cloud breakup under more realistic conditions. A new method that extracts information about Aitken-mode aerosols from measurements of aerosols onto which cloud droplets can form finds that Aitken-mode aerosols do vary seasonally over the Southern Ocean, with a peak in summertime, as described above. Other work during this project has focused on understanding how patterns of water vapor, clouds and precipitation are coupled within low-lying clouds over the oceans, and also on how cloud droplets cluster within clouds and how the distribution of cloud droplet sizes change as dry air is mixed into clouds, with the latter studies also using observations from ACE-ENA.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Time-dependent phenomena in correlated materials

Understanding time-dependent processes and light-matter interaction in strongly correlated materials, and the interplay between electronic, orbital, vibrational, and spin degrees of freedom, is a cornerstone of condensed matter. These mechanisms can be proven by measuring the response of the systems to time-dependent perturbations. The corresponding time scales are dictated by the way light couples to the different excitations, and how these excitations exchange energy and momentum. Our research advances our understanding of these processes, and the interpretation of different equilibrium and time-resolved spectroscopies. Our project encompasses two main themes: (i) developing and refining computational techniques to study non-equilibrium spectroscopies including non-perturbative effects and (ii) applications to non-equilibrium phenomena. We have developed a new computational approach that works directly in the time domain: by including all the degrees of freedom involved in the scattering process (e.g. electrons, photons, neutrons), we solve the time dependent problem: a faithful numerical simulation of the experiment. By measuring the energy and momentum of the outgoing particles, we can extract information about the energy and momentum absorbed by the system. Prior to our work, people attempting to model and calculate non-equilibrium spectral functions relied on a description of the scattering cross section based on a formulation in the frequency domain, a treatment that is extremely cumbersome and complex. Our technique works in and out of equilibrium and can reproduce spectra by several spectroscopic techniques, such as time-resolved photoemission, neutron scattering, Raman, X-ray spectroscopies (RIXS, Auger, XAS, XMCD), and, by not relying on analytical approximations, yields results that reveal novel overlooked transient mechanisms. These tools provide sorely needed intuition for understanding the phenomenology of strongly correlated materials and will help experimentalists in identifying signatures of relevant excitations in pump-probe experiments, such as those conducted in DOE supported facilities.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