Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Transfer Learning Model”

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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Transfer Learning-Based Independent Component Analysis

Understanding the underlying component structure is crucial for multivariate signal analysis. Among all the techniques that try to learn the latent structure, independent component analysis (ICA) is one of the most important and popular methods, which aims to extract independent components from multivariate signals and enables further analysis. For example, in electroencephalogram (EEG) analysis, artifacts filtering and disease detection are conducted based on the independent components of the signals. One critical challenge in existing ICA approaches is that the component extraction accuracy may degrade when the available data of a unit are limited. To address this issue, this paper proposes a transfer learning-based ICA method by innovatively transferring component distribution from a source domain, so that accurate component extraction results can be achieved even when only limited data are available in the target domain. To the best of our knowledge, this is the first work that leverages transfer learning to improve ICA accuracy with limited available data. In particular, we first extract all the independent components from the source domain by maximizing the log-likelihood function with a Newton-like method on a smooth manifold. Then for the target domain, the component with the largest negentropy is extracted in each round. To effectively leverage the knowledge from the source domain and to prevent the negative transfer, we try to find a component in the source domain that matches the component we are extracting. The probability density function of the matched component will then be used to improve the component extraction accuracy if such matched component can be found; otherwise, no knowledge will be transferred. Finally, numerical simulations and a case study with electrocardiogram (ECG) data are conducted, showing the effectiveness of the proposed method in transferring knowledge and reducing negative transfer.

42 ENGINEERING↗
DOE OSTI2022

Using ensembles and distillation to optimize the deployment of deep learning models for the classification of electronic cancer pathology reports

One of the goals of the Surveillance, Epidemiology, and End Results (SEER) program is to estimate incidence, prevalence, and mortality of all cancers. To that end, cancer registries across the country maintain a massive database of cancer pathology reports which contain rich information to understand cancer trends. However, these reports are stored in the form of unstructured text, and human annotators are required to read and extract relevant information. In this article, we show that existing deep learning models for automating information extraction from cancer pathology reports can be significantly improved by using ensemble model distillation. We found that by training multiple predictive models and transferring their knowledge to a single, low-resource model, we can reduce the number of highly confident wrong predictions. Our results show that our implemented methods could save 1000s of manual annotation hours.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Influence of extreme temperature conditions on CO 2 direct air capture using amino-acid solutions

Geological features play a pivotal role in determining the feasibility of deploying CO₂ direct air capture (DAC) technologies, primarily because they influence the availability of cost-effective energy sources, such as natural gas and geothermal energy, and also due to the potential for CO₂ sequestration. Many regions face challenges due to variable weather conditions including seasonal temperature fluctuations, high or low humidity, and sub-ambient temperatures. These extremes can reduce DAC performance or even lead to catastrophic events. Aqueous solvents considered for DAC systems are particularly vulnerable to seasonal variations in colder climates, where the solvent may underperform or freeze. It is therefore essential to investigate the CO₂ capture efficiency of aqueous solvents across a broad range of environmental temperatures, spanning sub-zero to hot conditions (>30 °C). In this study, DAC operation is examined using a high-flux solvent–air crossflow contactor under two major weather scenarios: (i) cold conditions below 0 °C and (ii) hot conditions above 30 °C. A parametric study is conducted to investigate the contactor performance regarding CO₂ removal efficiency, uptake capacity, and reaction kinetics versus temperature when the air velocity through the contactor exceeds 1 m/s. The efficacy of the contactor is systematically investigated using various anti-freeze amino-acid solvent formulations. A mass-transfer mechanistic model is developed to assess the process performance over a wide temperature range and propose scalable design guidelines. Machine learning is also employed to identify key parameters affecting the CO₂ capture efficiency. It is shown that air velocity and temperature are the primary factors influencing CO₂ uptake. Based on performance data obtained under subfreezing temperatures, a technoeconomic analysis is conducted to evaluate the feasibility of using aqueous solvents in seasonal cold regions. In conclusion, the findings of this study provide valuable insights into siting considerations for deploying solvent-based DAC, thereby contributing to the advancement of sustainable carbon removal solutions.

