Search NASA⌕ Search

SEARCH · Search NASA

Results for “Observational methods”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Innovating the next generation of commercial smart building software

Nearly 30% of commercial building energy use is wasted due to equipment faults and HVAC controls problems. The result is increased emissions, compromised comfort and productivity, and less reliable coordination of building power needs with a clean grid. The energy impact alone represents $17 billion in potential savings. Today’s smart building software provides a robust solution to address these operational deficiencies. Energy management and information systems (EMIS) are saving up to 9% on average, with two-year paybacks. They are being incorporated into energy management processes, commissioning services, and utility programs. As effective as they are, two barriers prevent even deeper benefits; limited personnel to fix problems once they are identified, and the expense and time to manually implement changes in control systems. In partnership with the research community, the EMIS industry is developing new capabilities to overcome these barriers. Moving beyond siloed products for either fault detection and diagnostics, or optimal control, these new capabilities empower users to not only automatically identify faults, but also to push corrective action, and control improvements to their buildings. In this paper, several areas for enhancements are documented: ‘one-time’ correction of faults such as setpoints, schedules, and economizer lockouts; short-term active testing for automated proportional integral derivative (PID) loop tuning and functional testing; and continuous supervisory control for demand flexibility and year-round efficiency. Results are presented from a pair of partner implementations out of a dozen providers integrating these enhancements into their products, including field tests from across the country, and insights into operator acceptance and integration into operations and maintenance practices.

Casillas, Armando↗
DOE OSTI2025

Probing circular polarization and magnetic field structure in active galactic nuclei

The composition and magnetic field morphology of relativistic jets can be studied using circular polarization (CP) measurement. Recent three-dimensional relativistic magnetohydrodynamic (3D RMHD) simulations coupled with radiative transfer (RT) calculations make strong predictions about the level (and morphology) of the jet’s CP emission. These simulations show that the sign of CP and the electric vector position angle (EVPA) are both sensitive to the jet’s magnetic field morphology within the radio core. We probe this theory by exploring whether the jet’s radio core EVPA orientation is consistent with the observed sign of the core CP in deep full-track polarimetric observations. Based on a selection of sources from earlier MOJAVE observations, we aim to probe the nature of linear polarization (LP) and CP in the innermost regions of jets from a small sample of nine blazars. This sample includes sources that have exhibited: (i) positive CP; (ii) negative CP; or (iii) positive and negative CP simultaneously in the radio core region. By coupling deep polarimetric observations of a carefully selected sample of blazars with state-of-the-art RMHD and RT calculations, we hope to gain a deeper understanding of the physics of blazar jets.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

When to vaccinate for seasonal influenza: check the peak forecast

Background Seasonal influenza infects 5-20% of people every year in the United States, resulting in hospitalizations, deaths, and adverse economic impacts. To mitigate these impacts, influenza vaccines are developed and distributed annually; however, growing evidence suggests that vaccine effectiveness (VE) wanes over the course of a flu season. Delaying influenza vaccination for older adults has attracted attention as a potential public health strategy. However, given the uncertainties in seasonal peak, vaccine effectiveness, and waning rates, postponing vaccination could also lead to increased morbidity, motivating an evaluation of a range of potential scenarios. The aim of this study was to investigate favorable age group-specific vaccination schedules that could lead to the greatest disease burden reduction. Methods We systematically investigated a broad range of vaccination start times for five age groups under six combinations of initial effectiveness and waning rates, based on influenza cases and vaccine uptake data from 10 influenza seasons. We defined the most favorable vaccination schedule as the one that resulted in the greatest reduction in disease burden. Results In scenarios with fast waning, all age groups benefit from delaying vaccination regardless of initial VE and peak timing. In scenarios with slower waning, results are mixed. For the ≥65 group, high initial VE and slow waning suggests that in early-peaking seasons, early vaccination most effectively reduces disease burden, while in late-peaking seasons delaying vaccination is most effective. For the ≥65 group in medium and low initial VE, and slow waning scenarios, delaying vaccination appears to prevent the greatest number of cases, regardless of whether the season peaks early or late. Conclusion The most favorable vaccination schedule is sensitive to changes in initial VE, waning rate, and peak timing. Given estimates of these quantities from statistical and immunological models and observations, our methods can inform vaccination recommendations in order to most effectively reduce the annual disease burden caused by seasonal influenza. Specifically, accurate peak timing forecasts for the upcoming season have the potential to guide decisions on when to vaccinate.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Oxidative Dehydrogenation of N ‐Heteroaromatic Alkyl Alcohols and Amines Facilitated by Dearomative Tautomerization

