Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “database for model validation”

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 OSTI2025

Analysis of the impact of parallel magnetic fluctuations on linear gyrokinetic stability in NSTX-U and verification of gyro-fluid models

In this work, we use the CGYRO gyrokinetic code to analyze two L- and one H-mode discharges from the National Spherical Torus Experiment (NSTX) and NSTX-Upgrade (NSTX-U) selected due to their different mix of ion-scale driftwaves, ion temperature gradient (ITG) mode and trapped electron mode (TEM), and electromagnetic instabilities, kinetic ballooning mode (KBM), and micro-tearing mode (MTM) in the plasma core. It is found that the effect of parallel magnetic fluctuations is strongly destabilizing to the unstable KBMs compared to calculations with only perpendicular magnetic fluctuations. Two discharges have a mix of ITG/TEM and MTMs that are predicted to be dominant instability across the plasma radius. The parallel magnetic fluctuations are found to have little effect on the MTM stability but are destabilizing to ITG/TEM modes. To test the validity of the gyro-fluid linear stability codes TGLF and GFS at low aspect ratio, a database of linear growth rates has been created using the CGYRO gyrokinetic code. The database is comprised of various parameter scans around a standardized set of NSTX-U core parameters. It contains a group of electrostatic cases and an electromagnetic group that includes the effects of perpendicular and parallel magnetic fluctuations. Comparing the results from the GFS and TGLF models, we find that GFS exhibits the best agreement with the database of CGYRO linear growth rates. Comparing the model results for the electromagnetic scans shows that GFS captures the effects of parallel magnetic fluctuations accurately, while the TGLF model does not, as it lacks sufficient perpendicular energy resolution.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

TRIPOLI-4 neutronics calculations for IAEA-CRP benchmark of CEFR start-up tests using new libraries JEFF-3.3 and ENDF/B-VIII

Sodium-cooled Fast Reactors (SFR) are one of the promising Generation IV fast reactors. The China Experimental Fast Reactor (CEFR) is a 65 MWth pool-type SFR with a high neutron leakage core using high enriched uranium oxide fuel. The CEFR start-up tests in 2010 consist of series of neutronics experiments. Essential experimental data are available from the 2018 IAEA-CEFR-CRP benchmark document and useful for the validation of neutron transport codes and nuclear data libraries. The TRIPOLI-4 Monte Carlo transport code is a general-purpose neutronics code using continuous-energy nuclear data libraries. It has a rich validation database covering different computational and experimental benchmark data sets to assure the accuracy and credibility of numerical studies. Previous TRIPOLI-4 SFR core physics calculations used mainly MOX fuels. SFR control rod worth studies with TRIPOLI-4 were mainly on big-size cores. To test the modeling capability of TRIPOLI-4 on fuel loading patterns and on variable control rods positions for SFRs and to check recent nuclear data libraries, it is interesting to investigate the CEFR start-up tests in this work, including core states from subcritical to supercritical, control rods and rod group worth, point kinetics parameters, and radial foil activation measurements. TRIPOLI-4 calculation results using new data libraries JEFF-3.3, ENDF/B-VIII, and those of ENDF/B-VII.1 for different CEFR core states are reported here. By means of different options of TRIPOLI-4, control-rod SAs reactivity worth, point kinetics parameters, and radial {sup 237}Np(n,f) fission rate distribution were successfully evaluated. Both ENDF/B-VIII and JEFF-3.3 nuclear data libraries provided reliable results with a difference of 170 +/- 11 pcm in k{sub eff}.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Consensus DOE Advanced Fuels Campaign TREAT/SATS Test Plan [Slides]

