SEARCH · Search NASA

Results for “machine learning 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.

SourceResearch connectionFrom yearThrough year

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

At least 523 records · Page 29

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Explosively driven Richtmyer–Meshkov instability jet suppression and enhancement via coupling machine learning and additive manufacturing

The ability to control the behavior of fluid instabilities at material interfaces, such as the shock-driven Richtmyer–Meshkov instability, is a grand technological challenge with a broad number of applications ranging from inertial confinement fusion experiments to explosively driven shaped charges. In this work, we use a linear-geometry shaped charge as a means of studying methods for controlling material jetting that results from the Richtmyer–Meshkov instability. A shaped charge produces a high-velocity jet by focusing the energy from the detonation of high explosives. The interaction of the resulting detonation wave with a hollowed cavity lined with a thin metal layer produces the unstable jetting effect. By modifying the characteristics of the detonation wave prior to striking the lined cavity, the kinetic energy of the jet can be enhanced or reduced. Modifying the geometry of the liner material can also be used to alter jetting properties. We apply optimization methods to investigate several design parameterizations for both enhancing or suppressing the shaped-charge jet. This is accomplished using 2D and 3D hydrodynamic simulations to investigate the design space that we consider. We also apply new additive manufacturing methods for producing the shaped-charge assemblies, which allow for the experimental testing of complicated design geometries obtained through computational optimization. We present a direct comparison of our optimized designs with experimental results carried out at the High Explosives Application Facility at Lawrence Livermore National Laboratory.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Machine learning prediction of enzyme optimum pH

The relationship between pH and enzyme catalytic activity, especially the optimal pH (pH opt ) at which enzymes function, is critical for biotechnological applications. Hence, computational methods to predict pH opt will enhance enzyme discovery and design by facilitating accurate identification of enzymes that function optimally at specific pH levels, and by elucidating sequence-function relationships. Here, in this study, we proposed and evaluated various machine learning methods for predicting pH opt , conducting extensive hyperparameter optimization and training over 11,000 model instances. Our results demonstrate that models utilizing language model embeddings markedly outperform other methods in predicting pHopt. We present EpHod, the best-performing model, to predict pHopt, making it publicly available to researchers. From sequence data, EpHod directly learns structural and biophysical features that relate to pH opt , including proximity of residues to the catalytic centre and the accessibility of solvent molecules. Overall, EpHod presents a promising advancement in pH opt prediction and will potentially speed up the development of enzyme technologies.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Calibration of the 2-Phase Bubble Tracking Model for Liquid Mercury Target Simulation with Machine Learning Surrogate Models

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory is one of the most powerful accelerator-driven neutron sources in the world. The intense protons strike on SNS's mercury target to provide bright neutron beams, which also leads to severe fluid-structure interactions inside the target. Prediction of resultant loading on the target is difficult particularly when helium gas is injected into mercury to reduce the loading and mitigate the pitting damage on vessel walls. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this multi-physics problem. However, several uncertain parameters in the R-P model require intensive simulations to determine their optimal values. With the help of machine learning and the measured target strain, we have studied the major uncertain parameters in this R-P model and developed a framework to identify optimal parameters that significantly reduce the discrepancy between simulations and experimental strains. The preliminary results show the possibility of using this mercury/helium mixture and surrogate models to predict a better match of target strain response when the helium gas is injected.

Lin, Lianshan↗

DOE OSTI2026

Search for single production of a vector-like T quark decaying to a top quark and a neutral scalar boson in the lepton+jets final state in proton-proton collisions at $\sqrt{s}=13$ TeV

A search for single production of a vector-like T quark with charge 2e/3, decaying to a top quark and a neutral scalar boson is presented. The boson can be a standard model Higgs boson (H) or a new scalar boson (ϕ). In the first case, a branching fraction of 25% is assumed for the decay T → tH, while in the second case the T quark is assumed to decay exclusively to tϕ. The top quark is identified via its lepton+jets decay, and the neutral boson via its decay into a bottom quark-antiquark pair. Final states with Lorentz-boosted topologies are considered and machine-learning techniques are exploited for optimal event classification. The analysis uses data collected by the CMS experiment in proton-proton collisions at a center-of-mass energy of 13 TeV, corresponding to an integrated luminosity of 138 fb −1 recorded at the CERN LHC in 2016–2018. Upper limits at 95% confidence level are set on the product of cross section and branching fraction for a T quark in a narrow-width approximation. They vary between 14.7 and 0.1 fb, for T quark masses in the range 1.3–3.0 TeV and ϕ boson masses in the range 25–250 GeV. These are the first exclusion limits set on the production of a single T quark decaying into a top quark and a new neutral scalar boson. For the decay channel into a top quark and a standard model Higgs boson, the results provide the best limits on production cross sections to date, for T quark masses above 2 TeV.