The oxidation of alcohols, amines, and halides is a fundamental transformation in organic chemistry with significant applications in the synthesis of fine chemicals, pharmaceuticals, and natural products. Here we show that a broad variety of N-heteroarenes bearing hydroxymethyl, aminomethyl, or halomethyl groups are oxidatively dehydrogenated to their respective aldehydes by simply heating them in acidic or basic aqueous solution under ambient atmosphere. The quantitative oxidation of 9-acridinemethanol to 9-acridinecarboxaldehyde serves as an illustrative example, proceeding to completion within 3 hours in refluxing 5% aqueous acetic acid or even household vinegar. Quinoline derivatives may be similarly oxidized but require higher temperatures and longer reaction times, while indole derivatives are oxidized under basic conditions. Based on comprehensive regioselectivity screens, internal kinetic isotope competition, and density functional theory (DFT) calculations, we propose a mechanism in which migration of a methylene hydrogen to the pyridinic nitrogen by acid-catalyzed dearomative tautomerization yields an unstable enol or enamine intermediate that then irreversibly loses two hydrogen atoms to atmospheric oxygen. In addition to the simplicity and environmentally benign nature of our method, we observe no indication of any over-oxidation to carboxylic acids. Finally, we demonstrate the synthetic utility of this reaction through two different one-pot formylations of acridine.

Chemistry↗
DOE OSTI2025

The latent variable proximal point algorithm for variational problems with inequality constraints

The latent variable proximal point (LVPP) algorithm is a framework for solving infinite-dimensional variational problems with pointwise inequality constraints. The algorithm is a saddle point reformulation of the Bregman proximal point algorithm. At the continuous level, the two formulations are equivalent, but the saddle point formulation is more amenable to discretization because it introduces a structure-preserving transformation between a latent function space and the feasible set. Working in this latent space is much more convenient for enforcing inequality constraints than the feasible set, as discretizations can employ general linear combinations of suitable basis functions, and nonlinear solvers can involve general additive updates. LVPP yields numerical methods with observed mesh-independence for obstacle problems, contact, fracture, plasticity, and others besides; in many cases, for the first time. The framework also extends to more complex constraints, providing means to enforce convexity in the Monge–Ampère equation and handling quasi-variational inequalities, where the underlying constraint depends implicitly on the unknown solution. Here, in this paper, we describe the LVPP algorithm in a general form and apply it to ten problems from across mathematics.

Inequality constraints↗
DOE OSTI2026

Performance Evaluation of an Offshore Wave Measurement Buoy in Monochromatic Waves

The accurate measurement of waves underpins marine energy resource characterization, device design, and project development. Datawell wave buoys are widely deployed and have long served as a trusted standard for wave measurements. We quantify the measurement performance, including wave elevation and energy flux estimation, of a Datawell DWR-MkIII buoy using prescribed monochromatic heave motions on a large-amplitude six-degree-of-freedom motion platform at the National Laboratory of the Rockies, assuming the buoy behaves as an ideal wave follower. Commanded motions were validated with an optical motion tracking system while buoy elevation and raw acceleration were recorded. Wave elevations were propagated to wave energy flux estimation using four methods, including one frequency-domain method and three time-domain methods. The Bayesian optimization was applied for design of experiments, and records from three test sites were also applied and evaluated in the present study. Results show two error regions within the nominal period range of 1.6 s to 30 s. For wave periods between 5 s and 25 s, the buoy provides accurate wave height measurements. For short periods less than 5 s, the 1.28 Hz sampling frequency induces sub-Nyquist artifacts that bias elevation and can drive maximum energy flux estimation errors above 100%. For long periods exceeding 25 s, the buoy reported elevation is underpredicted with error depending on period but relatively independent of wave height, with maximum wave height and wave energy flux errors reaching 64% and 87%, respectively. Furthermore, analysis of three field-derived cases shows that frequency-domain estimates at 1.28 Hz agree within 2% of the corresponding 100 Hz estimates, while larger method-dependent differences are observed for the Hilbert method.