This record is comprised of summary slides of the Combined TREAT-LOC & SATS Integral LOCA Experiment Plan. The experimental program has been developed to specifically address data gaps and opportunities identified through detailed review of the existing public knowledgebase on LOCA FFRD and specific experimental development for prototypic LOCA conditions for LWR systems. The test program relies on a unique combination of in-pile and out-of-pile experimental approaches to (1) provide clear tieback to the existing integral and semi-integral LOCA experiment database using state-of-the-art facilities. More importantly, this program will systematically investigate the impacts of: (2) prototypic HBu fuel and cladding thermomechanical behaviors under postulated LWR LOCA conditions never fully investigated before. These conditions correspond with prototypic decay-energy heat up (DEH) and stored-energy heat up (SEH) conditions. Unique TREAT capability will provide first evaluation of SEH conditions on HBu fuels. The test program includes an emphasis on developing improved mechanistic understanding of key phenomena through independent experimental systems, development of a database to support fuel performance modeling tools, world leading advanced materials characterization, and the most advanced approach to in-situ diagnostics ever deployed to evaluate FFRD. The results will represent a significant leap forward in the evaluation of prototypic conditions and novel data to support modeling development and validation, as well as to inform the technical basis of LOCA-induced FFRD.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

FY23 Status of Quality Assurance Plan for Out-of-Pile Test Data

The DOE Advanced Reactor Technology program has supported recovery and preservation of legacy metallic fuel data collected as part of the US fast reactor program, recognizing it as essential to development and licensing activities for advanced fast reactors. Databases were established as organized collections of experimental records and data generated from in-pile experiments at EBRII, FFTF, and TREAT as well as related out-of-pile examinations of irradiated fuels. The Out-of-Pile Transient Database (OPTD), includes records of over 150 out-of-pile furnace transient tests on metallic fuels conducted at Argonne’s Alpha-Gamma Hot Cell Facility to evaluate their transient performance and characterize fuel/cladding interaction. The database is accessible to registered users from US universities, laboratories, and nuclear industry. Because the data in OPTD has not been formally qualified, its applicability and ability to support licensing activities is limited. This report outlines progress and plans to quality assure data in OPTD, maximizing its impact for model validation and verification as well as qualification of fuels for safe and effective use in advanced reactor designs.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Data and Code for: Observation-constrained agroecosystem model inversion reveals continental-scale variation of winter wheat traits

This repository contains the simulation outputs and processing scripts associated with the study of winter wheat traits across the United States, utilizing the Ecosys agroecosystem model. The dataset includes model results for both rainfed and irrigated winter wheat systems, supporting the findings presented in the manuscript titled "Observation-constrained agroecosystem model inversion reveals continental-scale variation of winter wheat traits." Data includes the original Ecosys simulation outputs (archived in .db format within the compressed .zip files) and extracted analysis data (stored in .pkl files for efficient processing). Python code for data processing and figure generation is provided in a Jupyter notebook. External Observational Datasets should refer to the following official repositories for the input and validation data used in this study. The eddy covariance data from the AmeriFlux network (https://ameriflux.lbl.gov/). Climate-forcing data of NLDAS-2 from NASA LDAS (https://ldas.gsfc.nasa.gov/nldas/nldas-2-forcing-data). Soil data from the Gridded Soil Survey Geographic Database (gSSURGO), available at (https://www.nrcs.usda.gov/resources/data-and-reports/gridded-soil-survey-geographic-gssurgo-database). Crop yields, planting and harvest dates from the USDA public databases (https://quickstats.nass.usda.gov/; https://webapp.rma.usda.gov/apps/actuarialinformationbrowser/CropCriteria.aspx). Satellite-derived SLOPE GPP data from ORNL DAAC (https://daac.ornl.gov/cgi-bin/dsviewer.pl?ds_id=1786). Land use and crop progress information from the USDA Crop Data Layer and Crop Progress and Condition Gridded Layers (https://www.nass.usda.gov/Research_and_Science/). The Ecosys model code is available online at https://github.com/jinyun1tang/ECOSYS.

