Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Average model”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Large Eddy Simulation of Lean Mixed-Mode Combustion Assisted by Partial Fuel Stratification in a Spark-Ignition Engine

Partial fuel stratification (PFS) is a promising fuel injection strategy to improve the stability of lean combustion by applying a small amount of pilot injection right before spark timing. Mixed-mode combustion, which makes use of end-gas autoignition following conventional deflagration-based combustion, can be further utilized to speed up the overall combustion. In this study, PFS-assisted mixed-mode combustion in a lean-burn direct injection spark-ignition (DISI) engine is numerically investigated using multi-cycle large eddy simulation (LES). A previously developed hybrid G-equation/well-stirred reactor combustion model for the well-mixed operation is extended to the PFS-assisted operation. The experimental spray morphology is employed to derive spray model parameters for the pilot injection. The LES-based model is validated against experimental data and is further compared with the Reynolds-averaged Navier–Stokes (RANS)-based model. Overall, both RANS and LES predict the mean pressure and heat release rate traces well, while LES outperforms RANS in capturing the cycle-to-cycle variation (CCV) and the combustion phasing in the mass burned space. Liquid and vapor penetrations obtained from the simulations agree reasonably well with the experiment. Detailed flame structures predicted from the simulations reveal the transition from a sooting diffusion flame to a lean premixed flame, which is consistent with experimental findings. LES captures more wrinkled and stretched flames than RANS. Finally, the LES model is employed to investigate the impacts of fuel properties, including heat of vaporization (HoV) and laminar burning speed (SL). Combustion phasing is found more sensitive to SL than to HoV, with a larger fuel property sensitivity of the heat release rate from autoignition than that from deflagration. Moreover, the combustion phasing in the PFS-assisted operation is shown to be less sensitive to SL compared with the well-mixed operation.

fuel property sensitivity↗
DOE OSTI2022

Evaluation of obstacle modelling approaches for resource assessment and small wind turbine siting: case study in the northern Netherlands

Abstract. Growth in adoption of distributed wind turbines for energy generation is significantly impacted by challenges associated with siting and accurate estimation of the wind resource. Small turbines, at hub heights of 40 m or less, are greatly impacted by terrestrial obstacles such as built structures and vegetation that can cause complex wake effects. While some progress in high-fidelity complex fluid dynamics (CFD) models has increased the potential accuracy for modelling the impacts of obstacles on turbulent wind flow, these models are too computationally expensive for practical siting and resource assessment applications. To understand the efficacy of available models in situ, this study evaluates classic and commonly used methods alongside new state-of-the-art lower-order models derived from CFD simulations and machine learning approaches. This evaluation is conducted using a subset of an extensive original dataset of measurements from more than 300 operational wind turbines in the northern Netherlands. The results show that data-driven methods (e.g. machine learning and statistical modelling) are most effective at predicting production at real sites with an average error in annual energy production of 2.5 %. When sufficient data may not be available de novo to support these data-driven approaches, models derived from high-fidelity simulations show promise and reliably outperform classic methods. On average these models have 6.3 %–11.5 % error compared with 26 % for classic methods and 27 % baseline error for reanalysis data without obstacle correction. While more performant on average, these methods are also sensitive to the quality of obstacle descriptions and reanalysis inputs.

17 WIND ENERGY↗
DOE OSTI2022

(Invited) Continuum Mathematical Modeling of Water Electrolysis: A Tutorial

Widespread use of hydrogen energy is contingent on the development of reliable and economical sources of hydrogen. Electrolysis from renewably-derived low-carbon electricity is a potentially viable method of hydrogen generation. Prime among the electrolysis technologies are those utilizing ion-conducting polymers (ionomers) including proton-exchange-membrane water electrolyzer (PEMWE). However, these technologies need to exhibit increased efficiency, performance, and durability to become commercially viable. Like most electrochemical devices, PEMWEs involve multiple components (e.g., catalyst, ionomer, transport layers, membrane, plates) and multiple phases, with phenomena occurring across different time and length scales. Furthermore, it is difficult to experimentally probe many of the species and phenomena during operation. Thus, mathematical modeling at the continuum level has been an invaluable aid in exploring, understanding, and optimizing PEMWE cell and components. Furthermore, this is especially true in the highly coupled and complex physics and chemistries that occur with the membrane-electrode assembly (MEA). The physics in a typical volume-averaged non-isothermal model include multiphase transport in porous media, concentrated-solution theory, Ohm's Law, and Butler-Volmer kinetics, and ion, gas, and water transport in the ionomer.

