Search NASA⌕ Search

SEARCH · Search NASA

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

Pneumatic Regolith Transfer Systems for In-Situ Resource Utilization

One aspect of In-Situ Resource Utilization (lSRU) in a lunar environment is to extract oxygen and other elements from the minerals that make up the lunar regolith. Typical ISRU oxygen production processes include but are not limited to hydrogen reduction, carbothermal and molten oxide electrolysis. All of these processes require the transfer of regolith from a supply hopper into a reactor for chemical reaction processing, and the subsequent extraction of the reacted regolith from the reactor. This paper will discuss recent activities in the NASA ISRU project involved with developing pneumatic conveying methods to achieve lunar regolith simulant transfer under I-g and 1/6-g gravitational environments. Examples will be given of hardware that has been developed and tested by NASA on reduced gravity flights. Lessons learned and details of pneumatic regolith transfer systems will be examined as well as the relative performance in a 1/6th G environment

Mueller, Robert P.↗
NASA NTRS1990

Momentum harvesting techniques for solar system travel

Astronomers are lately estimating there are 400,000 Earth visiting asteroids larger than 100 meters in diameter. These asteroids are accessible sources of building materials, propellants, oxygen, water, and minerals which also constitute a huge momentum reserve, potentially usable for travel throughout the solar system. To use this momentum, these stealthy objects must be tracked and the extraction of the momentum wanted must be learned. Momentum harvesting by momentum transfer from asteroid to spacecraft, and by using the momentum of the extraterrestrial material to help deliver itself to the destination are discussed. A net and tether concept is the suggested means of asteroid capture, the basic momentum exchange process. The energy damping characteristics of the tether will determine the velocity mismatch that can be tolerated, and hence the amount of momentum that can be harvested per capture. As it plays out of its reel, drag on the tether steadily accelerates the spacecraft. A variety of concepts for riding and using the asteroid after capture are discussed. The hitchhiker uses momentum transfer only. The beachcomber, the caveman, the swinger, the prospector, and the rock wrecker also take advantage of raw asteroidal materials. The chemist and the hijacker go further, they process the asteroid into propellant. Or, an 'asteroid railway system' could evolve with each hijacked asteroid becoming a scheduled train. Travelers could board the space railway system assured that water, oxygen, and propellants await them.

Willoughby, Alan J.↗
DOE OSTI2026

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model

Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However, point predictions alone are insufficient for scientific inference; reliable uncertainty quantification (UQ) is essential. We compare seven UQ methods on galaxy property regression using frozen AION-1 foundation-model embeddings, predicting redshift, stellar mass, stellar-population age, gas-phase metallicity, and specific star-formation rate, from Legacy Survey photometry/imaging and DESI spectra, with PROVABGS-derived labels. Distribution-free conformal methods achieve marginal coverage within $\sim$1 pp of the nominal 90% across all properties, while non-conformal baselines (Deep Ensembles, MC~Dropout) fail to calibrate reliably. Among conformal approaches, Conformalized Quantile Regression (CQR) delivers the best coverage in the bin with the poorest model predictions. More importantly, only the Locally Valid and Discriminative (LVD) framework -- particularly when operating on AION-1 embeddings -- also provides finite-sample \emph{local validity}, producing intervals that adapt to each galaxy's local prediction difficulty rather than relying on marginal guarantees alone. These results establish conformal prediction, and LVD in particular, as the preferred UQ framework for uncertainty-aware inference on foundation-model embeddings in astrophysics.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
NASA NTRSDate not supplied

NESC GN&C TDT Workshop on 2D Image Motion Optical Transfer Functions, Pointing Performance Analysis, and Requirements