Wheat↗
DOE OSTI2022

Classification of bacterial plasmid and chromosome derived sequences using machine learning

Plasmids are important genetic elements that facilitate horizonal gene transfer between bacteria and contribute to the spread of virulence and antimicrobial resistance. Most bacterial genome sequences in the public archives exist in draft form with many contigs, making it difficult to determine if a contig is of chromosomal or plasmid origin. Using a training set of contigs comprising 10,584 chromosomes and 10,654 plasmids from the PATRIC database, we evaluated several machine learning models including random forest, logistic regression, XGBoost, and a neural network for their ability to classify chromosomal and plasmid sequences using nucleotide k-mers as features. Based on the methods tested, a neural network model that used nucleotide 6-mers as features that was trained on randomly selected chromosomal and plasmid subsequences 5kb in length achieved the best performance, outperforming existing out-of-the-box methods, with an average accuracy of 89.38% ± 2.16% over a 10-fold cross validation. The model accuracy can be improved to 92.08% by using a voting strategy when classifying holdout sequences. In both plasmids and chromosomes, subsequences encoding functions involved in horizontal gene transfer—including hypothetical proteins, transporters, phage, mobile elements, and CRISPR elements—were most likely to be misclassified by the model. This study provides a straightforward approach for identifying plasmid-encoding sequences in short read assemblies without the need for sequence alignment-based tools.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Simulations of self- and Xe diffusivity in uranium mononitride including chemistry and irradiation effects

A combination of density functional theory and empirical potential atomic scale simulations have been used to determine a model for defect stability and mobility in uranium mononitride (UN), as a function of temperature (T) and N 2 partial pressure (p N 2 ). Using the model, predictions of hypo-stoichiometry under U-rich conditions compare favorably to CALPHAD calculations using the TAF-ID database. Furthermore, our predictions of U and N self-diffusivity are in good agreement with experiments carried out as a function of T at specific partial pressures under thermal equilibrium. The validated atomic scale data have then been implemented within a cluster dynamics method to simulate irradiation-enhanced defect concentrations. All defects and clusters studied have significantly enhanced concentrations, with respect to thermal equilibrium, as T is lowered. The irradiation-enhanced Xe diffusivity is compared to post-irradiation annealing and in-pile experiments. In conclusion, the contributions of various defects and clusters to non-stoichiometry, self-diffusivity, and Xe diffusivity are discussed.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2020

Radionuclide Screening Analysis and Transport Parameters for Pahute Mesa Detonations, Nevada National Security Site

A “screening analysis” is implemented at Pahute Mesa (PM), Nevada National Security Site (NNSS), to determine subsets of the 43 radionuclides listed in the radionuclide inventory of Finnegan et al. (2016) that are of relevance or potential relevance to the hydrologic source term (HST) for assessment of radionuclide transport in groundwater. Consideration is added to how levels of contamination are defined and whether any other radionuclides not in the inventory are relevant to the HST. A model is developed to estimate a range of possible source concentrations in groundwater that account for uncertainty in partitioning into melt glass and sorption into surrounding rock of the exchange zone for the 82 PM underground nuclear tests detonated in vertical shafts. The model also accounts for the varied hydrogeochemical settings. Transport parameters needed for the screening model calculations are developed from databases for hydrogeologic units, chemistry, mineralogy, fracture spacing, fracture aperture, fracture openness, matrix porosity, bulk density, saturation, and alteration. Of key importance is consideration of diagenetic zonation of the mineralogy related to hydrothermal alteration. The screening analysis compares model results with available groundwater radiochemistry data. Consistency between screening model results and available data helps validate the model for application to all 43 radionuclides, most of which have no measurements or only non-detect measurements of concentration in groundwater. The screening analysis determines that ten radionuclides – tritium, Sr-90, I-129, Cs-137, U-232, U-233, U-234, U-238, and the total of Pu-239 and Pu-240 are relevant to the HST. Determination of relevance is primarily based on data and/or model results indicating source concentration exceeding a maximum contaminant level (MCL) out to 100 years since the time of detonation. U-238 is relevant to assessment of contamination relative to MCLs for uranium and gross alpha particle activity. Five other radionuclides – C-14, Cl-36, Tc-99, Np-237, and Pu-238 – are determined potentially relevant to the HST based on a 0.1 MCL threshold. The screening analysis recommends additional attention to the natural daughter radionuclides of the uranium series (U-238) and thorium series (Th-232) decay chains, particularly Ra-226 and Ra-228, that were not included the inventory.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2023

