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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Dehydration-Driven Ion Aggregation and the Onset of Gelation in ZnCl2 Solution

A minimal model of ionic aggregation in concentrated ZnCl2 is developed, guided by molecular dynamics simulations with a machine-learned potential. It explicitly incorporates solvent-site depletion, correlated chloride binding, and allows for loops within Zn–Cl clusters. Dehydration drives two coordination-controlled structural changes: a crossover at Z=2 from predominantly isolated Zn-containing species to Cl-bridged clusters and the onset of gelation near Z≈3. The model reproduces the concentration-dependent trends observed in the molecular dynamics simulations with two fitted parameters, while the cluster-size distribution at the highest concentration is consistent with three-dimensional percolation scaling over the accessible range of cluster sizes.

25 ENERGY STORAGE↗
DOE OSTI2024

Cookie-Jar: An Adaptive Re-configurable Framework for Wireless Network Infrastructures

5G advancements like Massive Multiple Input Multiple Output (MIMO) bring high capacity and low latency, but also intensify interference challenges. Static and dynamic coordination techniques address this, often at the cost of increased power draw. We introduce Cookie-Jar (CJ), an interference coordination (IC) framework using reinforcement learning for multi-goal optimization. By dynamically adjusting network, power, and topology parameters based on real-time conditions, CJ improves Signal to Noise and Interference Ratio (SINR) while minimizing power consumption. Simulated 5G experiments showcase CJ's potential, achieving a 15% SINR improvement with near-identical power draw compared to existing methods.

Network↗
DOE OSTI2025

Conin

SAND2025-07645O Conin is a Python library that supports constrained analysis of probabilistic graphical models (PGMs). It enables constrained inference and learning for hidden Markov models, Bayesian networks, dynamic Bayesian networks, and Markov networks. Conin interfaces with the pgmpy library to specify general probabilistic graphical models with a variety of optimization solvers to support learning and inference. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Hart, William [Sandia National Lab. (SNL-CA), Live↗
DOE OSTI2026

Deciphering the Solvation Structure of Aqueous ZnCl 2 Solutions from X-ray Absorption Spectra Using the Interpretable Graph Neural Network

Machine learning (ML) provides powerful pathways for predicting spectroscopic observables from atomic structures, but its broader impact depends on making model predictions interpretable in terms of physical and chemical principles. Here, we introduce a physics-guided graph neural network (GNN) model that predicts Zn K-edge X-ray spectroscopy (XAS) spectra of aqueous ZnCl 2 solutions. Training data are generated from ab initio XAS calculations on molecular dynamics snapshots obtained using a machine learning interatomic potential. The GNN reproduces experimental spectra across concentrations from dilute (<0.1 m) to highly concentrated (30 m, “water-in-salt”) regimes and scales efficiently to large, disordered liquid systems beyond the reach of conventional ab initio approaches. Gradient-based attribution analysis reveals that the model learns physically meaningful structure-spectrum relationships. Ligand-specific attributions reflect orbital hybridization patterns and the origin of the excitations derived from the density functional theory. Bond-length attributions recover spectral shifts consistent with multiple-scattering theory. Finally, this work bridges data-driven prediction with electronic-structure theory, establishing a general paradigm for interpretable ML that links atomic structure, electronic structure, and spectroscopic observables.

25 ENERGY STORAGE↗
DOE OSTI2024

Heisenberg-limited Hamiltonian learning for interacting bosons

We develop a protocol for learning a class of interacting bosonic Hamiltonians from dynamics with Heisenberg-limited scaling. For Hamiltonians with an underlying bounded-degree graph structure, we can learn all parameters with root mean square error ϵ using ${\mathcal{O}}(1/\epsilon )$ total evolution time, which is independent of the system size, in a way that is robust against state-preparation and measurement error. In the protocol, we only use bosonic coherent states, beam splitters, phase shifters, and homodyne measurements, which are easy to implement on many experimental platforms. A key technique we develop is to apply random unitaries to enforce symmetry in the effective Hamiltonian, which may be of independent interest.

computer science↗
DOE OSTI2024

Online Dynamic Cyber-Attack Diagnosis in Power Electronics Systems Based on Few-Shot Learning

With increasing exposure to software-based sensing and control, power electronics systems are facing higher risks of cyber-physical attacks. To ensure system stability and minimize potential economic losses, it is critical to monitor the operating states and detect those attacks at the early stage. However, anomaly detection and diagnosis of attacks are still challenging, especially when labeled anomaly data is difficult or even infeasible to obtain. To overcome this problem, we propose a Few-Shot Learning (FSL) based approach for cyber-attack diagnosis leveraging the waveform data. To the best of our knowledge, this work is the first attempt at leveraging FSL for cyber-attack diagnosis in power electronics systems. Extensive experimental results demonstrate that our proposed approach can achieve comparable diagnosis accuracy with the state-of-the-art data-driven methods using less than 0.04% of the training samples.

