Search NASA⌕ Search

SEARCH · Search NASA

Results for “parameter tuning”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Enhanced climate reproducibility testing with false discovery rate correction

Simulating the Earth's climate is an important and complex problem, thus climate models are similarly complex, comprised of millions of lines of code. In order to appropriately utilize the latest computational and software infrastructure advancements in Earth system models running on modern hybrid computing architectures to improve their performance, precision, accuracy, or all three; it is important to ensure that model simulations are repeatable and robust. This introduces the need for establishing statistical or non-bit-for-bit reproducibility, since bit-for-bit reproducibility may not always be achievable. Here, we propose a short-simulation ensemble-based test for an atmosphere model to evaluate the null hypothesis that modified model results are statistically equivalent to that of the original model. We implement this test in version 2 of the US Department of Energy's Energy Exascale Earth System Model (E3SM). The test evaluates a standard set of output variables across the two simulation ensembles and uses a false discovery rate correction to account for multiple testing. The false positive rates of the test are examined using re-sampling techniques on large simulation ensembles and are found to be lower than the currently implemented bootstrapping-based testing approach in E3SM. We also evaluate the statistical power of the test using perturbed simulation ensemble suites, each with a progressively larger magnitude of change to a tuning parameter. The new test is generally found to exhibit more statistical power than the current approach, being able to detect smaller changes in parameter values with higher confidence.

Kelleher, Michael E. [Oak Ridge National Laborator↗
DOE OSTI2025

Rare Lepton Decays and Differentiable Hadronization Models - From Signatures of New Physics to Data-driven Event Generation

This dissertation is partitioned into two parts: phenomenological studies focused on rare lepton decays as probes of heavy and light new physics, and the development of differentiable, data-driven hadronization models. Part I develops the phenomenology of new physics signatures stemming from rare charged lepton flavor violating decays probed by experiments at the intensity frontier. These include interactions mediated by both high-scale effective operators and light new physics, manifesting in multi-lepton final states ($\mu \to 5e$), elastic nuclear transitions ($\mu \to e$ conversion), baryon-number-violating muon capture, and time-dependent signals from ultralight dark matter ($\mu \to e \phi, \tau \to \ell \phi$). Part II develops two distinct strategies for advancing differentiable and data-driven hadronization models. One involves comprehensive reweighting frameworks for hadronization that enable efficient uncertainty estimation, facilitate parameter tuning, and interface naturally with differentiable programming paradigms. The other introduces machine-learning-based methods for extracting microscopic fragmentation dynamics directly from macroscopic observables through the deformation of existing models -- effectively providing solutions to the inverse problem of hadronization. Altogether, these studies advance the interpretability, flexibility, and precision of theoretical predictions for both high-intensity and high-energy experiments.

Menzo, Tony [Cincinnati U.] (ORCID:000000022013457↗
DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗
DOE OSTI2026

Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models

We study concept-level forgetting in pretrained vision models: removing an entire semantic category so the system no longer recognizes that object in unseen images and contexts, rather than merely forgetting specific training examples. Prior work either applies blunt global projections or fine-tunes parameters, which can introduce collateral damage to unrelated features, add compute, and become unstable as forgetting strength increases. We introduce Contrastive Subnet Erasure (CSE), a training-free, encoder-centric edit that targets a compact set of channels most responsible for the class and attenuates them in a calibrated manner. The modification is algebraically folded into the subsequent layer, yielding no inference-time overhead and leaving task heads unchanged. To evaluate whether forgetting generalizes beyond the data used to specify the class, we introduce a cross dataset protocol in which the class is defined on a source dataset and performance is measured on a disjoint target dataset drawn from a different distribution with no shared images. This setup tests whether the model still fails to recognize the object when it looks different or appears in new scenes, and it helps avoid overfitting to patterns in the source dataset. Across CIFAR 10, CIFAR 100, and ImageNet under this protocol, CSE achieves stronger forgetting of the target class while better preserving non target utility than existing baselines in both single class and multi class settings. Overall, CSE provides a simple, stable, and deployment-ready mechanism for class-level unlearning in vision.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2026

Active Learning‐Driven Inkless Additive Nanomanufacturing for Printed Electronics

