Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ensemble optimization”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Machine-learning accelerated geometry optimization in molecular simulation

Geometry optimization is an important part of both computational materials and surface science because it is the path to finding ground state atomic structures and reaction pathways. These properties are used in the estimation of thermodynamic and kinetic properties of molecular and crystal structures. This process is slow at the quantum level of theory because it involves an iterative calculation of forces using quantum chemical codes such as density functional theory (DFT), which are computationally expensive and which limit the speed of the optimization algorithms. It would be highly advantageous to accelerate this process because then one could do either the same amount of work in less time or more work in the same time. Here, we provide a neural network (NN) ensemble based active learning method to accelerate the local geometry optimization for multiple configurations simultaneously. We illustrate the acceleration on several case studies including bare metal surfaces, surfaces with adsorbates, and nudged elastic band for two reactions. In all cases, the accelerated method requires fewer DFT calculations than the standard method. In addition, we provide an Atomic Simulation Environment (ASE)-optimizer Python package to make the usage of the NN ensemble active learning for geometry optimization easier.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Mechanistic Insights and Rational Design of Ca-Doped CeO 2 Catalyst for Acetic Acid Ketonization

Carboxylic acid ketonization has recently gained significant attention to produce biomass-derived hydrocarbon fuels as it not only removes the highly reactive carboxylic functional group but also increases the size of the carbon chain. In this work, Ca-doped CeO 2 -based catalysts were investigated for acetic acid ketonization using a combined experimental and computational approach. Acetic acid conversion was performed across a range of temperatures including higher temperatures relevant to catalytic hot gas filtration (450 °C). Ca addition slightly decreases overall acetic acid ketonization reactivity yet stabilizes the catalyst at the higher temperatures necessary for catalytic hot gas filtration. From density functional theory calculations of the ketonization reaction mechanism, the C–C coupling and water formation steps are identified as two of the most energy-consuming steps on a CeO 2 surface with a proximal oxygen vacancy and the presence of a Ca dopant stabilizes the key intermediates. Calculations predict an optimal structure comprising three Ca ensembles to minimize the reaction free energies for C–C coupling and water formation steps. These findings provide a priori information to guide future experiments for ketonization catalyst design and development.

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

Prediction of Distributed River Sediment Respiration Rates Using Community-Generated Data and Machine Learning

River sediment microbial respiration is a key indicator of ecosystem functioning and the biogeochemical fluxes across this critical zone link surface and subsurface waters. As such, there is tremendous interest in measuring and mapping these respiration rates. Respiration observations are expensive and labor intensive; there is limited data available to the community. An open science, collaborative initiative is collecting samples for respiration rate analysis and multi-scale metadata; this evolving data set is being used for making machine learning (ML) predictions at unsampled sites to help inform continued community engagement. However, it is a challenge to find an optimum configuration for ML models to work with this feature-rich (i.e., 100+ possible input variables) data set. Here, we present results from a two-tiered approach to managing the analysis of this complex data set: (a) a stacked ensemble of models that automatically optimizes hyperparameters and manages the training of many models and (b) feature permutation importance to detect the most important features in the models. The major elements of this workflow are modular, portable, open, and cloud-based thus making this implementation a potential template for other applications. The models developed here predict that sediment organic matter chemistry is one of the most important features for predicting sediment respiration rate. Other larger-scale, important features fall into the categories of climatic, ecological, geological, and fluvial settings. Leveraging these larger-scale features to generate data-driven estimates of river sediment respiration rates reveals spatially consistent but heterogeneous patterns across the river network of the Columbia River Basin.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Testing the predictive power of theory for Pd x Ir (100-x) alloy nanoparticles for the oxygen reduction reaction

Here, density functional theory (DFT) calculations of O and OH binding energies on triatomic surface ensembles of Pd x Ir (100-x) nanoalloys successfully predicted the overall trend in experimental oxygen reduction reaction (ORR) activity as a function of nanoparticle (NP) composition. Specifically, triatomic Pd 3 ensembles were found to possess optimal O and OH binding energies and were predicted to be highly active sites for the ORR, rivaling that of Pt(111). However, DFT calculations suggest that the O binding energy increases at active sites containing Ir, thereby decreasing ORR activity. Pd x Ir (100-x) nanoalloys were synthesized using a microwave-assisted method and their activity towards the ORR was tested using rotating disk voltammetry (RDV). As predicted, the bimetallic electrocatalysts exhibited worse catalytic activity than the Pd-only NPs. The strong qualitative correlation between the theoretical and experimental results demonstrates that the activity of individual active sites on the surface of NPs can serve as a proxy for overall activity. This is a particularly useful strategy for applying DFT calculations to electrocatalysts that are too large for true first-principle analysis.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Validating first-principles molecular dynamics calculations of oxide/water interfaces with x-ray reflectivity data

