Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Optimization and modeling”

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 1,549 records · Page 86
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach

Modeling dynamical systems is crucial for a wide range of tasks, but it remains challenging due to complex nonlinear dynamics, limited observations, or lack of prior knowledge. Recently, data-driven approaches such as Neural Ordinary Differential Equations (NODE) have shown promising results by leveraging the expressive power of neural networks to model unknown dynamics. However, these approaches often suffer from limited labeled training data, leading to poor generalization and suboptimal predictions. On the other hand, semi-supervised algorithms can utilize abundant unlabeled data and have demonstrated good performance in classification and regression tasks. We propose TS-NODE, the first semi-supervised approach to modeling dynamical systems with NODE. TS-NODE explores cheaply generated synthetic pseudo rollouts to broaden exploration in the state space and to tackle the challenges brought by lack of ground-truth system data under a teacher-student model. TS-NODE employs an unified optimization framework that corrects the teacher model based on the student's feedback while mitigating the potential false system dynamics present in pseudo rollouts. TS-NODE demonstrates significant performance improvements over a baseline Neural ODE model on multiple dynamical system modeling tasks.

Wang, Yu↗
DOE OSTI2026

A Comprehensive Comparative Study of Active Learning Schemes for Nanophotonics Design

We present a benchmarking study of active learning (AL) schemes for designing planar multilayer nanophotonic metamaterials, where the design tasks are formulated as binary optimization problems. Different surrogate models, including factorization machine (FM), Gaussian process regression (GPR), and convolutional neural network (CNN), combined with different optimization methods, including exhaustive enumeration, discrete particle swarm optimization (DPSO), quantum annealing (QA), hybrid QA, and simulated annealing are studied. The benchmark cases investigated range from small problems with short binary lengths (N = 25) to large problems with N up to 100, focusing on the design of two classes of photonic structures, including antireflective coatings for the long-wavelength infrared region and transparent radiative coolers. For small problems, CNN coupled with DPSO in AL achieves the best performance. As N increases, FM with QA outperforms GPR and CNN. For FM-based AL, hybrid QA yields the best optimization results, particularly in high-dimensional cases (N = 100). These results demonstrate that the optimization method can significantly affect in AL performance as N increases, and that QA-based optimization can provide practical routes for mitigating the optimization bottleneck in high-dimensional problems.

Jung, Serang [Kyung Hee University, Korea]↗
DOE OSTI2021

Development of Explainable, Knowledge-Guided AI Models to Enhance the E3SM Land Model Development and Uncertainty Quantification

Focal Area(s): (2)Predictive modeling using AI techniques and AI-derived model components; use of AI and other tools to design a prediction system comprising of a hierarchy of models. (3) Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge- guided AI. Science Challenge: The Energy Exascale Earth System Model (E3SM) is a fully coupled, state-of-the-science Earth system model that uses code optimized for DOE's advanced computers to address the most critical scientific questions facing our nation and society (Golaz et al., 2019). The E3SM Land model (ELM) is designed to understand how the changes in terrestrial land surfaces will interact with other Earth system components and has been used to understand hydrologic cycles, biogeophysics, and ecosystem dynamics. In spite of great successes, the ELM has several known issues that restrain rapid improvements. For example, the ELM uses equilibrium models to simulate dynamic land-climate interactions and it requires long model spin-up time to identify suitable initial conditions for transient simulations. The ELM lacks built-in uncertainty mechanisms that can improve the robustness of model predictions. The ELM is a holistic, deterministic model system with a rigid design, and in many situations, it is hard to modify the ELM system to incorporate new theory/hypothesis and new data across scales to address emerging science problems (such as predicting the impacts of water cycle extremes). In addition, The ELM is technically optimized for traditional CPU-centric computers and it cannot fully utilize the current and incoming leadership computers for model simulations and uncertainty quantification (UQ). The success of artificial intelligence (AI) has inspired scientists to use AI models to discover intrinsic features from simulation data (Chattopadhyay et al., 2020) and observational data (Reichstein et al., 2019) to gain further process understanding of Earth science problems. However, autonomous AI model training through deep learning usually requires a huge amount of annotated data. To overcome the limitations from the data and computing resources, knowledge-guided AI models are necessary where human-knowledge is ingested in model construction (Banino et al., 2018) and training process (Silver et al., 2016) for efficient learning. Herein, we present a new way that leverages the process understanding from the ELM to guide AI model development for the ELM enhancement and UQ. We hope this study can inspire further Earth and environmental system model developments and transformations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