Air–liquid contactor↗
NASA NTRSDate not supplied

Synthetic Hyperspectral Data for Global Water Quality Algorithm Development

Eutrophication and increasing prevalence of potentially toxic algal blooms (cyanoHABs) among global inland water bodies have become a major ecological concern and require direct attention. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local aquatic processes, to spatially resolved global products. Planned aquatic biogeochemistry remote sensing data products from hyperspectral imagers such as NASA’s Surface Biology and Geology (SBG) mission and relevant aquatic sensor sensitivity precursor airborne imaging spectrometer data provide unprecedented radiometric resolution and sensor sensitivity for characterizing complex aquatic ecosystems. However, scarcity of high-quality freshwater in-situ optical data hinders our capability to develop and validate robust retrieval algorithms. A state-of-the-art synthetic dataset of paired top-of-atmosphere, bottom-of-atmosphere, and optical and biogeophysical data was developed through radiative transfer modeling to simulate natural freshwater ecosystems. A synthetic or precursor dataset for SBG is being used to train robust machine learning models to derive water quality products pertinent to SBG mission objectives. The dataset is also used to show the potential of performing vigorous aquatic sensitivity studies and explored pathways for how best to optimize hyperspectral data for machine learning development. A processing pipeline and resultant global synthetic/precursor dataset for inland waters is presented to establish the innovation for water quality studies of inland waters globally. Optical Society of America Imaging and Applied Optics Congress, Hyperspectral Imaging and Sounding of the Environment (OSA HISE) Meeting, 19-23 July 2021, Virtual Meeting, https://www.osa.org/enus/meetings/osa_meetings/optical_sensors_and_sensing_congress/program/hyperspectral_imaging_and_sounding_of_the_environm/

Synthetic↗
NASA NTRS2021

Adaptive Data Screening for Multi-Angle Polarimetric Aerosol and Ocean Color Remote Sensing Accelerated by Automatic Differentiation

Remote sensing measurements from multi-angle polarimeters (MAPs) contain rich aerosol microphysical property information, and these sensors have been used to perform retrievals in optically complex atmosphere and ocean systems. Previous studies have concluded that, generally, five moderately separated viewing angles in each spectral band provide sufficient accuracy for aerosol property retrievals, with performance gradually saturating as angles are added above that threshold. The Hyper-Angular Rainbow Polarimeter (HARP) instruments provide high angular sampling with a total of 90-120 unique angles across four bands, a capability developed mainly for liquid cloud retrievals. In practice, not all view angles are optimal for aerosol retrievals due to impacts of clouds, sun glint, and other impediments. The many viewing angles of HARP can provide resilience to these effects, if the impacted views are screened from the dataset, as the remaining views may be sufficient for successful analysis. In this study, we discuss how the number of available viewing angles impacts aerosol and ocean color retrieval uncertainties, as applied to two versions of the HARP instrument. AirHARP is an airborne prototype that was deployed in the ACEPOL field campaign, while HARP2 is an instrument in development for the upcoming NASA Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission. Based on synthetic data, we find that a total of 20-30 angles across all bands (i.e. five to eight viewing angles per band) are sufficient to achieve good retrieval performance. Following from this result, we develop an adaptive multi-angle polarimetric data screening (MAPDS) approach to evaluate data quality by comparing measurements with their best-fitted forward model. The FastMAPOL retrieval algorithm is used to retrieve scene geophysical values, by matching an efficient, deep learning-based, radiative transfer emulator to observations. The data screening method effectively identifies and removes viewing angles affected by thin cirrus clouds and other anomalies, improving retrieval performance. This was tested with AirHARP data, and we found agreement with the High Spectral Resolution Lidar-2 (HSRL-2) aerosol data. The data screening approach can be applied to modern satellite remote sensing missions, such as PACE, where a large amount of multi-angle, hyperspectral, polarimetric measurements will be collected.