Metal oxide/water interfaces play a crucial role in many electrochemical and photocatalytic processes, such as photoelectrochemical water splitting, the creation of fuel from sunlight, and electrochemical CO 2 reduction. First-principles electronic structure calculations can reveal unique insights into these processes, such as the role of the alignment of the oxide electronic energy levels with those of liquid water. An essential prerequisite for the success of such calculations is the ability to predict accurate structural models of these interfaces, which in turn requires careful experimental validation. Here we report a general, quantitative validation protocol for first-principles molecular dynamics simulations of oxide/aqueous interfaces. The approach makes direct comparisons of interfacial x-ray reflectivity (XR) signals from experimental measurements and those obtained from ab initio simulations with semilocal and van der Waals functionals. The protocol is demonstrated here for the case of the Al 2 O 3 (001)/water interface, one of the simplest oxide/water interfaces. We discuss the technical requirements needed for validation, including the choice of the density functional, the simulation cell size, and the optimal choice of the thermodynamic ensemble. Our results establish a general paradigm for the validation of structural models and interactions at solid/water interfaces derived from first-principles simulations. Furthermore, while there is qualitative agreement between the simulated structures and the experimental best-fit structure, direct comparisons of simulated and measured XR intensities show quantitative discrepancies that derive from both bulk regions (i.e., alumina and water) as well as the interfacial region, highlighting the need for accurate density functionals to properly describe interfacial interactions. Our results show that XR data are sensitive not only to the atomic structure (i.e., the atom locations) but also to the electron-density distributions in both the substrate and at the interface.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Prediction of the development of islet autoantibodies through integration of environmental, genetic, and metabolic markers

The Environmental Determinants of the Diabetes in the Young (TEDDY) study has prospectively followed, from birth, children at increased genetic risk of type 1 diabetes. We evaluated the potential of machine learning to identify new biomarkers that predict imminent (within 6 months) development of persistent islet autoantibodies to insulin, GAD or IA-2 in TEDDY participants through integration of time-invariant risk factors with time-varying metabolomics. The predictive modeling was initiated with over 220 potential biomarkers; through ensemble-based feature evaluation, the optimal model included 42 biomarkers, returning a cross-validated receiver operating characteristic area under the curve of 0.74. The model identified a principal set of 20 time-invariant markers, including 16 single nucleotide polymorphisms and two HLA-DR genotypes, gestational age, and exposure to a prebiotic formula. Integration of the metabolome identified 22 high-priority metabolites and lipids, including adipic acid and ceramide d42:0, that predicted development of islet autoantibodies, dependent upon the time horizon. The majority (86%) of metabolites that predicted development of islet autoantibodies belonged to 3 pathways: lipid oxidation, phospholipase A2 signaling, and pentose phosphate pathway. TEDDY data suggest that these metabolic processes may play a role in triggering islet autoimmunity.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Bioactive scaffolds with enhanced supramolecular motion promote recovery from spinal cord injury

The signaling of cells by scaffolds of synthetic molecules that mimic proteins is known to be effective in the regeneration of tissues. Here, we describe peptide amphiphile supramolecular polymers containing two distinct signals and test them in a mouse model of severe spinal cord injury. One signal activates the transmembrane receptor β1-integrin and a second one activates the basic fibroblast growth factor 2 receptor. By mutating the peptide sequence of the amphiphilic monomers in nonbioactive domains, we intensified the motions of molecules within scaffold fibrils. This resulted in notable differences in vascular growth, axonal regeneration, myelination, survival of motor neurons, reduced gliosis, and functional recovery. Here, we hypothesize that the signaling of cells by ensembles of molecules could be optimized by tuning their internal motions.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Sensitivity Study for Forecasting Variables of WRF-Solar Using a Tangent Linear Approach