Inkless additive nanomanufacturing for printed electronics promises broad material and substrate versatility, yet the high-dimensional print parameter space makes tuning print parameters time-intensive. We present a Bayesian optimization study that constructs a digital twin from printed-silver data to benchmark surrogate models, acquisition functions, and batch sizes head-to-head to achieve user-specified target resistance. Tested surrogate models included Gaussian process, random forest, and Bayesian neural network surrogates with expected improvement and confidence bound acquisition functions. In total, we evaluate 48 unique model configurations alongside a random sampling baseline for comparison. For printed silver, the Bayesian neural network with a batch size of one achieved the lowest average cumulative regret, approximately four times more efficient on average than random sampling. To balance performance and substrate space, a random forest model with expected improvement and a batch size of four was chosen as the model for validation testing. Applying this chosen configuration to copper with an additional print parameter, the model achieved a resistance within 0.15 Ω of a 1 Ω target in fewer than 30 printed lines across five validation sets. Altogether, the workflow yields a tuned and validated model that efficiently guides experiments toward the target while simultaneously learning the parameter space.

Bevel, Colton [Auburn University, AL (United State↗
DOE OSTI2025

Performance Impact and Trade-Offs for Tuning Key Architectural Parameters on CPU+GPU Systems

In this work, we performed an initial design space exploration of an accelerated processing unit (APU)—a hybrid CPU+GPU architecture that integrates both compute units (CUs) and memory into a unified system. This integration aims to reduce data movement, enhance memory locality, and improve energy efficiency by enabling the CPU and GPU to share memory directly. This effort focused on the interplay of key design components—cache line size, the number of CUs, and main memory technology—and the trade-offs of each configuration were analyzed. This paper highlights the various configurations’ impact on memory accesses, data reuse, and power utilization. The results provide valuable insights that can be leveraged to optimize APU architectures for high-performance and energy-efficient computing and thus create a balanced architecture. This optimization can be achieved by adopting dynamic cache management, runtime CU scaling, and advanced memory integration, highlighting the potential of APUs to address critical challenges in compute, data movement, and memory power consumption.

Asifuzzaman, Kazi [ORNL] (ORCID:0000000240044791)↗
DOE OSTI2024

Impact of the Exciter and Governor Parameters on Forced Oscillations

In recent years, the frequency of forced oscillation events due to control system malfunctions or improper parameter settings has increased. Tuning the parameters of exciters and governor models is crucial for maintaining power system stability. Traditional simulation studies typically involve small transient disturbances or step changes to find optimal parameter sets, but existing optimization algorithms often fall short in fine-tuning for forced oscillations. Identifying the sensitive parameters within these control models is essential for ensuring stability during large, sustained disturbances. This study focuses on identifying these critical exciter and governor model parameters by analyzing their influence on sustained forced oscillations. Using Kundur’s two-area system, we analyze common exciter models such as SCRX, ESST1A, and AC7B, along with governor models like GAST, HYGOV, and GGOV1, utilizing PSS®E software version 34. Sustained forced oscillations are injected at generator-1 of area-1, with individual parameter changes dynamically simulated. By considering a local oscillation frequency of 1.4 Hz and an inter-area oscillation mode of 0.25 Hz, we analyze the impact of each parameter change on the magnitude and frequency of forced oscillations as well as on active and reactive power outputs. This novel approach highlights the most influential parameters of each tested model—such as exciter, governor, and turbine gains, as well as time constant parameters—on the impact of forced oscillations. Based on our findings, the sensitive parameters of each tested model are ranked. These would provide valuable insights for industry operators to fine-tune control settings during oscillation events, ultimately enhancing system stability.

42 ENGINEERING↗
DOE OSTI2025

GeoLoRA: Geometric integration for parameter efficient fine-tuning

Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face several challenges, including the need for rank adaptivity, robustness, and computational efficiency during the fine-tuning process. We introduce GeoLoRA, a novel approach that addresses these limitations by leveraging dynamical low-rank approximation theory. GeoLoRA requires only a single backpropagation pass over the small-rank adapters, significantly reducing computational cost as compared to similar dynamical low-rank training methods and making it faster than popular baselines such as AdaLoRA. This allows GeoLoRA to efficiently adapt the allocated parameter budget across the model, achieving smaller low-rank adapters compared to heuristic methods like AdaLoRA and LoRA, while maintaining critical convergence, descent, and error-bound theoretical guarantees. The resulting method is not only more efficient but also more robust to varying hyperparameter settings. We demonstrate the effectiveness of GeoLoRA on several state-of-the-art benchmarks, showing that it outperforms existing methods in both accuracy and computational efficiency.

