Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “transfer learning.”

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 649 records · Page 36
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Physics-based hybrid machine learning for critical heat flux prediction with uncertainty quantification

Critical heat flux (CHF) is a key quantity in nuclear system modeling due to its impact on heat transfer, safety margins, and reactor performance. This study develops and validates an uncertainty-aware hybrid modeling approach that combines machine learning with physics-based models to predict CHF in cases of dryout. The Biasi and Bowring empirical correlations were paired with three ML uncertainty quantification (UQ) techniques: deep neural network (DNN) ensembles, Bayesian neural networks (BNNs), and deep Gaussian processes (DGPs). A pure ML model without a base model was evaluated for comparison. Model performance was assessed under plentiful (7,350 points) and limited (9 points) training data scenarios using parity, uncertainty distributions, and calibration curves. Results show that the Biasi hybrid DNN ensemble achieved the best overall performance, with a mean absolute relative error of 1.846%, and well-calibrated uncertainty estimates. The BNN-based hybrids showed slightly higher error (2.14%) but superior uncertainty calibration. DGP models underperformed, with over 6% error and poor uncertainty calibration. All hybrid models outperformed pure machine learning configurations, demonstrating resistance against data scarcity. These findings indicate that hybrid modeling significantly improves predictive accuracy, interpretability, and resilience to data scarcity. The integration of uncertainty awareness provides actionable confidence in CHF predictions, which is vital for safety-critical decisions in nuclear applications. This hybrid approach offers a viable pathway for deploying ML models in reactor analysis tools while preserving domain knowledge and physical consistency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
DOE OSTI2022

Understanding and Leveraging the I/O Patterns of Emerging Machine Learning Analytics

The scientific community is currently experiencing unprecedented amounts of data generated by cutting-edge science facilities. Soon facilities will be producing up to 1 PB/s which will force scientist to use more autonomous techniques to learn from the data. The adoption of machine learning methods, like deep learning techniques, in large-scale workflows comes with a shift in the workflow’s computational and I/O patterns. These changes often include iterative processes and model architecture searches, in which datasets are analyzed multiple times in different formats with different model configurations in order to find accurate, reliable and efficient learning models. This shift in behavior brings changes in I/O patterns at the application level as well at the system level. These changes also bring new challenges for the HPC I/O teams, since these patterns contain more complex I/O workloads. In this paper we discuss the I/O patterns experienced by emerging analytical codes that rely on machine learning algorithms and highlight the challenges in designing efficient I/O transfers for such workflows. We comment on how to leverage the data access patterns in order to fetch in a more efficient way the required input data in the format and order given by the needs of the application and how to optimize the data path between collaborative processes. We will motivate our work and show performance gains with a study case of medical applications.

Gainaru, Ana↗
DOE OSTI2025

TPCpp-10M: Simulated proton-proton collisions in a time projection chamber for AI foundation models

Scientific foundation models hold great promise for advancing nuclear and particle physics by improving analysis precision and accelerating discovery. Yet, progress in this field is often limited by the lack of openly available large scale datasets, as well as standardized evaluation tasks and metrics. Furthermore, the specialized knowledge and software typically required to process particle physics data pose significant barriers to interdisciplinary collaboration with the broader machine learning community. This work introduces a large, openly accessible dataset of 10 million simulated proton-proton collisions, designed to support self-supervised training of foundation models. To facilitate ease of use, the dataset is provided in a common NumPy format. In addition, it includes 70,000 labeled examples spanning three well defined downstream tasks: track finding, particle identification, and noise tagging, to enable systematic evaluation of the foundation model's adaptability. The simulated data are generated using the Pythia Monte Carlo event generator at a center of mass energy of $\sqrt{s}$ = 200 GeV and processed with Geant4 to include realistic detector conditions and signal emulation in the sPHENIX Time Projection Chamber at the Relativistic Heavy Ion Collider, located at Brookhaven National Laboratory. This dataset resource establishes a common ground for interdisciplinary research, enabling machine learning scientists and physicists alike to explore scaling behaviors, assess transferability, and accelerate progress toward foundation models in nuclear and high energy physics. The complete simulation and reconstruction chain is reproducible with the sPHENIX software stack. All data and code locations are provided under Data Accessibility.

