Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “surrogates”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Technical note: Deep learning for creating surrogate models of precipitation in Earth system models

Abstract. We investigate techniques for using deep neural networks to produce surrogatemodels for short-term climate forecasts. A convolutional neural network istrained on 97 years of monthly precipitation output from the 1pctCO2 run (theCO 2 concentration increases by 1 % per year) simulated by the second-generation Canadian Earth System Model (CanESM2). The neural network clearly outperforms a persistence forecast anddoes not show substantially degraded performance even when the forecast lengthis extended to 120 months. The model is prone to underpredicting precipitationin areas characterized by intense precipitation events. Scheduled sampling(forcing the model to gradually use its own past predictions rather than groundtruth) is essential for avoiding amplification of early forecasting errors.However, the use of scheduled sampling also necessitates preforecasting(generating forecasts prior to the first forecast date) to obtain adequateperformance for the first few prediction time steps. We document the trainingprocedures and hyperparameter optimization process for researchers who wish toextend the use of neural networks in developing surrogate models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Testing Surrogate-Based Optimization with the Fortified Branin-Hoo Extended to Four Dimensions

Some popular functions used to test global optimization algorithms have multiple local optima, all with the same value, making them all global optima. It is easy to make them more challenging by fortifying them via adding a localized bump at the location of one of the optima. In previous work the authors illustrated this for the Branin-Hoo function and the popular differential evolution algorithm, showing that the fortified Branin-Hoo required an order of magnitude more function evaluations. This paper examines the effect of fortifying the Branin-Hoo function on surrogate- based optimization, which usually proceeds by adaptive sampling. Two algorithms are considered. The EGO algorithm, which is based on a Gaussian process (GP) and an algorithm based on radial basis functions (RBF). EGO is found to be more frugal in terms of the number of required function evaluations required to identify the correct basin, but it is expensive to run on a desktop, limiting the number of times the runs could be repeated to establish sound statistics on the number of required function evaluations. The RBF algorithm was cheaper to run, providing more sound statistics on performance. A four-dimensional version of the Branin-Hoo function was introduced in order to assess the effect of dimensionality. Furthermore, it was found that the difference between the ordinary function and the fortified one was much more pronounced for the four-dimensional function compared to the two dimensional one.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Photopolymerizable Sol-gel Synthesis for Faster Manufacturing of Surrogate Nuclear Debris

Simulated debris is used to train first responders for potential nuclear detonations. Sol gel chemistry has been used to produce surrogate material for these training exercises, but the current average production time is 4 hours. Optimization using UV-polymerizable sol gel precursors can potentially decrease time as well as cost of the production process. FT-IR spectroscopy was used to measure and compare gelation kinetics of the standard and photopolymerizable sol gel synthetic procedures. Addition of the UV-polymerizable precursors and controlling the aqueous phase volume resulted in a 120-fold decrease in vitrification time.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2023

Experiments and Simulations of Droplet Burning of Isobutanol Mixed with a Tier II Gasoline Certification Fuel and its Surrogate, Paper Number: SHTC2023-115267

This study presents an experimental and numerical results of combustion dynamics of a Tier II certification fuel/iso-butanol mixtures and its surrogate(S5)/iso-butanol mixtures. The experiments were carried out where gas transport was determined entirely by fuel evaporation to promote spherical symmetry during the burning process. The droplet initial diameters were in the range 0.55 mm to 0.62 mm. The combustion characteristics such as droplet diameters, flame standoff ratios and soot shell standoff ratios of indolene/iso-butanol mixtures are compared with S5/iso-butanol mixtures and the implications of iso-butanol addition to indolene and S5 on combustion are discussed. The presence of iso-butanol is experimentally found to reduce the formation of soot as the iso-butanol concentration was increased and the iso-butanol addition insignificantly influence the burning rate. Simulations were carried out with the detailed kinetic chemistry (324 species and 17608 reactions) from POLIMI. The detailed numerical model included unsteady gas and liquid transport, soot chemistry and radiative transport. The impact of iso-butanol on the burning rate, flame structure and soot formation are presented. Droplet burn rates were well predicted while flame diameters showed more variability depending on how the flame was defined in the numerical simulation (peak gas temperature and OH concentration). Simulations also show the influence of iso-butanol concentration on flame temperature, greenhouse gas emissions and soot formations.