multi-angle polarimeter↗
NASA NTRS1996

Investigation of Mechanisms Associated with Nucleate Boiling Under Microgravity Conditions

The focus of the present work is to experimentally study and to analytically/numerically model the mechanisms of growth of bubbles attached to, and sliding along, a heated surface. To control the location of the active cavities, the number, the spacing, and the nucleation superheat, artificial cavities will be formed on silicon wafers. In order to study the effect of magnitude of components of gravitational acceleration acting parallel to, and normal to the surface, experiments will be conducted on surfaces inclined at different angles including a downward facing surface. Information on the temperature field around bubbles, bubble shape and size, and bubble induced liquid velocities will be obtained through the use of holography, video/high speed photography and hydrogen bubble techniques, respectively. Analytical/numerical models will be developed to describe the heat transfer including that through the micro-macro layer underneath and around a bubble. In the micro layer model capillary and disjoining pressures will be included. Evolution of the interface along with induced liquid motion will be modelled. Subsequent to the world at normal gravity, experiments will be conducted in the KC-135 or the Lear jet especially to learn about bubble growth/detachment under low gravity conditions. Finally, an experiment will be defined to be conducted under long duration of microgravity conditions in the space shuttle. The experiment in the space shuttle will provide microgravity data on bubble growth and detachment and will lead to a validation of the nucleate boiling heat transfer model developed from the preceding studies performed at normal and low gravity (KC-135 or Lear jet) conditions.

Dhir, Vijay K.↗
NASA NTRS2020

Deep Learning Models for Planetary Seismicity Detection

Research in planetary seismology is fundamentally constrained by a lack of data. Seismo-logical science products of future missions can typically only be informed by theoretical signal/noise characteristics of the environment or likely Earth-analogues. Although objectives can be re-assessed after some initial data-collection upon lander arrival, transfer of high-resolution data back to Earth is costly on lander power usage. Over the last several years, development of GPU computing techniques and open-source high-level APIs have led to rapid advances in deep learning within the fields of computer vision, natural language processing, and collaborative filtering. These techniques are actively being adapted in seismology for a variety of tasks, including: earthquake detection, seismic phase discrimination, and ground-motion prediction. Until the recent detection of mars quakes during the Mars InSight mission, the only other measurements of seismicity recorded outside of Earth was on the Moon during the Apollo missions between 1969 to 1977. These unique data sets have been periodically revisited using new seismological methods, including ambient noise interferometry and Hidden Markov Models. Our objective is to develop a deep learning seismic detector and use it to catalog moonquakes from the Apollo 17 Lunar Seismic Profiling Experiment (LSPE) and compare the results with those obtained by other methods. Additionally, we will assess the accuracy tradeoff between using a training set of lunar data and one composed of Earth seismicity. In this document, we present preliminary results using a prototype classifier trained on a small set of earthquakes that was able to obtain detections for LSPE moonquakes with a greater accuracy than a recent study using Hidden Markov Models.

Civilini, F.↗
DOE OSTI2025

Machine learning-accelerated path integral molecular dynamics simulations of reactive organic electrolytes

Hydrogen bonded electrolytes that exhibit accelerated proton transport via sequential reactive hops have drawn interest for their promise in clean energy applications. Molecular dynamics simulations of these electrolytes offer the opportunity to uncover microscopic mechanistic details that could be used to design and tune the properties of candidate electrolyte technologies. However, accurately modeling the proton transfer reactions and transport properties that give rise to high charge conductivites in these electrolytes proves computationally challenging because of the need to perform lengthy condensed phase simulations, treating both the electronic and nuclear degrees of freedom quantum mechanically. In this paper, we demonstrate that such a modeling task can be efficiently achieved with the use of density functional theory (DFT)-trained machine learning potentials (MLP) to accelerate path integral molecular dynamics (PIMD) simulations. We highlight the practical utility of this approach by using it to benchmark how closely PIMD simulations employing different DFT exchange–correlation functionals reproduce the composition-dependent densities, diffusion coefficients, and electrical conductivities of mixtures consisting of imidazole and levulinic acid. Even with the speedup afforded by our MLPs, PIMD simulations remain quite expensive. Furthermore, in order to render PIMD more computationally tractable, we introduce and benchmark the accuracy of a ring polymer contraction approach that leverages a computationally efficient short-range MLP to accelerate our PIMD simulations by an additional factor of four.