Data Analysis, Statistics and Probability (physics↗
DOE OSTI2022

Effect of laser preheat in magnetized liner inertial fusion at OMEGA

Integrated magnetized liner inertial fusion (MagLIF) experiments on the OMEGA laser system are modeled to investigate the effects of laser preheat on implosion performance. In both simulations and experiments, preheating the fuel with a laser enhances the neutron yield, with the maximum yield occurring at an optimal preheat laser energy. Increasing the preheat energy past the optimal value reduces the neutron yield. In simulations, the rate of the drop in neutron yield depends on the inclusion of the Nernst effect. The Nernst effect advects the magnetic field away from the center of the fuel region during the preheat stage of MagLIF on OMEGA and weakens magnetic-flux compression. If the Nernst effect is not included, the simulated drop in yield past the optimal preheat laser energy is more gradual as opposed to the sharper drop seen in experiments. Simulations are able to model trend in measured ion temperatures seen in experiments. Here, a mix model is used to show that including mix from the wall in the simulated fuel region further degrades the yield and lowers the optimal preheat laser energy. Simulations with mix predict that increasing the initial axial magnetic field may still enhance yield performance in integrated implosions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1994

Teacher Enhancement Institute

In a team building, team teaching strategy with four faculty, can learning strategies such as educational technology and problem based learning be provided to forty local teachers of primary, elementary, and secondary students? The impetus for the effort is to provide information about science and engineering at NASA and motivate students to pursue careers in science and technology. Teachers, identified and selected through a rigorous application procedure, participated in a two week workshop for a graduate credit. Teachers were exposed to computer applications such as INTERNET, MOSAIC, Power Machintosh word processing, NASA scientists, and laboratory experiments. Teachers were evaluated on level and quality of their participation, design of teacher application materials and relevant lesson plans and presentations. The results show that teachers, regardless of preparation and background, can learn science and engineering applications and develop relevant materials to transfer information to their classroom. Follow-up during the academic year will show that teachers are successfully using materials.

Simmons, Ron W.↗
NASA NTRS1984

What you thought you knew about motion sickness isn't necessarily so

Motion sickness symptoms, stimuli, and drug therapy are discussed. Autogenic feedback training (AFT) methods of preventing motion sickness are explained. Research with AFT indicates that participants who had AFT could withstand longer periods of Coriolis acceleration, participants with high or low susceptibility to motion sickness could control their symptoms with AFT, AFT for Coriolis acceleration is transferable to other motion sickness stimuli, and most people can learn AFT, though with varying rates of learning.

Autogenic Training↗
NASA NTRS2021

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

Domain adaptation techniques have been developed to handle data from multiple sources or domains. Most existing domain adaptation models assume that source and target domains are homogeneous, i.e., they have the same feature space. Nevertheless, many real world applications often deal with data from heterogeneous domains that come from completely different feature spaces. In our remote sensing application, data in source domain (from an active spaceborne Lidar sensor CALIOP onboard CALIPSO satellite) contain 25 attributes, while data in target domain (from a passive spectroradiometer sensor VIIRS onboard Suomi-NPP satellite) contain 20 different attributes. CALIOP has better representation capability and sensitivity to aerosol types and cloud phase, while VIIRS has wide swaths and better spatial coverage but has inherent weakness in differentiating atmospheric objects on different vertical levels. To address this mismatch of features across the domains/sensors, we propose a novel end-to-end deep domain adaptation with domain mapping and correlation alignment (DAMA) to align the heterogeneous source and target domains in active and passive satellite remote sensing data. It can learn domain invariant representation from source and target domains by transferring knowledge across these domains, and achieve additional performance improvement by incorporating weak label information into the model (DAMA-WL). Our experiments on a collocated CALIOP and VIIRS dataset show that DAMA and DAMA-WL can achieve higher classification accuracy in predicting cloud types.

