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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,495 records · Page 83

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Overcoming sparse datasets with multi-task learning as applied to high entropy alloys

Abstract The design of novel High Entropy Alloys for use in high-temperature applications is an area of active interest due to their potential to provide exceptional properties compared to conventional alloys. Since the increased popularity of machine learning, an important cog in the design process has been training surrogate models on alloy properties. However, these Single-Task models are trained on individual mechanical properties and do not take advantage of the relatedness between properties. Multi-Task models can capture the interdependencies between tasks, leading to potentially more accurate predictions for all tasks. In this paper, we investigate if Multi-Task models can show improvement over Single-Task models when used for predicting the mechanical properties of these alloys. To ensure fair evaluation between the models, we apply L 0 regularization and skip connections to the models, which allows them to adjust the number of model parameters and depth for optimal performance. We find that the Multi-Task models can leverage task relationships to perform better than Single-Task models, especially for high amounts of missing data in the tasks. Furthermore, adding simple auxiliary targets can boost Multi-Task performance even further despite not being effective as input descriptors to single-task models themselves. We anticipate that the proposed strategies can achieve more accurate predictions and consequently enable better design capabilities for such data-constrained domains without incurring much additional computational cost.

Debnath, Arindam (ORCID:0000000194274499)↗

DOE OSTI2024

Western Interconnection Baseline Study

The purpose of the baseline study is to evaluate the degree to which current industry planning processes meet the national 2035 decarbonization goals for the Western Interconnection. This analysis serves as a comparative baseline for the scenario analysis conducted in the NTP Study using a Western Interconnection dataset that is readily available to industry. This baseline analysis differs from the production cost modeling analysis and power flow analysis in the main NTP Study report (forthcoming). In particular, the analysis presented in this report reflects a business-as-usual future with an optimistic build out of specific planned transmission projects and foreseeable generation. In contrast, the NTP Study models a future generation and transmission expansion based on optimization from a capacity expansion model. The analysis presented herein also reflects a 2030 timeframe, whereas the main NTP Study production cost modeling analysis and power flow analysis reflect a 2035 time frame. This baseline analysis utilizes industry’s most reliable data to account for future transmission projects across various stages of development, with a particular focus on those in the permitting stage. Additionally, it incorporates projections for changes in generation capacity (both additions and retirements). This baseline analysis outlines a probable trajectory, given current process and practice, for the future of the bulk power system with a horizon extending to 2030.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2021

Projecting the number of new HIV infections to formulate the "Getting to Zero" strategy in Illinois, USA

Objectives: Getting to Zero (GTZ) initiatives focus on expanding use of antiretroviral treatment (ART) and pre-exposure prophylaxis (PrEP) to eliminate new HIV infections. Computational models help inform policies for implementation of ART and PrEP continuums. Such models, however, vary in their design, and may yield inconsistent predictions. Using multiple approaches can help assess the consistency in results obtained from varied modeling frameworks, and can inform optimal implementation strategies. Methods: A study using three different modeling approaches is conducted. Two approaches use statistical time series analysis techniques that incorporate temporal HIV incidence data. A third approach uses stochastic stimulation, conducted using an agent-based network model (ABNM). All three approaches are used to project HIV incidence among a key population, young Black MSM (YBMSM), over the course of the GTZ implementation period (2016-2030). Results: All three approaches suggest that simultaneously increasing PrEP and ART uptake is likely to be more effective than increasing only one, but increasing ART and PrEP by 20% points may not eliminate new HIV infections among YBMSM. The results further suggest that a 20% increase in ART is likely to be more effective than a 20% increase in PrEP. All three methods consistently project that increasing ART and PrEP by 30% simultaneously can help reach GTZ goals. Conclusions: Increasing PrEP and ART uptake by about 30% might be necessary to accomplish GTZ goals. Such scale-up may require addressing psychosocial and structural barriers to engagement in HIV and PrEP care continuums. ABNMs and other flexible modeling approaches can be extended to examine specific interventions that address these barriers and may provide important data to guide the successful intervention implementation.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