Schotthoefer, Steffen [ORNL] (ORCID:00000002156965↗
DOE OSTI2025

Automated tuning for HMC mass ratios

We extended previous work on tuning HMC parameters using gradient information to include Hasenbusch mass ratios. The inclusion of mass ratios adds many more parameters that need to be tuned, and also allows for lots of variations in the choice of integrator pattern. We investigate the effectiveness of automatically tuning a large number of HMC parameters and compare the optimally tuned versions over a range of integrator variants.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

What can solve the strong CP problem?

Three possible strategies have been advocated to solve the strong CP problem. The first is the axion, a dynamical mechanism that relaxes any initial value of the CP violating angle $\overline{θ}$ to zero. The second is the imposition of new symmetries that are believed to set $\overline{θ}$ to zero in the UV. The third is the acceptance of the fine tuning of parameters. We argue that the latter two solutions do not solve the strong CP problem. The θ term of QCD is not a parameter — it does not exist in the Hamiltonian. Rather, it is a property of the quantum state that our universe finds itself in, arising from the fact that there are CP violating states of a CP preserving Hamiltonian. It is not eliminated by imposing parity as a symmetry since the underlying theory is already parity symmetric and that does not preclude the existence of CP violating states. Moreover, since the value of θ realized in our universe is a consequence of measurement, it is inherently random and cannot be fine tuned by choice of parameters. Rather any fine tuning would require a tuning between parameters in the theory and the random outcome of measurement. Our results considerably strengthen the case for the existence of the axion and axion dark matter. The confusion around θ arises from the fact that unlike classical mechanics, the Hamiltonian and Lagrangian are not equivalent in quantum mechanics. The Hamiltonian defines the differential time evolution, whereas the Lagrangian is a solution to this evolution. Consequently, initial conditions could in principle appear in the Lagrangian but not in the Hamiltonian. This results in aspects of the initial condition such as θ misleadingly appearing in the Lagrangian as parameters. We comment on the similarity between the θ vacua and the violations of the constraint equations of classical gauge theories in quantum mechanics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

End-to-end protocol for high-quality quantum approximate optimization algorithm parameters with few shots

The quantum approximate optimization algorithm (QAOA) is a quantum heuristic for combinatorial optimization that has been demonstrated to scale better than state-of-the-art classical solvers for some problems. For a given problem instance, QAOA performance depends crucially on the choice of the parameters. While average-case optimal parameters are available in many cases, meaningful performance gains can be obtained by fine-tuning these parameters for a given instance. This task is especially challenging, however, when the number of circuit executions (shots) is limited. In this work, we develop an end-to-end protocol that combines multiple parameter settings and fine-tuning techniques. We use large-scale numerical experiments to optimize the protocol for the shot-limited setting and observe that optimizers with the simplest internal model (linear) perform best. We implement the optimized pipeline on a trapped-ion processor using up to 32 qubits and 5 QAOA layers, and we demonstrate that the pipeline is robust to small amounts of hardware noise. To the best of our knowledge, these are the largest demonstrations of QAOA parameter fine-tuning on a trapped-ion processor in terms of two-qubit gate count.

quantum algorithms & computation↗
DOE OSTI2026

Magnetic field dependence of the spin fluctuations in CeCu 5.8 ⁢Ag 0.2

Quantum phase transitions are among the most intriguing phenomena that can occur when the electronic ground state of correlated metals are tuned by external parameters such as pressure, magnetic field, or chemical substitution. Such transitions between distinct states of matter are driven by quantum fluctuations, and can give rise to macroscopically coherent phases that are at the forefront of condensed matter research. However, the nature of the critical fluctuations, and thus the fundamental physics controlling many quantum phase transitions, remain poorly understood in numerous strongly correlated metals. Here we study the model material CeCu 5.8⁢ Ag 0.2 to gain insight into the implications of critical fluctuations originating from different regions in reciprocal space. By employing an external magnetic field along the crystallographic 𝑎 and 𝑐 axis as auxiliary tuning parameter, we observe a pronounced anisotropy in the suppression of the quantum critical fluctuations, reflecting the spin anisotropy of the long-range ordered ground state at larger silver concentration. Coupled with the temperature dependence of the quantum fluctuations, these results suggest that the quantum phase transition in CeCu 5.8⁢ Ag 0.2 is driven by three-dimensional spin-density wave fluctuations.