domain adaptation↗
NASA NTRS1998

From the Chemistry Lab to Licensing

This is a story of technology maturation and transfer, and licensing. It traces the history of the recently patented ion- exchange material (IEM) from the accidental discovery that this polymer, a battery separator of marginal performance, picked up copper from distilled water passing through corroded copper tubing in the laboratory, to a point where five organizations and one individual have applied for licenses to manufacture and market it or to use it in a wide variety of applications. This story discusses in detail the problems of converting an immature technology into a mature and eventually commercialized technology, without dedicated resources. Readers will develop an appreciation for how the obstacles to maturation and licensing of the technology were faced and overcome. The lessons learned will be discussed, with the hope of enhancing the technology transfer process.

Savino, Joseph M.↗
DOE OSTI2020

Feedback from International Decommissioning Planning Projects - 20269

Decommissioning of Nuclear Power Plants is an increasing reality in many countries with nuclear power. Already many years before final shutdown, planning of the decommissioning work is usually started in order to understand for example the costs, waste volume capacity and licensing work needed. In many countries it is required to have a final decommissioning plan before any decommissioning work is allowed to start. Westinghouse has been involved in international decommissioning planning for more than 30 years, where the first 20 years was mostly funding and preliminary plans due to that decommissioning was many years away. However, as many more plants are now moving into decommissioning, the focus has shifted to final decommissioning plans with budgets instead of funding plans, strategic decisions instead of choices, waste volume specifications instead of estimates and a defined approach instead of what ifs. Westinghouse has developed a methodology based on the planning and execution of many decommissioning projects in Europe, America and Asia. That international experience and understanding helps the customers to adopt a systematic planning process where strategy development is done with the end state in mind, where the goals are clearly outlined and the starting point described. The process and steps to reach the desired end state need to be clearly defined and all options/alternatives evaluated from a cost/benefit point of view. This is followed by a thorough and quantitative risk analysis in order to give solid recommendations and credible conclusions. One important feedback has been that real decommissioning experience from reference projects is invaluable for an efficient and timely progress in order not to spend unnecessary time and effort on understanding the barriers and links between different activities in decommissioning. Skilled project managers or engineers can drive the project forward, but without decommissioning experience previously gained, valuable lessons learned are not used and the same mistakes can be made again. Many utilities have invested in knowledge transfer from other decommissioning projects through site visits, exchange programs and supplier meetings, which is a valuable asset and way of implementing lessons learned from performed decommissioning projects into the planning process. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

Machine Learning Analysis of Hydrologic Exchange Flows and Transit Time Distributions in a Large Regulated River

Hydrologic exchange between river channels and adjacent subsurface environments is a key process that influences water quality and ecosystem function in river corridors. High-resolution numerical models were often used to resolve the spatial and temporal variations of exchange flows, which are computationally expensive. In this study, we adopt Random Forest (RF) and Extreme Gradient Boosting (XGB) approaches for deriving reduced order models of hydrologic exchange flows and associated transit time distributions, with integrated field observations (e.g., bathymetry) and hydrodynamic simulation data (e.g., river velocity, depth). The setup allows an improved understanding of the influences of various physical, spatial, and temporal factors on the hydrologic exchange flows and transit times. The predictors also contain those derived using hybrid clustering, leveraging our previous work on river corridor system hydromorphic classification. The machine learning-based predictive models are developed and validated along the Columbia River Corridor, and the results show that the top parameters are the thickness of the top geological formation layer, the flow regime, river velocity, and river depth; the RF and XGB models can achieve 70% to 80% accuracy and therefore are effective alternatives to the computational demanding numerical models of exchange flows and transit time distributions. Each machine learning model with its favorable configuration and setup have been evaluated. The transferability of the models to other river reaches and larger scales, which mostly depends on data availability, is also discussed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Automated characterization of spatial and dynamical heterogeneity in supercooled liquids via implementation of machine learning