Dizon, Arthur↗
DOE OSTI2021

Comparing Global Spray Combustion Characteristics and Local Shot-to-Shot Variations in a Reacting n -Heptane Spray

In support of efforts to develop improved models of turbulent spray behavior and combustion in diesel engines, experimental data and analysis must be obtained for guidance and validation. For Reynolds-averaged Navier–Stokes (RANS)-based Computational fluid dynamics (CFD) modeling approaches, representative ensemble average experimental results are important. For high-fidelity models such as large eddy simulations (LES)-based CFD, precise individual experimental results are desirable. However, making comparisons between a given experiment and LES is a challenge since local parameters cannot be directly compared. In this work, an optically accessible constant pressure flow rig (CPFR) is utilized to acquire diesel-like fuel injection and reaction behavior simultaneously with three optical diagnostic techniques: rainbow Schlieren deflectometry (RSD), OH* chemiluminescence (OH*), and two-color pyrometry (2CP). The CPFR allows a large number of repeated injection experiments to be performed for statistical analysis and convergence using ensemble-averaging techniques, while maintaining highly repeatable test conditions. Even for stable test conditions, variations in local turbulent fuel–air mixing introduce variability, which manifests as significant differences in OH* and 2CP results. Experimental measurements of characteristic parameters including liquid and vapor jet penetration, liftoff length, soot temperature and concentration, and turbulent flame speed, along with the shot-to-shot variability of each dataset, are presented and discussed. Finally, a statistical method is utilized to analyze the extent of this variability, and to identify superlative injections within the dataset for discussion and analysis of shot-to-shot variations.

42 ENGINEERING↗
DOE OSTI2021

Mitigating Depolarizing Noise on Quantum Computers with Noise-Estimation Circuits

A significant problem for current quantum computers is noise. While there are many distinct noise channels, the depolarizing noise model often appropriately describes average noise for large circuits involving many qubits and gates. We present a method to mitigate the depolarizing noise by first estimating its rate with a noise-estimation circuit and then correcting the output of the target circuit using the estimated rate. The method is experimentally validated on the simulation of the Heisenberg model. We find that our approach in combination with readout-error correction, randomized compiling, and zero-noise extrapolation produces results close to exact results even for circuits containing hundreds of CNOT gates.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Operating Hardware Impact on the Heat Transfer Properties of Windows

Despite significant advancements in fenestration technology in the last two decades, the thermal transmittance of fenestration products is still significantly higher than that of walls. This corresponds to 60% of the total energy loss of a modern building envelope through the windows. Hence, further development and improvements of fenestration products are necessary. Increasingly stringent codes and standards for fenestration stimulate industry to work on improved solutions. Thus, it is crucial that assessment techniques are able to account for innovations accurately. The thermal effects of non-continuous hardware in window frames are currently ignored by international rating procedures. A preliminary investigation conducted by our team showed significant performance degradation in two of the three out-opening casement profiles caused by the presence of operating hardware. Frames with the structure made of vinyl and fiberglass consist of many air cavities that are penetrated by operating hardware made of highly conductive materials. In these frames, in order to have an accurate assessment, it may be required to employ three-dimensional modeling due to the convective nature of heat transfer within the cavities. However, in this study, we demonstrate that the three-dimensional (3D) effects of non-continuous hardware can be approximated accurately with simpler two-dimensional (2D) simulations. We then develop a simplified model based on weighted average capable of replacing the time- and computation-intensive 3D simulations with 2D simulations and validate it against market available frames and their corresponding hardware. Validation results show that our approximation technique results in discrepancies lower than 0.05 W/(m2K), or 3% of the total thermal transmittance. Thus, we conclude that simplified 2D simulation models may be used for predicting hardware impact in window frames with reasonable accuracy. As windows and glazing structures are becoming ever better thermally insulated, it is becoming even more important to be able to model the impact of the operating hardware on the total thermal performance in order to design the best windows possible and not let the operating hardware ruin an otherwise well-proven design, which is hence addressed in this study.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Synthetic method of analogues for emerging infectious disease forecasting