CIGS Technology Advancement via Fundamental Modeling of Defect/Impurity Interactions (Final Technical Report)

The primary goals of the proposed work were to provide modeling tools (and the associated insight which comes along with model development) for design and optimization of CuIn x Ga 1-x Se 2 (CIGS) and CdSeTe (CST) solar cell manufacturing processes and to establish the foundation for comprehensive end-to-end predictive modeling tools to enable optimization of thin film photovoltaic technology for performance, cost, yield, and reliability. The initial focus of efforts within this project was to develop coupled process/optical/device models for CIGS PV technology and to work with Siva Power to apply that TCAD (technology computer-aided design) system to improve the efficiency and reduce manufacturing costs for CIGS solar cells. Our approach to that end was to generate an extensive database of DFT calculations and to use those calculations via statistical thermodynamics methods and Monte Carlo simulation to develop and characterize models for the behavior of native defects as well as intentional and unintentional impurities, including the redistribution of the primary components of CIGS films. Increased effort went toward coupling those models for defect behavior and composition evolution to the performance of multicrystalline CIGS solar cells via prediction of doping level and recombination lifetime as function of manufacturing process. In the second budget period, the project pivoted to developing a similar system for the CdSeTe system, focused especially on understanding the role of Se/Te alloy concentration. Execution of the project resulted in the successful development of TCAD systems for both CIGS and CdSeTe thin film PV within the Synopsys Sentaurus framework by utilizing the Alagator interface. In the first budget period of the project, we developed quantitative models for the major components of CIGS PV and implemented them within a framework that couples process, optical, and device simulation. From the insights we have gained, we identified novel opportunities for enhancing CIGS solar cell performance and have laid the groundwork to further optimize the layer structure, composition profile, and thermal cycles for substantially improved efficiency and lower manufacturing costs. For the CIGS system, process changes to achieve greater than 1% absolute enhancement in efficiency were identified, but testing of those approaches was stymied by lack of a domestic CIGS manufacturing partner after the closure of Siva Power as well as Miasole. For CdSeTe, a fully capable TCAD system only became ready to apply near the end of the project period, so substantial opportunities remain to apply those models to enhance the leading thin film PV technology.

14 SOLAR ENERGY↗

DOE OSTI2022

Distributed Training and Optimization of Neural Networks

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large requirements on computing resource and turn around time, even more so when hyperparameter optimization is done (e.g. search over model architectures). While this is a challenge that goes beyond particle physics, we review the various ways to do the necessary computations in parallel, and put it in the context of high-energy physics.

Vlimant, Jean-Roch↗

DOE OSTI2022

Calibrating uncertain parameters in melt pool simulations of additive manufacturing

Melt pool scale numerical modeling of additive manufacturing (AM) processes can provide predictive capabilities and theoretical insight into the process-property-structure-performance relationships for AM parts. Despite capabilities of numerical models to solve complex multi-physics problems, it is often important to consider a tradeoff between detailed physics and computational cost. Therefore, sources of uncertainty in both experimental conditions and the parameters needed for modeling require models to be validated against empirical evidence. Here, a method is proposed to calibrate uncertain parameters used in continuum-scale melt pool models for powder bed fusion (PBF) AM. Both a simplified heat transfer model and a heat transfer and fluid flow model were investigated. A surrogate model and Markov chain-based optimization algorithm calibrated melt pool geometry for models within experimental variation of the target melt pool width and depth from the NIST AM-Bench 2018-02 dataset. The melt pool temperature distributions, solidification parameters, and simulated multi-layer solidification microstructures were compared between the two models. Similar results from both models indicate that calibrated, lower fidelity numerical models may be used in place of higher fidelity models to generate melt pool solidification data. Finally, these calibrated models therefore enable lower computational cost melt pool simulations without a noticeable decrease in simulation accuracy for grain-scale microstructure simulations.

36 MATERIALS SCIENCE↗

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 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↗