Abstract A computational approach by an implementation of the principle component analysis (PCA) with K -means and Gaussian mixture (GM) clustering methods from machine learning algorithms to identify structural and dynamical heterogeneities of supercooled liquids is developed. In this method, a collection of the average weighted coordination numbers ( W C N s ‾ ) of particles calculated from particles’ positions are used as an order parameter to build a low-dimensional representation of feature (structural) space for K -means clustering to sort the particles in the system into few meso-states using PCA. Nano-domains or aggregated clusters are also formed in configurational (real) space from a direct mapping using associated meso-states’ particle identities with some misclassified interfacial particles. These classification uncertainties can be improved by a co-learning strategy which utilizes the probabilistic GM clustering and the information transfer between the structural space and configurational space iteratively until convergence. A final classification of meso-states in structural space and domains in configurational space are stable over long times and measured to have dynamical heterogeneities. Armed with such a classification protocol, various studies over the thermodynamic and dynamical properties of these domains indicate that the observed heterogeneity is the result of liquid–liquid phase separation after quenching to a supercooled state.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Data Generation for Machine Learning Interatomic Potentials and Beyond

The field of data-driven chemistry is undergoing an evolution, driven by innovations in machine learning models for predicting molecular properties and behavior. Recent strides in ML-based interatomic potentials have paved the way for accurate modeling of diverse chemical and structural properties at the atomic level. The key determinant defining MLIP reliability remains the quality of the training data. A paramount challenge lies in constructing training sets that capture specific domains in the vast chemical and structural space. This Review navigates the intricate landscape of essential components and integrity of training data that ensure the extensibility and transferability of the resulting models. We delve into the details of active learning, discussing its various facets and implementations. We outline different types of uncertainty quantification applied to atomistic data acquisition and the correlations between estimated uncertainty and true error. The role of atomistic data samplers in generating diverse and informative structures is highlighted. Furthermore, we discuss data acquisition via modified and surrogate potential energy surfaces as an innovative approach to diversify training data. The Review also provides a list of publicly available data sets that cover essential domains of chemical space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1993

Knowledge acquisition and interface design for learning on demand systems

The rapid changes in our world precipitated by technology have created new problems and new challenges for education and training. A knowledge 'explosion' is occurring as our society moves toward a service oriented economy that relies on information as the major resource. Complex computer systems are beginning to dominate the workplace, causing alarming growth and change in many fields. The rapidly changing nature of the workplace, especially in fields related to information technology, requires that our knowledge be updated constantly. This characteristic of modern society poses seemingly unsolvable instructional problems involving coverage and obsolescence. The sheer amount of information to be learned is rapidly increasing, while at the same time some information becomes obsolete in light of new information. Education, therefore, must become a lifelong process that features learning of new material and skills as needed in relation to the job to be done. Because of the problems cited above, the current model of learning in advance may no longer be feasible in our high-technology world. In many cases, learning in advance is impossible because there are simply too many things to learn. In addition, learning in advance can be time consuming, and often results in decontextualized knowledge that does not readily transfer to the work environment. The large and growing discrepancy between the amount of potentially relevant knowledge available and the amount a person can know and remember makes learning on demand an important alternative to current instructional practices. Learning on demand takes place whenever an individual must learn something new in order to perform a task or make a decision. Learning on demand is a promising approach for addressing the problems of coverage and obsolescence because learning is contextualized and integrated into the task environment rather than being relegated to a separate phase that precedes work. Learning on demand allows learners to see for themselves the usefulness of new knowledge for actual problem situations, thereby increasing the motivation for learning new information. Finally, learning on demand makes new information relevant to the task at hand, leading to more informed decision making, better quality products, and improved performance.

Nelson, Wayne A.↗
NASA NTRS1978

Vehicle Steering control: A model of learning

A hierarchy of strategies were postulated to describe the process of learning steering control. Vehicle motion and steering control data were recorded for twelve novices who drove an instrumented car twice a week during and after a driver training course. Car-driver describing functions were calculated, the probable control structure determined, and the driver-alone transfer function modelled. The data suggested that the largest changes in steering control with learning were in the way the driver used the lateral position cue.

Smiley, A.↗