Search NASA⌕ Search

SEARCH · Search NASA

Results for “scientific training”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Open Call LDRD: Physically Informed Autoencoders for Galactic Redshift Regression

Physical constraints have been suggested to make neural network models more generalizable, act scientifically plausible, and be more data-efficient over unconstrained baselines. In this report, we present preliminary work on evaluating the effects of adding soft physical constraints to computer vision neural networks trained to estimate the conditional density of redshift on input galaxy images for the Sloan Digital Sky Survey. We introduce physically motivated soft constraint terms that are not implemented with differential or integral operators. We frame this work as a simple ablation study where the effect of including soft physical constraints is compared to an unconstrained baseline. We compare networks using standard point estimate metrics for photometric redshift estimation, as well as metrics to evaluate how faithful our conditional density estimate represents the probability over the ensemble of our test dataset. We find no evidence that the implemented soft physical constraints are more effective regularizers than augmentation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Data-driven Whitney forms for structure-preserving control volume analysis

Control volume analysis models physics via the exchange of generalized fluxes between subdomains. Here, we introduce a scientific machine learning framework adopting a partition of unity architecture to identify physically-relevant control volumes, with generalized fluxes between subdomains encoded via Whitney forms. The approach provides a differentiable parameterization of geometry which may be trained in an end-to-end fashion to extract reduced models from full field data while exactly preserving physics. The architecture admits a data-driven finite element exterior calculus allowing discovery of mixed finite element spaces with closed form quadrature rules. An equivalence between Whitney forms and graph networks reveals that the geometric problem of control volume learning is equivalent to an unsupervised graph discovery problem. The framework is developed for manifolds in arbitrary dimension, with examples provided for H(div) problems in $\mathbb{R}$ establishing convergence and structure preservation properties. Finally, we consider a lithium-ion battery problem where we discover a reduced finite element space encoding transport pathways from high-fidelity microstructure resolved simulations. The approach reduces the 5.89M finite element simulation to 136 elements while reproducing pressure to under 0.1% error and preserving conservation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Growth of New High-Quality and Large-Size Single Crystals via High Pressure Floating-Zone Technique

This award supports experimental materials physics research on a class of technologically relevant materials that cannot form under ambient conditions. With the complementary expertise at Louisiana State University (LSU) and infrastructure at Oak Ridge National Laboratory (ORNL), single crystals of these materials will be synthesized using the high-pressure floating-zone technique. Our ability to grow high-quality single crystals will facilitate advanced characterization of these materials and improve the scientific outcomes. In addition to in-house material characterization, the principle investigator will partner with scientists at ORNL and Brookhaven National Laboratory (BNL) to tackle materials problems using the state-of-the-art characterization techniques. This will allow us to explore the fundamental physics underlying the emergent phenomena only seen in materials prepared under extreme conditions. Our ultimate goal is to address one of the grand challenges of materials science: how do complex phenomena emerge from simple ingredients? The proposed project will also spearhead a unique opportunity to train “new breed” scientists, co-advised by experts at both LSU and U. S. Department of Energy National Laboratories. They will be essential for expanding materials physics research with ability to grow crystals, characterize their properties, and design new materials -- an imperative skill that is scarce in the U. S. scientific community.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Evaluating causal‐based feature selection for fuel property prediction models

Abstract In‐silico screening of novel biofuel molecules based on chemical and fuel properties is a critical first step in the biofuel evaluation process due to the significant volumes of samples required for experimental testing, the destructive nature of engine tests, and the costs associated with bench‐scale synthesis of novel fuels. Predictive models are limited by training sets of few existing measurements, often containing similar classes of molecules that represent just a subset of the potential molecular fuel space. Software tools can be used to generate every possible molecular descriptor for use as input features, but most of these features are largely irrelevant and training models on datasets with higher dimensionality than size tends to yield poor predictive performance. Feature selection has been shown to improve machine learning models, but correlation‐based feature selection fails to provide scientific insight into the underlying mechanisms that determine structure–property relationships. The implementation of causal discovery in feature selection could potentially inform the biofuel design process while also improving model prediction accuracy and robustness to new data. In this study, we investigate the benefits causal‐based feature selection might have on both model performance and identification of key molecular substructures. We found that causal‐based feature selection performed on par with alternative filtration methods, and that a structural causal model provides valuable scientific insights into the relationships between molecular substructures and fuel properties.