Integrating solar generation in recent years has highlighted the need for improved accuracy in predicting solar power. Confidence in solar power forecasting can be achieved by designing an ensemble that provides reliable probabilistic information for solar radiation with reduced uncertainty and error. Ideally, ensemble members are created through the optimized perturbation of the initial conditions in numerical weather prediction (NWP) models. Tangent linear models are capable of efficiently investigating the sensitivity of solar radiation to model input parameters because they do not require individual perturbation of each variable. This sensitivity study using tangent linear models provide us the capability to identify the right variables to perturb in an ensemble prediction system. In this study, we developed tangent linear models for WRF-Solar modules that directly impact the computation of solar radiation and the simulation of cloud formation and dissipation including the Fast All-sky Model for Solar Applications (FARMS), the Noah land surface model (LSM), the Thompson microphysics, the Mello-Yamada-Nakanishi-Niino (MYNN) boundary layer parameterization, and the Deng scheme for a shallow-convection parameterization. A sensitivity analysis was conducted under various scenarios based on satellite observations and model simulations from the National Solar Radiation Data Base (NSRDB) and WRF-Solar, respectively. Critical forecasting variables that are highly sensitive to the forecasting of global horizontal irradiance (GHI), direct normal irradiance (DNI), cloud mixing ratio, cloud tendency, cloud fraction, and sensible and latent heat fluxes were determined using the relevant WRF-Solar module. This study will be used as a guidance on future research leading to high-quality probabilistic solar forecasting. In this presentation, we discuss the validation of tangent linear approach for WRF-Solar modules and illustrate how the sensitivity results are valuable in the improvement of probabilistic solar prediction.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Systems and methods for modeling water quality

A system, method, device and computer-readable medium for creating an ensemble model of water quality. The ensemble model is generated by determining a set of optimal component models for spectral regions of a body of water, and combining the optimal models. The optimal models can be based on remote sensing data, including satellite imagery. A K-fold partition approach or a global approach can be used to determine the optimal component models, and the optimal component models can be combined through spectral space partition rules to generate an ensemble model of water quality. The ensemble model not only has improved water quality prediction ability, but also has strong spatial and temporal extensibility. The spatial and temporal extensibility of the ensemble model is fundamentally important and desirable for long-term and large-scale remote sensing monitoring and assessment of water quality.

Liu, Hongxing↗
DOE OSTI2022

Scalable deep learning for watershed model calibration

Watershed models such as the Soil and Water Assessment Tool (SWAT) consist of high-dimensional physical and empirical parameters. These parameters often need to be estimated/calibrated through inverse modeling to produce reliable predictions on hydrological fluxes and states. Existing parameter estimation methods can be time consuming, inefficient, and computationally expensive for high-dimensional problems. In this paper, we present an accurate and robust method to calibrate the SWAT model (i.e., 20 parameters) using scalable deep learning (DL). We developed inverse models based on convolutional neural networks (CNN) to assimilate observed streamflow data and estimate the SWAT model parameters. Scalable hyperparameter tuning is performed using high-performance computing resources to identify the top 50 optimal neural network architectures. We used ensemble SWAT simulations to train, validate, and test the CNN models. We estimated the parameters of the SWAT model using observed streamflow data and assessed the impact of measurement errors on SWAT model calibration. We tested and validated the proposed scalable DL methodology on the American River Watershed, located in the Pacific Northwest-based Yakima River basin. Our results show that the CNN-based calibration is better than two popular parameter estimation methods (i.e., the generalized likelihood uncertainty estimation [GLUE] and the dynamically dimensioned search [DDS], which is a global optimization algorithm). For the set of parameters that are sensitive to the observations, our proposed method yields narrower ranges than the GLUE method but broader ranges than values produced using the DDS method within the sampling range even under high relative observational errors. The SWAT model calibration performance using the CNNs, GLUE, and DDS methods are compared using R 2 and a set of efficiency metrics, including Nash-Sutcliffe, logarithmic Nash-Sutcliffe, Kling-Gupta, modified Kling-Gupta, and non-parametric Kling-Gupta scores, computed on the observed and simulated watershed responses. The best CNN-based calibrated set has scores of 0.71, 0.75, 0.85, 0.85, 0.86, and 0.91. The best DDS-based calibrated set has scores of 0.62, 0.69, 0.8, 0.77, 0.79, and 0.82. The best GLUE-based calibrated set has scores of 0.56, 0.58, 0.71, 0.7, 0.71, and 0.8. The scores above show that the CNN-based calibration leads to more accurate low and high streamflow predictions than the GLUE and DDS sets. Our research demonstrates that the proposed method has high potential to improve our current practice in calibrating large-scale integrated hydrologic models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A novel machine learning-based optimization algorithm (ActivO) for accelerating simulation-driven engine design