The Method of Analogues (MOA) has gained popularity in the past decade for infectious disease forecasting due to its non-parametric nature. In MOA, the local behavior observed in a time series is matched to the local behaviors of several historical time series. The known values that directly follow the historical time series that best match the observed time series are used to calculate a forecast. This non-parametric approach leverages historical trends to produce forecasts without extensive parameterization, making it highly adaptable. However, MOA is limited in scenarios where historical data is sparse. This limitation was particularly evident during the early stages of the COVID-19 pandemic, where the emerging global epidemic had little-to-no historical data. In this work, we propose a new method inspired by MOA, called the Synthetic Method of Analogues (sMOA). sMOA replaces historical disease data with a library of synthetic data that describe a broad range of possible disease trends. This model circumvents the need to estimate explicit parameter values by instead matching segments of ongoing time series data to a comprehensive library of synthetically generated segments of time series data. We demonstrate that sMOA has competitive performance with state-of-the-art infectious disease forecasting models, out-performing 78% of models from the COVID-19 Forecasting Hub in terms of averaged Mean Absolute Error and 76% of models from the COVID-19 Forecasting Hub in terms of averaged Weighted Interval Score. Additionally, we introduce a novel uncertainty quantification methodology designed for the onset of emerging epidemics. Developing versatile approaches that do not rely on historical data and can maintain high accuracy in the face of novel pandemics is critical for enhancing public health decision-making and strengthening preparedness for future outbreaks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A single-point modeling approach for the intercomparison and evaluation of ozone dry deposition across chemical transport models (Activity 2 of AQMEII4)

A primary sink of air pollutants and their precursors is dry deposition. Dry deposition estimates differ across chemical transport models, yet an understanding of the model spread is incomplete. Here, we introduce Activity 2 of the Air Quality Model Evaluation International Initiative Phase 4 (AQMEII4). We examine 18 dry deposition schemes from regional and global chemical transport models as well as standalone models used for impact assessments or process understanding. We configure the schemes as single-point models at eight Northern Hemisphere locations with observed ozone fluxes. Single-point models are driven by a common set of site-specific meteorological and environmental conditions. Five of eight sites have at least 3 years and up to 12 years of ozone fluxes. The interquartile range across models in multiyear mean ozone deposition velocities ranges from a factor of 1.2 to 1.9 annually across sites and tends to be highest during winter compared with summer. No model is within 50 % of observed multiyear averages across all sites and seasons, but some models perform well for some sites and seasons. For the first time, we demonstrate how contributions from depositional pathways vary across models. Models can disagree with respect to relative contributions from the pathways, even when they predict similar deposition velocities, or agree with respect to the relative contributions but predict different deposition velocities. Both stomatal and nonstomatal uptake contribute to the large model spread across sites. Our findings are the beginning of results from AQMEII4 Activity 2, which brings scientists who model air quality and dry deposition together with scientists who measure ozone fluxes to evaluate and improve dry deposition schemes in the chemical transport models used for research, planning, and regulatory purposes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

CFD modeling of non-catalytic, partial-oxidation engine reformer for flare mitigation