Status of Mechanistic Fission Gas Model in High-Burnup Fuel

A desire to increase fuel burnup to decrease the cost of nuclear power plants has led to significant interest within the nuclear industry to develop improved understanding of high-burnup nuclear fuel microstructure and the potential for fuel fragmentation, relocation, and dispersal that contribute to burnup and safe operating limits. This milestone report describes joint research activities and program planning to develop mechanistic models for high-burnup UO 2 microstructure, including both intra- and intergranular gas bubble populations and fission gas release, specifically associated with transient release. This model development is being extensively leveraged against a rapidly growing experimental database of high-fidelity electron microscopy characterization of commercial, light water reactor fuel in the as-irradiated condition as well as that following simulated loss-of-coolant test conditions. This report describes the status of model development, highlights recent microstructural data, and summarizes the data needs to complete initial development and experimental validation of mechanistic models of fission gas and microstructural evolution at high burnup, as well as transient fission gas release.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

A critical review on additive manufacturing of refractory alloys from a data analytics perspective- beyond nickel-based superalloys

Refractory alloys (RAs) are promising materials due to their exceptional physicochemical properties, but most research remains at the laboratory scale. For broader adoption, advancements in manufacturing are essential. Because their high stability makes conventional methods like machining and casting difficult, additive manufacturing (AM) is emerging as an effective approach for fabricating refractory alloy components. However, AM's repeated non-equilibrium thermal cycles introduce undesired features (e.g. defects, anisotropic microstructures, and residual stresses), which are magnified due to RAs’ unique properties. This paper comprehensively reviews the state-of-the-art methods of AM for refractory alloys. It explores data analytics techniques to establish design rules based on multi-fidelity experimental and computational methods. Furthermore, it investigates integrated, collaborative efforts to harmonise standalone databases, information, knowledge, and predictive models at multi-physics, multi-stage, and multi-scale. Unlike the existing literature that focuses primarily on material systems or process fundamentals, this work provides an integrated perspective on AM of refractory alloys from a data analytics standpoint, highlighting the roles of integrated computational materials engineering (ICME), verification, validation, and uncertainty quantification (VV&UQ), and digital twin-driven qualification in overcoming data scarcity and accelerating rapid qualification.

Additive manufacturing↗
DOE OSTI2025

Multi-device analysis of energy loss duration and pellet penetration with implications for shattered pellet injection in ITER

A robust disruption mitigation system (DMS) requires accurate characterization of key disruption timescales, one of the most notable being the thermal quench (TQ). Recent modeling of shattered pellet injection (SPI) into ITER plasmas, using JOREK and INDEX, suggests long TQ durations (6–10 ms) and slow cold front propagation due to the large plasma size. If validated, these predictions would have an impact on the desired pellet parameters and mitigation strategies for the ITER DMS. To resolve these questions, a database of SPI experiments from several small-to-large sized devices (J-TEXT, KSTAR, AUG, DIII-D, and JET) has been compiled under the auspices of the International Tokamak Physics Activity MHD, disruptions, and control topical group. Analysis of the energy loss duration (proxy for the TQ duration) with machine size is presented for both mixed neon/deuterium (Ne/D) SPI and pure deuterium (D) SPI. Several metrics for the energy loss onset (e.g. soft x-ray signal drop, I p dip, and radiation flash) were considered as the conventional metric, electron cyclotron emission, is often cut-off during SPI. Several scalings with different onset metrics showed an increase in energy loss duration with machine size. The energy loss duration was additionally shown to be a function of the ratio between the number of SPI neon atoms injected and the stored energy. Analysis of the pellet shard position relative to the cold front found that in larger devices, pellets are typically found inboard of the q = 2 surface at the energy loss onset. Lastly, the delay between the pellet shards hitting the q = 2 surface and the energy loss onset was additionally found to increase with machine size. This suggests that the pellet shards in large devices will penetrate faster and further than the cooling front.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Theory-based scaling laws of near and far scrape-off layer widths in single-null L-mode discharges

