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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Tensorized Interior Radiative Heat Transfer for a Scalable and Calibrated Building Energy Simulator

Building energy simulation is a critical tool for developing and testing advanced control strategies, such as Reinforcement Learning (RL), to provide demand flexibility and affordable energy costs. The recently introduced Smart Buildings Control Suite (sbsim) provides a lightweight, scalable, and data-calibrated simulation environment based on a 2D finite-difference model. However, the initial model primarily focused on conductive and convective heat transfer, neglecting the significant impact of long-wave radiative heat exchange between interior surfaces. This paper presents a significant extension to the sbsim framework by incorporating a physically-grounded model for interior radiative heat transfer. Our primary contribution is the development and integration of a fully tensorized radiative heat transfer module, which preserves the computational efficiency and scalability of the original simulator. This was achieved by developing a pipeline for view factor calculation, including an algorithm to identify directly seeing surfaces within complex floor plans, and formulating the net radiation equations for efficient execution on modern hardware accelerators. We validate the numerical accuracy of our tensorized implementation by comparing its results against a traditional iterative approach, demonstrating identical outcomes. This enhancement increases the physical fidelity of sbsim, enabling more accurate training of RL agents for building energy optimization.

Ham, Sang woo↗
DOE OSTI2025

The Artificial Scientist: in-Transit Machine Learning of Plasma Simulations

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

Kelling, Jeffrey [Helmholtz-Zentrum Dresden Rossen↗
DOE OSTI2026

Deployment of Traditional and Hybrid Machine Learning for Critical Heat Flux Prediction in the CTF Thermal-Hydraulics Code

Critical heat flux (CHF) marks the transition from nucleate to film boiling, where heat transfer to the working fluid can rapidly deteriorate. Accurate CHF prediction is essential for efficiency, safety, and preventing equipment damage, particularly in nuclear reactors. Although widely used, empirical correlations frequently exhibit discrepancies when compared to experimental data, limiting their reliability in diverse operational conditions. Traditional machine learning (ML) approaches have demonstrated potential for CHF prediction but often suffer from limited interpretability, data scarcity, and insufficient knowledge of physical principles. Hybrid model approaches, which combine data-driven ML with base models, mitigate these concerns by incorporating prior knowledge of the domain. This study integrates an externally trained purely data-driven ML model and two hybrid models (using the Biasi and Bowring CHF correlations) within the CTF subchannel code via a custom Fortran framework. Performance was evaluated using two validation cases: a subset of the Nuclear Regulatory Commission (NRC) CHF database and the Bennett dryout experiments. In both cases, the hybrid models demonstrated significantly lower error metrics compared to conventional empirical correlations, with the best models often reducing relative error by about 5 percentage points. The pure ML model achieved comparable accuracy, outperforming the hybrid Biasi model in the NRC test case (3.3% versus 5.5% relative error) but exhibiting slightly higher error against the hybrid Bowring model in the Bennett test case (7.7% versus 6.1%). Trend analysis of error parity indicated that ML-based models reduced the tendency for CHF overprediction, improving overall accuracy. These results demonstrate that ML-based CHF models can be effectively integrated into subchannel codes and could potentially increase performance compared to conventional methods.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls

Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.

Kasparian, Armen [Thomas Jefferson National Accele↗
NASA NTRS1992

A radial basis function neurocomputer implemented with analog VLSI circuits

An electronic neurocomputer which implements a radial basis function neural network (RBFNN) is described. The RBFNN is a network that utilizes a radial basis function as the transfer function. The key advantages of RBFNNs over existing neural network architectures include reduced learning time and the ease of VLSI implementation. This neurocomputer is based on an analog/digital hybrid design and has been constructed with both custom analog VLSI circuits and a commercially available digital signal processor. The hybrid architecture is selected because it offers high computational performance while compensating for analog inaccuracies, and it features the ability to model large problems.

Watkins, Steven S.↗
NASA NTRS1993

An ASIC memory buffer controller for a high speed disk system

The need for large capacity, high speed mass memory storage devices has become increasingly evident at NASA during the past decade. High performance mass storage systems are crucial to present and future NASA systems. Spaceborne data storage system requirements have grown in response to the increasing amounts of data generated and processed by orbiting scientific experiments. Predictions indicate increases in the volume of data by orders of magnitude during the next decade. Current predictions are for storage capacities on the order of terabits (Tb), with data rates exceeding one gigabit per second (Gbps). As part of the design effort for a state of the art mass storage system, NASA Langley has designed a 144 CMOS ASIC to support high speed data transfers. This paper discusses the system architecture, ASIC design and some of the lessons learned in the development process.