16 TIDAL AND WAVE POWER↗
DOE OSTI2025

Redox Couples Control Band Bending, Photovoltage, and Quasi-Fermi Levels in Tungsten Oxide (WO 3 ) Photoanodes

Tungsten oxide (WO 3 ) is a well-known photoanode and photocatalyst for photoelectrochemical (PEC) water oxidation. Because the compound has a deep valence band, it can facilitate the oxygen evolution reaction without added cocatalysts, and it can drive the oxidation of species with much higher electrochemical potentials, including the conversion of water to hydrogen peroxide, sulfate to persulfate, and iodate to meta-periodate. Here, we use the liquid vibrating Kelvin probe surface photovoltage (liquid VK-SPV) technique in combination with open circuit potential (OCP) and photoelectrochemical (PEC) scans to assess the possibility of reaching such oxidizing potentials in aqueous electrolytes and at open circuit. Here, this is done by mapping the quasi-Fermi levels of electrons and holes at the interfaces as a function of the light intensity. Nanostructured WO 3 photoelectrodes for this purpose were fabricated by thermal annealing of a tungstic acid solution on fluorine-doped tin oxide. Electrochemical measurements are conducted at open circuit and 400 nm LED light illumination in electrolytes containing fast (O 2 /H 2 O 2 ), slow (O 2 /H 2 O), and very oxidizing (NaIO 4 /NaIO 3 ) redox couples. Photovoltage values scale with the light intensity and with the built-in potential for each redox couple and reach values up to 0.61 V under 20 mW cm –2 illumination for the NaIO 4 electrolyte. This shows that the photoelectrodes behave like Schottky-type diodes whose maximum possible energy output is determined mainly by the built-in voltage of each junction. For slow redox couples, the quasi-Fermi level of the holes increases with light intensity due to hole accumulation at the WO 3 –liquid interface. For example, for the O 2 /H 2 O electrolyte, interfacial hole accumulation and removal occur on the 90–300 s time scale. For the fast hole acceptor H 2 O 2 , on the other hand, the quasi-Fermi level of the photoholes is pinned to the electrochemical potential of the O 2 /H 2 O 2 couple. This limits the energy conversion efficiency of the electrode. Overall, these results reveal the influence of charge transfer thermodynamics and kinetics on the photovoltage of WO 3 . Furthermore, the work further establishes VK-SPV as a contactless method to observe the photovoltage, carrier dynamics, and quasi-Fermi levels of semiconductor-liquid junctions.

Electrodes↗
DOE OSTI2025

Mechanism of O 2 Activation and Cysteine Oxidation by the Unusual Mononuclear Cu(I) Active Site of the Formylglycine-Generating Enzyme

The formylglycine-generating enzyme (FGE) catalyzes the selective oxidation of a peptidyl-cysteine to form formylglycine, a critical cotranslational modification for type I sulfatase activation and a useful bioconjugation handle. Previous studies have shown that the substrate peptidyl-cysteine binds to the linear bis-thiolate Cu(I) site of FGE to form a trigonal planar tris-thiolate Cu(I) structure that activates O 2 for the oxidation of the C β –H of the cysteine substrate via an unknown mechanism. Here, we employed a combination of stopped-flow kinetic, spectroscopic (UV–vis absorption, XAS, and EPR), and computational (DFT/TD-DFT calculations) methods to observe and characterize the key intermediates in this reaction for FGE from Streptomyces coelicolor. Our results define the reaction coordinate of FGE, which involves H-atom abstraction from the C β –H bond of the cysteine substrate by a reactive Cu(II)–O 2 •– species to form the now experimentally observed Cu(I)–OOH intermediate bound to a peptidyl-thioaldehyde, which proceeds to oxidize one of the protein-derived cysteine residues to a sulfenate that is end-on O-coordinated to Cu(I). These results provide fundamental insights into how the unusual mononuclear Cu(I) site of FGE activates O 2 for cysteine oxidation and stores oxidizing equivalents during catalysis by employing a Cu(I)–sulfenate intermediate with an end-on O-coordination that is unprecedented in biology.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Inverse Mapping of the Collision Kernel and Wall Flux Scaling in a Tall Convection‐Cloud Chamber Using Local Sensors and Knowledge‐Informed Deep Learning

