Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning dynamics”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

Algorithm for Training a Recurrent Multilayer Perceptron

An improved algorithm has been devised for training a recurrent multilayer perceptron (RMLP) for optimal performance in predicting the behavior of a complex, dynamic, and noisy system multiple time steps into the future. [An RMLP is a computational neural network with self-feedback and cross-talk (both delayed by one time step) among neurons in hidden layers]. Like other neural-network-training algorithms, this algorithm adjusts network biases and synaptic-connection weights according to a gradient-descent rule. The distinguishing feature of this algorithm is a combination of global feedback (the use of predictions as well as the current output value in computing the gradient at each time step) and recursiveness. The recursive aspect of the algorithm lies in the inclusion of the gradient of predictions at each time step with respect to the predictions at the preceding time step; this recursion enables the RMLP to learn the dynamics. It has been conjectured that carrying the recursion to even earlier time steps would enable the RMLP to represent a noisier, more complex system.

Parlos, Alexander G.↗
DOE OSTI2026

AGFormer: Adaptive Spatiotemporal graph informed transformer for multi-reservoir inflow forecasting

Accurate reservoir inflow forecasting is crucial for effective water resource management, yet most machine learning models focus on single-reservoir prediction and overlook spatial dependencies among hydrologically connected reservoirs. Here, we propose AGFormer (Adaptive Graph-Informed Transformer), an end-to-end framework that integrates adaptive graph learning with temporal sequence modeling for multi-reservoir inflow forecasting. A shared encoder and graph attention mechanism generate reservoir-specific embeddings, which are then processed by the Transformer-based encoder–decoder for multi-step inflow forecasting. We also introduce a pretraining paradigm to learn robust temporal embeddings from misaligned historical records. Evaluated on 30 reservoirs in the Upper Colorado River Basin, AGFormer achieves superior seven-day-ahead forecasts, with NSE > 0.75 for 20 reservoirs—outperforming Encoder–Decoder LSTM, GCN+LSTM, and Transformer baselines. Adaptive graph learning captures dynamic inter-reservoir dependencies, and feature attribution aligns with snowmelt-driven hydrology. Incorporating forecasted meteorological inputs further enhances accuracy, demonstrating AGFormer’s potential to support reservoir management under dynamic hydrological conditions.

Adaptive graph learning↗
NASA NTRSDate not supplied

Mission Status, On-Orbit Performance, and Lessons Learned of the Global Ecosystem Dynamics Investigation (GEDI) Lidar Laser Transmitters

The Global Ecosystems Dynamics Investigation (GEDI) Lidar, is a global 3-dimensional biomass lidar instrument aboard the International Space Station (ISS) and the Japanese Experiment Module (JEM). Its core mission is to measure the global carbon balance of Earth’s forests with 3 laser transmitters using multi-beam waveform-capture methods. GEDI’s laser transmitter concept was originally funded by NASA Goddard’s Earth Science Technology Office (ESTO) for future Earth Altimetry and Lidar missions ~ 20 years ago, and after a long road of development, the first flight-ready unit was a 10 mJ-class system for GEDI’s ISS-based specifications. Furthermore, no adjustment in drive parameters has been required nor significant decay detected after 4 years of near continuous operation of 3 on-board lasers, which were designed for a 2-year mission. We report on the GEDI laser design process, their on-orbit performance, the major lessons learned, and some critical insight into our in-house flight quality development process that enabled their delivery within budget, schedule, and low risk extended mission life capability.