Hodson, Robert F.↗
NASA NTRS2000

Modal Survey Test of the SOTV 2X3 Meter Off-Axis Inflatable Concentrator

NASA's Marshall Space Flight Center has had several projects involving inflatable space structures. Projects in solar thermal propulsion have had the most involvement, primarily inflatable concentrators. A flight project called Shooting Star Experiment initiated the first detailed design, analysis and testing effort involving an inflatable concentrator that supported a Fresnel lens. The lens was to concentrate the sun's rays to provide an extremely large heat transfer for an experimental solar propulsion engine. Since the conclusion of this experiment, research and development activities for solar propulsion at Marshall Space Flight Center have continued both in the solar propulsion engine technology as well as inflatable space structures. Experience gained in conducting modal survey tests of inflatable structures for the Shooting Star Experiment has been used by dynamic test engineers at Marshall Space Flight Center to conduct a modal survey test on a Solar Orbital Transfer Vehicle (SOTV) off-axis inflatable concentrator. This paper describes how both previously learned test methods and new test methods that address the unique test requirements for inflatable structures were used. Effects of the inherent nonlinear response of the inflatable concentrator on test methods and test results are noted as well. Nine analytical mode shapes were successfully correlated to test mode shapes. The paper concludes with several "lessons learned" applicable to future dynamics testing and shows how Marshall Space Flight Center has utilized traditional and new methods for modal survey testing of inflatable space structures.

Engberg, Robert C.↗
NASA NTRS2024

Artificial Intelligence Medical Support for Long-Duration Space Missions

We envision an artificial intelligence (AI) based system that will provide support and recommendations to the crew medical officer (CMO) and ground flight surgeon during long-duration space missions. Such a system would be pretrained on the knowledgebase of clinical knowledge on Earth, minimizing the amount of Earth data that needs to be transferred into space. Then during deployment, the system would be constantly refined through active learning from diverse streams of data from sensors in the spacecraft, data collected daily from individual astronauts, and human-in-the-loop feedback from the crew. The model could be interrogated for predictions and recommendations on personalized crew health based on the overall status of the spacecraft, medicinal stores, and status of other crew members. Adaptation techniques would be used to incorporate spaceflight data that have very different distributions from the training data due to the extreme environment. Edge computing and the most advanced neuromorphic processing would enable computation in scenarios with low power and bandwidth, while dimensionality reduction would be employed to ensure that the input data streams from spaceflight are as small as possible. In order to realize this long-term vision, several hardware and software aspects need to be developed and assembled. First, models pretrained on Earth biomedical data would need to be evaluated for predictive accuracy, and the best one selected. That model would need to be adapted to learn from diverse, sparse, and inconsistently measured data streams, as well as human-in-the-loop feedback. A data integration, standardization, and dimensionality reduction methodology would need to be developed to handle all data types and feed them into the model. Once the software and data infrastructure is developed, it would need to be integrated with small footprint compute processors and tested in high-radiation, high-vibration, unregulated temperature situations. As a short-term goal, we recommend to focus on the development of the data and model software structure. Several large language models (LLM) already exist that have been trained on Earth biomedical and clinical knowledgebases, including BioMedLLM, Med-PaLM, SPOKE LLM, and Foresight. These models need to be evaluated for accuracy and the best one chosen for a proof-of-concept structure, while maintaining awareness of the accelerating AI field and incorporating any newly improved model architectures as needed. Then, we recommend to develop a database of synthetic data types to mimic the diverse data streams that are expected in a long-duration space mission. This should include environmental and microbial data from the spacecraft, non-invasive data from wearables and point-of-care devices employed by astronauts, and more invasive molecular and physiological monitoring of clinical and biomarker data from astronauts. The data standardization methodology should be developed, and these data streams used to refine the clinical LLM. Several scenarios should be developed that could plausibly come up in a long-duration space mission, and changes or aberrations introduced to the data at specific times to mimic these scenarios. Then, question and answer tasks should be designed to interrogate the model for predictions and recommendations, with acceptable answers already identified.