Abstract Theory-based scaling laws of the near and far scrape-off layer (SOL) widths are analytically derived for L-mode diverted tokamak discharges by using a two-fluid model. The near SOL pressure and density decay lengths are obtained by leveraging a balance among the power source, perpendicular turbulent transport across the separatrix, and parallel losses at the vessel wall, while the far SOL pressure and density decay lengths are derived by using a model of intermittent transport mediated by filaments. The analytical estimates of the pressure decay length in the near SOL is then compared to the results of three-dimensional, flux-driven, global, two-fluid turbulence simulations of L-mode diverted tokamak plasmas, and validated against experimental measurements taken from an experimental multi-machine database of divertor heat flux profiles, showing in both cases a very good agreement. Analogously, the theoretical scaling law for the pressure decay length in the far SOL is compared to simulation results and to experimental measurements in TCV L-mode discharges, pointing out the need of a large multi-machine database for the far SOL decay lengths.

Physics↗
DOE OSTI2022

Analysis of historic fires to determine most frequent challenging events

The fire probabilistic risk assessment framework for nuclear power plants relies on experimental data to determine expected fire behavior or to validate models to predict fire conditions in the plant. To support reducing the uncertainty in this experimental data, a research effort was conducted to identify the most frequent and challenging fire scenarios using historic fire data from nuclear power plants in the United States. To support this effort, an electronic version of the publicly available Updated Fire Event Database developed by Electric Power Research Institute was produced resulting in data on 2111 fire events, 540 events were labelled as being challenging fires with 74.2% of these challenging fire events being due to eleven selected fire types. In conclusion, of these fire types, electrical and electronic equipment, transient combustibles, and liquid fires were the most frequent of the challenging fires. The fire scenario specifics were characterized for each of the eleven selected types and then related to existing fire experiments.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Uncertainty propagation in pore water chemical composition calculation using surrogate models

Performance assessment in deep geological nuclear waste repository systems necessitates an extended knowledge of the pore water chemical conditions prevailing in host-rock formations. In the last two decades, important progress has been made in the experimental characterization and thermodynamic modeling of pore water speciation, but the influence of experimental artifacts and uncertainties of thermodynamic input parameters are seldom evaluated. In this respect, we conducted an uncertainty propagation study in a reference geochemical model describing the pore water chemistry of the Callovian-Oxfordian clay formation. Nineteen model input parameters were perturbed, including those associated to experimental characterization (leached anions, exchanged cations, cation exchange selectivity coefficients) and those associated to generic thermodynamic databases (solubilities). A set of 13 quantities of interest were studied by the use of polynomial chaos expansions built non-intrusively with a least-squares forward stepwise regression approach. Training and validation sets of simulations were carried out using the geochemical speciation code PHREEQC. The statistical results explored the marginal distribution of each quantity of interest, their bivariate correlations as well as their global sensitivity indices. The influence of the assumed distributions for input parameters uncertainties was evaluated by considering two parametric domain sizes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

In situ tumor model for longitudinal in silico imaging trials

Abstract Objective.In this article, we introduce a computational model for simulating the growth of breast cancer lesions accounting for the stiffness of surrounding anatomical structures.Approach.In our model, ligaments are classified as the most rigid structures while the softer parts of the breast are occupied by fat and glandular tissues As a result of these variations in tissue elasticity, the rapidly proliferating tumor cells are met with differential resistance. It is found that these cells are likely to circumvent stiffer terrains such as ligaments, instead electing to proliferate preferentially within the more yielding confines of the breast’s soft topography. By manipulating the interstitial tumor pressure in direct proportion to the elastic constants of the tissues surrounding the tumor, this model thus creates the potential for realizing a database of unique lesion morphology sculpted by the distinctive topography of each local anatomical infrastructure. We modeled the growth of simulated lesions within volumes extracted from fatty breast models, developed by Graffet alwith a resolution of 50μm generated with the open-source and readily available Virtual Imaging Clinical Trials for Regulatory Evaluation (VICTRE) imaging pipeline. To visualize and validate the realism of the lesion models, we leveraged the imaging component of the VICTRE pipeline, which replicates the siemens mammomat inspiration mammography system in a digital format. This system was instrumental in generating digital mammogram (DM) images for each breast model containing the simulated lesions.Results.By utilizing the DM images, we were able to effectively illustrate the imaging characteristics of the lesions as they integrated with the anatomical backgrounds. Our research also involved a reader study that compared 25 simulated DM regions of interest (ROIs) with inserted lesions from our models with DM ROIs from the DDSM dataset containing real manifestations of breast cancer. In general the simulation time for the lesions was approximately 2.5 hours, but it varied depending on the lesion’s local environment.Significance.The lesion growth model will facilitate and enhance longitudinal in silico trials investigating the progression of breast cancer.