Nguyen, Bernard↗
DOE OSTI2025

From PINNs to PIKANs: recent advances in physics-informed machine learning

Physics-Informed Neural Networks (PINNs) have emerged as a key tool in Scientific Machine Learning since their introduction in 2017, enabling the efficient solution of ordinary and partial differential equations using sparse measurements. Over the past few years, significant advancements have been made in the training and optimization of PINNs, covering aspects such as network architectures, adaptive refinement, domain decomposition, and the use of adaptive weights and activation functions. A notable recent development is the Physics-Informed Kolmogorov-Arnold Networks (PIKANS), which leverage a representation model originally proposed by Kolmogorov in 1957, offering a promising alternative to traditional PINNs. In this review, we provide a comprehensive overview of the latest advancements in PINNs, focusing on improvements in network design, feature expansion, optimization techniques, uncertainty quantification, and theoretical insights. We also survey key applications across a range of fields, including biomedicine, fluid and solid mechanics, geophysics, dynamical systems, heat transfer, chemical engineering, and beyond. Lastly, we review computational frameworks and software tools developed by both academia and industry to support PINN research and applications.

Kolmogorov-Arnold networks↗
DOE OSTI2022

Fusion RF Modeling Machine Learning (FusionML_RF) v1.0

FusionML_RF consists of multiple codes and trained machine learning (ML) models that perform low-cost output modeling from the Genray-CQL3D. Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. For example, completing a single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time. On the other hand, these ML models achieve ~ms of inference time with high accuracy across the input parameter space. This software collection consists of multiple components. (1) codes that use ML methods and precomputed Genray-CQL3D simulation output to build regression models that enable approximate computations of Genray-CLQ3D outputs from arbitrary but physically meaningful input parameters (surrogate modeling); (2) three trained models created by the team, using a database of 16,000+ GENRAY/CQL3D simulations, to study the performance of ML models for surrogate modeling; (3) codes that load the trained models and simulation data, and then compute mean squared error between the models' predictions and the ground truth of simulation output data. This collection is being made available in conjunction with a scientific publication about the work to promote reusability and provide an artifact of the scientific work.

Bai, Zhe↗
DOE OSTI2025

Retrospective on decadal progress of the NOAA/NPS ocean noise reference station network

The National Oceanic and Atmospheric Administration (NOAA), in partnership with the U.S. National Park Service (NPS), established the Ocean Noise Reference Station Network (NRS) in 2014 as a foundational component of NOAA’s Ocean Noise Strategy. This long-term effort aims to characterize baseline ocean ambient sound conditions across diverse marine environments and to inform management of noise impacts on protected species and habitats within U.S. waters. The NRS is now composed of 13 autonomous passive acoustic monitoring stations strategically positioned across the U.S. Exclusive Economic Zone (EEZ), extending from Arctic regions to tropical waters in depths ranging from 33 to 4,790 m. These locations include several National Marine Sanctuaries and National Parks, such as the recently designated Chumash Heritage National Marine Sanctuary off the coast of California. Each station is equipped to continuously sample low-frequency underwater sound at five kHz, enabling the detection of anthropogenic, geophysical, and biological acoustic signals. To date the network has sampled over 72 years of calibrated acoustic data. The spatial breadth and consistent methodology of the NRS allow for comparative acoustic assessments across diverse marine ecosystems. In addition to applied research functions, the NRS has served as a platform for education and training, offering opportunities for students to develop skills for marine science and data analysis. Looking forward, the NRS project team is focused on network expansion, improved data delivery, and broader integration with collaborative scientific initiatives. NRS recordings are being archived in partnership with NOAA’s National Centers for Environmental Information to enhance accessibility and long-term utility. Efforts are underway to develop standardized metadata and summary products to accompany raw audio files, making the data more usable for a wide range of stakeholders in the ocean science community. The NRS is evolving into a fully integrated national framework for ocean sound monitoring that supports scientific inquiry, management decision-making, national security interests, and public engagement with ocean acoustic environments.