Droplet collision–coalescence is a crucial process in cloud physics, but accurately representing this process under different dynamical conditions remains challenging. A proposed future convective‐cloud chamber aims to investigate this key process, but the method for observing it remains unclear, even though it is theoretically established that collision‐coalescence will occur. This study serves as a proof‐of‐concept demonstration of how knowledge‐informed deep learning, combined with measurement data from local sensors in the chamber, can be used to estimate the collision kernels, which determine how the droplet size distribution evolves during collision‐coalescence. In addition to estimating the collision kernel, we also address wall fluxes, another uncertain but important process that acts as a source of heat and moisture in the chamber. Ensemble runs of large‐eddy simulations are conducted by scaling the wall fluxes and the collision kernel, while the measured flow and cloud properties are used as inputs for a neural network. Results indicate that this approach successfully maps the scaling of wall fluxes and the collision kernel with biases of approximately 1% or less relative to the range of the target data. This proof‐of‐concept lays the groundwork for future applications; when the real measurements are available, real sensor data combined with the trained model presented in this work will enable estimation of the actual wall fluxes and collision kernel.

cloud chamber↗
DOE OSTI2025

Theoretical and experimental quantification of Suzuki segregation enthalpy and strengthening mechanisms in a binary alloy

Solute segregation to planar defects in metallic alloys has been shown to drastically alter mechanical properties. While various works using first-principles and thermodynamic calculations have studied the fundamental driving forces for solute segregation via the Suzuki criterion, planar defect energy, or a comparison of energies of the HCP-like phase and FCC matrix, a quantitative experimental and computational comparison of equilibrium composition and segregation enthalpies has not yet been reported. In this work, we predict the equilibrium composition and segregation enthalpy to intrinsic stacking faults in a Ni-60Co (at.%) alloy and compare the results to two independent experimental methods. We observed that Co segregates to the innermost two planes of the intrinsic stacking fault, and we found that the experimental segregation enrichment, measured from transmission electron microscopy energy dispersive X-ray spectroscopy, of the faults is 6.8 at.% Co, which is 2.2 at.% less than the predicted value at the same temperature. We also find that the segregation enthalpy measured from the composition profile is −21.1 ± 6.4 meV/atom and separately from differential scanning calorimetry segregation enthalpy is −33.2 meV/atom, whereas the predicted enthalpy is −31 ± 1 meV/atom. Based on these results, we determine that segregation occurs very rapidly, within 8 min at temperatures as low as 36% of the homologous solidus temperature. Furthermore, this analysis provides an overview of the possible dislocation mechanisms responsible for strengthening effects due to solute segregation, and concludes that changes in room temperature hardness from local phase transformation is likely tied to post-segregation room temperature equilibrium partial separation distance.

Ab initio calculation↗
DOE OSTI2025

Candidate strongly lensed type Ia supernovae in the Zwicky Transient Facility archive

Gravitationally lensed type Ia supernovae (glSNe Ia) are unique astronomical tools that can be used to study cosmological parameters, distributions of dark matter, the astrophysics of the supernovae, and the intervening lensing galaxies themselves. A small number of highly magnified glSNe Ia have been discovered by ground-based telescopes such as the Zwicky Transient Facility (ZTF), but simulations predict that a fainter, undetected population may also exist. We present a systematic search for glSNe Ia in the ZTF archive of alerts distributed from June 1 2019 to September 1 2022. Using the AMPEL platform, we developed a pipeline that distinguishes candidate glSNe Ia from other variable sources. Initial cuts were applied to the ZTF alert photometry (with constraints on the peak absolute magnitude and the distance to a catalogue-matched galaxy, as examples) before forced photometry was obtained for the remaining candidates. Additional cuts were applied to refine the candidates based on their light curve colours, lens galaxy colours, and the resulting parameters from fits to the SALT2 SN Ia template. The candidates were also cross-matched with the DESI spectroscopic catalogue. Seven transients were identified that passed all the cuts and had an associated galaxy DESI redshift, which we present as glSN Ia candidates. Although superluminous supernovae (SLSNe) cannot be fully rejected as contaminants, two events, ZTF19abpjicm and ZTF22aahmovu, are significantly different from typical SLSNe and their light curves can be modelled as two-image glSN Ia systems. From this two-image modelling, we estimate time delays of 22 ± 3 and 34 ± 1 days for the two events, respectively, which suggests that we have uncovered a population of glSNe Ia with longer time delays. The pipeline is efficient and sensitive enough to parse full alert streams. It is currently being applied to the live ZTF alert stream to identify and follow-up future candidates while active. This pipeline could be the foundation for glSNe Ia searches in future surveys, such as the Rubin Observatory Legacy Survey of Space and Time.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