Flaring associated natural gas is commonly employed in the oil and gas industry to reduce methane (CH 4 ) emissions but generates carbon dioxide (CO 2 ) and harmful pollutants, significantly contributing to air pollution and posing risks to public health. To mitigate this impact, M2X Energy Inc. has developed a small-scale, modular gas-to-methanol system. This system features an engine reformer that performs fuel-rich partial oxidation of wellhead gas to produce syngas—a mixture of carbon monoxide (CO) and hydrogen (H 2 )—followed by a downstream reactor for methanol synthesis. This study focused on computational fluid dynamics (CFD) modeling of the engine reformer to simulate partial oxidation chemistry, predict the rich-burn operating limit, and assess syngas quality, ultimately aiding in design and operational optimization. The CFD model, developed within a Reynolds-Averaged Navier-Stokes (RANS) turbulence framework, incorporated sub-models for turbulent combustion, a chemical mechanism with polycyclic aromatic hydrocarbon (PAH) pathways, and soot emissions to accurately capture the fuel-rich, turbulent jet ignition and combustion processes. Model validation against experimental data showed good agreement across pre- and main-chamber pressures, apparent heat release rates, and exhaust gas concentrations of key species (H 2 , CO, CO 2 , CH 4 ) for varying intake equivalence ratios. Here, the model identified a rich-burn operating limit near a fuel-air equivalence ratio of 2.35, consistent with experimental observations. Furthermore, syngas quality analysis revealed that extending the rich-burn limit through engine reformer optimization could enhance syngas production, contributing to higher methanol synthesis efficiency.

Computational Fluid Dynamics↗
DOE OSTI2023

Denial of Service Attack Detection via Differential Analysis of Generalized Entropy Progressions

Denial-of-Service (DoS) attacks are one the most common and consequential cyber attacks in computer networks. While existing research offers a plethora of detection methods, the issue of achieving scalability, a low false positive rate, and high detection accuracy remains open. In this work, we address this problem by developing a differential method based on generalized entropy progression. In this method, named as DoDGE, we continuously fit the line of best fit to the entropy progression of destination addresses and check if the derivative, that is, the slope of this line is less than the negative of the dynamically computed standard deviation of the derivatives. Furthermore, to distinguish from flash events, we leverage the symmetry that when a flash event occurs, the derivative of the entropy progression of source addresses is positive. With this design, we omit the usage of the thresholds and the results with five real-world network traffic datasets confirm that DoDGE outperforms threshold-based DoS attack detection by two orders of magnitude in terms of false positives on average. When compared to ten machine learning (ML) models, DoDGE achieves a balanced accuracy of 99%, while the average balanced accuracy for the ML models is 52%. Moreover, the results show that DoDGE successfully differentiates between a flash event and a DoS attack. Furthermore, since the main computation cost of DoDGE is the entropy computation, which is linear in the volume of the unit-time network flow, uses integer only operations, and works on a small fraction of the total flow, it is lightweight and scalable.

Cybersecurity, wireless communication↗
DOE OSTI2025

Recent Improvements in Pronghorn for Advanced Reactor Modeling

Pronghorn is a thermal-hydraulics computational tool developed using the Idaho National Laboratory's Multiphysics Object-Oriented Simulation Environment (MOOSE). It is designed to support Computational Fluid Dynamics (CFD) modeling, ranging from subchannel and porous media analysis to Reynolds Averaged Navier-Stokes (RANS) turbulence modeling. As an integral part of the MOOSE-based suite of tools, Pronghorn seamlessly couples with other MOOSE-based applications to simulate a variety of physical phenomena. This article highlights recent significant enhancements to Pronghorn's CFD modeling capabilities and demonstrates their application to advanced nuclear reactor designs. The recent improvements in Pronghorn primarily focus on modifications to its turbulence modeling capabilities, near-wall corrections and numerical schemes. In terms of turbulence modeling, the two-equation $k-\epsilon$ and $k-\omega$ SST models have been implemented and validated with both equilibrium and non-equilibrium wall treatments. Additionally, corrections for wall roughness, and curvature, and wall-channeling in pebble beds have been introduced in the near-wall modeling. These developments enable more accurate simulations of advanced nuclear reactors. Two case studies are presented in this work: a pool-type Molten Chloride Reactor and a salt-cooled Pebble-Bed High Temperature Reactor. In both cases, the previous models in Pronghorn are compared with the new implementations, demonstrating the improved accuracy achieved with the updated models.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