With the sharp increasing volume of user data, Deep Learning Recommendation Model (DLRM) becomes an indispensable infrastructure in large technology companies. However, large-scale DLRM on the multi-GPU platform is still inefficient due to unbalanced workload partitioning and intensive inter-GPU communication. To this end, we propose OPER, an OPtimality guided Embedding table placement for large-scale Recommendation model training and inference. OPER explores the potential of mitigating remote memory access latency in DLRM through fine-grained embedding table placement. Specifically, OPER proposes a theoretical modeling that builds up the relationship between EMT placement and the embedding communication latency in both training and inference. OPER proves the NP hardness of finding the optimal embedding table placement and proposes a heuristic algorithm that yields near optimal placement. OPER implements a SHMEM-based embedding table training system and a unified embedding index mapping to support fine-grained embedding table sharding and placement. Comprehensive experiments reveal that OPER achieves on average 3.4× and 5.1× speedup on training and inference respectively over state-of-the-art DLRM frameworks.

Wang, Zheng↗
DOE OSTI2025

DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning

Machine learning models are increasingly applied across scientific disciplines, yet their effectiveness often hinges on heuristic decisions—such as data transformations, training strategies, and model architectures—that are not learned by the models themselves. Automating the selection of these heuristics and analyzing their sensitivity is crucial for building robust and efficient learning workflows. DeepHyper addresses this challenge by democratizing hyperparameter optimization, providing accessible tools to streamline and enhance machine learning workflows from a laptop to the largest supercomputer in the world. Building on top of hyperparameter optimization, it unlocks new capabilities around ensembles of models for improved accuracy and uncertainty quantification. All of these organized around efficient parallel computing.

ensemble↗
DOE OSTI2020

Error field correction strategies in preparation to MAST-U operation

In magnetic fusion devices, unwanted non-axisymmetric magnetic field perturbations, known as error fields (EF), can have detrimental effects on plasma stability and confinement. Such EFs may originate from several sources, such as axi-symmetric coil misalignments, coil feeds, 3D structures in the wall surrounding the plasma, presence of ferromagnetic materials near the plasma surface, blanket materials in future devices. To minimize their impact on plasma performance and on the available operational space, it is important to identify the EF sources and develop EF control strategies. MAST Upgrade (MAST-U) is a spherical tokamak which will operate in the near future after a series of enhancements from the previous MAST experiment. To deliver a machine with EF amplitude low enough to allow a high quality experimental programme, systematic analysis of the intrinsic EF sources has been carried out for poloidal eld (P) and divertor (D) coils. To deliver a machine with EF amplitude low enough to allow a high quality experimental programme, systematic analysis of the intrinsic EF sources has been carried out for poloidal field (P) and divertor (D) coils, whose magnetic eld measurements were available when writing this paper. Such measurements reveal that P and D coils are 3D deformed and thus are responsible for intrinsic EFs, with mainly n=1 and n=2 toroidal mode numbers. In preparation to MAST-U operation, both passive and active EF control strategies have been adopted for n=1 and n=2 EFs compensation. Passive EF control consisted of installing finely each D and P coil within MAST-U device so as to minimize the intrinsic n=1 EF amplitude. The optimal coil alignment has been determined based on magnetic eld measurements and the corresponding 3D electro-magnetic modelling, and envisaged coil shift and tilt of 3.2 mm and 0.7 mrad, respectively, in the case of P coil named P4. Conversely, active control will be use during MAST-U operation to reduce the n=2 EF which is associated mainly with P4 and P5, as well. Since these coils have been re-used from the MAST device, studies attempting n=2 EF control, based on MAST plasmas, have been modelled utilizing the MARS-F code to interpret experimental results in MAST and to give hints for future n=2 EF control studies in MAST-U. Here, a model-based control set for n=2 EF control has been identified which would allow for the minimization of rotation braking, of the resonant magnetic field at the q=2 and of the plasma displacement in MAST-U, simultaneously.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Airport Risk Assessment Model (ARAM)

The Airport Risk Assessment Model (ARAM) model automatically determines the optimal allocation of limited security resources to minimize total risk to the airport. At the same time, the model adds an element of randomness to the, reducing the predictability of asset schedules and further increasing countermeasure effectiveness.