D. Barry Coyle↗
DOE OSTI2026

Microscopic Mechanisms of Superionic Na-ion Conductivity in Crystalline and Amorphous NaMOCl 4 (M = Nb, Ta) Solid Electrolytes

Sodium-ion solid electrolytes offer a sustainable route toward next-generation batteries, but few match the performance of their lithium counterparts. Halide-based NaMOCl 4 (M = Nb, Ta) has recently emerged as a promising analogue to LiMOCl 4 , yet its structure–transport relationships remain unclear due to poor crystallinity in experiments. Here, we combine density functional theory and machine-learned molecular dynamics to reveal that crystalline NaMOCl 4 exhibits negligible room-temperature conductivity with high activation barriers arising from vacancy-mediated diffusion below an order–disorder transition. Above this transition, rotational and translational motion of the [MO 2/2 Cl 4 – ] ∞ chains create new Na sites and enhances transport. In contrast, the amorphous phase inherently supports facile, three-dimensional Na diffusion through dynamic framework flexibility. These results show that ordered crystalline phases hinder ionic transport, while disorder – either thermally induced or structural – facilitates it, revising prior assumptions from the Li system and providing design principles for high-conductivity Na halide electrolytes.

Wei, Grace [University of California, Berkeley, CA↗
DOE OSTI2025

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have been developed to understand the mechanisms leading to complex morphologies. However, the LMD governing equations in these models often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, numerical stiffness in the PDEs requires an extremely refined time step size (on the order of 10 -12 s or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose a U-shaped adaptive Fourier neural operator (U-AFNO), a machine learning (ML) based model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics of mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g., the deformation of the liquid-metal interface, lost metal, etc.) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in spite of the chaotic nature of LMD. Most notably, our model reproduces the key microstructure statistics and QoIs with a level of accuracy on par with the high-fidelity numerical solver, while achieving a significant 11, 200 × speed-up on a high-resolution grid when comparing the computational expense per time step. Finally, we also investigate the opportunity of using hybrid simulations, in which we alternate forward leaps in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Data-Driven Voltage Regulation of Distribution Grid Using Nonlinear Autoregressive Model with Exogenous Inputs (NARX)

This article proposes data-driven control via a nonlinear autoregressive model with exogenous inputs (NARX) for real-time voltage regulation of a modified feeder using reactive power sources. Traditional voltage control strategies rely on rule-based heuristics or optimization techniques, which often require detailed system models and extensive computational resources. The NARX-based controller learns system dynamics from historical data and predicts optimal reactive power dispatch in real-time for voltage correction. The proposed approach is evaluated on a power system feeder model under varying load and network conditions. Simulation results demonstrate that the NARX-based controller achieves improved voltage regulation, offering higher adaptability to system fluctuations. This study highlights the potential of data-driven control for enhancing the reliability of power distribution networks.

Donge, Vrushabh [ORNL] (ORCID:0000000306062803)↗
DOE OSTI2024

Mid-IR UAV-based sensing platform with deep learning to Identify and Quantify Gaseous Emission in Gas Flares

This report details the development and evaluation of a Mid-Infrared (Mid-IR) Unmanned Aerial Vehicle (UAV)-based sensing platform integrated with deep learning algorithms for the identification and quantification of gaseous emissions in gas flares. The project, spearheaded by Omega Optics, Inc., aimed to address environmental monitoring challenges by leveraging advanced photonic technologies and autonomous UAV operations. The research focused on designing, optimizing, and fabricating photonic crystal waveguides and grating couplers to enhance the sensitivity and accuracy of gas detection. A comprehensive drone-based system was developed, featuring a miniaturized sensor, GPS module, and microcontroller communication network for real-time gas concentration monitoring. The system's adaptive sampling algorithm, implemented using the Robot Operating System (ROS), enables autonomous detection and localization of gas emission sources. Preliminary results demonstrate the platform's capability to detect and monitor gas emissions with high precision, cost-effectiveness, and scalability. Future work will expand upon this foundation by introducing 3D wind model-based learning for dynamic environmental conditions and further enhancing the user interface and data processing algorithms to support broader environmental monitoring applications. Overall, this project represents a significant step forward in UAV-based environmental sensing technologies, offering robust solutions for detecting and mitigating the impacts of gaseous emissions on public health and safety.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

A system identification approach for non-intrusive reduced order modeling of radiation-induced photocurrents