What You Will Learn: The focus is on payload imaging performance due to pointing motion. Some historical background on pointing performance analysis is given. The Optical Transfer Function (OTF) and Modulation Transfer Function (MTF) are defined. The imaging performance due to pointing motion is measured by image motion optical transfer functions (IM OTF). IM OTFs are defined for displacement, smear, and jitter motions, which are all rigorously defined. Deterministic and Statistical IM OTFs are briefly derived and graphically illustrated and compared. The IM OTFs are parameterized by pointing error metrics(PEM), which are means and covariances of displacement, smear, and jitter. Emphasis is on procedures and algorithms to evaluate the image motion optical transfer functions and pointing error metrics. Three procedures are covered, which depend on whether the pointing error data is from time-domain simulation, frequency-domain analysis, or stochastic modeling. A method to evaluate the relative contribution of disturbance sources and to identify the most significant contributors is presented. The presentation includes pertinent discussion of flexible structures and control-structure interaction. No single book can adequately cover this subject, so a book is not required for the course. A list of selected articles, reports, documents, and books is provided for reference and further study. Mathis kept to the minimum necessary to convey principles; lengthy derivations are left to the reference material. Graphics are used to illustrate concepts. As with any such learning endeavor, the knowledge gained will be retained and strengthened through actual practice.c©2019–2021 Mark E. Pittelkau— 5

NASA Engineering and Safety Center (NESC)↗
NASA NTRSDate not supplied

Improving Sim-to-Real Transfer in Vision-Based Robot Navigation Via Instance-Level GAN-Based Data Augmentation

Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.

artificial intelligence↗
DOE OSTI2024

Numerical simulation projects in micromagnetics with Jupyter

We report a case study where an existing materials science course was modified to include numerical simulation projects on the micromagnetic behavior of materials. The Ubermag micromagnetic simulation software package is used in order to solve problems computationally. The simulation software is controlled through the Python code in Jupyter notebooks. Our experience is that the self-paced problem-solving nature of the project work can facilitate a better in-depth exploration of the course contents. We discuss which aspects of the Ubermag and the project Jupyter ecosystem have been beneficial for the students' learning experience and which could be transferred to similar teaching activities in other subject areas.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

The Lessons Learned Process: An Effective Countermeasure Against Avoidable Risk

The potential for errors in engineering judgement arguably present the highest level of risk when applied to interplanetary spaceflight. JPL has been refining its lessons learned process to optimize the collection and transfer of critical success factors applicable to current and future spaceflight projects.

lessons learned information system process improve↗
DOE OSTI2026

Adaptive Cybersecurity for Distributed Energy Resources (AdCyDER): Online Reinforcement Learning with Stackelberg-Optimized Defenses — Pipeline Architecture, Evaluation Methodology, and Findings from a Synthetic-Data Evaluation

This report documents the design and evaluation of an integrated online-learning pipeline developed within the AdCyDER project for Distributed Energy Resource (DER) cybersecurity. The pipeline couples a Reinforcement Learning (RL) attack classifier — which produces an attack-type probability distribution — with a Stackelberg game-theoretic (GT) defense selector that consumes those distributions alongside SME-encoded priors over (defense, attack) effectiveness pairings and perdefense costs to choose grid-health-preserving defenses. The objective is not attack classification per se but production of distributions that drive effective defense selection through the Stackelberg layer, learned from delayed grid-health feedback rather than labeled attack data. AdCyDER as a whole is broader than the work presented here; this report covers the specific RL/GT loop integration and its evaluation. We present the integrated pipeline (SCADA telemetry with Fronius inverter physics, Suricata IDS, time-windowed aggregation, per-facility LSTM classifier, Stackelberg optimizer, OpenC2 actuators), an experimental campaign of 28 eight-hour iterations across three baseline modes, and a pipeline-ordered diagnostic protocol. The protocol identifies two distinct failure modes within the loop: paired supervised ceilings on the same features establish that the deployed online RL classifier (macro F1 ≈ 0.07) sits at least 4.7× below a same-architecture supervised LSTM (≈ 0.34) and 10–11× below a linear feature-signal ceiling (≈ 0.70–0.79 depending on per-facility isolation), localizing the dominant failure to the training procedure; and the reward signal driving online updates carries weak directional coupling with classifier correctness in the methodology-expected direction (multi-lens convergent: top-decile P(true) records produce more frequent state changes and slightly larger improvements, top-vs-bot Cohen’s 𝑑 ≈ −0.19), but at effect magnitudes too small to drive gradient-based learning at the campaign sample size. The original learning hypothesis is not supported by the data. The primary contributions are the diagnostic methodology — proposed as a transferable falsification protocol for online RL/GT defense pipelines learning from delayed environmental reward — and the open, reproducible experimental infrastructure. We outline reward reformulation as the highest-priority aspirational next step given the underpowered-but-aligned Q6 reading, with hardware-in-the-loop evaluation as the broadest scope-expansion option.