Brigantic, Robert↗
DOE OSTI2023

Development of Building Design Optimization Methodology: Residential Building Applications

Building design optimization is a highly complex problem, requiring long computational running processes because of the many options that exist when a building is being designed. This paper introduces an integrated approach through which to perform this optimization within an acceptable time frame. The approach includes the methods of variable selection, model simplification, and a sequential optimization process. Using singular value decomposition, a large number of design variables is reduced to a smaller subset that can be solved more quickly through the optimization algorithm. To expedite the variable selection process, a modeling approach that quickly simulates annual energy consumption was developed to replace full annual energy simulations. The developed methodology was applied to two residential buildings in the US, and the results are discussed herein. To assess the accuracy of the integrated optimization methodology, the optimized life cycle costs are compaa variables demonstrating the strongest contributions in the optimization study were identified. The proposed methodology significantly shortened the time requirements for the optimization processes of the two case studies by 74% and 84%; the optimized life cycle costs were within 0.05% and 0.06%, respectively, of the optimum point.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Optimal experimental design for prediction based on push-forward probability measures

Incorporating experimental data is essential for increasing the credibility of simulation-aided decision making and design. This paper presents a method which uses a computational model to guide the optimal acquisition of experimental data to produce data-informed predictions of quantities of interest (QoI). Many strategies for optimal experimental design (OED) select data that maximize some utility that measures the reduction in uncertainty of uncertain model parameters, for example the expected information gain between prior and posterior distributions of these parameters. In this paper, we seek to maximize the expected information gained from the pushforward of an initial (prior) density to the push-forward of the updated (posterior) density through the parameter-to-prediction map. The formulation presented is based upon the solution of a specific class of stochastic inverse problems which seeks a probability density that is consistent with the model and the data in the sense that the push-forward of this density through the parameter-to-observable map matches a target density on the observable data. While this stochastic inverse problem forms the mathematical basis for our approach, we develop a one-step algorithm, focused on push-forward probability measures, that leverages inference-for-prediction to bypass constructing the solution to the stochastic inverse problem. A number of numerical results are presented to demonstrate the utility of this optimal experimental design for prediction and facilitate comparison of our approach with traditional OED.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Higher-order factorization machine for accurate surrogate modeling in material design

Efficient and robust optimization is important in material science for identifying optimal structural parameters and enhancing material performance. Surrogate-based active learning algorithms have recently gained great attention for their ability to efficiently navigate large, high-dimensional design spaces. Among surrogate models, 2 nd -order factorization machine (FM) models are widely employed as the surrogate model in active learning algorithms due to their balance between simplicity and effectiveness. However, their quadratic nature limits their capacity to capture complex, higher-order interactions among variables, often leading to suboptimal solutions. To overcome this limitation, we propose an active learning scheme integrating a 3 rd -order FM model, capable of modeling three-variable interactions and more intricate relationships in material systems. We comprehensively evaluate the surrogate modeling performance of the 3 rd -order FM case using various objective functions. Furthermore, we examine the optimization reliability and efficiency of the 3 rd -order FM-based active learning in a real-world material design task (e.g., nanophotonic structures for transparent radiative cooling). Our study shows that the 3 rd -order FM outperforms the 2 nd -order model in both surrogate accuracy and optimization performance, highlighting higher-order models’ promises for material design and optimization problems.

Factorization machine↗
DOE OSTI2022

Development of a Control Co-Design Modeling Tool for Marine Hydrokinetic Turbines: Preprint

This report describes the ongoing and planned development of the software package CT-Opt (Current/Tidal Optimization), a control co-design modeling tool for marine hydrokinetic turbines. The commercialization of these turbines has faced significant challenges due to the complex, multidisciplinary nature of their design and the extreme environmental conditions of their operation. This project aims to create a modeling tool that will enable the efficient design of robust, cost-competitive hydrokinetic turbine systems. Rather than using traditional optimization methods, CT-Opt combines multiple models across a range of fidelities to enable coupled optimization of the system design and system controller via a control co-design approach. With this method, the parameters that affect system performance are considered more comprehensively at every stage of the design process. The lowest-fidelity, frequency-domain model called by CT-Opt is RAFT (Response Amplitudes of Floating Turbines), which was originally developed by the National Renewable Energy Laboratory (NREL) to model response amplitudes of floating offshore wind turbines. The highest-fidelity, time-domain model is OpenFAST, which was developed by NREL for land-based and offshore wind turbines. As part of the CT-Opt project, new functionalities will be added to RAFT and OpenFAST to enable the accurate simulation of fixed and floating marine hydrokinetic turbines. In addition to expanding the capabilities of RAFT and OpenFAST, new midfidelity models will be developed. These models will be based on RAFT and OpenFAST and will consist of linearized, state-space models derived from the fully coupled, nonlinear OpenFAST equations and derivative function surrogate models that approximate the nonlinear system behavior. Each model will be coupled with controllers to allow control co-design methods to be applied both within models and across fidelity levels, enabling efficient system optimization.