In this study, development of compact photocurrent models is currently dominated by analytical techniques that rely on physical assumptions to render the governing equations solvable in a closed form. Violation of these assumptions can reduce the accuracy of the models and/or limit their scope. In this paper we show that system identification of nonlinear state-space systems can serve as an alternative numerical basis for non-intrusive reduced order modeling of photocurrent effects. To that end we develop a compact gray box photocurrent model (GBPM) by using a state-space representation with a low-dimensional latent state equation that mimics a mathematical model for the response of an idealized class of devices to ionizing radiation. In so doing we obtain a model that learns the dynamics of a quantity of interest directly from its measurements without requiring snapshots of the internal device state or its discretized model, and can be inferred from very small data sets. To demonstrate the approach we train the GBPM using a small experimental data set for a Z5236 Zener diode and a small synthetic data set obtained by simulating a synthetic pn-junction device. We then compare the GBPMs with black box models trained on the same data and show that performance of the latter is limited by the size of the data set, while the former are able to achieve excellent performance in both the reproductive and the predictive regimes.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2004

Flywheel Technology

Throughout the summer of 2004, I am working on a number of different projects. While located in the Space Power and Propulsion Test Engineering branch, my main area of study is flywheel technology. I have been exposed to flywheels, their components, and their uses in today's society. I have been able to experience numerous flywheels here in the flywheel lab at NASA Glenn. My first main project was to explore the attributes and physical characteristics of a flywheel. Our branch was constructing a flywheel demonstration to be presented at the public open house taking place in June. Our Flywheel Interactive Demo, or FIDO, represents a real life multi-flywheel system here at NASA. I was given the opportunity to learn about how these flywheels store energy and are able to position a satellite. With all of this new knowledge, I was able to create the posters that explained how our demonstration worked. I also composed a step-by-step process made up of four experiments that any visitor could follow and perform on FIDO. By stepping through these experiments, the individual learns how a flywheel works. They not only read the explanation of what is happening, but they are also able to see it happen. Creating these two posters not only taught me, but also helped teach the general public during the open house, how flywheel technology is a very important part of our future. Through my research, I have learned that flywheels are able to store massive amounts of energy. They can be described as an electro-mechanical battery that stores kinetic energy while rotating. The faster it rotates, the more energy it stores. Their lifetime is about triple that of an ordinary battery. Flywheels also have the ability to combine energy storage with attitude control all in a single system. Attitude control is the ability to position a satellite as required. FIDO helps us to understand the rotational force (torque) that is applied upon a turn-table or satellite during wheel acceleration/deceleration. My other main project that I have just begun is to create a flywheel presentation, brochure, and video all explaining the history, applications, early attempts, and working processes of modem flywheels. These items are all usefull tools for educating school children and even adults about flywheels. This task will require a large amount of research and skills in the use of multiple applications. My goal this summer is to learn the dynamics and uses of a flywheel in today s society, and then inform and encourage the public about flywheels. I am able to express my knowledge by creating some effective as well as attractive posters, presentations, brochures, videos, etc. that are able to explain how a flywheel works along with how our FIDO demonstration simulates a real flywheel. My goal is underway, and should be successfully reached with the help of my mentor, other coworkers, and fellow interns.

Ritchie, Lisa M.↗
NASA NTRS2004

Perceptual learning through optimization of attentional weighting: human versus optimal Bayesian learner

Human performance in visual detection, discrimination, identification, and search tasks typically improves with practice. Psychophysical studies suggest that perceptual learning is mediated by an enhancement in the coding of the signal, and physiological studies suggest that it might be related to the plasticity in the weighting or selection of sensory units coding task relevant information (learning through attention optimization). We propose an experimental paradigm (optimal perceptual learning paradigm) to systematically study the dynamics of perceptual learning in humans by allowing comparisons to that of an optimal Bayesian algorithm and a number of suboptimal learning models. We measured improvement in human localization (eight-alternative forced-choice with feedback) performance of a target randomly sampled from four elongated Gaussian targets with different orientations and polarities and kept as a target for a block of four trials. The results suggest that the human perceptual learning can occur within a lapse of four trials (<1 min) but that human learning is slower and incomplete with respect to the optimal algorithm (23.3% reduction in human efficiency from the 1st-to-4th learning trials). The greatest improvement in human performance, occurring from the 1st-to-2nd learning trial, was also present in the optimal observer, and, thus reflects a property inherent to the visual task and not a property particular to the human perceptual learning mechanism. One notable source of human inefficiency is that, unlike the ideal observer, human learning relies more heavily on previous decisions than on the provided feedback, resulting in no human learning on trials following a previous incorrect localization decision. Finally, the proposed theory and paradigm provide a flexible framework for future studies to evaluate the optimality of human learning of other visual cues and/or sensory modalities.