Artificial Intelligence↗
DOE OSTI2026

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗
DOE OSTI2024

Integrating an Ensemble Reward System into an Off-Policy Reinforcement Learning Algorithm for the Economic Dispatch of Small Modular Reactor-Based Energy Systems

Nuclear Integrated Energy Systems (NIES) have emerged as a comprehensive solution for navigating the changing energy landscape. They combine nuclear power plants with renewable energy sources, storage systems, and smart grid technologies to optimize energy production, distribution, and consumption across sectors, improving efficiency, reliability, and sustainability while addressing challenges associated with variability. The integration of Small Modular Reactors (SMRs) in NIES offers significant benefits over traditional nuclear facilities, although transferring involves overcoming legal and operational barriers, particularly in economic dispatch. This study proposes a novel off-policy Reinforcement Learning (RL) approach with an ensemble reward system to optimize economic dispatch for nuclear-powered generation companies equipped with an SMR, demonstrating superior accuracy and efficiency when compared to conventional methods and emphasizing RL’s potential to improve NIES profitability and sustainability. Finally, the research attempts to demonstrate the viability of implementing the proposed integrated RL approach in spot energy markets to maximize profits for nuclear-driven generation companies, establishing NIES’ profitability over competitors that rely on fossil fuel-based generation units to meet baseload requirements.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS1987

Attention theory and training research

This study used elements of attention theory as a methodological basis to decompose a complex training task in order to improve training efficiency. The complex task was a microcomputer flight simulation where subjects were required to control the stability of their own helicopter while acquiring and engaging enemy helicopers in a threat enviroment. Subjects were divided into whole-task, part-task, and part/open loop adaptive task groups in a transfer of training paradigm. The effect of reducing mental workload at the early stages of learning was examined with respect to the degree that subordinate elements of the complex task could be automated through practice of consistent, learnable stimulus-response relationships. Results revealed trends suggesting the benefit of isolating consistently mapped sub-tasks for part-task training and the presence of a time-sharing skill over and above the skill required for the separate subtasks.

Connelly, James G., Jr.↗
NASA NTRS2021

Integrated Demand Management Techport Closeout

Over the period 2016 to 2020, Integrated Demand Management (IDM) concept, procedures, and tools have been developed - first for clear-weather and a single airport constraint and then expanded to handle a multi-constraint problem during convective weather at Newark (EWR), LaGuardia (LGA) and Philadelphia (PHL) airports. The concept was evaluated in a series of human-in-the-loop simulations to confirm concept benefits in terms of better schedule predictability, reduction of delays, and increased throughput, especially during convective weather. In addition, other conditions with mixed participation of multi-trajectories from the airlines were evaluated that showed significant benefits to the individual airlines as well as the overall traffic flow. The IDM concept was initiated in the SMART-NAS project, was completed under the ATM-X project, and was developed collaboratively with the FAA and airline partners. Over the course of IDM development, NASA researchers produced 19 conference papers and publications. Outside supporting organizations, funded by IDM, produced 20 additional conference papers and publications, in which they advanced fundamental research on topics such as better stochastic traffic demand prediction, and application of machine learning techniques for modeling traffic management initiatives. Final concept procedures and tool specifications have been transferred to the FAA Air Traffic Organization Operational Concepts, Validation, and Requirements group.

William N Chan↗
NASA NTRS2022

Developing Data-Driven Artificial Neural Network for A High Throughput Retrieval of Aerosol Optical Depth and Surface Temperature of Mars

In this work, we aim to developartificial neural network(ANN)techniquesto reproduce the retrieval results ofphysical quantities from spacecraft observations of solar system bodiesusing radiative transfer methods. The particular application here is the retrieval of dust optical depth, water-ice optical depth, and surface temperatureonMarsusingdaytime observationsobtained by the Thermal Emission Spectrometer (TES) onboard the Mars Global Surveyor.Compared against the results obtained from traditional radiative transfer retrieval techniques, our ANN successfully recoveredthe three quantitiesusingdaytime observations. The principal advantage of thesemachine learning(ML) algorithms istheir complete automation and highthroughput. Therefore, the algorithms presented here would be useful for very large datasets andwould make practical the sampling of many different approximations or boundary conditions related to a given observation dataset and retrieval problem.