Blakely, Benjamin [Argonne National Laboratory (AN↗
DOE OSTI2025

Contrastive learning for robust representations of neutrino data

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalize effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a promising solution to this challenge. By applying controlled data augmentations to simulated data, contrastive learning enables the extraction of robust and transferable features. This improves the ability of models trained on simulations to adapt to real experimental data distributions. In this paper, we investigate the application of contrastive learning methods in the context of neutrino physics. Through a combination of empirical evaluations and theoretical insights, we demonstrate how contrastive learning enhances model performance and adaptability. Additionally, we compare it to other domain adaptation techniques, highlighting the unique advantages of contrastive learning for this field. Published by the American Physical Society 2025

Wilkinson, Alex (ORCID:0000000253404506)↗
DOE OSTI2024

Resilient Control of Networked Microgrids Using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations

Improving system-level resiliency of networked microgrids against adversarial cyber-attacks is an important aspect in the current regime of increased inverter-based resources (IBRs). To achieve that, this paper contributes in designing a hierarchical control layer, in conjunction with the existing control layers, resilient to adversarial attack signals. Considering model complexities, unknown dynamical behaviors of IBRs, and privacy issues regarding data sharing in multi-party-owned microgrids, designing such a control layer is non-trivial. Here, to tackle these issues, a novel federated reinforcement learning (Fed-RL) method is proposed. To grasp the interconnected dynamics of networked microgrids, the paper develops Federated Soft Actor-Critic (FedSAC) algorithm following the vertical structure of implementing Fed-RL. Next, utilizing the OpenAI Gym interface, we built a custom set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark comprising 3 interconnected microgrids. Finally, the learned policies in the simulation are transferred to the real-time hardware-in-the-loop (HIL) test-bed developed using the high-fidelity Hypersim platform. Finally, experiments show that the simulator-trained RL controllers achieve desirable performance with the test-bed platform, validating the minimization of the sim-to-real gap.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Development and implementation of high-throughput proteomic and metabolomics assays by using advanced chromatographic and mass spectrometric systems (CRADA Final Report)

The mission of this CRADA with Agilent was to couple powerful MS platforms (QQQ, IM-QTOFMS) with Agilent’s novel Ultra-High-Performance Liquid Chromatography (UHPLC) fast metabolomic workflows and perform ABF Machine Learning (ML) to generated datasets. Agilent transferred UHPLC methods to PNNL and LBNL and methods were implemented and demonstrated in both labs, achieving total acquisition times of < 10 min. Metabolites analyzed using Agilent’s shared methods included metabolites from central carbon metabolism, common across hosts, and metabolites unique to engineered strains. Standards were acquired in an UHPLC-Drift Tube Ion Mobility Mass Spectrometer (DTIMS) system for the first time within the context of ABF and methods were optimized based on Agilent’s protocols. Samples from ABF hosts Pseudomonas putida, Aspergillus pseudoterreus, Aspergillus niger and Rhodosporidium toruloides were analyzed using the UHPLC-DTIMS platform for a total of 276 runs. A data analysis workflow compatible with the Experimental Data Depot (EDD) and completely shareable was developed for the acquired UHPLC-DTIMS data. Samples were analyzed using a Data Independent Acquisition Approach (DIA), which for most of the standards provided more transitions therefore increasing detection confidence. Using the data acquired by PNNL, LBNL, and Agilent’s specifications from previous ML projects, SNL applied an ensemble ML strategy to pick the best performing model for automated LC-method selection. Finally, with the contribution of the participant labs and Agilent, SNL developed an Automated Method Selection (AMS) software tool to predict the best liquid chromatography method for analysis of any new molecules of interest. Samples with novel pathways and new metabolite targets of interest are generated at a high pace in the ABF. Overall, the project advanced rapid metabolomics by combining liquid chromatography, ion mobility spectrometry, and data-independent mass spectrometry with machine learning. This multidimensional approach uses retention time, collision cross-section, precursor mass, and fragment-ion information to distinguish chemically similar metabolites that can be difficult to resolve using conventional liquid- or gas-chromatography methods. The resulting workflow also provided automated metabolite-identification error estimates, addressing a recognized need for statistical confidence measures in metabolomics.