A novel design optimization approach (ActivO) that employs an ensemble of machine learning algorithms is presented. The proposed approach is a surrogate-based scheme, where the predictions of a weak leaner and a strong learner are utilized within an active learning loop. The weak learner is used to identify promising regions within the design space to explore, while the strong learner is used to determine the exact location of the optimum within promising regions. For each design iteration, exploration is done by randomly selecting evaluation points within regions where the weak learner-predicted fitness is high. The global optimum obtained by using the strong learner as a surrogate is also evaluated to enable rapid convergence once the most promising region has been identified. First, the performance of ActivO was compared against five other optimizers on a cosine mixture function with 25 local optima and one global optimum. In the second problem, the objective was to minimize indicated specific fuel consumption of a compression-ignition internal combustion (IC) engine while adhering to desired constraints associated with in-cylinder pressure and emissions. In this work, the efficacy of the proposed approach is compared to that of a genetic algorithm, which is widely used within the internal combustion engine community for engine optimization, showing that ActivO reduces the number of function evaluations needed to reach the global optimum, and thereby time-to-design by 80%. Furthermore, the optimization of engine design parameters leads to savings of around 1.9% in energy consumption, while maintaining operability and acceptable pollutant emissions.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

DeepONet-Assisted Optimization of Surface Topography for Transition Delay in A Mach 4.5 Boundary Layer

We use deep learning, an ensemble variationaltechnique (EnVar), and direct numerical simulations(DNS) to design an optimal topography for a two-dimensional roughness element that delays the on-set of laminar-turbulent transition in a Mach 4.5 flat-plate boundary layer. Deep operator networks (Deep-ONets), which have the known ability to learn com-plex nonlinear operators within dynamical systems,are used for machine learning. For the baseline config-uration of a smooth flat plate, the second-mode wavesat the DNS inflow cause a quick nonlinear breakdownof the high-speed boundary layer within the computa-tional domain. Results reported in the present studyvalidate the ability of DeepONets to model the tran-sition delay via a given topography of the roughnesselement. The computing cost to optimize the rough-ness element for minimal skin-friction drag is substan-tially lowered by the DeepONets-based reduced-ordermodel. In comparison to the baseline method of EnVaroptimization based on DNS alone, the DeepONets-based EnVar optimizer is able to delay transition pastthe outflow boundary of the computational domainwhile utilizing almost 5–6 times fewer DNS.

Machine Learning↗
DOE OSTI2024

CeO2 Nanoparticle Doping as a Probe of Active Site Speciation in the Catalytic Hydrolysis of Organophosphates

Organophosphate hydrolysis is important for degrading environmentally harmful compounds and recovering phosphate ions in biological molecules. CeO2 nanocrystals have been well-studied for dephosphorylation via hydrolysis owing to the accessible and tunable distribution of Ce3+ and Ce4+ ions. However, there remains uncertainty in the literature regarding which surface defect properties direct catalytic activity, such as the Ce3+/Ce4+ distribution, oxygen vacancies, faceting, and dopants, and to what degree they contribute to efficient hydrolysis. Trivalent (M3+) dopants serve as a tool for manipulating defects, including the concentration of Ce3+ and oxygen vacancies, thereby influencing the hydrolytic activity of CeO2. Herein, trivalent metal ions (M = Y3+, Cr3+, In3+, and Gd3+) were employed to modulate the active sites on the CeO2 nanocrystal surface, and the effects of each metal dopant on the cerium oxide active sites for organophosphate hydrolysis were investigated. M-doped CeO2 nanoparticles were synthesized via hydrothermal methods, followed by annealing to remove ligands and prime the nanocrystal surface for catalysis. Catalytic performance was evaluated using dimethyl-p¬-nitrophenyl phosphate (DMNP) as a model organophosphate substrate, with degradation monitored over time using UV-visible absorption spectroscopy. Powder X-ray diffraction (PXRD), X-ray photoelectron spectroscopy (XPS), and Raman spectroscopy revealed successful doping of CeO2 in all cases, albeit with distinctive characteristics demonstrating how M3+ dopants affect catalysis. We show that CeO2 exhibits high sensitivity to dopants that generate lattice strain, Ce3+ ions, and oxygen vacancy defects. Consequently, achieving high catalytic efficiency within CeO2 requires a balanced active site ensemble, wherein defects are maintained at optimal concentrations and distributions on the nanocrystal surface.

