Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data integrity”

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 1,117 records · Page 62
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

The Relationship Between Area-Time Integrals Determined from Satellite Infrared Data by Means of a Fixed-Threshold Approach and Convective Rainfall Volumes

The relationship of the rainfall from convective clouds to area-time integrals determined from satellite infrared data using a fixed infrared-temperature threshold is investigated. Concurrent radar and rapid-scan satellite data obtained during field projects in the northern High Plains and the southeastern United States were used in this study. The fixed IR threshold appropriate for each region was determined by an optimization procedure that identified the brightness threshold that yields the strongest relationship between estimated rainfall from a cloud cluster and its satellite Area-Time Integral (ATI) for each dataset. For the North Dakota-Montana area the optimization procedure indicated that the area enclosed by the -22.5 C isotherm provides satellite ATI values most closely related to the estimated rainfalls. For the southeastern United States project, the optimized tem- perature threshold was 8.5'C. The difference between the thresholds determined for the two geographic areas suggests that a different 'calibration' for each distinct area may be needed to make use of this relationship. Slopes of the two log-log rainfall-ATI regressions are less than unity, indicating that a relative horizontal expansion and/or increase in persistence of a cloud cluster exceeds the associated increase in precipitation. Implications for the Geostationary Operational Environmental Satellite precipitation index are discussed. New results concerning the rain volume-radar ATI relationship for the southeastern United States are also appended to the paper.

Johnson, L. Ronald↗
DOE OSTI2021

KS4A-Omics1.0_FspDS682

Soil fungi facilitate the translocation of inorganic nutrients from soil minerals to other microorganisms and plants. This ability is particularly advantageous in impoverished soils, because fungal mycelial networks can bridge otherwise spatially disconnected and inaccessible nutrient hotspots. However, the molecular mechanisms underlying fungal mineral weathering and transport through soil remains poorly understood. Here, we addressed this knowledge gap by directly visualizing nutrient acquisition and transport through fungal hyphae in a mineral doped soil micromodel using a multimodal imaging approach. Here, we observed how a representative of common saprotrophic soil fungi, Fusarium sp. DS 682, exhibited a mechanosensory response (thigmotropism) around obstacles and through pore spaces (~12 μm) in the presence of minerals.This study establishes the significance of fungal biology and nutrient translocation mechanisms in maintaining fungal growth under water and nutrient limitations in a soil-like microenvironment, using a high-throughput multi-omic analysis approach. Data package KS4A-Omics.1.0_FspDS682 (Publication: Fungal Mineral Weathering Mechanisms Revealed Through Direct Molecular Visualization) contents reported here are the first version (1.0) and contain pre- and post-processed data using high throughput data capture technologies for multi-omic analysis and integration, this data package contains raw and post-processed experimental data for X-Ray Absorption Near Edge Structure Spectroscopy (XANES/XRF), Optical Microscopy, Proteomics, Scanning Electron Microscope (SEM), Time-of-Flight Secondary Ion Mass Spectroscopy (ToF-SIMS), X-Ray Diffraction Spectroscopy (XRD) files, and X- Ray Photoelectron Spectroscopy (XPS) using EMSL capabilities. This data package DOI contains a comprehensive collection of high-throughput multi-omics data and process metadata catalog. Support files include additional data download contents “Read Me” with dataset descriptor information and data source method application ontologies (see data dictionary section). Reported data download content is structured for compliance with reported guidelines provided by community standard initiatives and publisher stakeholder policies supporting FAIR data principles.

47 OTHER INSTRUMENTATION↗
NASA NTRS1981

Application of digital terrain data to quantify and reduce the topographic effect on Landsat data

Landsat multispectral scanner (MSS) data are integrated with 30 m US Geological Survey digital terrain data to quantify and reduce topographic effects on imagery of a forested mountain ridge in central Pennsylvania. Spectral band ratioing slightly decreased variation of Landsat data for 50% of the transects and could not eliminate direct-light topographic effects. A Lambertian model increased topographic effect, and a modified Lambertian model decreased variation produced by the original model, but gave higher variances than found in the raw Landsat data. A non-Lambertian model, however, decreased variation by 86%, reducing topographic effects. The study demonstrated that high quality digital terrain data can be used to develop and test improved radiative transfer models, and enhance the utility of MSS data.