Long-term monitoring↗
DOE OSTI2024

Speeding up and reducing memory usage for scientific machine learning via mixed precision

Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems. Within this field, physics-informed neural networks (PINNs) and deep operator networks (DeepONets) stand out as the leading techniques for solving partial differential equations by incorporating both physical equations and experimental data. However, training PINNs and DeepONets require significant computational resources, including long computational times and large amounts of memory. In search of computational efficiency, training neural networks using half precision (float16) rather than the conventional single (float32) or double (float64) precision has gained substantial interest, given the inherent benefits of reduced computational time and memory consumed. However, we find that float16 cannot be applied to SciML methods, because of gradient divergence at the start of training, weight updates going to zero, and the inability to converge to a local minima. To overcome these limitations, we explore mixed precision, which is an approach that combines the float16 and float32 numerical formats to reduce memory usage and increase computational speed. Our experiments showcase that mixed precision training not only substantially decreases training times and memory demands but also maintains model accuracy. Here, we also reinforce our empirical observations with a theoretical analysis. The research has broad implications for SciML in various computational applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Nuclear Criticality Experiments Research Center Futures: A Report of a Workshop held September 6-9, 2022, Los Alamos, NM, November, 2022

Experiments and training with critical assemblies and fissionable material (at or near the critical state) that explore reactivity phenomena are central to a number of national security challenges. From fission energy to nuclear weapons to a broad suite of scientific challenges, it is clear that additional capacity and capability are needed. The National Criticality Experiments Research Center (NCERC) marked 10 years of operations in 2021. This anniversary was an opportune time to celebrate our successes and progress, and to evaluate the remaining and emergent challenges. Against this backdrop, a workshop of approximately 140 national and international leaders in nuclear research was convened in Los Alamos, New Mexico to explore “NCERC Futures.” Therefore, the present workshop focused specifically on needed capabilities and tools to meet the research challenges in eight topical mission areas served by NCERC. As each Topical Group summarized their discussions in the out brief, it was recognized that key challenges could be met through enabling infrastructure investments and new critical assemblies. Enabling infrastructure includes staffing, additional space/buildings, developing an agile bounding safety basis, the ability to keep pace with technological advances in detectors and data acquisition systems (allowing use of those with Bluetooth™ and similar technologies), an expanded set of materials options (especially plutonium), a “Plug and Play” design and implementation mindset, and a facility that enabled free-field measurements. The new critical assemblies that were identified as having the most impact were a bare plutonium (Pu) Critical Assembly, a Horizontal Split Table (HST), a Super Comet, and a Uranium Solution Burst Assembly. NECRC is a unique, one-of-a-kind facility in the United States. If all the improvements were to be made, NCERC would enable the United States and its partners to address many important research questions related to criticality. These include but are not limited to: (1) Covering the entire neutron energy spectrum for both highly enriched uranium (HEU) and Pu in configurations for virtually all conceivable applications; (2) Performing multi-physics solution experiments and irradiations with a Uranium Solution Burst Assembly, which more closely resembles actual criticality accidents; (3) Conducting free-field experiments to make basic fission physics measurements and much cleaner benchmarks with various experimental observables; and (4) Providing more training classes and more experiments annually at greater cost efficiency enabled by additional buildings and machines and an agile, bounding, risk-balanced Safety Basis. In the end, workshop attendees enthusiastically concluded that NCERC Futures are bright and the workshop helped to identify a roadmap of capability gaps that need to be addressed. This report documents the results of those efforts.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Leveraging History to Predict Infrequent Abnormal Transfers in Distributed Workflows

Scientific computing heavily relies on data shared by the community, especially in distributed data-intensive applications. This research focuses on predicting slow connections that create bottlenecks in distributed workflows. In this study, we analyze network traffic logs collected between January 2021 and August 2022 at the National Energy Research Scientific Computing Center (NERSC). Based on the observed patterns, we define a set of features primarily based on history for identifying low-performing data transfers. Typically, there are far fewer slow connections on well-maintained networks, which creates difficulty in learning to identify these abnormally slow connections from the normal ones. We devise several stratified sampling techniques to address the class-imbalance challenge and study how they affect the machine learning approaches. Our tests show that a relatively simple technique that undersamples the normal cases to balance the number of samples in two classes (normal and slow) is very effective for model training. This model predicts slow connections with an F1 score of 0.926.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Generalized parton distributions from symbolic regression