Non-NASA Center↗
NASA NTRS2001

Control of a simulated arm using a novel combination of Cerebellar learning mechanisms

We present a model of cerebellar cortex that combines two types of learning: feedforward predicitve association based on local Hebbian-type learning between granule cell ascending branch and parallel fiber inputs, and reinforcement learning with feedback error correction based on climbing fiber activity.

cerebellum cerebellar learning dynamic state estim↗
NASA NTRS2005

Method of Real-Time Principal-Component Analysis

Dominant-element-based gradient descent and dynamic initial learning rate (DOGEDYN) is a method of sequential principal-component analysis (PCA) that is well suited for such applications as data compression and extraction of features from sets of data. In comparison with a prior method of gradient-descent-based sequential PCA, this method offers a greater rate of learning convergence. Like the prior method, DOGEDYN can be implemented in software. However, the main advantage of DOGEDYN over the prior method lies in the facts that it requires less computation and can be implemented in simpler hardware. It should be possible to implement DOGEDYN in compact, low-power, very-large-scale integrated (VLSI) circuitry that could process data in real time.

Duong, Tuan↗
NASA NTRS2020

X-56A Structural Dynamics Ground Testing Overview and Lessons Learned

The X-56A Multi-Utility Technology Testbed (MUTT) is a subscale, fixed-wing aircraft designed for high-risk aeroelastic flight demonstration and research. Structural dynamics ground testing for model validation was especially important for this vehicle because the structural model was directly used in the development of a flight control system with active flutter suppression capabilities. Structural dynamics ground tests of the X-56A MUTT with coupled rigid-body and structural modes provided a unique set of challenges. An overview of the ground vibration test (GVT) and moment of inertia (MOI) test setup and execution is presented. The series of GVTs included the wing by itself attached to a strongback and complete vehicle at two mass conditions: empty and full fuel. Two boundary conditions for the complete-vehicle test were studied: on landing gear and suspended free-free. Pitch MOI tests were performed using a compound pendulum method and repeated with two different pendulum lengths for independent verification. The original soft-support test configuration for the GVT used multiple bungees, resulting in unforeseen coupling interactions between the soft-support bungees and the vehicle structural modes. To resolve this problem, the soft-support test setup underwent multiple iterations. The various GVT configurations and boundary-condition modifications are highlighted and explained. Lessons learned are captured for future consideration when performing structural dynamics testing with similar vehicles.

Chin, Alexander W.↗
DOE OSTI2025

Machine Learning-Accelerated First-Principles Molecular Dynamics Explains Anomalous Lattice Thermal Expansion in BaZr 0.78 Y 0.22 O 3-δ

Fuel cells are a vital clean energy technology that converts chemical energy directly into electricity with high efficiency, making them a cornerstone of a sustainable energy future. Herein we investigate the thermal and chemical lattice expansion behavior of hydrated BaZr 0.78 Y 0.22 O 3-δ using machine learning-accelerated ab initio molecular dynamics simulations. Here, our results reproduce the experimentally observed non-monotonic and anomalous temperature dependence of lattice expansion, which we attribute to the competing effects of thermal expansion and dehydration—two mechanisms that influence the lattice expansion in opposite directions. The importance of this work lies in its detailed demonstration of how advanced computational techniques can accurately capture complex environmental effects, providing a valuable framework for modeling similar phenomena in a variety of material systems and applications.

Proton conducting fuel cell↗