Justice, C. O.↗
NASA NTRS1986

Precise GPS orbit determination results from 1985 field tests

Data from three different receiver types have been used to obtain precise orbits for the satellites of the Global Positioning System (GPS). The data were collected during the 1985 March-April GPS experiment to test and validate GPS techniques for precision orbit determination and geodesy. A new software package developed at the Jet Propulsion Laboratory (JPL), GIPSY (GPS Inferred Positioning SYstem), was used to process the data. To assess orbit accuracy, solutions are compared using integrated doppler data from various different receiver types, different fiducial sites, and independent data arcs, including one spanning six days. From these intercomparisons, orbit accuracy for a well-tracked GPS satellite of three meters in altitude and about five meters in each of down and cross-track components are inferred.

Lichten, S. M.↗
NASA NTRS2012

Linked-List-Based Multibody Dynamics (MBDyn) Engine

This new release of MBDyn is a software engine that calculates the dynamics states of kinematic, rigid, or flexible multibody systems. An MBDyn multibody system may consist of multiple groups of articulated chains, trees, or closed-loop topologies. Transient topologies are handled through conservation of energy and momentum. The solution for rigid-body systems is exact, and several configurable levels of nonlinear term fidelity are available for flexible dynamics systems. The algorithms have been optimized for efficiency and can be used for both non-real-time (NRT) and real-time (RT) simulations. Interfaces are currently compatible with NASA's Trick Simulation Environment. This new release represents a significant advance in capability and ease of use. The two most significant new additions are an application programming interface (API) that clarifies and simplifies use of MBDyn, and a link-list infrastructure that allows a single MBDyn instance to propagate an arbitrary number of interacting groups of multibody top ologies. MBDyn calculates state and state derivative vectors for integration using an external integration routine. A Trickcompatible interface is provided for initialization, data logging, integration, and input/output.

MacLean, John↗
NASA NTRSDate not supplied

Using NASA Earth Observations to Identify Wildfire Impacts on Hydrologic Functions and Recovery in the Gila National Forest

Wildfires can dramatically influence both abiotic and biotic components of a landscape, including soil stability and chemistry; vegetation health, density, and composition; and water flow and quality. In addition to the immediate hazards posed by wildfires, subsequent hazards such as flooding and debris flow can impact the area. In New Mexico’s Gila National Forest, wildfire events have occurred with increasing frequency and severity over recent years, notably including the Whitewater Baldy Complex Fire (2012) and Silver Fire (2013), which burned over 290,000 acres and 138,698 acres, respectively, according to the Burned Area Emergency Response Team Executive Summary reports. Following a significant wildfire, land and resource management decisions are made, including when and where to focus vegetation and stream restoration efforts. This research is the result of a collaboration between the NASA DEVELOP National Program and the US Forest Service, which aimed to utilize NASA Earth observations to help inform those critical land management decisions. The project had two main objectives: 1) assess the efficacy of post-fire vegetation restoration efforts and 2) analyze the impact of burn events on the hydrology at the watershed-scale. To accomplish this first goal, data from Landsat 5 Thematic Mapper (TM), Landsat 7 Enhanced Thematic Mapper Plus (ETM+), and Landsat 8 Operational Land Imager (OLI) were used to study the vegetation health over time of treated and non-treated burn areas. To accomplish the latter, various aspects of stream behavior were examined in relation to burn events, including the runoff coefficient and “flashiness” of streams based on USGS stream gauge data and Integrated Multi-satelllite Retrievals for GPM (IMERG) precipitation data. This will allow land managers to better understand the complex ecological relationship between the cascading effects after wildfire and the greater forest ecosystem.

Madeline Allen↗
NASA NTRSDate not supplied

Lunar Resources Catalog (LRC): Viper Pathfinder Dataset

Introduction: A new era in lunar exploration has recently begun. Through NASA’s robotic Commercial Lunar Payload Services (CLPS) initiative, international and the human Artemis programs, multiple assets are being deployed to explore the Moon and at a rapid cadence. There will be a huge expanse in lunar surface exploration with mobility (e.g., rovers). Several missions are focused on collecting data for assessing lunar resources for potential In-Situ Resource Utilization (ISRU). With this expansion in exploration there will be a commensurate expansion in the volume and variety of data. Work has begun on establishing a measurement plan (i.e., what data is needed) for ISRU [1] but how to integrate these data into the broader Planetary Data Ecosystem (PDE) following FAIR (i.e., Findability, Accessibility, Interoperability, and Reuse) data practices has not been addressed. The VIPER team intends to engage this challenge.

VIPER↗
NASA NTRS1989

Intelligent multi-sensor integrations

Growth in the intelligence of space systems requires the use and integration of data from multiple sensors. Generic tools are being developed for extracting and integrating information obtained from multiple sources. The full spectrum is addressed for issues ranging from data acquisition, to characterization of sensor data, to adaptive systems for utilizing the data. In particular, there are three major aspects to the project, multisensor processing, an adaptive approach to object recognition, and distributed sensor system integration.