Engineering↗
DOE OSTI2024

Leveraging BERT and Network-Based Attention Analysis for Identifying Treatment Milestones in EHRs

This study introduces a sophisticated data-driven framework for analyzing Electronic Health Records (EHRs) using transformer-based models to identify and disentangle overlapping treatment contexts. The framework leverages a preprocessing pipeline that transforms structured procedural codes into semantically enriched descriptive text, enabling the use of attention mechanisms to cluster medical events into treatment milestones—cohesive and distinct components of care processes. The methodology is rigorously validated using synthetic datasets derived from the MIMIC-III database, designed to simulate the heterogeneity and overlapping procedural contexts characteristic of real-world EHR scenarios. Quantitative evaluation highlights the framework’s robustness in disentangling concurrent care pathways, with attention metrics and unsupervised clustering approaches demonstrating the ability to preserve intra-context relationships while distinguishing inter-context dependencies. By addressing challenges inherent in data heterogeneity, this approach provides a foundation for uncovering complex treatment patterns, advancing clinical decision-making, and optimizing resource allocation in diverse healthcare environments.

Kim, Minsu [ORNL] (ORCID:0000000224185535)↗
DOE OSTI2020

FeGenie: a comprehensive tool for the identification of iron genes and iron gene neighborhoods in genomes and metagenome assemblies

Iron is a micronutrient for nearly all life on Earth. It can be used as an electron donor and electron acceptor by iron-oxidizing and iron-reducing microorganisms and is used in a variety of biological processes, including photosynthesis and respiration. While it is the fourth most abundant metal in the Earth’s crust, iron is often limiting for growth in oxic environments because it is readily oxidized and precipitated. Much of our understanding of how microorganisms compete for and utilize iron is based on laboratory experiments. However, the advent of next-generation sequencing and surge in publicly available sequence data has made it possible to probe the structure and function of microbial communities in the environment. To bridge the gap between our understanding of iron acquisition, iron redox cycling, iron storage, and magnetosome formation in model microorganisms and the plethora of sequence data available from environmental studies, we have created a comprehensive database of hidden Markov models (HMMs) based on genes related to iron acquisition, storage, and reduction/oxidation in Bacteria and Archaea. Along with this database, we present FeGenie, a bioinformatics tool that accepts genome and metagenome assemblies as input and uses our comprehensive HMM database to annotate provided datasets with respect to iron-related genes and gene neighborhood. An important contribution of this tool is the efficient identification of genes involved in iron oxidation and dissimilatory iron reduction, which have been largely overlooked by standard annotation pipelines. We validated FeGenie against a selected set of 28 isolate genomes and showcase its utility in exploring iron genes present in 27 metagenomes, 4 isolate genomes from human oral biofilms, and 17 genomes from candidate organisms, including members of the candidate phyla radiation. We show that FeGenie accurately identifies iron genes in isolates. Furthermore, analysis of metagenomes using FeGenie demonstrates that the iron gene repertoire and abundance of each environment is correlated with iron richness. While this tool will not replace the reliability of culture-dependent analyses of microbial physiology, it provides reliable predictions derived from the most up-to-date genetic markers. FeGenie’s database will be maintained and continually updated as new genes are discovered.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

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}↗