An accurate measurement of the spectral resolution of the JWST Near Infrared Spectrograph

The spectral resolution (R ≡ λ/Δλ) of spectroscopic data is crucial information for accurate kinematic measurements. In this letter we present a robust measurement of the spectral resolution of the JWST Near Infrared Spectrograph (NIRSpec) in fixed slit (FS) and integral field spectroscopy (IFS) modes. Due to the similarity of the utilized slit dimension in the FS mode to that of the shutters in the multi-object spectroscopy (MOS) mode, our resolution measurements in the FS mode can also be used for the MOS mode in principle. We modeled H and He lines of the planetary nebula SMP LMC 58 using a Gaussian line spread function (LSF) to estimate the wavelength-dependent resolution for multiple disperser and filter combinations. We corrected for the intrinsic width of the planetary nebula’s H and He lines due to its expansion velocity by measuring it from a higher-resolution X-shooter spectrum. We find that NIRSpec’s in-flight spectral resolutions exceed the pre-launch estimates provided in the JWST User Documentation by 11–53% in the FS mode and by 1–24% in the IFS mode across the covered wavelengths. We recover the expected trend that the resolution increases with the wavelength within a configuration. The robust and accurate LSFs presented in this letter will enable high-accuracy kinematic measurements using NIRSpec for applications in cosmology and galaxy evolution.

methods: data analysis↗
DOE OSTI2025

Bayesian Gaussian process inference for neutron spin echo measurement

Neutron spin echo (NSE) spectroscopy provides unique access to microscopic dynamics, but its application is often constrained by low neutron flux, long acquisition times, and significant noise. Here, we present a Bayesian inference approach based on Gaussian process regression (GPR) to reconstruct high-quality spin echo signals from sparse and noisy data by exploiting correlations in reciprocal space. Benchmarks on synthetic datasets and validation with experimental NSE measurements of dendrimers show that GPR suppresses noise, interpolates missing intensity values, and accommodates irregular observations. The method improves accuracy, shortens acquisition times, and enables high-throughput and real-time studies. Beyond NSE, the framework is broadly applicable to other low signal-to-noise ratio scattering techniques, thereby extending the scope of neutron spectroscopy.

Tung, Chi-Huan [Oak Ridge National Laboratory (ORN↗
DOE OSTI2025

Azimuthal correlation anisotropies in p + p collisions simulated using Pythia

Stimulated by a keen interest in possible collective behavior in high-energy proton-proton and proton-nucleus collisions, we study two-particle angular correlations in pseudorapidity and azimuthal differences in simulated p + p interactions using the Pythia 8 event generator. Multi-parton interactions and color connection are included in these simulations, which have been perceived to produce collectivity in final-state particles. Meanwhile, contributions from genuine few-body nonflow correlations, not of collective flow behavior, are known to be severe in these small-system collisions. We present our Pythia correlation studies pedagogically and report azimuthal harmonic anisotropies analyzed using several methods. We observe anisotropies in these Pythia simulated events qualitatively and semi-quantitatively, similar to experimental data. Furthermore, our findings highlight the delicate nature of azimuthal anisotropies in small-system collisions and provide a benchmark that can aid in improving data analysis and interpreting experimental measurements in small-system collisions.