Chemical bonding↗
DOE OSTI2026

Self-supervised and multi-fidelity learning for extended predictive soil spectroscopy

Infrared spectroscopy is a cost-effective, non-destructive, and environmentally benign technology that is increasingly recognized as an important solution for meeting the global demand for soil data. While both near-infrared (NIR) and mid-infrared (MIR) diffuse reflectance spectroscopy enable rapid estimation of soil properties, they present a significant trade-off: NIR offers superior scalability and lower operational costs, whereas MIR provides higher analytical fidelity by capturing fundamental molecular vibrations. In this study, we propose a self-supervised, multi-fidelity learning framework designed to bridge this gap. Our approach leverages large-scale MIR spectral libraries to learn a compact, transferable latent representation, into which NIR spectra are subsequently aligned for downstream prediction. The workflow consists of pretraining a latent model on a large MIR library, adapting the representation using a smaller paired NIR–MIR dataset, and evaluating generalization on an independent external test set. Across a range of chemical and physical soil properties, we found that MIR-derived embeddings improved prediction accuracy relative to baseline models that used raw MIR inputs. Predictions derived from the spectrum conversion (NIR to MIR) task did not match the performance of the original MIR spectra but were similar or superior to predictive performance of NIR-only models, suggesting the unified spectral latent space can effectively leverage the larger and more diverse MIR dataset for prediction of soil properties not well represented in current NIR libraries.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Transformer quantum state: A multipurpose model for quantum many-body problems

Here, inspired by the advancements in large language models based on transformers, we introduce the transformer quantum state (TQS): a versatile machine learning model for quantum many-body problems. In sharp contrast to Hamiltonian/task specific models, TQS can generate the entire phase diagram, predict field strengths with experimental measurements, and transfer such a knowledge to new systems it has never been trained on before, all within a single model. With specific tasks, fine-tuning the TQS produces accurate results with small computational cost. Versatile by design, TQS can be easily adapted to new tasks, thereby pointing towards a general-purpose model for various challenging quantum problems.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

HydraGNN_GFM_FineTuning4Materials v1.0

This repository enables fine-tuning of the HydraGNN Predictive GFM 2026 — an open-source ensemble of pre-trained graph foundation models for atomistic materials modeling, developed at Oak Ridge National Laboratory. The GFM 2026 is freely available and downloadable via Globus from the OLCF Data Constellation (DOI: 10.13139/OLCF/2562660). Starting from these pre-trained weights, this repository provides a complete transfer learning pipeline for adapting the GFM ensemble to domain-specific molecular and materials property prediction tasks. It includes: 1) Utilities for ensemble fine-tuning with task-specific output heads 2) Example pipelines for eight widely-used materials and molecular datasets 3) Tools for model adaptation and head configuration 4) Data preprocessing utilities for each supported dataset 5) Benchmarking and evaluation scripts

Ungerboeck, Linda↗
DOE OSTI2025

Virtual Reality for Shoot/No-Shoot Decision Training in Law Enforcement: A Literature Review and Research Agenda