Guo, Songtao↗
DOE OSTI2022

Combustion Characteristics of a Tier II Gasoline Certification Fuel and its Surrogate with Iso-butanol: experiments and detailed numerical modeling

This presentation will describe results of an experimental and numerical study of combustion of a Tier II gasoline certification fuel and its surrogate blended with iso-butanol as a potential biofuel additive. The experiments were carried out under conditions where gas transport originated entirely by fuel evaporation with external convection (both forced and natural) were minimized. The resulting near spherically symmetric droplet flames were amenable to detailed numerical modeling. The droplet initial diameters were in the narrow range of 0.55 mm to 0.62 mm while and burning is performed under standard atmosphere. The combustion characteristics such as evolution of droplet, flame and soot shell diameters for indolene/iso-butanol and surrogate/iso-butanol mixtures are compared. The presence of iso-butanol is experimentally found to reduce the formation of soot as the iso-butanol concentration was increased. Simulations are also reported using a detailed kinetic chemistry comprised of 324 species and 17608 reactions using the CRECK POLIMI mechanism. The detailed numerical model included unsteady gas and liquid transport, soot chemistry and radiative transport. Droplet burn rates were well predicted while flame diameters showed more variability depending on how the flame was defined in the numerical simulation (peak gas temperature and OH concentration). Simulations also show the influence of iso-butanol concentration on flame temperature, greenhouse gas emissions and particulate emissions.

Guo, Songtao↗
DOE OSTI2024

Equipping Neural Network Surrogates with Uncertainty for Propagation in Physical Systems

Coarse-grained or filtered models typically rely on closure models to account for unresolved scales. For instance, large eddy simulation for modeling turbulent fluid flows explicitly resolves the largest scales, but requires modeling closure terms to account for the sub-filter scales. With the vast amount of data available from high-fidelity simulations, there are unique opportunities to leverage data-driven modeling techniques to formulate expressive and flexible closure models. Despite their flexibility, data-driven models struggle in domain shift settings, i.e. when deployed in configurations not captured in the training dataset. In particular, the efficacy of neural network surrogates is difficult to assess a priori due to the deterministic, point-estimate nature of predictions. In high-consequence applications, such models require reliable uncertainty estimates in the data-informed and out-of-distribution regimes. To quantify uncertainties in both regimes, we employ Bayesian neural networks which are able to capture both epistemic and aleatoric uncertainties. We will discuss challenges associated with the training and evaluation of these networks. Furthermore, we will discuss uncertainty embedding strategies to enable efficient sampling and propagation of uncertainty through high-fidelity simulations.

Bayesian neural networks↗
DOE OSTI2024

A Graph Neural Network Surrogate Model for hls4ml

Recent advancements in use of machine learning (ML) techniques on field-programmable gate arrays (FPGAs) have allowed for the implementation of embedded neural networks with extremely low latency. This is invaluable for particle detectors at the Large Hadron Collider, where latency and used area are strictly bounded. The hls4ml framework is a procedure that converts trained ML model software to a synthesis result to can be used on an FPGA. However, running the pipeline is a time-consuming procedure, and there is a strong risk of failure. In particular, it may not be possible to successfully convert a model into a synthesis result, or the resource consumption of the model may exceed the resources of the target FPGA. To aid with this development, we introduce wa-hls4ml, a surrogate model using a graph neural network to emulate the structure of the source models. The goal is to estimate the chance of success and resource consumption of a given model when passed through the hls4ml pipeline, without needing to run the pipeline.

Plotnikov, Dennis↗
DOE OSTI2024

Milestone 1.2.16. Reconciling the Impacts of Thermal Pretreatment on Radiation-Induced H2 Generation from Aluminum-Clad Spent Nuclear Fuel Surrogate Materials

To support the technical basis for the extended dry storage of aluminum-clad spent nuclear fuel (ASNF), thermal pretreatment procedures to minimize the radiation-induced generation of molecular hydrogen (H2) have been investigated. The aim of thermal pretreatment is to eliminate the residual adsorbed water content on the ASNF’s corrosion layers, precursors for H2 generation. To date, irradiation studies in this area have found conflicting results for the effectiveness of thermal pretreatment procedures. The aim of this study was to reconcile those differences. However, the presented results, which utilized a modified in situ thermal pretreatment procedure, afforded H2 yield data that further indicates that thermal pretreatment does not significantly reduce the radiation-induced yield of H2 from gamma irradiated ASNF surrogate materials. Assessment of the differences between thermal pretreatment studies suggests that stainless-steel—present in the irradiation setup of studies that demonstrated a reduction in the yield of H2 with thermal pretreatment—may afford not only unanticipated interfacial chemistry, but also the formation and radiolytic contribution of iron oxides to the chemistry underpinning the formation of H2 in these systems. Given the Department of Energy Standard Canister—proposed for the extended dry storage of ASNF—is predominantly composed of stainless-steel, the potential contribution of stainless-steel and its corrosion layers to radiolytic H2 production should be further investigated. This research was funded by the U.S. Department of Environmental Management, Office of Technology Development, under contract DE-AC07-05ID14517.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2025