Volz, Richard A.↗
DOE OSTI2025

Integrated GW Farm ABM

This Data Repository includes data used for the integrated groundwater- farm ABM model, raw model output from scenario ensemble, and processed outputs that isolate the groundwater storage depletion outcomes for the 35,000 farm cells. Model Inputs: Farm ABM Inputs: This folder contains the input data used by the integrated groundwater - farm ABM modelling script (Python file) used for the high performance computing (HPC) experiments. The sub-folder "data inputs" contains all of the farm attribute data, while the three files in the folder have the hydrogeological data lookup table (NLDAS Cost Curve Attributes.csv), a lookup table (Theis well function table.csv) for the groundwater cost curve function, and the farm indexes and corresponding NLDAS ids for all of the cells run in this experiment (nldas farms subset final.csv). NLDAS Cost curve hydrogeological data: Hydrogeological data aggregated to 1/8 degree resolution and aligned with the NLDAS grid. Parameters include: water depth below ground surface [meters], subsurface porosity [unitless], aquifer depth from ground surface to aquifer bottom [meters], annual average recharge (USGS: mm, Doll: meters), and three different hydraulic conductivity (K) values (meters/day). The three K values represent the mean value from Gleeson et al. (2018), one standard deviation above the mean from Gleeson et al. (2018), and the de Graaf et al. 2020 modifications to certain lithologies. Additional information about these datasets and their processing are documented in the supplement to Yoon et al. 2025 (in review). Output: Raw outputs: This folder contains a .zip file that has model outputs for the entire scenario ensemble. There is one csv for each farm id, using the format "farm farmid cases.csv". The relationship between the farm id and NLDAS id is defined by the "nldas farms subset final.csv" located in the Farm ABM Inputs folder. Each csv has 625 rows, corresponding to 625 combinations of different scenario parameter values. Each row (scenario) represents the outcome of a 100 year simulation. Columns define scenario settings and summary statistics for each scenario. The first four columns define the scenario settings: "hydro ratio," "econ ratio," "K scenario," and "gamma scenario." The hydro and econ ratios are values passed to the modeling script that influence multipliers for other model parameters, as documented in the supplement to Yoon et al. 2025 (in review). The gamma multiplier is a coefficient multiplier applied to the baseline gamma values (values below 1 represent lower unobserved costs compared to baseline, values above 1 represent higher costs). The K scenario names represent K values of: "low": 0.5 m/d, "int 1": 2.5 m/d, "int 2": 10 m/d, "high": 50 m/d, and "gleeson": mean Gleeson K value. "Perc vol depleted" is the fraction of groundwater depleted at the end of the 100 simulation. Processed Output: Derived depletion outcomes from raw outputs: All of the individual csv files from the Raw outputs were aggregated into a single file that has the scenario settings and fraction depletion "Perc vol depleted" for every farm cell, for every scenario. The other two files define relationships between the farm id, NLDAS id, and local and major aquifer units, used for aquifer-level depletion analysis.

Agent based modeling↗
DOE OSTI2023

Observations and Lessons Learned in Residential Roofing Integrated Photovoltaics

The data file includes field observations of residential roofing integrated photovoltaics installation that happened between July 2021 and June 2022 in California. There are 21 observations - 2 in the re-roofing category and 19 in the new construction category. The file includes two time and motion forms (Re-Roofing & New Construction) we used to capture the time it takes for each activity in the rooftop solar and electrical installation process. You will see the duration for detailed steps along with activities that are included for total installation time for the paper. There are three parts to the time and motion form - Part 1 has project and crew characteristics, product information, and inspection and permitting data and can be filled before the installation. Part 2 has the actual installation time stamps and related notes. Part 3 has the crew information and can be filled on-site or off-site, but this section is optional. The re-roofing form has pre-solar activities and gutters and vents section in Part 2 of the form, whereas new construction form includes a section for capturing the time it took for rough wiring. The re-roofing form does not include rough wiring but instead includes the final electrical wiring process. These are the key differences in both the forms. Each day/step/installation activity needs to include the crew break time as they happen and there is space available to capture the crew breaks duration. In Table 1 below, the different terms used in the time and motion form are defined and their corresponding unit of measurement stated. We also highlight the optional sections. The data is captured in total mins, total hours, person mins, person hours. You can use this form or make edits to the form to recreate the study or make your own observations. The data herein was reviewed but may not be comprehensive. NREL invites questions and inputs to improve the data, including to: Correct erroneous information Fill in missing/updated information Clarifications on data and variables Updated information may be submitted to Sushmita Jena at sushmita.jena@nlr.gov.