control co-design↗
DOE OSTI2019

Review of Carbonaceous Annealing Effects on O 2 and CO 2 Coal Reactivity

Coal is, and will remain for the foreseeable future, a critical energy production resource. Advanced models of coal conversion behavior in air and oxy-coal environments enhance the boiler operational efficiency and design optimization. Although coal conversion models have continuously improved over decades of research, not all aspects of coal particle heating and conversion have received equal treatment. Coal particle annealing is one aspect of the coal conversion process that is simultaneously highly sensitive to the conversion environment, exceptionally impactful on coal chemistry, and frequently neglected in coal models. However, the current body of literature has explored numerous aspects of coal annealing and has shed much light on a complex subject. In conclusion, this review fulfills two purposes: (1) to highlight quantitative observations from the literature and (2) to compile and make conveniently available a clean collection of literature data to facilitate future annealing models.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2025

Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom

Energy-efficient ventilation control plays an important role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representations of indoor airflow, their high computational cost limits their use in real-time building control. In this work, we present a neural operator learning framework that combines the physical accuracy of CFD with the computational efficiency of machine learning to enable building ventilation control with the high-fidelity fluid dynamics models. Our method jointly optimizes the airflow supply rates and vent angles to reduce energy use and adhere to air quality constraints. We train an ensemble of neural operator transformer models to learn the mapping from building control actions to airflow fields using high-resolution CFD data. This learned neural operator is then embedded in an optimization-based control framework for building ventilation control. Experimental results show that our approach achieves significant energy savings compared to maximum airflow rate control, rule-based control, as well as data-driven control methods using spatially averaged CO 2 prediction and deep learning–based reduced-order models, while consistently maintaining safe indoor air quality. These results highlight the practicality and scalability of our method in maintaining energy efficiency and indoor air quality in real-world buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Techno-economic life cycle assessment of CO 2 -EOR operations towards net negative emissions at farnsworth field unit

Optimizations of CO 2 Water Alternating Gas(WAG)- systems with multi-objectives of incremental recovery and maximization of CO 2 storage are challenging. Here, the incorporation of a total Greenhouse gas (GHG) life cycle assessment is mostly ignored leading to inaccurate estimation of overall net carbon emissions of their operations. In this study, the effect of a total GHG life cycle assessment on a multi-objective CO 2 -WAG optimization with integrated techno-economic assessment (TEA) which factors carbon tax credit is conducted. A life cycle assessment (LCA) was conducted utilizing a 20 -year optimized post history matched data from a high fidelity reservoir simulation model. Using data generated from the optimum result, a techno-economic life cycle analysis was further conducted. The first scenario classified as the base model had an estimated 81% of purchased CO 2 sequestered. The results through a comprehensive techno-economic LCA model yielded a net estimate of 73% of purchased CO 2 . The optimized forecasted model which considered key operational and reservoir factors such as WAG ratio, injection rates and periods, and well specification resulted in an improved sequestration of 92% of purchased CO 2 . However, this also dropped to 84% after taking it through LCA. These results clearly indicate a significant amount of net CO 2 is not accounted for when operations are not analyzed through LCA. From the LCA, direct flaring volumes of CO 2 , energy consumption and efficiency of unit equipment were noticed to be the major causes of these reductions. Considering ten main sources of energy as source of energy generation, a comparative techno-eco LCA was conducted. The results confirmed a lower net volume and NPV for energy sources with higher carbon footprints and vice versa. Thus, a total LCA of CO 2 -WAG greatly influences net storage factor of purchased CO 2 and hence project NPV where tax credit/incentives per ton of CO 2 sequestered is considered. Although operational conditions are optimized for best results, there are significant factors that leads to minimization of net storage factor. This study therefore provides an insightful information for optimizing CO 2 -WAG multi-objectives to achieve minimum GHG emission.