A Nonergodic Ground-Motion Model for the San Francisco Bay Area for Small-Magnitude Earthquakes

ABSTRACT Recently, generative models have become a computationally efficient alternative to physics-based numerical simulations of ground motions. Neural networks can learn from existing ground-motion data to generate unobserved ground-motion data at new source and site locations. A key challenge with generative models is ensuring that predicted ground motions remain within a physically realistic range. For this purpose, we developed an empirical, nonergodic ground-motion model (GMM) for small-magnitude earthquakes in the San Francisco Bay area based on about 5000 recordings per component for Mw ≤ 4 earthquakes. The nonergodic GMM predicts spatially varying median source, site, and path effects for both the Fourier amplitude spectrum (FAS) and the Fourier phase derivative (a proxy for duration), as well as the corresponding epistemic uncertainty for each term. For FAS, our model shows above-average source and site effects in the western part of the region and below-average effects in the eastern part, with regional effects exhibiting larger spatial correlation lengths with increasing frequency. For duration, the source term is negligible for small-magnitude earthquakes, and the site term leads to site-specific variations up to 5 s. Path effects for FAS and duration depend on the source–site pair and are extrapolated spatially using recent methods for path-effect modeling. The aleatory variability of the within-site within-path residuals is similar to the variability found in previous studies for other regions. The nonergodic model provides two key contributions: first, median adjustment terms that are transferable to larger magnitude earthquakes, further reducing aleatory variability in probabilistic seismic hazard analysis; second, region-specific criteria for validating machine learning-based ground-motion generators to evaluate whether synthetic ground motions exhibit physically realistic source, site, and path effects.

Lacour, Maxime↗
DOE OSTI2023

The Spread of Ocean Heat Uptake Efficiency Traced to Ocean Salinity

Abstract Ocean heat uptake (OHU) plays an important role in determining the rate of surface warming under CO 2 forcing. We examined the transient response to CO 2 forcing in a set of 30 climate models from Coupled Model Intercomparison Project Phase 6 (CMIP6) and found that the intermodel spread in OHU efficiency largely depends on the base‐state ocean stratification, especially in the Southern Ocean. This dependence is primarily traced to ocean salinity rather than ocean temperature. Models with weaker ocean stratification primarily due to higher upper‐ocean salinity tend to sequester heat into the deeper ocean, leading to a lower rate of surface warming, a primary reason for higher OHU efficiency; the stratification impact on total OHU is secondary. We applied the relationship between salinity and OHU efficiency for an emergent constraint on OHU efficiency, suggesting an OHU efficiency higher than the CMIP6 multimodel average and arguing against models with extremely low efficiency.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Microstructure in matrix elements

We investigate the simple model of Pennington, Shenker, Stanford and Yang for modeling the density matrix of Hawking radiation, but further include dynamics for EOW branes behind the horizon. This allows interactions that scatter one interior state to another, and also allows EOW loops. At strong coupling, we find that EOW states are no longer random; the ensemble has collapsed, and coupling constants encode the microscopic matrix elements of Hawking radiation. This suggests strong interior dynamics are important for understanding evaporating black holes, without any ensemble average. In this concrete model the density matrix of the radiation deviates from the thermal state, small off-diagonal fluctuations encode equivalences between naively orthogonal states, and bound the entropy from above. For almost evaporated black holes the off-diagonal terms become as large as the diagonal ones, eventually giving a pure state. We also find the unique analytic formula for all Renyi entropies.