AI/ML informed Symbolic Regression is the next stage of scientific modeling. We utilize a highly customizable symbolic regression package “PySR” to model the x and t dependence of the flavor isovector combination Hu-d(x, t, ) at = 0. These PySR models were trained on GPD results provided by both Lattice QCD and phenomenological sources GGL, GK, and VGG. We demonstrate, for the first time, the consistency and systematic convergence of Symbolic Regression by quantifying the disparate models through their Taylor expansion coefficients. In addition to PySR penalizing models with higher complexity and mean-squared error, we implement schemes that test specific physics hypotheses, including force-factorized x and t dependence and Regge behavior in PySR GPDs. We show that PySR can identify factorizing GPD sources based on their response to the Force-Factorized model. Here, knowing the precise behavior of the GPDs, and their uncertainties in a wide range in x and t, crucially impacts our ability to concretely and quantitatively predict hadronic spatial distributions and their derived quantities.

Dotson, Andrew [New Mexico State University, Las C↗
DOE OSTI2022

Ideas and perspectives: Enhancing research and monitoring of carbon pools and land-to-atmosphere greenhouse gases exchange in developing countries

Carbon (C) and greenhouse gas (GHG) research has traditionally required data collection and analysis using advanced and often expensive instruments, complex and proprietary software, and highly specialized research technicians. Partly as a result, relatively little C and GHG research has been conducted in resource-constrained developing countries. At the same time, these are often the same countries and regions in which climate change impacts will likely be strongest and in which major science uncertainties are centered, given the importance of dryland and tropical systems to the global C cycle. Increasingly, scientific communities have adopted appropriate technology and approach (AT&A) for C and GHG research, which focuses on low-cost and low-technology instruments, open-source software and data, and participatory and networking-based research approaches. Adopting AT&A can mean acquiring data with fewer technical constraints and lower economic burden and is thus a strategy for enhancing C and GHG research in developing countries. However, AT&A can have higher uncertainties; these can often be mitigated by carefully designing experiments, providing clear protocols for data collection, and monitoring and validating the quality of obtained data. For implementing this approach in developing countries, it is first necessary to recognize the scientific and moral importance of AT&A. At the same time, new AT&A techniques should be identified and further developed. All these processes should be promoted in collaboration with local researchers and through training local staff and encouraged for wide use and further innovation in developing countries.

Kim, Dong-Gill↗
DOE OSTI2020

On Transfer Learning Of Neural Networks Using Bi-Fidelity Data For Uncertainty Propagation

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to evaluate and remove the need for repeated evaluations of computationally expensive models in uncertainty quantification applications. However, given the highly parameterized construction of neural networks, especially deep neural networks, accurate training often requires large amounts of simulation data that may not be available in the case of computationally expensive systems. In this paper, to alleviate this issue for uncertainty propagation, we explore the application of transfer learning techniques using training data generated from both high- and low-fidelity models. We explore two strategies for coupling these two datasets during the training procedure, namely, the standard transfer learning and the bi-fidelity-weighted learning. In the former approach, a neural network model mapping the inputs to the outputs of interest is trained based on the low-fidelity data. The high-fidelity data are then used to adapt the parameters of the upper layer(s) of the low-fidelity network, or train a simpler neural network to map the output of the low-fidelity network to that of the high-fidelity model. In the latter approach, the entire low-fidelity network parameters are updated using data generated via a Gaussian process model trained with a small high-fidelity dataset. The parameter updates are performed via a variant of stochastic gradient descent with learning rates given by the Gaussian process model. Using three numerical examples, we illustrate the utility of these bi-fidelity transfer learning methods where we focus on accuracy improvement achieved by transfer learning over standard training approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Gaming the beamlines—employing reinforcement learning to maximize scientific outcomes at large-scale user facilities