Boraley, Xavier [Paul Scherrer Inst. (PSI), Villig↗
DOE OSTI2026

A multi-backend autotuning study of feature selection on GPUs

Abstract Feature selection is an important step in machine learning that can benefit from GPU acceleration. As the number of GPU vendors increases, it is imperative to adapt algorithms such as the minimum Redundancy Maximum Relevance (mRMR) feature selection method to different backends that support several GPU architectures. This work presents a multi-backend implementation of mRMR across CUDA, HIP, and SYCL, and studies its performance when combined with Bayesian optimization and transfer learning to automatically tune execution parameters for different platforms and datasets. Our experimental results show that when tuned, CUDA and HIP achieve comparable performance on NVIDIA architectures, while SYCL exhibits a moderate performance gap. Overall, this work highlights the impact of backend choice and autotuning on GPU-accelerated feature selection and provides insights into deploying mRMR across heterogeneous environments.

Beceiro, Bieito (ORCID:0000000333014890)↗
DOE OSTI2025

Calibration of RAFM Micromechanical Model for Creep Using Bayesian Optimization for Functional Output

A Bayesian optimization procedure is presented for calibrating a multimechanism micromechanical model for creep to experimental data of F82H steel. Reduced activation ferritic martensitic (RAFM) steels based on Fe(8–9)%Cr are the most promising candidates for some fusion reactor structures. Although there are indications that RAFM steel could be viable for fusion applications at temperatures up to 600°C, the maximum operating temperature will be determined by the creep properties of the structural material and the breeder material compatibility with the structural material. Due to the relative paucity of available creep data on F82H steel compared to other alloys such as Grade 91 steel, micromechanical models are sought for simulating creep based on relevant deformation mechanisms. As a point of departure, this work recalibrates a model form that was previously proposed for Grade 91 steel to match creep curves for F82H steel. Due to the large number of parameters (9) and cost of the nonlinear simulations, an automated approach for tuning the parameters is pursued using a recently developed Bayesian optimization for functional output (BOFO) framework (Huang et al., 2021, “Bayesian optimization of functional output in inverse problems,” Optim. Eng., 22, pp. 2553–2574). Incorporating extensions such as batch sequencing and weighted experimental load cases into BOFO, a reasonably small error between experimental and simulated creep curves at two load levels is achieved in a reasonable number of iterations. In conclusion, validation with an additional creep curve provides confidence in the fitted parameters obtained from the automated calibration procedure to describe the creep behavior of F82H steel.

42 ENGINEERING↗
DOE OSTI2025

Modeling of Stress and Temperature Effects on Creep of Reduced Activation Ferritic-Martensitic Steel Alloy F82H (Tertiary Creep Modeling of RAFM Steel)

A Bayesian optimization procedure is presented for calibrating a multi-mechanism micromechanical model for creep to experimental data of F82H steel. Reduced activation ferritic martensitic (RAFM) steels based on are the most promising candidates for some fusion reactor structures. Although there are indications that RAFM steel could be viable for fusion applications at temperatures up to 600 °C, the maximum operating temperature will be determined by the creep properties of the structural material and the breeder material compatibility with the structural material. Due to the relative paucity of available creep data on F82H steel compared to other alloys such as Grade 91 steel, micromechanical models are sought for simulating creep based on relevant deformation mechanisms. As a point of departure, this work recalibrates a model form that was previously proposed for Grade 91 steel to match creep curves for F82H steel. Due to the large number of parameters (9) and cost of the nonlinear simulations, an automated approach for tuning the parameters is pursued using a recently developed Bayesian optimization for functional output (BOFO) framework [1]. Incorporating extensions such as batch sequencing and weighted experimental load cases into BOFO, a reasonably small error between experimental and simulated creep curves at two load levels is achieved in a reasonable number of iterations. Validation with an additional creep curve provides confidence in the fitted parameters obtained from the automated calibration procedure to describe the creep behavior of F82H steel at 600 °C. The model is further extended using a temperature dependent scaling law approach to simulate creep response between 550 °C and 650 °C. The efficacy of this extension is compared with the previously used scaling law approach for Grade 91 steel.