Pythia↗
DOE OSTI2026

Two-pion contribution to the hadronic vacuum polarization with staggered quarks

We present results from the first lattice QCD calculation of the two-pion contributions to the light-quark connected vector-current correlation function obtained from staggered-quark operators. We employ the MILC Collaboration’s gauge-field ensemble with 2 + 1 + 1 flavors of highly improved staggered sea quarks at a lattice spacing of a ≈ 0.15 fm with a light sea-quark mass at its physical value. The two-pion contributions allow for a refined determination of the noisy long-distance tail of the vector-current correlation function, which we use to compute the light-quark connected contribution to hadronic vacuum polarization (HVP) with improved statistical precision. We compare our results with traditional noise-reduction techniques used in lattice QCD calculations of the light-quark connected HVP, namely, the so-called fit and bounding methods. We observe a factor of roughly 3 improvement in the statistical precision in the determination of the HVP contribution to the muon’s anomalous magnetic moment over these approaches. We also lay the group theoretical groundwork for extending this calculation to finer lattice spacings with increased numbers of staggered two-pion taste states.

Lahert, Shaun [Utah U.; Illinois U., Urbana] (ORCI↗
DOE OSTI2025

Reducing the Risk of Airborne Contamination through Intelligent Container Surveillance

DOE Manual 441.1-1 provides a set of performance criteria that nuclear material storage containers must achieve to provide protection to the worker, public, and environment. At Los Alamos National Laboratory, the SAVY-4000 is the container of choice for nuclear material storage, meeting all Manual requirements. At the outset, polymer components of the SAVY 4000 were considered to be life-limiting components due to their performance degradation resulting from radiation exposure. However, recent annual surveillance results revealed another life-limiting phenomenon for the container: a deterioration of the package integrity through corrosion of the stainless steel components, primarily the body. Container surveillance remains the choice method of observing, measuring, and tracking container health in service.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

Hydrodynamic Coupling to a Homogenized Radiation Transport Method based on Young Measures

Resolving radiation transport fields subject to opacity profiles with strong, oscillatory line structure while potentially falling under intermediate optical depth conditions presents a numerical challenge in radiation transport modeling. The Young measure-based homogenization technique formulated by Haut et al. (2017) was investigated as a candidate method for resolving radiation fields under such conditions more accurately. The method was compared against frequently-utilized mean opacity methods as the Rosseland and Planck formulations. In this work, all methods were tested through radiation slab calculations separately comprised of aluminum, copper, and krypton, each for different thermodynamic conditions. Following these offline radiation slab calculations, demonstrations shifted towards the SCEPTRE radiation transport code and, subsequently, the multiphysics ALEGRA code for approximately-coupled radiation-material simulations. Throughout all the simulations shown in this study, for a fixed computational cost, the homogenized method was observed to be more accurate than any of the solutions determined through traditional mean opacity approaches.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications

Introduction Reconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.TrkX Project, an illustrative HEP application, preprocessed simulation data is fed into a state-of-art Graph Neural Network (GNN) model, accelerated by GPUs. However, limited GPU memory often leads to Out-of-Memory (OOM) exceptions during training, due to the large size of models and datasets. This problem is exacerbated when deploying models on High-Performance Computing (HPC) systems designed for large-scale applications. Methods We observe a high workload imbalance issue during GNN model training caused by the irregular sizes of input graph samples in HEP datasets, contributing to OOM exceptions. We aim to scale GNNs on HPC systems, by prioritizing workload balance in graph inputs while maintaining model accuracy. Our paper introduces diverse balancing strategies aimed at decreasing the maximum GPU memory footprint and avoiding the OOM exception, across various datasets. Results Our experiments showcase memory reduction of up to 32.14% compared to the baseline. We also demonstrate the proposed strategies can avoid OOM in application. Additionally, we create a distributed multi-GPU implementation using these samplers to demonstrate the scalability of these techniques on the HEP dataset. Discussion By assessing the performance of these strategies as data loading samplers across multiple datasets, we can gauge their effectiveness in both single-GPU and distributed environments. Our experiments, conducted on datasets of varying sizes and across multiple GPUs, broaden the applicability of our work to various GNN applications that handle input datasets with irregular graph sizes.

Lee, Claire Songhyun↗