14 SOLAR ENERGY↗
DOE OSTI2026

Cyote-attack Chain Estimator

Attack Chain Estimator (ACE) Application Overview The Attack Chain Estimator (ACE) Application is a sophisticated tool designed for the ingestion, classification, sequencing, and enrichment of cybersecurity threat reports. This application leverages advanced machine learning models and extensive historical data to provide comprehensive insights into cyber threats, specifically targeting Industrial Control Systems (ICS). Purpose The primary functions of the ACE Application include: Ingestion of Cybersecurity Threat Reporting: Capable of ingesting text-based threat reports in markdown or text file format. Supports ingestion of structured data from other sources in STIX/JSON format. Classification of Report’s Text-Based Events: Utilizes a DeBERTa classifier, specifically trained on cybersecurity data, to map the events to MITRE ATT&CK for ICS Tactics and Techniques. Classification is performed using multiple Jupyter notebooks and machine learning workflows hosted as FastAPI microservices: regex_data deberta_base_35_train_hft_classifier_mlflow.ipynb hft_regex_classifier_mlflow.ipynb param_train_hft_classifier_mlflow.ipynb regex_tactic_tech.ipynb Ordering of Tactics, Techniques, and Observable Events: Sequences the identified tactics, techniques, and events to form a coherent attack chain. Enrichment with Historical Attack Chain Details: Enhances the attack chain with details from historical attacks using a Markov model developed from CyOTE Precursor Analysis Report data. The Markov model is available as a FastAPI endpoint for seamless integration. Enrichment with Adversary Emulation Capabilities Data: Integrates adversary emulation capabilities data using MITRE Caldera for OT adversary abilities UUIDs. Export of Output Files: Provides options to export the enriched attack chain in JSON or CSV formats. Routing of Output to Other Applications: Facilitates routing of output to various platforms and applications, including: Threat Intelligence Platforms COREII Scout for Threat Intelligence Analysis COREII Modeling and Simulation for Adversary Emulation Technical Description The ACE Application is an advanced cybersecurity tool designed to provide detailed threat analysis and sequence generation. It is built on a robust architecture that integrates natural language processing, machine learning, and historical data modeling. Key Components: Data Ingestion Module: Handles the input of threat reports and data from various formats, ensuring flexibility in data sources. Classification Engine: Employs DeBERTa-based classifiers hosted as FastAPI microservices to analyze and classify threat report events in accordance with the MITRE ATT&CK framework for ICS. Sequence Generator: Orders the classified events into a logical attack chain, providing clear insight into the sequence of tactics and techniques used in the threat. Enrichment Engine: Integrates historical data and adversary emulation capabilities to enhance the attack chain with valuable context and additional details. The historical data enrichment is powered by a Markov model, which is available as a FastAPI endpoint. Export and Routing Module: Facilitates the export of the enriched attack chain in multiple formats and routes the output to designated applications for further analysis or emulation.

Paul, Tony [Idaho National Laboratory (INL), Idaho↗
DOE OSTI2022

Substructure in the stellar halo near the Sun: I. Data-driven clustering in integrals-of-motion space

Context. Merger debris is expected to populate the stellar haloes of galaxies. In the case of the Milky Way, this debris should be apparent as clumps in a space defined by the orbital integrals of motion of the stars. Aims. Our aim is to develop a data-driven and statistics-based method for finding these clumps in integrals-of-motion space for nearby halo stars and to evaluate their significance robustly. Methods. We used data from Gaia EDR3, extended with radial velocities from ground-based spectroscopic surveys, to construct a sample of halo stars within 2.5 kpc from the Sun. We applied a hierarchical clustering method that makes exhaustive use of the single linkage algorithm in three-dimensional space defined by the commonly used integrals of motion energy E, together with two components of the angular momentum, L z and L ⊥ . To evaluate the statistical significance of the clusters, we compared the density within an ellipsoidal region centred on the cluster to that of random sets with similar global dynamical properties. By selecting the signal at the location of their maximum statistical significance in the hierarchical tree, we extracted a set of significant unique clusters. By describing these clusters with ellipsoids, we estimated the proximity of a star to the cluster centre using the Mahalanobis distance. Additionally, we applied the HDBSCAN clustering algorithm in velocity space to each cluster to extract subgroups representing debris with different orbital phases. Results. Our procedure identifies 67 highly significant clusters (> 3σ), containing 12% of the sources in our halo set, and 232 subgroups or individual streams in velocity space. In total, 13.8% of the stars in our data set can be confidently associated with a significant cluster based on their Mahalanobis distance. Inspection of the hierarchical tree describing our data set reveals a complex web of relations between the significant clusters, suggesting that they can be tentatively grouped into at least six main large structures, many of which can be associated with previously identified halo substructures, and a number of independent substructures. This preliminary conclusion is further explored in a companion paper, in which we also characterise the substructures in terms of their stellar populations. Conclusions. Our method allows us to systematically detect kinematic substructures in the Galactic stellar halo with a data-driven and interpretable algorithm. The list of the clusters and the associated star catalogue are provided in two tables available at the CDS.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Missing Photovoltaic Data Imputation