Virtual reality (VR) can materially improve “shoot / no-shoot” (SNS) training by giving officers realistic, repeatable practice making high-stakes decisions under pressure. Traditional tools—live-fire ranges and video simulators—build basics, but they cannot adapt to each officer in real time or fully mirror the complexity of the field. VR closes that gap by creating immersive scenarios that are safer, more flexible, easier to scale across units, and able to capture objective performance data. SNS decisions are not just about marksmanship; they rely on perception, judgment, memory, and the ability to hold fire when a threat is uncertain. Effective training therefore needs realism, decision complexity, and branching outcomes that reflect the true consequences of choices. These elements strengthen recognition of hostile intent while reducing false positives and building the self-control required in ambiguous situations. VR brings specific advantages: dynamic environments, full-body interaction, and the ability to measure performance with precision—enabling targeted feedback and better transfer of learning to the street. At the same time, responsible deployment must address scenario quality (credible environments and behaviors), lawful decision models, and user wellbeing (appropriate stress levels, comfort, and safety). Sandia’s VIPER Lab is positioned to lead this work. The team combines human-performance science, AI/ML, and VR/AR development with a deep equipment bench (e.g., omnidirectional treadmill, eye-tracking, haptics, multiple HMDs). This ecosystem supports building and validating next-generation SNS training that is immersive, measurable, and trustworthy. Bottom line: Investment in VR-enabled SNS training that blends evidence-based design with careful validation and legal safeguards is expected to pay off in safer, more consistent decision-making and improved community trust, delivered through training that is practical to deploy at scale.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
NASA NTRS1989

Evolution of the solar nebula. I - Nonaxisymmetric structure during nebula formation

Numerical solutions of the equations of hydrodynamics, gravitation, and radiative transfer in three spatial dimensions are used to model the formation and time evolution of the early solar nebula in order to learn whether or not gravitational torques between nonaxisymmetric structures in the solar nebula can transport angular momentum rapidly enough to produce nebula clearing on astronomically indicated (10 to the 5 to 10 to the 7 yr) time scales. The models involve solutions for the collapse of spherical clouds with assumed initial density and rotation profiles onto protosuns of variable mass. Most of the models assume uniform initial density and rotation, and have variations in the initial parameters of cloud mass, cloud rotation rate, and protosun mass which are chosen to simulate a range of possible phases of early solar nebula evolution. The models show little tendency for directly forming small numbers of giant gaseous protoplanets through gaseous gravitational instability.

Boss, Alan P.↗
DOE OSTI2021

Machine learning dielectric screening for the simulation of excited state properties of molecules and materials

Accurate and efficient calculations of absorption spectra of molecules and materials are essential for the understanding and rational design of broad classes of systems. Solving the Bethe–Salpeter equation (BSE) for electron–hole pairs usually yields accurate predictions of absorption spectra, but it is computationally expensive, especially if thermal averages of spectra computed for multiple configurations are required. We present a method based on machine learning to evaluate a key quantity entering the definition of absorption spectra: the dielectric screening. We show that our approach yields a model for the screening that is transferable between multiple configurations sampled during first principles molecular dynamics simulations; hence it leads to a substantial improvement in the efficiency of calculations of finite temperature spectra. We obtained computational gains of one to two orders of magnitude for systems with 50 to 500 atoms, including liquids, solids, nanostructures, and solid/liquid interfaces. Importantly, the models of dielectric screening derived here may be used not only in the solution of the BSE but also in developing functionals for time-dependent density functional theory (TDDFT) calculations of homogeneous and heterogeneous systems. Overall, our work provides a strategy to combine machine learning with electronic structure calculations to accelerate first principles simulations of excited-state properties.

36 MATERIALS SCIENCE↗
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↗
DOE OSTI2025

Inverse model based error detection in beamline optics

Optics tuning in transfer lines and LINACs can be challenging due to the fact that multiple combinations of machine settings can lead to the same diagnostic output. Moreover, the lack of a periodic solution can limit the ability to infer optics in the same way as rings from BPM signals. Model based approaches are often used to assist with the optics tuning in combination with optimization or parameter estimation. Here we have developed a novel approach using machine learning inverse models trained on a known configuration to detect variations in quadrupole settings without explicitly including them in the model. This paper shows a comparison of neural network models and linear models on both a simulation based study and experimental studies conducted at the AGS to RHIC transfer line at Brookhaven National Lab.

43 PARTICLE ACCELERATORS↗