Miura-Stempel, Emily L.↗
DOE OSTI2025

Off-Equilibrium Reactivity of Boron-Enriched Metal Diboride Surfaces in Electroreduction Conditions

Boron-based materials, featuring B-dependent reactivity and diverse phases, are emerging as promising catalyst systems. However, the catalytic mechanism on many borides remains poorly understood due to complex surface reconstructions under reaction conditions. Here, we investigate the MoB 2 surface in conditions of hydrogen evolution reaction in acidic media, using grand canonical global optimization, grand canonical density functional theory, ab initio molecular dynamics, free energy surface sampling, and an analytical model for electrochemical barrier evaluation. We propose a boron-enrichment strategy to tune the surface reactivity of the hexagonal face of MoB 2 . We reveal the dynamic nature of the B-enriched surface under H coverage and kinetic trapping of the system in the metastable regime with an extensive examination of the deactivation pathways. The metastable center B site on B-enriched surfaces, featuring buckled-up configuration and a usual relaxation effect, is found to be highly active toward HER via the Volmer–Heyrovsky mechanism. In conclusion, this work demonstrates how off-equilibrium behaviors can arise from the interplay between adsorbate coverage and surface reconstruction on a seemingly simple surface, and we present a theoretical framework and computational workflows to address these behaviors, along with other realistic complexities, in kinetics simulations.

Adsorption↗
DOE OSTI2023

Enhancing the activity of Pd ensembles on graphene by manipulating coordination environment

Atomic dispersion of metal catalysts on a substrate accounts for the increased atomic efficiency of single-atom catalysts (SACs) in various catalytic schemes compared to the nanoparticle counterparts. However, lacking neighboring metal sites has been shown to deteriorate the catalytic performance of SACs in a few industrially important reactions, such as dehalogenation, CO oxidation, and hydrogenation. Metal ensemble catalysts (M n ), an extended concept to SACs, have emerged as a promising alternative to overcome such limitation. Inspired by the fact that the performance of fully isolated SACs can be enhanced by tailoring their coordination environment (CE), we here evaluate whether the CE of M n can also be manipulated in order to enhance their catalytic activity. We synthesized a set of Pd ensembles (Pd n ) on doped graphene supports (Pd n /X-graphene where X = O, S, B, and N). We found that introducing S and N onto oxidized graphene modifies the first shell of Pd n converting Pd–O to Pd–S and Pd–N, respectively. Also, we further found that the B dopant significantly affected the electronic structure of Pd n by serving as an electron donor in the second shell. We examined the performance of Pd n /X-graphene toward selective reductive catalysis, such as bromate reduction, brominated organic hydrogenation, and aqueous-phase CO 2 reduction. We observed that Pd n /N-graphene exhibited superior performance by lowering the activation energy of the rate-limiting step, i.e., H 2 dissociation into atomic hydrogen. The results collectively suggest controlling the CE of SACs in an ensemble configuration is a viable strategy to optimize and enhance their catalytic performance.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Optimizers for stabilizing likelihood-free inference

A growing number of applications in particle physics and beyond use neural networks as unbinned likelihood ratio estimators applied to real or simulated data. Precision requirements on the inference tasks demand a high-level of stability from these networks, which are affected by the stochastic nature of training. We show how physics concepts can be used to stabilize network training through a physics-inspired optimizer. In particular, the energy conserving descent (ECD) optimization framework uses classical Hamiltonian dynamics on the space of network parameters to reduce the dependence on the initial conditions while also stabilizing the result near the minimum of the loss function. We develop a version of this optimizer known as , which has few free hyperparameters with limited ranges guided by physical reasoning. We apply to representative likelihood-ratio estimation tasks in particle physics and find on average that it out-performs the widely used Adam optimizer. We expect that ECD will be a useful tool for wide array of data-limited problems, where it is computationally expensive to exhaustively optimize hyperparameters and mitigate fluctuations with ensembling.

Monte Carlo methods↗
DOE OSTI2025

A Semi-supervised Hybrid Machine Learning Framework for the Qualification of Resistance Spot Welds

• Industries requiring high structural integrity, including automotive, aerospace, and construction, place considerable significance on weld quality classification. • The inspection normally involves human expertise through predefined quality metrics that are subjective, error-prone, and time-intensive • The challenge to classification model development is the scarcity of labeled data and imbalanced distributions in the data that are labeled. • This work develops a new hybrid methodology that achieves clustering using KMeans++ together with supervised classification to overcome these challenges. • The ensemble-based classifiers were identified as optimal, with accuracy enhancements of up to 8% using the pseudo-labeled dataset. • The work provides practical insight into feature engineering and machine learning integration in industrial quality assurance applications.

Rogers, Jeremy K. [Savannah River National Laborat↗