hadron-hadron scattering↗

DOE OSTI2023

Systematically derived thermodynamic properties for alkane oxidation

Key combustion properties, such as ignition delay time, show strong sensitivity to the thermochemistry of the main species in the standard radical oxidation pathway at low temperatures (600-1000K). Significant uncertainties persist in current estimates of thermodynamic properties, particularly for the larger species of relevance to common practical fuels. In this article, we use advanced computational schemes to evaluate thermodynamic properties for the fuel, fuel radical, peroxy, hydroperoxy-alkyl radical, and hydroperoxide species for a set of 17 fuels containing up to 9 carbon atoms, and with various degrees of branching in the alkane backbone. The procedure, termed STAR-1D, combines conformer sampling to find the minimum geometry, B2PLYP-D3/cc-pVTZ harmonic frequency evaluations, and omega B97X-D/cc-pVTZ one-dimensional torsional mapping. It includes two physically-based scaling routines: a frequency-dependent scaling to B2PLYP-D3/cc-pVTZ anharmonic frequencies and a scaling of one-dimensional omega B97X-D/ccpVTZ torsional profiles to reproduce the product of the B2PLYP-D3/cc-pVTZ frequencies in the harmonic limit. Substantive comparisons with existing experimental databases, together with careful examinations of key theoretical assumptions, are used to explore the accuracy of the predictions. These computationally intensive explorations of 195 species were facilitated by automated thermochemistry software. Further, high accuracy 0 K heats of formation from a separate study are used with the STAR-1D computations to generate NASA polynomial representations. In addition to their intrinsic value, the present results also provide a reliable database for the optimization of group additivity or machine learning schemes for scaling to larger combustion systems. Towards this end a complementary extensive conformational analysis is carried out for the medium sized species and the thermodynamic properties of the lowest energy hydrogen-bonded and non-hydrogen bonded conformers are contrasted for larger hydroperoxy-alkyl radical species.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Revisiting point defect thermodynamics in group IVB and VB transition metal carbides

We present a comprehensive re-examination of point defect thermodynamics in group IVB and VB transition metal carbides (TMCs) with the rocksalt structure using a combination of density functional theory (DFT) calculations and a statistical mechanical Wagner-Schottky model within the canonical ensemble. The most stable configurations of point defects were discovered using basin-hopping global optimization, driven by either a machine learning interatomic potential (MLIP) or DFT. A key finding is the identification of previously unreported dicarbon antisites—a C–C dimer occupying a metal site—as the structural (constitutional) defects on the carbon-rich side of stoichiometry in all group IVB and VB TMCs except TaC. Furthermore, dicarbon antisite-containing thermal defect complexes, such as quadruple and interbranch defects, can dominate in TMCs under specific stoichiometric and temperature conditions. In conclusion, by incorporating dicarbon antisites into the defect landscape, this work provides a revised understanding of the thermodynamics of point defects in TMCs.

Carbides↗

DOE OSTI2022

Using genetic algorithms to systematically improve the synthesis conditions of Al-PMOF

The synthesis of metal-organic frameworks (MOFs) is often complex and the desired structure is not always obtained. In this work, we report a methodology that uses a joint machine learning and experimental approach to optimize the synthesis conditions of Al-PMOF (Al 2 (OH) 2 TCPP) [H 2 TCPP = meso-tetra(4-carboxyphenyl)porphine], a promising material for carbon capture applications. Al-PMOF was previously synthesized using a hydrothermal reaction, which gave a low throughput yield due to its relatively long reaction time (16 hours). Here, we use a genetic algorithm to carry out a systematic search for the optimal synthesis conditions and a microwave-based high-throughput robotic platform for the syntheses. We show that, in just two generations, we could obtain excellent crystallinity and yield close to 80% in a much shorter reaction time (50 minutes). Moreover, by analyzing the failed and partially successful experiments, we could identify the most important experimental variables that determine the crystallinity and yield.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Global minimization via classical tunneling assisted by collective force field formation