Li, Qi↗
DOE OSTI2024

Weak-form latent space dynamics identification

Recent work in data-driven modeling has demonstrated that a weak formulation of model equations enhances the noise robustness of a wide range of computational methods. In this paper, we demonstrate the power of the weak form to enhance the LaSDI (Latent Space Dynamics Identification) algorithm, a recently developed data-driven reduced order modeling technique. We introduce a weak form-based version WLaSDI (Weak-form Latent Space Dynamics Identification). WLaSDI first compresses data, then projects onto the test functions and learns the local latent space models. Notably, WLaSDI demonstrates significantly enhanced robustness to noise. With WLaSDI, the local latent space is obtained using weak-form equation learning techniques. Compared to the standard sparse identification of nonlinear dynamics (SINDy) used in LaSDI, the variance reduction of the weak form guarantees a robust and precise latent space recovery, hence allowing for a fast, robust, and accurate simulation. We demonstrate the efficacy of WLaSDI vs. LaSDI on several common benchmark examples including viscid and inviscid Burgers', radial advection, and heat conduction. For instance, in the case of 1D inviscid Burgers' simulations with the addition of up to 100% Gaussian white noise, the relative error remains consistently below 6% for WLaSDI, while it can exceed 10,000% for LaSDI. Similarly, for radial advection simulations, the relative errors stay below 15% for WLaSDI, in stark contrast to the potential errors of up to 10,000% with LaSDI. Moreover, speedups of several orders of magnitude can be obtained with WLaSDI. For example applying WLaSDI to 1D Burgers' yields a 140X speedup compared to the corresponding full order model.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

Learning and tuning fuzzy logic controllers through reinforcements

A new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. In particular, our Generalized Approximate Reasoning-based Intelligent Control (GARIC) architecture: (1) learns and tunes a fuzzy logic controller even when only weak reinforcements, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto, Sutton, and Anderson to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and has demonstrated significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.

Berenji, Hamid R.↗
NASA NTRS1992

Accelerating Learning By Neural Networks

Electronic neural networks made to learn faster by use of terminal teacher forcing. Method of supervised learning involves addition of teacher forcing functions to excitations fed as inputs to output neurons. Initially, teacher forcing functions are strong enough to force outputs to desired values; subsequently, these functions decay with time. When learning successfully completed, terminal teacher forcing vanishes, and dynamics or neural network become equivalent to those of conventional neural network. Simulated neural network with terminal teacher forcing learned to produce close approximation of circular trajectory in 400 iterations.

Toomarian, Nikzad↗
NASA NTRS2022

Learning-Based State-Dependent Coefficient Form Task Space Tracking Control of Soft Robot

n this paper, a data-driven modeling and control framework is developed for task space control of a soft robot gripper which consists of four individual soft fingers. Each of the four fingers is modeled as a manipulator with high degrees of freedom. The corresponding task space dynamics of the manipulator are derived using a rigid-link approximation of the continuum manipulator. A neural network approach is used to learn the derived dynamics in State Dependent Coefficient (SDC) form. Using the learned SDC matrices, an asymptotically stable optimal closed-loop tracking controller which is based on solving the State Dependent Riccati Equation (SDRE) is derived. The model learning and trajectory tracking controller is implemented on an open source Soft Motion (SoMo) platform simulating the soft gripper motion and corresponding tracking results are presented.

Rounak Bhattacharya↗
DOE OSTI2025

Data from "Deep Potential Molecular Dynamics Simulations of Low-Temperature Plasma-Surface Interactions"

Data and input files related to the paper "Deep Potential Molecular Dynamics Simulations of Low-Temperature Plasma-Surface Interactions" (https://doi.org/10.1116/6.0004027). This includes the final DP model used in all simulations, training data set, example input files to run DeepMD (with LAMMPS), and data tables summarizing the results obtained from the simulations.

machine learning models↗
DOE OSTI2024

Harnessing graph convolutional neural networks for identification of glassy states in metallic glasses

Graph Convolutional Neural Networks (GCNNs) have emerged as powerful tools for analyzing materials. In this study, we employ GCNNs to examine structural characteristics of CuZr metallic glasses (MGs) and identify their states. We use molecular dynamics to simulate the quenching process of CuZr, using cooling rates ranging from 10 9 to 10 15 K/s, to produce six unique glassy states. For each state, we create a dataset comprising 1,800 distinct samples. We evaluate the effectiveness of various GCNNs, including Graph Attention Neural Network (GANN), Graph Sample and AggreGatE (GraphSAGE), Graph Isomorphism Network (GIN), and Relational Graph Convolutional Neural Network (RGCN). GANN and GraphSAGE demonstrate comparable performance, achieving an overall accuracy of 81% in classifying the MG states. Furthermore, these results underscore the potential of GCNNs to detect subtle structural variances in disordered materials and point to broader application of deep learning in the analysis of MGs and other amorphous substances.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Physics-informed Deep Reinforcement Learning-based Control in Power systems