Rafael Moreno↗
NASA NTRSDate not supplied

A Principal Component and Machine Learning Approach to Spatially Gap Fill Hyperspectral Ocean Color Satellite Retrievals

Retrievals of ocean color properties from space are important for monitoring the health of the ocean ecosystem but such retrievals tend to be limited in spatial coverage due to conditions such as clouds, aerosols, and sun glint. Gap filling of ocean color retrievals is typically performed by combining retrievals from multiple satellites or temporally averaging multiple days of retrievals but despite these techniques large gaps still exist posing challenges for near real time monitoring of events like harmful algae blooms. To address these limitations, we propose a spatial gap filling approach using machine learning to learn how to perform an atmospheric correction under challenging retrieval conditions. In this approach a principal component analysis is used to decompose the hyperspectral measurements into spectral features that describe the scattering and absorption of the atmosphere as well as the underlying surface. The coefficients of the principal components are then used to train a neural network to predict ocean color properties derived from a standard ocean color algorithm such as the MODIS atmospheric correction algorithm. This machine learning approach is independent of a priori information and does not rely on any radiative transfer modeling. We apply the approach to two hyperspectral UV/VIS instruments, the Ozone Monitoring Instrument (OMI) and TROPOspheric Monitoring Instrument (TROPOMI) to show that it can be used to estimate ocean color properties such as chlorophyll, remote sensing reflectance, and fluorescence line height. This method could be used as a gap-filling technique for the future Ocean Color Instrument (OCI) which will be onboard NASA's Plankton, Aerosol Cloud, ocean Ecosystem (PACE) ocean color satellite to provide additional information for monitoring the health of our global oceans. Additionally, it could be applied to the geostationary satellite Tropospheric Emissions: Monitoring of Pollution (TEMPO) to better understand diurnal variability in ocean ecology.

MODIS atmospheric correction algorithm↗
NASA NTRSDate not supplied

NASA SmallSat LEARN Forum Briefing: BioSentinel

We will focus on the technologies developed for BioSentinel, primarily the science payloads. One of them, the BioSensor, is a microfluidics-based instrument that houses a series of fluidic cards and manifolds. The fluidic cards can be loaded with microbial organisms to study the effect of the space environment on biology. For BioSentinel, we used the budding yeast as our model organism to study the response to the radiation environment in both low Earth orbit (ISS) and in deep space. The second instrument is a radiation spectrometer. This sensor allows the quantification of ionizing radiation as well as the characterization of the different particles based on the linear energy transfer or LET. Given that BioSentinel launched this past November (Artemis I), part of the presentation will include lessons learned and how we will apply them to future missions, including LEIA. LEIA was recently selected for a mission to the lunar surface on a CLPS lander vehicle, and is primarily based at NASA Ames.

BioSentinel↗
NASA NTRS2022

Mars Terrain Segmentation with Less Labels

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is very data hungry and difficult to train where only a small number of labeled samples are available. Moreover, the semantic classes are defined differently for different applications (e.g., rover traversal vs. geological) and as a result the network has to be trained from scratch each time, which is an inefficient use of resources. This research proposes a semi-supervised learning framework for Mars terrain segmentation where a deep segmentation network trained in an unsupervised manner on unlabeled images is transferred to the task of terrain segmentation trained on few labeled images. The network incorporates a backbone module which is trained using a contrastive loss function and an output atrous convolution module which is trained using a pixel-wise cross-entropy loss function. Evaluation results using the metric of segmentation accuracy show that the proposed method with contrastive pre-training outperforms plain supervised learning by 2%-10%. Moreover, the proposed model is able to achieve a segmentation accuracy of 91.1% using only 161 training images (1% of the original dataset) compared to 81.9% with plain supervised learning.

Wilson, Brian D↗
NASA NTRS2000

Hand-Held Sunphotometers for High School Student Construction and Measuring Aerosol Optical Thickness

Science education is taking the teaching of science from a traditional (lecture) approach to a multidimensional sense-making approach which allows teachers to support students by providing exploratory experiences. Using projects is one way of providing students with opportunities to observe and participate in sense-making activity. We created a learning environment that fostered inquiry-based learning. Students were engaged in a variety of Inquiry activities that enabled them to work in cooperative planning teams where respect for each other was encouraged and their ability to grasp, transform and transfer information was enhanced. Summer, 1998: An air pollution workshop was conducted for high school students in the Medgar Evers College/Middle College High School Liberty Partnership Summer Program. Students learned the basics of meteorology: structure and composition of the atmosphere and the processes that cause weather. The highlight of this workshop was the building of hand-held sunphotometers, which measure the intensity of the sunlight striking the Earth. Summer, 1999: high school students conducted a research project which measured the mass and size of ambient particulates and enhanced our ability to observe through land based measurements changes in the optical depth of ambient aerosols over Brooklyn. Students used hand held Sunphotometers to collect data over a two week period and entered it into the NASA GISS database by way of the internet.

Almonor, Linda↗