Simple elements interacting in networks can give rise to intricate emergent behaviors. Examples such as synchronization and phase transitions often apply in many contexts, as many different systems may reduce to the same effective model. Here, we demonstrate such a behavior in a model inspired by memristors. When weakly driven, the system is described by movement in an effective potential, but when strongly driven, instabilities cause escapes from local minima, which can be interpreted as an unstable tunneling mechanism. We dub this collective and nonperturbative effect a “Lyapunov force,” which steers the system toward the global minimum of the potential function, even if the full system has a constellation of equilibrium points growing exponentially with the system size. This mechanism is appealing for its physical relevance in nanoscale physics and for its possible applications in optimization, Monte Carlo schemes, and machine learning.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

OPFLearn.jl [SWR-21-109]

OPFLearn.jl is a Julia package for creating datasets for machine learning approaches to solving AC optimal power flow (AC OPF). It was developed to provide researchers with a standardized way to efficiently create AC OPF datasets that are representative of more of the AC OPF feasible load space compared to typical dataset creation methods. The OPFLearn dataset creation method uses a relaxed AC OPF formulation to reduce the volume of the unclassified input space throughout the dataset creation process. Over time this input space tightens around the relaxed AC OPF feasible region to increase the percentage of feasible load profiles found while uniformly sampling the input space. Load samples are processed using AC OPF formulations from PowerModels.jl. More information on the dataset creation method can be found in our publication, "OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets". To use OPFLearn.jl a PowerModels network data dictionary is required (can be loaded from Matpower ".m" files) to define the network the dataset is being created for.

Joswig-Jones, Trager↗

DOE OSTI2023

Spectral Peak Enhancement by Combining Trusted Response Elements via Machine Learning (SPECTRE-ML) v0.8.0

SPECTRE-ML (Spectral Peak Enhancement by Combining Trusted Response Elements via Machine Learning) is a machine learning based program for finding optimal clusters of radiation detector segments (i.e., pixels or voxels) in order to improve spectral performance. It provides facilities for pre-processing and analyzing training datasets, running ML algorithms, and evaluating and visualizing outputs. SPECTRE-ML outperforms simpler ad-hoc segmentation methods such as uniform depth clusters, learning detector performance trends such as dead layers, edge effects, and gain shifts. Although extensible to arbitrary highly-segmented spectroscopic radiation detectors, SPECTRE-ML currently focuses on improving spectral performance in highly-segmented CdZnTe (CZT) detectors for International Atomic Energy Agency (IAEA) non-destructive assay (NDA) safeguards tasks.

Vavrek, Jayson↗

DOE OSTI2025

Towards a Robust Adaptive Digital Twin for Fusion Applications

The development of a digital twin system for fusion applications is essential for enhancing the prediction, analysis, and optimization of complex plasma processes. Machine learning (ML), particularly deep learning has demonstrated strong capabilities in modeling such highly nonlinear and intricate systems. However, two critical challenges limit the deployment of deep learning-based digital twins: Uncertainty Quantification (UQ) and data drift. UQ is vital for ensuring trustworthy predictions, especially in decision-support scenarios. Additionally, data-driven models are often sensitive to changes in the underlying data distribution, such as shot-to-shot variations in fusion experiments, which can lead to performance degradation over time. To address these challenges, we are developing an uncertainty-aware, adaptive digital twin framework. Our approach incorporates deep learning models enhanced with Gaussian Process approximations for predictive uncertainty estimation, coupled with an online learning mechanism that enables continuous model adaptation to new experimental data. This adaptive capability allows the data driven models to respond effectively to evolving plasma behaviors and equipment conditions. Specifically, to mitigate the effects of shot-to-shot drift, our system updates itself incrementally as new data becomes available, improving both robustness and fidelity. Our vision is to evolve this data driven model into a self-sustaining digital twin system that leverages UQ based feedback to continuously refine itself and potentially support real-time decision making. This presentation will cover a brief background on uncertainty quantification for ML, our ongoing effort on development of UQ capabilities for ML, our data science pipeline from data collection to model development and analysis and online learning framework for modeling coil deflection at DIII-D. I will also briefly touch upon opportunities and challenges in development of digital twin framework.