36 MATERIALS SCIENCE↗
DOE OSTI2024

$\overline{TKE}$ Parameterization and $\bar{v}$ Uncertainty Analysis for CGMF

Previous work was performed on tuning CGMF parameters for 235 U, 238 U, and Plutonium isotopes. Now work is being done to tune minor uranium isotopes. However, uranium isotopes like 232 U and 236 U have almost no experimental data. We are applying cross-isotope models to extrapolate and tune CGMF on isotopes that lack experimental data. There exist several internal CGMF physics quantities that affect the output of CGMF—multi-chance fission probability, excitation energy sharing, spin-cutoff factor, spin scaling, and fragment total kinetic energy to name a few. The mean fragment total kinetic energy, $\overline{TKE}$, is particularly interesting because of its strong anti-correlation with $\bar{v}$. We are most interested in the mean fragment total kinetic energy before neutron emissions. $\overline{TKE}$ is assumed to be pre-neutron emission unless otherwise stated. Currently in CGMF, the $\overline{TKE}$ model for 233,234,235,238 U are tuned independently to reproduce ν for the associated isotopes. In this report, we will tune a cross-isotope $\overline{TKE}$ model to experimental $\overline{TKE}$ data for 232,233,234,235,236,238 U. Because of the unreliable and sparse nature of $\overline{TKE}$ experimental data, future work will use more reliable experimental $\bar{v}$ data to infer the $\overline{TKE}$ model (and likely other internal CGMF parameters) for uranium isotopes. Such work has been performed previously using a sensitivity analysis and Kalman filter methods.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2025

Enhancing ChatPORT with CUDA-to-SYCL Kernel Translation Capability

Large Language Models (LLMs) have shown strong capabilities in general code translation. However, code translation involving parallel programming models remains largely unexplored. This work enhances the capabilities of code LLMs in CUDA-to-SYCL kernel translation with parameter-efficient fine-tuning. The resultant fine-tuned LLM, called ChatPORT, is an effort to provide high-fidelity translations from one programming model to another. We describe the preparation of datasets from heterogeneous computing benchmarks for model fine-tuning and testing, the parameter-efficient fine-tuning of 19 open-source code models ranging in size from 0.5 to 34 billion parameters and evaluate the correctness rates of the SYCL kernels by the fine-tuned models. The experimental results show that most code models fail to translate CUDA codes to SYCL correctly. However, fine-tuning these models using a small set of CUDA and SYCL kernels can enhance the capabilities of these models in kernel translation. Depending on the sizes of the models, the correctness rate ranges from 19.9% to 81.7% for a test dataset of 62 CUDA kernels.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗
DOE OSTI2024

Towards Autonomous Experiments by Connecting High Performance Microscopy with High Performance Computing

The digitization of controls, data, and analysis in microscopy is bringing the idea of autonomous microscopes closer to reality than ever before. Automated transmission electron microscopy (TEM) is already fairly routine for some experiments the only require simple repetitive tasks such as imaging biological macromolecules for single particle cryoEM [1], tilt series for electron tomography [2], and movies for crystallography [3]. The vast majority of TEM experiments are conducted completely by human operators who choose the regions of interest, optimize experimental parameters, and make decisions about data quality visually during an experiment. The field is still a long way from having completely autonomous TEMs that can adapt to sample difficulties and tune experimental parameters based on data quality and desired experimental outcomes. Part of the issue is the lack of capability for feeding information learned from on-line, live data analysis back into the on-going experiment [4]. Furthermore, this presentation will discuss current capabilities for large scale data reduction and analysis using high performance computing (i.e. supercomputing) and progress towards developing a true feed-back loop that places data analysis and theory in the experimental loop.

97 MATHEMATICS AND COMPUTING↗