Abstract Beamline experiments at central facilities are increasingly demanding of remote, high-throughput, and adaptive operation conditions. To accommodate such needs, new approaches must be developed that enable on-the-fly decision making for data intensive challenges. Reinforcement learning (RL) is a domain of AI that holds the potential to enable autonomous operations in a feedback loop between beamline experiments and trained agents. Here, we outline the advanced data acquisition and control software of the Bluesky suite, and demonstrate its functionality with a canonical RL problem: cartpole. We then extend these methods to efficient use of beamline resources by using RL to develop an optimal measurement strategy for samples with different scattering characteristics. The RL agents converge on the empirically optimal policy when under-constrained with time. When resource limited, the agents outperform a naive or sequential measurement strategy, often by a factor of 100%. We interface these methods directly with the data storage and provenance technologies at the National Synchrotron Light Source II, thus demonstrating the potential for RL to increase the scientific output of beamlines, and layout the framework for how to achieve this impact.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Enabling scientific machine learning in MOOSE using Libtorch

A neural-network-based machine learning interface has been developed for the Multiphysics Object-Oriented Simulation Environment (MOOSE). The interface relies on Libtorch, the C++ front-end of PyTorch, and enables an online interaction between modern machine learning algorithms and all the existing simulation, modeling, and analysis processes available in MOOSE. New capabilities in MOOSE include the native generation and training of artificial neural networks together with options to load pretrained neural networks in TorchScript format. Furthermore, the MOOSE stochastic tools module (MOOSE-STM) has been enhanced with neural network-based surrogate and reduced-order model generation options for efficient stochastic analyses. Lastly, a reinforcement learning capability has been added to MOOSE-STM for the interactive control and optimization of complex multiphysics problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Test samples and infrastructure for accelerator magnet developments

LHC still does not operate at full energy due to training features in magnets. Higher field practical superconductors (Nb 3 Sn) show much worse training behavior than NbTi. Most magnet performance issues relate to quenching, and it is this phenomenon and its dependencies that need to be understood for us to succeed addressing them in magnets. For pragmatic and scientific reasons underlying mechanisms are hard to investigate in real magnets. Available data suggest that emulating local conditions at quench location may be enough to arrive at a good understanding of what drives observed behavior. "Local" conditions imply emulation by small samples of cables/"stacks" powered within a facility with controllable conditions, including external magnetic and force fields. This paper argues about the necessity of this approach, while reminding current understanding and directions of quench studies, and pointing out inadequacy of available techniques. Improved facilities and change of perspective are required for consistent and affordable development.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

PowerModel-AI: A First On-the-Fly Machine-Learning Predictor for AC Power Flow Solutions

The real-time creation of machine-learning models via active or on-the-fly learning has attracted considerable interest across various scientific and engineering disciplines. These algorithms enable machines to build models autonomously while remaining operational. Through a series of query strategies, the machine can evaluate whether newly encountered data fall outside the scope of the existing training set. In this study, we introduce PowerModel-AI, an end-to-end machine learning software designed to accurately predict AC power flow solutions. We present detailed justifications for our model design choices and demonstrate that selecting the right input features effectively captures load flow decoupling inherent in power flow equations. Our approach incorporates on-the-fly learning, where power flow calculations are initiated only when the machine detects a need to improve the dataset in regions where the model’s suboptimal performance is based on specific criteria. Otherwise, the existing model is used for power flow predictions. This study includes analyses of five Texas A&M synthetic power grid cases, encompassing the 14-, 30-, 37-, 200-, and 500-bus systems. The training and test datasets were generated using PowerModels.jl, an open-source power flow solver/optimizer developed at Los Alamos National Laboratory, NM, USA.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

GMT: A deep learning approach to generalized multivariate translation for scientific data analysis and visualization

In scientific visualization, despite the significant advances of deep learning for data generation, researchers have not thoroughly investigated the issue of data translation. We present a new deep learning approach called generalized multivariate translation (GMT) for multivariate time-varying data analysis and visualization. Like V2V, GMT assumes a preprocessing step that selects suitable variables for translation. However, unlike V2V, which only handles one-to-one variable translation during training and inference, GMT enables one-to-many and many-to-many variable translation in the same framework. We leverage the recent StarGAN design from multi-domain image-to-image translation to achieve this generalization capability. We experiment with different loss functions and injection strategies to explore the best choices and leverage pre-training for performance improvement. We compare GMT with other state-of-the-art methods (i.e., Pix2Pix, V2V, StarGAN). Furthermore, the results demonstrate the overall advantage of GMT in translation quality and generalization ability.

97 MATHEMATICS AND COMPUTING↗