The integration of the global Photovoltaic (PV) market with real time data-loggers has enabled large scale PV data analytical pipelines for power forecasting and long-term reliability assessment of PV fleets. Nevertheless, the performance of PV data analysis heavily depends on the quality of PV timeseries data. This paper proposes a novel Spatio-Temporal Denoising Graph Autoencoder (STD-GAE) framework to impute missing PV Power Data. STDGAE exploits temporal correlation, spatial coherence, and value dependencies from domain knowledge to recover missing data. It is empowered by two modules. (1) To cope with sparse yet various scenarios of missing data, STD-GAE incorporates a domain-knowledge aware data augmentation module that creates plausible variations of missing data patterns. This generalizes STD-GAE to robust imputation over different seasons and environment. (2) STD-GAE nontrivially integrates spatiotemporal graph convolution layers (to recover local missing data by observed “neighboring” PV plants) and denoising autoencoder (to recover corrupted data from augmented counterpart) to improve the accuracy of imputation accuracy at PV fleet level. We have evaluated our proposed model on two realworld PV datasets. Experimental results show that STD-GAE can achieve a gain of 43.14% in imputation accuracy and remains less sensitive to missing rate, different seasons, and missing scenarios, compared with state-of-the-art data imputation methods such as MIDA and LRTC-TNN.

Fan, Yangxin↗
DOE OSTI2026

A Scoping Review of Mixed Initiative Visual Analytics in the Automation Renaissance

Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation recalibrates the dynamic between humans and automating technology. To explore this question, we conducted a scoping review encompassing twenty years of mixed-initiative visual analytic systems. To describe and contrast the relationship between humans and automation, we developed an integrated taxonomy to delineate the objectives of these mixed-initiative visual analytics tools, how much automation they support, and the assumed roles of humans. Here, we describe our qualitative approach of integrating existing theoretical frameworks with new codes we developed. Our analysis shows that the visualization research literature lacks consensus on the definition of mixed-initiative systems and explores a limited potential of the collaborative interaction landscape between people and automation. Our research provides a scaffold to advance the discussion of human-AI collaboration during visual data analysis. Our integrated taxonomy is available in the form of a web application on https://smonadjemi.github.io/miva.

Monadjemi, Shayan [ORNL] (ORCID:0000000293855969)↗
DOE OSTI2024

Fast neutron leakage spectra of the EUCLID experiment

Special nuclear material in sub-critical and critical configurations measured in integral experiments are important for validation and adjustment of nuclear data. Many different evaluations of nuclear data exist, and these different evaluations can provide different values for individual cross sections that vary due to the uncertainties in differential experiments or lack of such data. For integral experiments, differences in these individual cross sections can have compensating errors, which lead to the same answer. One example of this is the Jezebel critical assembly, where k eff of the system is correctly computed by both ENDF/B-VIII.0 and JEFF-3.3, despite having substantially different underlying evaluated values for specific reactions (such as elastic and inelastic cross sections). To reduce compensating errors in nuclear data, the Experiments Underpinned by Computational Learning for Improvements in Nuclear Data (EUCLID) project has utilized machine learning to design a set of sub-critical and critical experiments. These experiments include slab- and cube-like configurations of 239 Pu in the form of the ZPPR plates. Six different responses were measured on a total of thirteen different configurations. One of these responses, the neutron leakage spectrum, was measured using an EJ301D detector. Finally, the results of the neutron leakage spectra show good agreement (within 1–2 σ ) with the expected spectrum from simulations and will be used in the subsequent nuclear data adjustment done by the EUCLID team.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization

Objective: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. Methods: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. Results: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. Conclusions: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

Zhou, Doudou↗