2D gravity↗
DOE OSTI2024

Evaluation of RANS vs. LES simulation of fluid flow through 3 × 3 rod bundle with a simple spacer grid as a precursor to coupled fluid–structure interaction simulations

The research literature on Computational Fluid Dynamics (CFD) of coolant flow through rod bundles with spacer-grids and mixing vanes is replete, ranging from high fidelity Large Eddy Simulation (LES)/Direct Numerical Simulation (DNS) simulations to Reynolds-Averaged Navier–Stokes (RANS) modeled studies. The mixing of flow between subchannels and the pressure drop through the bundle are fundamental quantities useful for comparing and evaluating CFD methods. Less commonly observed and compared are the forces exerted onto the structure by the fluid. The present study seeks to evaluate the use of RANS simulations for predicting the structural response to fluid flow. Wall resolved RANS simulations are benchmarked against LES simulations of fluid flow at a Reynolds number of 15,000 through a 3 × 3 fuel rod bundle with a simple spacer grid. Velocity line-plots are compared showing good agreement between RANS and LES results, ascertaining that the former is capable of capturing the essential time-averaged velocity profile. Additionally, the distribution of forces on the spacer grid and fuel rods are collected as a function of time and space. The RANS methods are evaluated using the frequency and magnitude of the fluctuating forces on various portions of the structure as compared to LES. In conclusion, the power spectral density evaluation of the models reveal underprediction of force amplitude on the rod walls by RANS and also discrepancy in the prediction of high frequency spectra, especially in the immediate vicinity of spacer-grid structure, which may be attributed to the lack of random turbulence fluctuation or insufficient modeling of small-scale eddies in RANS simulation.

FIV↗
DOE OSTI2023

Optimizing Phase Change Composite Thermal Energy Storage Using the Thermal Ragone Framework

The thermal Ragone framework can be applied to the design of thermal energy storage heat exchangers to identifying relationships between their power requirements and energy capabilities. This presentation focuses on the design of planar thermal energy storage heat exchangers with phase change materials and thermal conductivity additives. Finite-difference models were used to optimize thermal storage heat exchanger designs focusing on key design parameters of conductivity additive volume fraction, spacing between tubes, and the phase transition temperatures. Design trends were developed for optimal designs based on varying thermal power requirements. To aid in future device design, models of reduced complexity were developed with the ability to predict optimal designs with computational speeds up to 5,000 times faster than finite-difference models.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION,↗
DOE OSTI2025

A hybrid surrogate modeling framework for the Digital Twin of a Fluoride-salt-cooled High-temperature Reactor (FHR)

While nuclear energy is a non-greenhouse-gas emitting energy source, expensive operational costs due to the high-level of safety requirements decreases their competitiveness in the sustainable energy market. Advanced reactor concepts paired with Digital Twins aim to increase the commercialization gains of nuclear energy by reducing operational costs, increasing reactor reliability and enhancing power generation. To support Digital Twin tasks such as real-time autonomous control, proactive maintenance monitoring or optimizing power demand operations, a fast and accurate virtual representation of the Nuclear Power Plant (NPP) is required. The computational cost of high-fidelity, physics-based models are unsuitable for real-time analysis or scalability. Here, in this work, a hybrid surrogate modeling framework is developed fora Fluoride-salt-cooled High-temperature Reactor (FHR) that leverages physics-inspired models for key reactor components and uses data-driven methods for rapid system state space prediction. The Xenon reactivity feedback model is integrated to inform the surrogate model about the reactor core and the homologous pump theory model is the basis for representing pump degradation. Using a detailed, two dimensional thermal hydraulics model to generate data on the FHR, we train a network of Vectorized Autoregressive Moving-Average with eXogenous input (VARMAX) models to predict the remaining state values. The result is a surrogate model that provides a detailed reactor state representation of 41 system states and a pump degradation analysis. The framework is applied to Load Follows profiles, yielding high accuracy and a speedup that is more than 4000x faster compared to the higher- fidelity thermal hydraulics model, enabling real-time operational intelligence and applications in long horizon predictions. While the surrogate model framework is demonstrated for the particular case of FHR, the hybrid physical/data-driven modeling approach including the network of surrogates and the underlying modularity has the potential to be applied to other physical asset systems.

Digital Twins↗
DOE OSTI2025

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