Sammuli, Brian [General Atomics]↗

DOE OSTI2023

Automated Quantification of Wind Turbine Blade Leading Edge Erosion from Field Images

Wind turbine blade leading edge erosion is a major source of power production loss and early detection benefits optimization of repair strategies. Two machine learning (ML) models are developed and evaluated for automated quantification of the areal extent, morphology and nature (deep, shallow) of damage from field images. The supervised ML model employs convolutional neural networks (CNN) and learns features (specific types of damage) present in an annotated set of training images. The unsupervised approach aggregates pixel intensity thresholding with calculation of pixel-by-pixel shadow ratio (PTS) to independently identify features within images. The models are developed and tested using a dataset of 140 field images. The images sample across a range of blade orientation, aspect ratio, lighting and resolution. Each model (CNN v PTS) is applied to quantify the percent area of the visible blade that is damaged and classifies the damage into deep or shallow using only the images as input. Both models successfully identify approximately 65% of total damage area in the independent images, and both perform better at quantifying deep damage. The CNN is more successful at identifying shallow damage and exhibits better performance when applied to the images after they are preprocessed to a common blade orientation.

Aird, Jeanie A.↗

NASA NTRS2023

NASA’s Digital Information Platform to Accelerate the Transformation of the National Airspace System

In order to accelerate the digital transformation of airspace operations, a foundational framework and infrastructure for providing sustainable, data-driven, and cohesive decision-making digital services for both traditional and emergent air vehicles is being developed. The reference implementation of Digital Information Platform builds an ecosystem for the aviation community by providing access to a secure and trusted source of aviation data and services. Several key features and services have been implemented to enable secure data sharing, communication, and service registration on the Platform. The technical approach used to implement these features is presented here. NASA-developed integrated aviation data and machine learning based prediction services to optimize airspace operations are available on the Platform. These services are being evaluated in an operational environment by flight operators and the real-world benefits are being captured. The Platform fosters collaboration among industry and researchers to develop complex aviation services and the aim is to make it publicly accessible for consumption by the aviation community.

Digital Transformation↗

NASA NTRSDate not supplied

NASA’s Digital Information Platform to Accelerate the Transformation of the National Airspace System

Digital Transformation↗

DOE OSTI2020

Topological Regularization via Persistence-Sensitive Optimization

Optimization, a key tool in machine learning and statistics, relies on regularization to reduce overfitting. Traditional regularization methods control a norm of the solution to ensure its smoothness. Recently, topological methods have emerged as a way to provide a more precise and expressive control over the solution, relying on persistent homology to quantify and reduce its roughness. All such existing techniques back-propagate gradients through the persistence diagram, which is a summary of the topological features of a function. Their downside is that they provide information only at the critical points of the function. We propose a method that instead builds on persistence-sensitive simplification and translates the required changes to the persistence diagram into changes on large subsets of the domain, including both critical and regular points. This approach enables a faster and more precise topological regularization, the benefits of which we illustrate with experimental evidence.

Nigmetov, Arnur↗

DOE OSTI2021

OPFLearn.jl v0.1.2 5/18/2023 [SWR-21-109]

Joswig-Jones, Trager↗

NASA NTRSDate not supplied

Optimization-Based Parametric Design via High-Fidelity Simulation: Overview + Examples

Design-Build-Test approaches for developing spaceflight hardware are prohibitively time and cost intensive and often lead to suboptimal mechanism designs. Approaches that couple machine learning and high-fidelity physics simulation could eliminate the need for hardware prototyping and dramatically accelerate the engineering design cycle, ultimately reducing cost. This talk presents a modular NASA-developed toolchain to optimize hardware mechanisms in a virtual environment using numerical optimization and multi-body physics simulation and includes example applications related to rigid wheel design for autonomous rovers and computational fluid dynamics.

optimization↗

DOE OSTI2021

Can Simple Machine Learning Tools Extend and Improve Temperature-Based Methods to Infer Streambed Flux?

Temperature-based methods have been developed to infer 1D vertical exchange flux between a stream and the subsurface. Current analyses rely on fitting physically based analytical and numerical models to temperature time series measured at multiple depths to infer daily average flux. These methods have seen wide use in hydrologic science despite strong simplifying assumptions including a lack of consideration of model structural error or the impacts of multidimensional flow or the impacts of transient streambed hydraulic properties. We performed a “perfect-model experiment” investigation to examine whether regression trees, with and without gradient boosting, can extract sufficient information from model-generated subsurface temperature time series, with and without added measurement error, to infer the corresponding exchange flux time series at the streambed surface. Using model-generated, synthetic data allowed us to assess the basic limitations to the use of machine learning; further examination of real data is only warranted if the method can be shown to perform well under these ideal conditions. We also examined whether the inherent feature importance analyses of tree-based machine learning methods can be used to optimize monitoring networks for exchange flux inference.

54 ENVIRONMENTAL SCIENCES↗