Petzold, Christopher [Lawrence Berkeley National L↗
NASA NTRS2000

A strategic systems perspective of organizational learning theory: models for a case study at the Jet Propulsion Laboratory

Organizational learning is an umbrella term that covers a variety of topics including; learning curves, productivity, organizational memory, organizational forgetting, knowledge transfer, knowledge sharing and knowledge creation. This treatise will review some of these theories in concert with a model of how organizations learn.

organizational learning strategy innovation design↗
DOE OSTI2024

Identifying atmospheric rivers and their poleward latent heat transport with generalizable neural networks: ARCNNv1

Abstract. Atmospheric rivers (ARs) are extreme weather events that can alleviate drought or cause billions of US dollars in flood damage. By transporting significant amounts of latent energy towards the poles, they are crucial to maintaining the climate system's energy balance. Since there is no first-principle definition of an AR grounded in geophysical fluid mechanics, AR identification is currently performed by a multitude of expert-defined, threshold-based algorithms. The variety of AR detection algorithms has introduced uncertainty into the study of ARs, and the thresholds of the algorithms may not generalize to new climate datasets and resolutions. We train convolutional neural networks (CNNs) to detect ARs while representing this uncertainty; we name these models ARCNNs. To detect ARs without requiring new labeled data and labor-intensive AR detection campaigns, we present a semi-supervised learning framework based on image style transfer. This framework generalizes ARCNNs across climate datasets and input fields. Using idealized and realistic numerical models, together with observations, we assess the performance of the ARCNNs. We test the ARCNNs in an idealized simulation of a shallow-water fluid in which nearly all the tracer transport can be attributed to AR-like filamentary structures. In reanalysis and a high-resolution climate model, we use ARCNNs to calculate the contribution of ARs to meridional latent heat transport, and we demonstrate that this quantity varies considerably due to AR detection uncertainty.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2019

Physically-Informed Artificial Neural Networks for Atomistic Modeling of Materials

A new approach is presented for the development of classical interatomic potentials using physically-informed neural networks (PINN) combined with an analytical bond-order atomic interaction model. Due to the strong physical underpinnings, the PINN potentials demonstrate much better transferability than the existing machine-learning potentials while drastically improving the accuracy in comparison with traditional potentials. PINN potentials can be constructed for both metallic and covalent materials in a unified manner. A number of applications of PINN potentials to large-scale molecular dynamics and Monte Carlo simulations and calculation of thermal and mechanical properties of diverse materials are demonstrated. Some of the specific materials systems include silicon and aluminum, as well as alloys and compounds. Computational aspects of PINN potentials are discussed and future developments in this field are outlined.

J Hickman↗
NASA NTRS2018

Evolution of KSC EGS Post Space Shuttle - Success Factors and Lessons Learned

The Human Exploration and Operations Mission Directorate (HEOMD) Knowledge Capture & Transfer (KCT) team conducted video interviews with element managers in the Exploration Ground Systems (EGS) Program Office at Kennedy Space Center (KSC). The immediate goal was to capture a point-in-time profile of challenges, solutions, and lessons learned derived from EGS element development activity from the end of the Space Shuttle Program (SSP) to the present time.

Johnson, Patrick↗
NASA NTRS2010

Lessons Learned from Performance Testing of Humans in Spacesuits in Simulated Reduced Gravity