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Neural Architecture Search is a powerful approach for automating model design, but existing methods struggle to accurately optimize for real hardware performance, often relying on proxy metrics such as bit operations. We present Surrogate Neural Architecture Codesign Package (SNAC-Pack), an integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment. SNAC-Pack combines Neural Architecture Codesign's multi-stage search capabilities with the Resource Utilization and Latency Estimator, enabling multi-objective optimization across accuracy, FPGA resource utilization, and latency without requiring time-intensive synthesis for each candidate model. We demonstrate SNAC-Pack on a high energy physics jet classification task, achieving 63.84% accuracy with resource estimation. When synthesized on a Xilinx Virtex UltraScale+ VU13P FPGA, the SNAC-Pack model matches baseline accuracy while maintaining comparable resource utilization to models optimized using traditional BOPs metrics. This work demonstrates the potential of hardware-aware neural architecture search for resource-constrained deployments and provides an open-source framework for automating the design of efficient FPGA-accelerated models.

Weitz, Jason [UC, San Diego] (ORCID:00090004631535↗
DOE OSTI2025

Insights from Surrogate Industries on Remote Operations for Advanced Reactors

With development of advanced reactors, understanding the human factors considerations related to remote operations remains an important topic. This work presents insights captured from reviewing relevant surrogate industries with remote operations, as they may apply to advanced reactor development. This work provides insights into important human factors considerations for remote operations to ensure safe and reliable adoption of these prospective reactor technologies.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2020

Effect of ionizing radiation on PuO2 and surrogate oxide materials under storage conditions

The stockpile of plutonium separated from used nuclear fuel amounts to many 100s of tonnes. The majority of this plutonium is stored as PuO2 powder packaged in multi-can containers. The conditions during the packaging of reprocessed PuO2 for long term storage are closely controlled to limit water uptake as radiolytic decomposition of any adsorbed water will lead to the formation of both a potentially flammable atmosphere containing molecular hydrogen as well as reactive oxygen species which may be incorporated into the oxide phase. Consequently, the safety case for the long-term storage of PuO2 requires a complete understanding of the fundamental physical, chemical and materials degradation processes occurring at the water-oxide interface inside the storage canisters. This study investigates the effect of ionizing radiation on PuO2 and various surrogate oxides under atmospheres potentially encountered in storage canisters.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

SLIP (Surrogate Launching and Integration Platform)

SLIP (Surrogate Launching and Integration Platform) is a software ecosystem for downloading and running ML/AI benchmarks. SLIP automatically downloads and sets up the code and data running a benchmark. The large data sets and model code are cached locally with a specific ID within a designated cache directory.

Brown, Cade↗
DOE OSTI2023

Retention of radionuclides in sol–gel surrogate nuclear explosive debris

Sol–gel vitrification can be used to rapidly produce solid, vitreous materials to support nuclear forensics research. Here, this work investigates three sol–gel synthetic approaches’ ability to retain fission products within the glass as a function of drying temperature. Eight of the ten fission products studied were quantitatively retained (less than 5% losses) at temperatures up to 600 °C for glasses prepared using an acidic catalyst and at temperatures up to 300 °C for glasses prepared using a basic catalyst. Both systems show partial loss of ruthenium and complete loss of iodine at temperatures above 300 and 100 °C, respectively.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2024

Investigating sol–gel matrix loading capacity toward producing surrogate nuclear explosive debris with realistic composition

Post detonation nuclear forensic materials which resemble the size, color, elemental composition, and radionuclide content of real nuclear debris would be valuable for developing and validating new nuclear forensic techniques. As nuclear fallout types vary significantly, the ability to tailor each of these parameters accurately is desired to produce materials capable of testing analytical methods under a wide array of forensic scenarios. Sol–gel synthesis techniques can provide tunability of size, shape and composition for producing a wide variety of solid nuclear forensics benchmarking materials. Further, the sol–gel process consists of forming a metal oxide material, often silica, through polymerization of a metal-alkoxy precursor. In this work, we characterize the ability to load sol–gel particles with secondary elemental components such as iron, aluminum, and calcium toward producing benchmarking materials approximating the elemental composition of historic nuclear debris from the Nevada National Security Site. We also demonstrate quantitative radionuclide encapsulation toward producing benchmarking materials with controllable radionuclide content. Finally, we employ these techniques to produce nuclear debris benchmarking materials with controllable elemental matrix composition and radionuclide content and compare these samples with the composition of a historic fallout sample previously reported from the Nevada National Security Site.

36 MATERIALS SCIENCE↗