Incorporating physics information into the deep reinforcement learning (DRL) process is a promising approach for addressing the challenges faced in learning-based control design problems for physical systems. Power grid dynamics, being a physical system, adheres to specific physical laws, constraints, as well as operational and control rules. Therefore, consideration of such physics-based law improves the learning process drastically. In general, traditional grid control schemes rely on rule-based mechanisms that cannot adapt to changing operating conditions. To improve the adaptability and computation time, recent research has seen a surge of DRL-based applications in power grid control. A generic DRL-based control design imposes the system performance requirements through the design of reward functions. In some cases, some of the important physics information is injected through this reward function. However, due to the complex dynamics and large state-action space, learning an optimal DRL policy often becomes challenging. Inspired by the latest developments in general machine learning (ML) research, power system researchers have been investigating more direct ways of incorporating physics knowledge into DRL training. This chapter specifically focuses on these aspects of physics-informed DRL designs in grid control. It discusses the significance, applications, research gaps, and open problems that need to be addressed in future research.

artificial intelligence, machine learning↗
DOE OSTI2025

A physics-constrained neural ordinary differential equations approach for robust learning of stiff chemical kinetics

The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. While deep learning techniques have been explored to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because traditional deep learning approaches optimize for training error without ensuring compatibility with ordinary differential equation (ODE) solvers, resulting in accumulation of errors over time. Recently, neuralODE (NODE) based approaches have been shown to be a promising technique to emulate and accelerate detailed chemistry computations. Here, in the present work, we extend this NODE framework for stiff chemical kinetics by incorporating mass conservation constraints directly into the loss function during training. This ensures that the total mass as well as the individual elemental species masses are conserved in an a-posteriori manner. Proof-of-concept studies are performed with the novel physics-constrained NODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions. It is demonstrated that the PC-NODE framework not only improves the physical consistency of the resulting data-driven model with respect to mass conservation criteria, but also improves training efficiency. PC-NODE is shown to achieve 2–100× speedup relative to the hydrogen-air detailed chemical mechanism depending on the type of the ODE solver (implicit or explicit) used during autoregressive inference tests. Lastly, a-posteriori studies are performed wherein the trained PC-NODE model is coupled with a CFD solver. It is shown that higher accuracy is achieved with PC-NODE relative to the purely data-driven NODE approach. Moreover, PC-NODE also exhibits robustness and generalizability to unseen initial conditions from within (interpolative capability) as well as outside (extrapolative capability) the training regime.

computational combustion↗
DOE OSTI2024

Efficient learning of accurate surrogates for simulations of complex systems

Machine learning methods are increasingly deployed to construct surrogate models for complex physical systems at a reduced computational cost. However, the predictive capability of these surrogates degrades in the presence of noisy, sparse or dynamic data. Here, we introduce an online learning method empowered by optimizer-driven sampling that has two advantages over current approaches: it ensures that all local extrema (including endpoints) of the model response surface are included in the training data, and it employs a continuous validation and update process in which surrogates undergo retraining when their performance falls below a validity threshold. We find, using benchmark functions, that optimizer-directed sampling generally outperforms traditional sampling methods in terms of accuracy around local extrema even when the scoring metric is biased towards assessing overall accuracy. Finally, the application to dense nuclear matter demonstrates that highly accurate surrogates for a nuclear equation-of-state model can be reliably autogenerated from expensive calculations using few model evaluations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Learning Latent Representations to Bridge Coarse-Grained and Atomistic Resolutions in Polymer Simulations

We present a machine-learning-based framework for learning reduced-order representations of polymer chain conformations across coarse-grained (CG) and united-atom (UA) fidelities. By employing linear singular value decomposition and nonlinear autoencoders, we compress high-dimensional polymer configurations into latent spaces with minimal loss of structural accuracy. Crucially, we demonstrate a near-perfect linear mapping between CG and UA latent spaces, enabling an efficient super-resolution back-mapping procedure that reconstructs high-fidelity UA configurations from CG simulations. While minor structural inaccuracies occur, they are effectively corrected through a brief molecular dynamics relaxation, forming a practical hybrid machine learning−physics scheme. This approach establishes the key structural prerequisites for accelerated polymer dynamics simulations: a compact and accurate latent encoding of polymer chain conformations and a validated multi-fidelity mapping that permits reconstruction of UA structures from CG configurations. The extension of this framework to explicit time evolution within the latent space, enabling dynamics to be propagated at CG fidelity and decoded to UA resolution only when required, represents a natural and well-motivated direction for future work.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1987

Parallel image compression

A parallel compression algorithm for the 16,384 processor MPP machine was developed. The serial version of the algorithm can be viewed as a combination of on-line dynamic lossless test compression techniques (which employ simple learning strategies) and vector quantization. These concepts are described. How these concepts are combined to form a new strategy for performing dynamic on-line lossy compression is discussed. Finally, the implementation of this algorithm in a massively parallel fashion on the MPP is discussed.

Reif, John H.↗