Introduction: The overarching objective of the Integrated Suit Test (IST) series is to evaluate suited human performance using reduced-gravity analogs and learn what aspects of an EVA suit system affect human performance. For this objective to be successfully achieved, the testing methodology should be valid and reproducible, and the partial-gravity simulations must be as accurate and realistic as possible. Objectives: To highlight some of the key lessons learned about partial-gravity analogs and testing methodology, and to suggest considerations for optimizing the effectiveness and quality of results of future tests. Methods: Performance testing of suited and unsuited subjects was undertaken in different reduced-gravity analogs including the Space Vehicle Mockup Facility s Partial Gravity Simulator (POGO), parabolic flight on the C-9 aircraft, underwater environments including NASA s Extreme Environment Mission Operations (NEEMO) and the Neutral Buoyancy Lab (NBL), and in field analogs including Desert Research and Technology Studies (RATS), the Haughton Mars Project (HMP), and the JSC Rock Pile. Subjects performed level walking, incline/decline walking, running, shoveling, picking up and transferring rocks, kneeling/standing, and task boards. Lessons Learned Analogs: No single analog will properly simulate all aspects of the true partial-gravity environment. The POGO is an ideal environment from the standpoint that there are no time limits or significant volumetric constraints, but it does have several limitations. It allows only 2 translational degrees of freedom (DOF) and applies true partial-gravity offload only through the subject s center of gravity (CG). Also, when a subject is doing non-stationary tasks, significant overhead inertia from the lift column seems to have a negative impact on performance. Parabolic flight allows full translational and rotational DOF and applies offload to all parts of the body, but the simulation lasts less than 30 seconds. When this is coupled with the volumetric constraints of the plane, both task selection and data collection options are significantly limited. The underwater environments also allow all 6 DOF and allow off-loading to be applied throughout the body, but the data collection capabilities are limited to little more than subjective ratings. In addition, water drag negatively affects performance of tasks requiring dynamic motion. Field analogs provide the ability to simulate lunar terrain and more realistic mission-like objectives, but all of them operate at 1-g, so suited human performance testing generally must utilize a reduced-mass or "mockup" suit, depending on study objectives. In general, the ground-based overhead-suspension partial-gravity analogs like POGO allow the most diverse data collection methods possible while still simulating partial gravity. However, as currently designed, the POGO has significant limitations. Design of the Active Response Gravity Offload System (ARGOS) has begun and is focusing on adding full x,y,z translational DOF, improved offload accuracy, increased lift capacity, and active control of the x and y axes to minimize offload system inertia. Additionally, a new gimbal is being designed to reduce mass and inertia and to be able to work with different suits, as the current gimbal only supports suited testing with the Mark III Technology Demonstrator Suit (MKIII).

Norcross, Jason R.↗
DOE OSTI2024

Scaling whole-chip QAOA for higher-order ising spin glass models on heavy-hex graphs

Abstract We show that the quantum approximate optimization algorithm (QAOA) for higher-order, random coefficient, heavy-hex compatible spin glass Ising models has strong parameter concentration across problem sizes from 16 up to 127 qubits for p = 1 up to p = 5, which allows for computationally efficient parameter transfer of QAOA angles. Matrix product state (MPS) simulation is used to compute noise-free QAOA performance. Hardware-compatible short-depth QAOA circuits are executed on ensembles of 100 higher-order Ising models on noisy IBM quantum superconducting processors with 16, 27, and 127 qubits using QAOA angles learned from a single 16-qubit instance using the JuliQAOA tool. We show that the best quantum processors find lower energy solutions up to p = 2 or p = 3, and find mean energies that are about a factor of two off from the noise-free distribution. We show that p = 1 QAOA energy landscapes remain very similar as the problem size increases using NISQ hardware gridsearches with up to a 414 qubit processor.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS1987

Commercial users panel

The discussions of motives and requirements for telerobotics application demonstrated that, in many cases, lack of progress was a result not of limited opportunities but of inadequate mechanisms and resources for promoting opportunities. Support for this conclusion came from Telerobotics, Inc., one of the few companies devoted primarily to telerobot systems. They have produced units for such diverse applications as nuclear fusion research, particle accelerators, cryogenics, firefighting, marine biology/undersea systems and nuclear mobile robotics. Mr. Flatau offered evidence that telerobotics research is only rarely supported by the private sector and that it often presents a difficult market. Questions on the mechanisms contained within the NASA technology transfer process for promoting commercial opportunities were fielded by Ray Gilbert and Tom Walters. A few points deserve emphasis: (1) NASA/industry technology transfer occurs in both directions and NASA recognizes the opportunity to learn a great deal from industry in the fields of automation and robotics; (2) promotion of technology transfer projects takes a demand side approach, with requests to industry for specific problem identification. NASA then proposes possible solutions; and (3) comittment ofmotivated and technically qualified people on each end of a technology transfer is essential.

Byrd, Joseph S.↗