02 PETROLEUM↗
DOE OSTI2021

A forecast-driven decision-making model for long-term operation of a hydro-wind-photovoltaic hybrid system

Hydro-wind-photovoltaic (PV) hybrid system has the potential to increase the integration of renewable energy sources into an existing grid. For the long-term operation of the system, due to the non-storable nature of wind and PV power, it is essentially to decide the optimal long-term carryover storage of cascade reservoirs. However, it remains a challenge due to high uncertainties of long-term forecasts and complicated hydraulic/electrical relationships between cascade reservoirs. Here in this study, a forecast-driven decision-making model is proposed for the hybrid system, which converts the multi-stage long-term operation process into a two-stage operation problem (including current stage and carryover stage) to avoid using longer-horizon forecast information with lower accuracy. First, the carryover stage energy surfaces (CESs) considering the forecast uncertainties of wind, solar and hydro resources are proposed to characterize carryover stage benefit quantitatively. Then a CESs-based forward decision-making optimization model is developed to guide the long-term operation of a hydro-wind-photovoltaic hybrid system. The applications in a hydro-wind-PV hybrid system of Yalong River basin results show that: compared with conventional operation, 1) power generation increases 9.03%; 2) in terms of the carryover storages control, the reservoir impounding and drawdown timing are delayed, and the drawdown depth is increased, which can be used to formulate better reservoir operation rules.

13 HYDRO ENERGY↗
DOE OSTI2020

Quantum Chemistry-Informed Active Learning to Accelerate the Design and Discovery of Sustainable Energy Storage Materials

Here we employed Density Functional Theory (DFT) to compute oxidation potentials of 1,400 homobenzylic ether molecules to search for the ideal sustainable redoxmer design. The generated data were used to construct an active learning model based on Bayesian optimization (BO) that targets candidates with desired oxidation potentials utilizing only a minimal number of DFT calculations. The active learning model demonstrated not only significant efficiency improvement over the random selection approach but also robust capability in identifying desired candidates in an untested set of 112,000 homobenzylic ether molecules. Our findings highlight the efficacy of quantum chemistry-informed active learning to accelerate the discovery of materials with desired properties from a vast chemical space.

25 ENERGY STORAGE↗
DOE OSTI2024

Wind Turbine Design Optimization for Hydrogen Production

To help meet the need for inexpensive green fuels, we are working on wind turbine design optimization specifically for hydrogen production. We have thus far achieved a 1.53% decrease in LCOH as compared to a turbine optimized for LCOE using the same code, design variables, and models. We accomplished this by optimizing some components of the wind turbine tower, rotor, and drivetrain design with hydrogen production and costs in the design loop.

hydrogen↗
DOE OSTI2022

FutureTense

Protective vaccines and reliable diagnostics are essential tools for controlling viral diseases. However, the efficacy of these tools can be diminished by mutations in viral genomes. The delay between the emergence of new viral strains and the redesign of vaccines and diagnostics allows for continued viral transmission. Is it possible to address this challenge by computationally predicting viral genome sequence evolution? Can we “future-proof” vaccines and diagnostics by targeting both current and anticipated future sequence variants? While predicting viral evolution is still an unsolved, “grand challenge” problem in biology, the large, and rapidly growing, number of SARS-CoV-2 genome sequences provide an opportunity to quantify the ability of machine learning to predict viral genome sequence evolution. Towards this end, we have developed a simple computational model for predicting viral evolution at the level of individual nucleotides. The key metric for quantifying the per-base, prediction accuracy for viral evolution is the Mann-Whitney U statistic (or, equivalently, the area under the receiver operator curve). Since the Mann-Whitney U statistic is not a differentiable function, existing deep leaning packages (like Pytorch and Keras/TensorFlow) are not useful, as they require that the accuracy metric/objective function be analytically differentiable with respect to the model parameters. To overcome this challenge, we have implemented custom software, “FutureTense”, that can train a machine learning model by maximizing the non-differentiable Mann-Whitney U statistic. This software trains a machine learning model by exploring along the direction of the discrete gradient of the Mann-Whitney U statistic in the model parameter space. Parallel computing and genome sequence-specific optimizations are used to accelerate model training. The resulting machine learning model learns the observed high C->U mutation rates in the SARS-CoV-2 genome (which are potentially induced by host defenses) and provides prediction accuracies that are significantly better than one would expect from random chance. While predicting viral evolution is still quite far from a solved problem, the surprising performance of this simple model gives hope that the accuracy of predicting viral genome evolution can be further increased by more sophisticated approaches.

Gans, Jason↗